Informe Final: Analisis Estadistico
Daniel Gómez, Salomon Zabaleta, Victor Caballero, Carlos Daniel Rodriguez
Universidad del Norte30/8/2021
Introducción
La aplicación de R studio es un sistema que nos permite analizar y recopilar información. De esta forma poder mantener un análisis más eficiente del área que se busca estudiar. Siendo este sistema, un entorno de desarrollo integrado, el cual se encuentra destinado hacia la computación estadística y todo lo que está concierne. Por ejemplo: la realización de gráficos en la que se compilen datos estadísticos. De esta forma, esta aplicación se encuentra integrada con su lenguaje de programación único y por excelencia, el cual facilita su comprensión y utilización, conociéndose este lenguaje como el de programación R. Se caracteriza por su fácil automatización, así como también es capaz de leer cualquier tipo de datos sin olvidar que es gratuito y se puede ejecutar en cualquier tipo de plataforma. concluyendo, R Studio es un lenguaje bastante adecuado para la estadística, ya que permite manipular los datos rápidamente y de forma precisa. Por esta razón para nuestro informe fue muy importante su utilización y entendimiento; siendo de gran aporte para la organización de nuestro orden de una forma más entendible.
Gráfica de histogramas, para todas las longitudes de deslizamiento de America Central
Dado el siguiente conjunto de datos realice: tablas de frecuencia, gráficos de series temporales, diagramas de tallo y hojas, diagramas de pareto, gráfico circular, gráfico de barras clasico, agrupado y apilado, tablas de frecuencia simple y agrupada, medidas de tendencia central, medidas de variabilidad, medidas de posicíon y diagramas de caja y bigotes.
Gráfico para Panamá
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unioncolnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_PA <- subset(df, country_name == "Panama")
knitr::kable(head(df_PA))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 750 | 8/26/08 | NA | NA | Panama | PA | Panamá | 1287 | Cerro Azul | 1.84596 | NA | 9.1559 | -79.4295 | (9.1559000000000008, -79.429500000000004) | Landslide | Landslide | Medium | Downpour | NA | NA | NA | NA | http://news.xinhuanet.com/english/2008-08/27/content_9721298.htm |
| 905 | 11/25/08 | NA | NA | Panama | PA | Chiriquí | 6123 | Boquete | 9.83700 | NA | 8.7870 | -82.3440 | (8.7870000000000008, -82.343999999999994) | Landslide | Complex | Medium | Downpour | NA | NA | 8 | NA | http://www.iht.com/articles/ap/2008/11/26/news/LT-Panama-Flooding.php |
| 2794 | 12/8/10 | NA | NA | Panama | PA | Colón | 1310 | El Giral | 1.80330 | NA | 9.2332 | -79.6961 | (9.2332000000000001, -79.696100000000001) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.portworld.com/news/i98731/Panama_Canal_disrupted_by_floods |
| 2795 | 12/9/10 | Morning | NA | Panama | PA | Colón | 1274 | Portobelo | 0.09491 | Deforested slope | 9.5493 | -79.6505 | (9.5493000000000006, -79.650499999999994) | Landslide | Mudslide | Medium | Downpour | NA | NA | 8 | Fox News Latino | http://latino.foxnews.com/latino/news/2010/12/09/heavy-rains-kill-panama-force-canal-close/ |
| 3167 | 3/2/11 | Night | NA | Panama | PA | Los Santos | 1283 | La Palma | 13.40535 | NA | 7.5955 | -80.3800 | (7.5955000000000004, -80.38) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.newsroompanama.com/panama/2434-off-season-rain-creating-crop-worries-and-landslides.html |
| 3168 | 3/2/11 | Night | NA | Panama | PA | Bocas del Toro | 8114 | Almirante | 8.41491 | NA | 9.3224 | -82.4732 | (9.3224, -82.473200000000006) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.newsroompanama.com/panama/2434-off-season-rain-creating-crop-worries-and-landslides.html |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_PA, aes(fill= state, y=distance, x=country_name)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_PA, aes(fill=state, y=distance, x=country_name)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_PA, aes(x=country_name, y=distance, fill=state)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_PA <- df_PA %>%
arrange(desc(state)) %>%
mutate(prop = distance / sum(df_PA$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)## Loading required package: scales##
## Attaching package: 'scales'## The following object is masked from 'package:readr':
##
## col_factorggplot(df_PA, aes(x=country_name, y=prop, fill=state)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)## Warning: package 'forecast' was built under R version 4.1.1## Registered S3 method overwritten by 'quantmod':
## method from
## as.zoo.data.frame zoodata<- ts(df_PA$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 1.84596 |
| 2.81479 |
| 1.41526 |
| 4.18074 |
| 2.24069 |
| 0.48725 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)## Package 'qcc' version 2.7## Type 'citation("qcc")' for citing this R package in publications.distance <- df_PA$distance
names(distance) <- df_PA$state
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por estados"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Los Santos 13.40535000 13.40535000 11.36719394 11.36719394
## Chiriquí 9.83700000 23.24235000 8.34137764 19.70857158
## Bocas del Toro 8.41491000 31.65726000 7.13550291 26.84407449
## Chiriquí 6.74338000 38.40064000 5.71811316 32.56218765
## Bocas del Toro 6.65185000 45.05249000 5.64049943 38.20268708
## Bocas del Toro 5.97977000 51.03226000 5.07060280 43.27328989
## Bocas del Toro 5.13913000 56.17139000 4.35777413 47.63106401
## Colón 4.74914000 60.92053000 4.02707840 51.65814241
## Bocas del Toro 4.45630000 65.37683000 3.77876194 55.43690435
## Panamá 4.18074000 69.55757000 3.54509822 58.98200257
## Bocas del Toro 3.92621000 73.48378000 3.32926708 62.31126965
## Chiriquí 3.66775000 77.15153000 3.11010347 65.42137312
## Panamá 3.54386000 80.69539000 3.00504977 68.42642289
## Chiriquí 3.33873000 84.03412000 2.83110784 71.25753073
## Panamá 3.30848000 87.34260000 2.80545706 74.06298779
## Panamá 2.81479000 90.15739000 2.38682793 76.44981572
## Colón 2.67409000 92.83148000 2.26752003 78.71733575
## Panamá 2.59449000 95.42597000 2.20002245 80.91735821
## Panamá 2.57852000 98.00449000 2.18648054 83.10383875
## Chiriquí 2.44254000 100.44703000 2.07117501 85.17501375
## Colón 2.28589000 102.73292000 1.93834215 87.11335590
## Panamá 2.24069000 104.97361000 1.90001438 89.01337029
## Panamá 1.84596000 106.81957000 1.56529933 90.57866961
## Panamá 1.80341000 108.62298000 1.52921865 92.10788826
## Colón 1.80330000 110.42628000 1.52912537 93.63701364
## Panamá 1.41526000 111.84154000 1.20008317 94.83709680
## Chiriquí 0.90169000 112.74323000 0.76459661 95.60169341
## Colón 0.76740000 113.51063000 0.65072412 96.25241753
## Colón 0.74760000 114.25823000 0.63393453 96.88635206
## Chiriquí 0.64491000 114.90314000 0.54685756 97.43320962
## Colón 0.63948000 115.54262000 0.54225314 97.97546277
## Panamá 0.48725000 116.02987000 0.41316827 98.38863103
## Chiriquí 0.37999000 116.40986000 0.32221613 98.71084717
## Chiriquí 0.35187000 116.76173000 0.29837151 99.00921868
## Bocas del Toro 0.29869000 117.06042000 0.25327702 99.26249570
## Coclé 0.21605000 117.27647000 0.18320165 99.44569735
## Colón 0.20365000 117.48012000 0.17268695 99.61838430
## Colón 0.18619000 117.66631000 0.15788158 99.77626588
## Colón 0.16894000 117.83525000 0.14325428 99.91952016
## Colón 0.09491000 117.93016000 0.08047984 100.00000000stem(df_PA$"distance")##
## The decimal point is at the |
##
## 0 | 122223445667894888
## 2 | 234667833579
## 4 | 2571
## 6 | 077
## 8 | 48
## 10 |
## 12 | 4head(df_PA)## # A tibble: 6 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 750 8/26/08 <NA> <NA> Panama PA Panamá 1287
## 2 5562 9/29/13 <NA> <NA> Panama PA Panamá 69102
## 3 6701 9/14/14 Morning <NA> Panama PA Panamá 19782
## 4 6703 6/17/14 <NA> <NA> Panama PA Panamá 321501
## 5 6705 6/24/14 <NA> <NA> Panama PA Panamá 9169
## 6 7453 6/5/15 Afternoon <NA> Panama PA Panamá 0
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_PA))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 750 | 8/26/08 | NA | NA | Panama | PA | Panamá | 1287 | Cerro Azul | 1.84596 | NA | 9.1559 | -79.4295 | (9.1559000000000008, -79.429500000000004) | Landslide | Landslide | Medium | Downpour | NA | NA | NA | NA | http://news.xinhuanet.com/english/2008-08/27/content_9721298.htm | 1.5652993 | 0.7826497 |
| 5562 | 9/29/13 | NA | NA | Panama | PA | Panamá | 69102 | Las Cumbres | 2.81479 | NA | 9.0655 | -79.5516 | (9.0655000000000001, -79.551599999999993) | Landslide | Landslide | Medium | Downpour | NA | NA | NA | www.newsroompanama.com | http://www.newsroompanama.com/panama/6467--nearly-800-affeccted-by-floods-in-panama-city-region.html | 2.3868279 | 2.7587133 |
| 6701 | 9/14/14 | Morning | NA | Panama | PA | Panamá | 19782 | Alcaldedíaz | 1.41526 | Urban area | 9.1139 | -79.5626 | (9.1138999999999992, -79.562600000000003) | Landslide | Other | Small | Rain | NA | 0 | 0 | Estrella de Panama | http://laestrella.com.pa/panama/nacional/colapsa-pared-vivienda-alcade-diaz/23804690/foto/50372 | 1.2000832 | 4.5521688 |
| 6703 | 6/17/14 | NA | NA | Panama | PA | Panamá | 321501 | San Miguelito | 4.18074 | Unknown | 9.0329 | -79.5380 | (9.0328999999999997, -79.537999999999997) | Landslide | Mudslide | Medium | Unknown | NA | 0 | 0 | PanamaAmerica | http://www.panamaamerica.com.pa/nacion/reportan-deslizamiento-en-autopista-panama-colon# | 3.5450982 | 6.9247595 |
| 6705 | 6/24/14 | NA | NA | Panama | PA | Panamá | 9169 | Ancón | 2.24069 | Below road | 8.9763 | -79.5391 | (8.9763000000000002, -79.539100000000005) | Landslide | Landslide | Small | Unknown | NA | 0 | 0 | Ministerio de Obras Públicas de Panamá | http://www.mop.gob.pa/poste-electrico-de-la-avenida-frangipany-cae-sobre-camion-del-mop/ | 1.9000144 | 9.6473158 |
| 7453 | 6/5/15 | Afternoon | NA | Panama | PA | Panamá | 0 | Las Margaritas | 0.48725 | Above road | 9.1805 | -79.0896 | (9.1805000000000003, -79.089600000000004) | Landslide | Landslide | Medium | Downpour | NA | 0 | 0 | La Estrella de Panama | http://laestrella.com.pa/panama/nacional/deslizamiento-tierra-bayano-inundaciones-colon/23870997/foto/136658 | 0.4131683 | 10.8039072 |
stem(df_PA$"distance")##
## The decimal point is at the |
##
## 0 | 122223445667894888
## 2 | 234667833579
## 4 | 2571
## 6 | 077
## 8 | 48
## 10 |
## 12 | 4stem(df_PA$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 12222344566789
## 1 | 4888
## 2 | 2346678
## 3 | 33579
## 4 | 257
## 5 | 1
## 6 | 077
## 7 |
## 8 | 4
## 9 | 8
## 10 |
## 11 |
## 12 |
## 13 | 4Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.09491 | 1 | 2.5 | 2.5 | 2.5 | 2.5 |
| 0.16894 | 1 | 2.5 | 2.5 | 5.0 | 5.0 |
| 0.18619 | 1 | 2.5 | 2.5 | 7.5 | 7.5 |
| 0.20365 | 1 | 2.5 | 2.5 | 10.0 | 10.0 |
| 0.21605 | 1 | 2.5 | 2.5 | 12.5 | 12.5 |
| 0.29869 | 1 | 2.5 | 2.5 | 15.0 | 15.0 |
| 0.35187 | 1 | 2.5 | 2.5 | 17.5 | 17.5 |
| 0.37999 | 1 | 2.5 | 2.5 | 20.0 | 20.0 |
| 0.48725 | 1 | 2.5 | 2.5 | 22.5 | 22.5 |
| 0.63948 | 1 | 2.5 | 2.5 | 25.0 | 25.0 |
| 0.64491 | 1 | 2.5 | 2.5 | 27.5 | 27.5 |
| 0.7476 | 1 | 2.5 | 2.5 | 30.0 | 30.0 |
| 0.7674 | 1 | 2.5 | 2.5 | 32.5 | 32.5 |
| 0.90169 | 1 | 2.5 | 2.5 | 35.0 | 35.0 |
| 1.41526 | 1 | 2.5 | 2.5 | 37.5 | 37.5 |
| 1.8033 | 1 | 2.5 | 2.5 | 40.0 | 40.0 |
| 1.80341 | 1 | 2.5 | 2.5 | 42.5 | 42.5 |
| 1.84596 | 1 | 2.5 | 2.5 | 45.0 | 45.0 |
| 2.24069 | 1 | 2.5 | 2.5 | 47.5 | 47.5 |
| 2.28589 | 1 | 2.5 | 2.5 | 50.0 | 50.0 |
| 2.44254 | 1 | 2.5 | 2.5 | 52.5 | 52.5 |
| 2.57852 | 1 | 2.5 | 2.5 | 55.0 | 55.0 |
| 2.59449 | 1 | 2.5 | 2.5 | 57.5 | 57.5 |
| 2.67409 | 1 | 2.5 | 2.5 | 60.0 | 60.0 |
| 2.81479 | 1 | 2.5 | 2.5 | 62.5 | 62.5 |
| 3.30848 | 1 | 2.5 | 2.5 | 65.0 | 65.0 |
| 3.33873 | 1 | 2.5 | 2.5 | 67.5 | 67.5 |
| 3.54386 | 1 | 2.5 | 2.5 | 70.0 | 70.0 |
| 3.66775 | 1 | 2.5 | 2.5 | 72.5 | 72.5 |
| 3.92621 | 1 | 2.5 | 2.5 | 75.0 | 75.0 |
| 4.18074 | 1 | 2.5 | 2.5 | 77.5 | 77.5 |
| 4.4563 | 1 | 2.5 | 2.5 | 80.0 | 80.0 |
| 4.74914 | 1 | 2.5 | 2.5 | 82.5 | 82.5 |
| 5.13913 | 1 | 2.5 | 2.5 | 85.0 | 85.0 |
| 5.97977 | 1 | 2.5 | 2.5 | 87.5 | 87.5 |
| 6.65185 | 1 | 2.5 | 2.5 | 90.0 | 90.0 |
| 6.74338 | 1 | 2.5 | 2.5 | 92.5 | 92.5 |
| 8.41491 | 1 | 2.5 | 2.5 | 95.0 | 95.0 |
| 9.837 | 1 | 2.5 | 2.5 | 97.5 | 97.5 |
| 13.40535 | 1 | 2.5 | 2.5 | 100.0 | 100.0 |
| Total | 40 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 41 obs. of 5 variables:
## $ n : num 1 1 1 1 1 1 1 1 1 1 ...
## $ % : num 2.5 2.5 2.5 2.5 2.5 2.5 2.5 2.5 2.5 2.5 ...
## $ val% : num 2.5 2.5 2.5 2.5 2.5 2.5 2.5 2.5 2.5 2.5 ...
## $ %cum : num 2.5 5 7.5 10 12.5 15 17.5 20 22.5 25 ...
## $ val%cum: num 2.5 5 7.5 10 12.5 15 17.5 20 22.5 25 ...x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.09491 | 1 |
| 0.16894 | 1 |
| 0.18619 | 1 |
| 0.20365 | 1 |
| 0.21605 | 1 |
| 0.29869 | 1 |
| 0.35187 | 1 |
| 0.37999 | 1 |
| 0.48725 | 1 |
| 0.63948 | 1 |
| 0.64491 | 1 |
| 0.7476 | 1 |
| 0.7674 | 1 |
| 0.90169 | 1 |
| 1.41526 | 1 |
| 1.8033 | 1 |
| 1.80341 | 1 |
| 1.84596 | 1 |
| 2.24069 | 1 |
| 2.28589 | 1 |
| 2.44254 | 1 |
| 2.57852 | 1 |
| 2.59449 | 1 |
| 2.67409 | 1 |
| 2.81479 | 1 |
| 3.30848 | 1 |
| 3.33873 | 1 |
| 3.54386 | 1 |
| 3.66775 | 1 |
| 3.92621 | 1 |
| 4.18074 | 1 |
| 4.4563 | 1 |
| 4.74914 | 1 |
| 5.13913 | 1 |
| 5.97977 | 1 |
| 6.65185 | 1 |
| 6.74338 | 1 |
| 8.41491 | 1 |
| 9.837 | 1 |
| 13.40535 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.09491 2.09491 4.09491 6.09491 8.09491 10.09491 12.09491 14.09491distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.0949,2.09] | 17 | 0.4358974 | 17 |
| (2.09,4.09] | 12 | 0.3076923 | 29 |
| (4.09,6.09] | 5 | 0.1282051 | 34 |
| (6.09,8.09] | 2 | 0.0512821 | 36 |
| (8.09,10.1] | 2 | 0.0512821 | 38 |
| (10.1,12.1] | 0 | 0.0000000 | 38 |
| (12.1,14.1] | 1 | 0.0256410 | 39 |
str(Freq_table)## 'data.frame': 7 obs. of 4 variables:
## $ distance: Factor w/ 7 levels "(0.0949,2.09]",..: 1 2 3 4 5 6 7
## $ Freq : int 17 12 5 2 2 0 1
## $ Rel_Freq: num 0.4359 0.3077 0.1282 0.0513 0.0513 ...
## $ Cum_Freq: int 17 29 34 36 38 38 39df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.0949,2.09] | 17 |
| (2.09,4.09] | 12 |
| (4.09,6.09] | 5 |
| (6.09,8.09] | 2 |
| (8.09,10.1] | 2 |
| (10.1,12.1] | 0 |
| (12.1,14.1] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)## Warning: package 'pastecs' was built under R version 4.1.1##
## Attaching package: 'pastecs'## The following objects are masked from 'package:dplyr':
##
## first, laststat.desc(df_PA)## id date time continent_code country_name country_code
## nbr.val 4.000000e+01 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 7.500000e+02 NA NA NA NA NA
## max 7.512000e+03 NA NA NA NA NA
## range 6.762000e+03 NA NA NA NA NA
## sum 2.479400e+05 NA NA NA NA NA
## median 7.450500e+03 NA NA NA NA NA
## mean 6.198500e+03 NA NA NA NA NA
## SE.mean 3.051354e+02 NA NA NA NA NA
## CI.mean.0.95 6.171945e+02 NA NA NA NA NA
## var 3.724304e+06 NA NA NA NA NA
## std.dev 1.929846e+03 NA NA NA NA NA
## coef.var 3.113407e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 4.000000e+01 NA 40.0000000 NA
## nbr.null NA 8.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 0.000000e+00 NA 0.0949100 NA
## max NA 3.215010e+05 NA 13.4053500 NA
## range NA 3.215010e+05 NA 13.3104400 NA
## sum NA 2.041483e+06 NA 117.9301600 NA
## median NA 2.365500e+03 NA 2.3642150 NA
## mean NA 5.103707e+04 NA 2.9482540 NA
## SE.mean NA 1.674111e+04 NA 0.4634140 NA
## CI.mean.0.95 NA 3.386208e+04 NA 0.9373432 NA
## var NA 1.121058e+10 NA 8.5900997 NA
## std.dev NA 1.058800e+05 NA 2.9308872 NA
## coef.var NA 2.074571e+00 NA 0.9941095 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 40.00000000 4.000000e+01 NA NA NA
## nbr.null 0.00000000 0.000000e+00 NA NA NA
## nbr.na 0.00000000 0.000000e+00 NA NA NA
## min 7.59550000 -8.286620e+01 NA NA NA
## max 9.56760000 -7.908960e+01 NA NA NA
## range 1.97210000 3.776600e+00 NA NA NA
## sum 361.65930000 -3.232397e+03 NA NA NA
## median 9.07300000 -7.989490e+01 NA NA NA
## mean 9.04148250 -8.080992e+01 NA NA NA
## SE.mean 0.05632097 2.230672e-01 NA NA NA
## CI.mean.0.95 0.11391991 4.511960e-01 NA NA NA
## var 0.12688206 1.990359e+00 NA NA NA
## std.dev 0.35620508 1.410801e+00 NA NA NA
## coef.var 0.03939676 -1.745826e-02 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 28.000000 38.0000000 NA
## nbr.null NA NA NA 27.000000 33.0000000 NA
## nbr.na NA NA NA 12.000000 2.0000000 NA
## min NA NA NA 0.000000 0.0000000 NA
## max NA NA NA 45.000000 8.0000000 NA
## range NA NA NA 45.000000 8.0000000 NA
## sum NA NA NA 45.000000 23.0000000 NA
## median NA NA NA 0.000000 0.0000000 NA
## mean NA NA NA 1.607143 0.6052632 NA
## SE.mean NA NA NA 1.607143 0.3099568 NA
## CI.mean.0.95 NA NA NA 3.297585 0.6280321 NA
## var NA NA NA 72.321429 3.6507824 NA
## std.dev NA NA NA 8.504201 1.9107021 NA
## coef.var NA NA NA 5.291503 3.1568121 NA
## source_link prop ypos
## nbr.val NA 40.00000000 40.0000000
## nbr.null NA 0.00000000 0.0000000
## nbr.na NA 0.00000000 0.0000000
## min NA 0.08047984 0.7826497
## max NA 11.36719394 98.1106190
## range NA 11.28671410 97.3279694
## sum NA 100.00000000 1766.6812798
## median NA 2.00475858 42.6414180
## mean NA 2.50000000 44.1670320
## SE.mean NA 0.39295627 4.2497154
## CI.mean.0.95 NA 0.79482907 8.5958607
## var NA 6.17658511 722.4032223
## std.dev NA 2.48527365 26.8775598
## coef.var NA 0.99410946 0.6085435boxplot(data, horizontal=TRUE, col='green')
Gráfico para Bocas del Toro (Panama)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_PA<- subset(df, state == "Bocas del Toro")
knitr::kable(head(df_PA))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 3168 | 3/2/11 | Night | NA | Panama | PA | Bocas del Toro | 8114 | Almirante | 8.41491 | NA | 9.3224 | -82.4732 | (9.3224, -82.473200000000006) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.newsroompanama.com/panama/2434-off-season-rain-creating-crop-worries-and-landslides.html |
| 7489 | 6/21/15 | Morning | NA | Panama | PA | Bocas del Toro | 993 | Punta Peña | 0.29869 | Above road | 8.9070 | -82.1867 | (8.907, -82.186700000000002) | Landslide | Landslide | Small | Rain | NA | 0 | 0 | tvn | http://www.tvn-2.com/videos/noticias/Deslizamientos-Punta-Pena-Chiriqui-Grande_2_4237096253.html |
| 7497 | 6/29/15 | NA | NA | Panama | PA | Bocas del Toro | 22900 | Changuinola | 5.97977 | Above road | 9.3880 | -82.4858 | (9.3879999999999999, -82.485799999999998) | Landslide | Landslide | Small | Downpour | NA | 0 | 0 | La Prensa | http://www.prensa.com/provincias/Continuan-fuertes-lluvias-Bocas-Toro_0_4243075788.html |
| 7498 | 6/29/15 | NA | NA | Panama | PA | Bocas del Toro | 918 | Valle del Risco | 6.65185 | Unknown | 9.2102 | -82.3705 | (9.2102000000000004, -82.370500000000007) | Landslide | Landslide | Medium | Downpour | NA | 0 | 0 | La Prensa | http://www.prensa.com/provincias/Continuan-fuertes-lluvias-Bocas-Toro_0_4243075788.html |
| 7499 | 12/21/15 | NA | NA | Panama | PA | Bocas del Toro | 0 | Pueblo Nuevo | 3.92621 | Above road | 8.8543 | -82.1825 | (8.8543000000000003, -82.182500000000005) | Landslide | Mudslide | Small | Rain | NA | 0 | 0 | Panama America | http://www.panamaamerica.com.pa/provincias/despejan-hacia-bocas-del-toro-por-deslizamiento-1005781 |
| 7500 | 5/24/15 | 23:30 | NA | Panama | PA | Bocas del Toro | 918 | Valle del Risco | 5.13913 | Above road | 9.2279 | -82.3808 | (9.2279, -82.380799999999994) | Landslide | Mudslide | Medium | Rain | NA | 0 | 0 | Panama America | http://www.panamaamerica.com.pa/provincias/deslizamiento-de-tierra-en-bocas-del-toro-provoca-obstruccion-de-ambos-panos-977372 |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_PA, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_PA, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_PA, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_PA <- df_PA %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_PA$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_PA, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_PA$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 6.65185 |
| 5.13913 |
| 0.29869 |
| 3.92621 |
| 5.97977 |
| 4.45630 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_PA$distance
names(distance) <- df_PA$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Almirante 8.4149100 8.4149100 24.1344073 24.1344073
## Valle del Risco 6.6518500 15.0667600 19.0778579 43.2122652
## Changuinola 5.9797700 21.0465300 17.1502969 60.3625620
## Valle del Risco 5.1391300 26.1856600 14.7392969 75.1018589
## Cauchero 4.4563000 30.6419600 12.7809043 87.8827632
## Pueblo Nuevo 3.9262100 34.5681700 11.2605781 99.1433413
## Punta Peña 0.2986900 34.8668600 0.8566587 100.0000000stem(df_PA$"distance")##
## The decimal point is at the |
##
## 0 | 3
## 2 | 9
## 4 | 51
## 6 | 07
## 8 | 4head(df_PA)## # A tibble: 6 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 7498 6/29/15 <NA> <NA> Panama PA Boca~ 918
## 2 7500 5/24/15 23:30 <NA> Panama PA Boca~ 918
## 3 7489 6/21/15 Morning <NA> Panama PA Boca~ 993
## 4 7499 12/21/15 <NA> <NA> Panama PA Boca~ 0
## 5 7497 6/29/15 <NA> <NA> Panama PA Boca~ 22900
## 6 7501 10/8/15 <NA> <NA> Panama PA Boca~ 0
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_PA))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 7498 | 6/29/15 | NA | NA | Panama | PA | Bocas del Toro | 918 | Valle del Risco | 6.65185 | Unknown | 9.2102 | -82.3705 | (9.2102000000000004, -82.370500000000007) | Landslide | Landslide | Medium | Downpour | NA | 0 | 0 | La Prensa | http://www.prensa.com/provincias/Continuan-fuertes-lluvias-Bocas-Toro_0_4243075788.html | 19.0778579 | 9.538929 |
| 7500 | 5/24/15 | 23:30 | NA | Panama | PA | Bocas del Toro | 918 | Valle del Risco | 5.13913 | Above road | 9.2279 | -82.3808 | (9.2279, -82.380799999999994) | Landslide | Mudslide | Medium | Rain | NA | 0 | 0 | Panama America | http://www.panamaamerica.com.pa/provincias/deslizamiento-de-tierra-en-bocas-del-toro-provoca-obstruccion-de-ambos-panos-977372 | 14.7392969 | 26.447506 |
| 7489 | 6/21/15 | Morning | NA | Panama | PA | Bocas del Toro | 993 | Punta Peña | 0.29869 | Above road | 8.9070 | -82.1867 | (8.907, -82.186700000000002) | Landslide | Landslide | Small | Rain | NA | 0 | 0 | tvn | http://www.tvn-2.com/videos/noticias/Deslizamientos-Punta-Pena-Chiriqui-Grande_2_4237096253.html | 0.8566587 | 34.245484 |
| 7499 | 12/21/15 | NA | NA | Panama | PA | Bocas del Toro | 0 | Pueblo Nuevo | 3.92621 | Above road | 8.8543 | -82.1825 | (8.8543000000000003, -82.182500000000005) | Landslide | Mudslide | Small | Rain | NA | 0 | 0 | Panama America | http://www.panamaamerica.com.pa/provincias/despejan-hacia-bocas-del-toro-por-deslizamiento-1005781 | 11.2605781 | 40.304102 |
| 7497 | 6/29/15 | NA | NA | Panama | PA | Bocas del Toro | 22900 | Changuinola | 5.97977 | Above road | 9.3880 | -82.4858 | (9.3879999999999999, -82.485799999999998) | Landslide | Landslide | Small | Downpour | NA | 0 | 0 | La Prensa | http://www.prensa.com/provincias/Continuan-fuertes-lluvias-Bocas-Toro_0_4243075788.html | 17.1502969 | 54.509540 |
| 7501 | 10/8/15 | NA | NA | Panama | PA | Bocas del Toro | 0 | Cauchero | 4.45630 | Above road | 9.1261 | -82.2996 | (9.1260999999999992, -82.299599999999998) | Landslide | Landslide | Small | Rain | NA | 0 | 0 | Mi Diario | http://m.midiario.com/uhora/nacionales/se-registran-deslizamientos-en-chiriqu%C3%AD-grande | 12.7809043 | 69.475141 |
stem(df_PA$"distance")##
## The decimal point is at the |
##
## 0 | 3
## 2 | 9
## 4 | 51
## 6 | 07
## 8 | 4stem(df_PA$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 3
## 1 |
## 2 |
## 3 | 9
## 4 | 5
## 5 | 1
## 6 | 07
## 7 |
## 8 | 4Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.29869 | 1 | 14.3 | 14.3 | 14.3 | 14.3 |
| 3.92621 | 1 | 14.3 | 14.3 | 28.6 | 28.6 |
| 4.4563 | 1 | 14.3 | 14.3 | 42.9 | 42.9 |
| 5.13913 | 1 | 14.3 | 14.3 | 57.1 | 57.1 |
| 5.97977 | 1 | 14.3 | 14.3 | 71.4 | 71.4 |
| 6.65185 | 1 | 14.3 | 14.3 | 85.7 | 85.7 |
| 8.41491 | 1 | 14.3 | 14.3 | 100.0 | 100.0 |
| Total | 7 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 8 obs. of 5 variables:
## $ n : num 1 1 1 1 1 1 1 7
## $ % : num 14.3 14.3 14.3 14.3 14.3 14.3 14.3 100
## $ val% : num 14.3 14.3 14.3 14.3 14.3 14.3 14.3 100
## $ %cum : num 14.3 28.6 42.9 57.1 71.4 85.7 100 100
## $ val%cum: num 14.3 28.6 42.9 57.1 71.4 85.7 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.29869 | 1 |
| 3.92621 | 1 |
| 4.4563 | 1 |
| 5.13913 | 1 |
| 5.97977 | 1 |
| 6.65185 | 1 |
| 8.41491 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.29869 3.29869 6.29869 9.29869distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.299,3.3] | 0 | 0.0000000 | 0 |
| (3.3,6.3] | 4 | 0.6666667 | 4 |
| (6.3,9.3] | 2 | 0.3333333 | 6 |
str(Freq_table)## 'data.frame': 3 obs. of 4 variables:
## $ distance: Factor w/ 3 levels "(0.299,3.3]",..: 1 2 3
## $ Freq : int 0 4 2
## $ Rel_Freq: num 0 0.667 0.333
## $ Cum_Freq: int 0 4 6df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.299,3.3] | 0 |
| (3.3,6.3] | 4 |
| (6.3,9.3] | 2 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_PA)## id date time continent_code country_name country_code
## nbr.val 7.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 3.168000e+03 NA NA NA NA NA
## max 7.501000e+03 NA NA NA NA NA
## range 4.333000e+03 NA NA NA NA NA
## sum 4.815200e+04 NA NA NA NA NA
## median 7.498000e+03 NA NA NA NA NA
## mean 6.878857e+03 NA NA NA NA NA
## SE.mean 6.184780e+02 NA NA NA NA NA
## CI.mean.0.95 1.513361e+03 NA NA NA NA NA
## var 2.677605e+06 NA NA NA NA NA
## std.dev 1.636339e+03 NA NA NA NA NA
## coef.var 2.378795e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 7.000000e+00 NA 7.0000000 NA
## nbr.null NA 2.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 0.000000e+00 NA 0.2986900 NA
## max NA 2.290000e+04 NA 8.4149100 NA
## range NA 2.290000e+04 NA 8.1162200 NA
## sum NA 3.384300e+04 NA 34.8668600 NA
## median NA 9.180000e+02 NA 5.1391300 NA
## mean NA 4.834714e+03 NA 4.9809800 NA
## SE.mean NA 3.197087e+03 NA 0.9626098 NA
## CI.mean.0.95 NA 7.822989e+03 NA 2.3554214 NA
## var NA 7.154954e+07 NA 6.4863239 NA
## std.dev NA 8.458696e+03 NA 2.5468262 NA
## coef.var NA 1.749575e+00 NA 0.5113103 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 7.00000000 7.000000e+00 NA NA NA
## nbr.null 0.00000000 0.000000e+00 NA NA NA
## nbr.na 0.00000000 0.000000e+00 NA NA NA
## min 8.85430000 -8.248580e+01 NA NA NA
## max 9.38800000 -8.218250e+01 NA NA NA
## range 0.53370000 3.033000e-01 NA NA NA
## sum 64.03590000 -5.763791e+02 NA NA NA
## median 9.21020000 -8.237050e+01 NA NA NA
## mean 9.14798571 -8.233987e+01 NA NA NA
## SE.mean 0.07607773 4.668383e-02 NA NA NA
## CI.mean.0.95 0.18615551 1.142312e-01 NA NA NA
## var 0.04051475 1.525566e-02 NA NA NA
## std.dev 0.20128276 1.235138e-01 NA NA NA
## coef.var 0.02200296 -1.500049e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 6 7 NA
## nbr.null NA NA NA 6 7 NA
## nbr.na NA NA NA 1 0 NA
## min NA NA NA 0 0 NA
## max NA NA NA 0 0 NA
## range NA NA NA 0 0 NA
## sum NA NA NA 0 0 NA
## median NA NA NA 0 0 NA
## mean NA NA NA 0 0 NA
## SE.mean NA NA NA 0 0 NA
## CI.mean.0.95 NA NA NA 0 0 NA
## var NA NA NA 0 0 NA
## std.dev NA NA NA 0 0 NA
## coef.var NA NA NA NaN NaN NA
## source_link prop ypos
## nbr.val NA 7.0000000 7.0000000
## nbr.null NA 0.0000000 0.0000000
## nbr.na NA 0.0000000 0.0000000
## min NA 0.8566587 9.5389289
## max NA 24.1344073 87.9327964
## range NA 23.2777486 78.3938674
## sum NA 100.0000000 322.4534988
## median NA 14.7392969 40.3041025
## mean NA 14.2857143 46.0647855
## SE.mean NA 2.7608160 10.0760751
## CI.mean.0.95 NA 6.7554733 24.6552675
## var NA 53.3547333 710.6910217
## std.dev NA 7.3044324 26.6587888
## coef.var NA 0.5113103 0.5787238boxplot(data, horizontal=TRUE, col='green')
Gráfico para Chiriquí (Panama)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_PA<- subset(df, state == "Chiriquí")
knitr::kable(head(df_PA))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 905 | 11/25/08 | NA | NA | Panama | PA | Chiriquí | 6123 | Boquete | 9.83700 | NA | 8.7870 | -82.3440 | (8.7870000000000008, -82.343999999999994) | Landslide | Complex | Medium | Downpour | NA | NA | 8 | NA | http://www.iht.com/articles/ap/2008/11/26/news/LT-Panama-Flooding.php |
| 6699 | 9/12/14 | NA | NA | Panama | PA | Chiriquí | 11245 | Volcán | 0.35187 | Above road | 8.7636 | -82.6342 | (8.7636000000000003, -82.634200000000007) | Landslide | Landslide | Small | Rain | NA | 0 | 0 | Estrella de Panama | http://laestrella.com.pa/panama/nacional/reportan-deslizamiento-tierra-chiriqui/23804230 |
| 6700 | 9/25/14 | NA | NA | Panama | PA | Chiriquí | 1908 | Río Sereno | 0.64491 | Above road | 8.8229 | -82.8416 | (8.8229000000000006, -82.8416) | Landslide | Landslide | Medium | Downpour | NA | 0 | 0 | Estrella de Panama | http://laestrella.com.pa/panama/nacional/deslizamiento-tierra-obstruye-sereno/23807753 |
| 6704 | 8/17/14 | Afternoon | NA | Panama | PA | Chiriquí | 2957 | Cerro Punta | 3.33873 | Unknown | 8.8528 | -82.5969 | (8.8528000000000002, -82.596900000000005) | Landslide | Landslide | Small | Downpour | NA | 0 | 0 | FullPassPanama | http://fullpasspanama.net/situacion-en-cerro-punta-chiriqui/ |
| 7502 | 2/10/15 | NA | NA | Panama | PA | Chiriquí | 0 | Boca de Balsa | 2.44254 | Above road | 8.5121 | -82.0513 | (8.5121000000000002, -82.051299999999998) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | NA | http://www.telemetro.com/nacionales/Crecida-Chiriqui-provoca-puente-potabilizadoras_0_860014389.html |
| 7503 | 11/23/15 | NA | NA | Panama | PA | Chiriquí | 1908 | Río Sereno | 3.66775 | Unknown | 8.7868 | -82.8662 | (8.7867999999999995, -82.866200000000006) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | La Estrella | http://laestrella.com.pa/panama/nacional/inundaciones-deslizamientos-afectan-chiriqui/23905610 |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_PA, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_PA, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_PA, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_PA <- df_PA %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_PA$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_PA, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_PA$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 0.35187 |
| 0.64491 |
| 3.66775 |
| 0.90169 |
| 6.74338 |
| 3.33873 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_PA$distance
names(distance) <- df_PA$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Boquete 9.837000 9.837000 34.750066 34.750066
## Monte Lirio 6.743380 16.580380 23.821582 58.571648
## Río Sereno 3.667750 20.248130 12.956649 71.528296
## Cerro Punta 3.338730 23.586860 11.794357 83.322653
## Boca de Balsa 2.442540 26.029400 8.628487 91.951140
## Palmira Centro 0.901690 26.931090 3.185299 95.136439
## Río Sereno 0.644910 27.576000 2.278201 97.414640
## Breñón 0.379990 27.955990 1.342348 98.756988
## Volcán 0.351870 28.307860 1.243012 100.000000stem(df_PA$"distance")##
## The decimal point is at the |
##
## 0 | 4469
## 2 | 437
## 4 |
## 6 | 7
## 8 | 8head(df_PA)## # A tibble: 6 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 6699 9/12/14 <NA> <NA> Panama PA Chir~ 11245
## 2 6700 9/25/14 <NA> <NA> Panama PA Chir~ 1908
## 3 7503 11/23/15 <NA> <NA> Panama PA Chir~ 1908
## 4 7504 11/22/15 <NA> <NA> Panama PA Chir~ 0
## 5 7507 11/11/15 <NA> <NA> Panama PA Chir~ 2823
## 6 6704 8/17/14 Afternoon <NA> Panama PA Chir~ 2957
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_PA))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 6699 | 9/12/14 | NA | NA | Panama | PA | Chiriquí | 11245 | Volcán | 0.35187 | Above road | 8.7636 | -82.6342 | (8.7636000000000003, -82.634200000000007) | Landslide | Landslide | Small | Rain | NA | 0 | 0 | Estrella de Panama | http://laestrella.com.pa/panama/nacional/reportan-deslizamiento-tierra-chiriqui/23804230 | 1.243012 | 0.6215058 |
| 6700 | 9/25/14 | NA | NA | Panama | PA | Chiriquí | 1908 | Río Sereno | 0.64491 | Above road | 8.8229 | -82.8416 | (8.8229000000000006, -82.8416) | Landslide | Landslide | Medium | Downpour | NA | 0 | 0 | Estrella de Panama | http://laestrella.com.pa/panama/nacional/deslizamiento-tierra-obstruye-sereno/23807753 | 2.278201 | 2.3821122 |
| 7503 | 11/23/15 | NA | NA | Panama | PA | Chiriquí | 1908 | Río Sereno | 3.66775 | Unknown | 8.7868 | -82.8662 | (8.7867999999999995, -82.866200000000006) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | La Estrella | http://laestrella.com.pa/panama/nacional/inundaciones-deslizamientos-afectan-chiriqui/23905610 | 12.956649 | 9.9995372 |
| 7504 | 11/22/15 | NA | NA | Panama | PA | Chiriquí | 0 | Palmira Centro | 0.90169 | Above road | 8.7463 | -82.4569 | (8.7462999999999997, -82.456900000000005) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | Estrella de Panama | http://laestrella.com.pa/panama/nacional/inundaciones-deslizamientos-afectan-chiriqui/23905610 | 3.185299 | 18.0705112 |
| 7507 | 11/11/15 | NA | NA | Panama | PA | Chiriquí | 2823 | Monte Lirio | 6.74338 | Above road | 8.8330 | -82.8014 | (8.8330000000000002, -82.801400000000001) | Landslide | Landslide | Small | Downpour | NA | 0 | 0 | Bugaba | http://www.soydebugaba.com/noticias/fuertes-lluvias-causaron-inundaciones-en-boquete-y-deslizamientos-en-renacimiento | 23.821582 | 31.5739515 |
| 6704 | 8/17/14 | Afternoon | NA | Panama | PA | Chiriquí | 2957 | Cerro Punta | 3.33873 | Unknown | 8.8528 | -82.5969 | (8.8528000000000002, -82.596900000000005) | Landslide | Landslide | Small | Downpour | NA | 0 | 0 | FullPassPanama | http://fullpasspanama.net/situacion-en-cerro-punta-chiriqui/ | 11.794357 | 49.3819208 |
stem(df_PA$"distance")##
## The decimal point is at the |
##
## 0 | 4469
## 2 | 437
## 4 |
## 6 | 7
## 8 | 8stem(df_PA$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 4469
## 1 |
## 2 | 4
## 3 | 37
## 4 |
## 5 |
## 6 | 7
## 7 |
## 8 |
## 9 | 8Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.35187 | 1 | 11.1 | 11.1 | 11.1 | 11.1 |
| 0.37999 | 1 | 11.1 | 11.1 | 22.2 | 22.2 |
| 0.64491 | 1 | 11.1 | 11.1 | 33.3 | 33.3 |
| 0.90169 | 1 | 11.1 | 11.1 | 44.4 | 44.4 |
| 2.44254 | 1 | 11.1 | 11.1 | 55.6 | 55.6 |
| 3.33873 | 1 | 11.1 | 11.1 | 66.7 | 66.7 |
| 3.66775 | 1 | 11.1 | 11.1 | 77.8 | 77.8 |
| 6.74338 | 1 | 11.1 | 11.1 | 88.9 | 88.9 |
| 9.837 | 1 | 11.1 | 11.1 | 100.0 | 100.0 |
| Total | 9 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 10 obs. of 5 variables:
## $ n : num 1 1 1 1 1 1 1 1 1 9
## $ % : num 11.1 11.1 11.1 11.1 11.1 11.1 11.1 11.1 11.1 100
## $ val% : num 11.1 11.1 11.1 11.1 11.1 11.1 11.1 11.1 11.1 100
## $ %cum : num 11.1 22.2 33.3 44.4 55.6 66.7 77.8 88.9 100 100
## $ val%cum: num 11.1 22.2 33.3 44.4 55.6 66.7 77.8 88.9 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.35187 | 1 |
| 0.37999 | 1 |
| 0.64491 | 1 |
| 0.90169 | 1 |
| 2.44254 | 1 |
| 3.33873 | 1 |
| 3.66775 | 1 |
| 6.74338 | 1 |
| 9.837 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.35187 2.35187 4.35187 6.35187 8.35187 10.35187distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.352,2.35] | 3 | 0.375 | 3 |
| (2.35,4.35] | 3 | 0.375 | 6 |
| (4.35,6.35] | 0 | 0.000 | 6 |
| (6.35,8.35] | 1 | 0.125 | 7 |
| (8.35,10.4] | 1 | 0.125 | 8 |
str(Freq_table)## 'data.frame': 5 obs. of 4 variables:
## $ distance: Factor w/ 5 levels "(0.352,2.35]",..: 1 2 3 4 5
## $ Freq : int 3 3 0 1 1
## $ Rel_Freq: num 0.375 0.375 0 0.125 0.125
## $ Cum_Freq: int 3 6 6 7 8df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.352,2.35] | 3 |
| (2.35,4.35] | 3 |
| (4.35,6.35] | 0 |
| (6.35,8.35] | 1 |
| (8.35,10.4] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_PA)## id date time continent_code country_name country_code
## nbr.val 9.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 9.050000e+02 NA NA NA NA NA
## max 7.507000e+03 NA NA NA NA NA
## range 6.602000e+03 NA NA NA NA NA
## sum 5.852900e+04 NA NA NA NA NA
## median 7.502000e+03 NA NA NA NA NA
## mean 6.503222e+03 NA NA NA NA NA
## SE.mean 7.116808e+02 NA NA NA NA NA
## CI.mean.0.95 1.641139e+03 NA NA NA NA NA
## var 4.558406e+06 NA NA NA NA NA
## std.dev 2.135042e+03 NA NA NA NA NA
## coef.var 3.283053e-01 NA NA NA NA NA
## state population city distance location_description latitude
## nbr.val NA 9.000000e+00 NA 9.000000 NA 9.00000000
## nbr.null NA 3.000000e+00 NA 0.000000 NA 0.00000000
## nbr.na NA 0.000000e+00 NA 0.000000 NA 0.00000000
## min NA 0.000000e+00 NA 0.351870 NA 8.51210000
## max NA 1.124500e+04 NA 9.837000 NA 8.85280000
## range NA 1.124500e+04 NA 9.485130 NA 0.34070000
## sum NA 2.696400e+04 NA 28.307860 NA 78.68170000
## median NA 1.908000e+03 NA 2.442540 NA 8.78680000
## mean NA 2.996000e+03 NA 3.145318 NA 8.74241111
## SE.mean NA 1.219922e+03 NA 1.088227 NA 0.03937552
## CI.mean.0.95 NA 2.813145e+03 NA 2.509457 NA 0.09080011
## var NA 1.339389e+07 NA 10.658149 NA 0.01395388
## std.dev NA 3.659766e+03 NA 3.264682 NA 0.11812656
## coef.var NA 1.221551e+00 NA 1.037950 NA 0.01351190
## longitude geolocation hazard_type landslide_type
## nbr.val 9.000000e+00 NA NA NA
## nbr.null 0.000000e+00 NA NA NA
## nbr.na 0.000000e+00 NA NA NA
## min -8.286620e+01 NA NA NA
## max -8.205130e+01 NA NA NA
## range 8.149000e-01 NA NA NA
## sum -7.434157e+02 NA NA NA
## median -8.263420e+01 NA NA NA
## mean -8.260174e+01 NA NA NA
## SE.mean 9.188235e-02 NA NA NA
## CI.mean.0.95 2.118811e-01 NA NA NA
## var 7.598130e-02 NA NA NA
## std.dev 2.756470e-01 NA NA NA
## coef.var -3.337061e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 8 9.0000000 NA
## nbr.null NA NA NA 8 8.0000000 NA
## nbr.na NA NA NA 1 0.0000000 NA
## min NA NA NA 0 0.0000000 NA
## max NA NA NA 0 8.0000000 NA
## range NA NA NA 0 8.0000000 NA
## sum NA NA NA 0 8.0000000 NA
## median NA NA NA 0 0.0000000 NA
## mean NA NA NA 0 0.8888889 NA
## SE.mean NA NA NA 0 0.8888889 NA
## CI.mean.0.95 NA NA NA 0 2.0497815 NA
## var NA NA NA 0 7.1111111 NA
## std.dev NA NA NA 0 2.6666667 NA
## coef.var NA NA NA NaN 3.0000000 NA
## source_link prop ypos
## nbr.val NA 9.000000 9.0000000
## nbr.null NA 0.000000 0.0000000
## nbr.na NA 0.000000 0.0000000
## min NA 1.243012 0.6215058
## max NA 34.750066 95.6857565
## range NA 33.507054 95.0642507
## sum NA 100.000000 337.6620486
## median NA 8.628487 31.5739515
## mean NA 11.111111 37.5180054
## SE.mean NA 3.844259 11.1563092
## CI.mean.0.95 NA 8.864877 25.7264952
## var NA 133.004927 1120.1691177
## std.dev NA 11.532776 33.4689276
## coef.var NA 1.037950 0.8920764boxplot(data, horizontal=TRUE, col='green')
Gráfico para Colón (Panama)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_PA<- subset(df, state == "Colón")
knitr::kable(head(df_PA))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2652 | 10/25/10 | NA | NA | Honduras | HN | Colón | 1441 | Cusuna | 36.37629 | NA | 15.5227 | -85.2650 | (15.5227, -85.265000000000001) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Richard | NA | 0 | NA | http://www.reliefweb.int/rw/RWFiles2010.nsf/FilesByRWDocUnidFilename/LSGZ-8ALBZE-full_report.pdf/$File/full_report.pdf |
| 2794 | 12/8/10 | NA | NA | Panama | PA | Colón | 1310 | El Giral | 1.80330 | NA | 9.2332 | -79.6961 | (9.2332000000000001, -79.696100000000001) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.portworld.com/news/i98731/Panama_Canal_disrupted_by_floods |
| 2795 | 12/9/10 | Morning | NA | Panama | PA | Colón | 1274 | Portobelo | 0.09491 | Deforested slope | 9.5493 | -79.6505 | (9.5493000000000006, -79.650499999999994) | Landslide | Mudslide | Medium | Downpour | NA | NA | 8 | Fox News Latino | http://latino.foxnews.com/latino/news/2010/12/09/heavy-rains-kill-panama-force-canal-close/ |
| 4632 | 11/25/12 | NA | NA | Panama | PA | Colón | 76643 | Colón | 0.16894 | NA | 9.3600 | -79.9001 | (9.36, -79.900099999999995) | Landslide | Landslide | Medium | Rain | NA | NA | 2 | NA | http://www.ndtv.com/article/world/two-dead-in-landslide-as-floods-hit-panama-297138 |
| 4879 | 5/28/13 | NA | NA | Panama | PA | Colón | 1274 | Portobelo | 2.67409 | NA | 9.5676 | -79.6667 | (9.5676000000000005, -79.666700000000006) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | www.newsroompanama.com | http://www.newsroompanama.com/panama/5804-rain-brings-floods-landslides-and-traffic-chaos-to-colon.html |
| 4880 | 5/28/13 | NA | NA | Panama | PA | Colón | 3302 | Margarita | 0.74760 | NA | 9.3381 | -79.8897 | (9.3381000000000007, -79.889700000000005) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | NA |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_PA, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_PA, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_PA, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_PA <- df_PA %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_PA$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_PA, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_PA$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 0.09491 |
| 2.67409 |
| 4.74914 |
| 0.18619 |
| 2.28589 |
| 0.74760 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_PA$distance
names(distance) <- df_PA$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Cusuna 36.3762900 36.3762900 71.7525220 71.7525220
## Nuevo San Juan 4.7491400 41.1254300 9.3677165 81.1202386
## Portobelo 2.6740900 43.7995200 5.2746638 86.3949024
## María Chiquita 2.2858900 46.0854100 4.5089363 90.9038387
## El Giral 1.8033000 47.8887100 3.5570236 94.4608623
## Margarita 0.7674000 48.6561100 1.5137026 95.9745649
## Margarita 0.7476000 49.4037100 1.4746470 97.4492119
## Cativá 0.6394800 50.0431900 1.2613794 98.7105913
## Colón 0.2036500 50.2468400 0.4017012 99.1122925
## Nueva Providencia 0.1861900 50.4330300 0.3672613 99.4795538
## Colón 0.1689400 50.6019700 0.3332355 99.8127893
## Portobelo 0.0949100 50.6968800 0.1872107 100.0000000stem(df_PA$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 00001112235
## 1 |
## 2 |
## 3 | 6head(df_PA)## # A tibble: 6 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 2795 12/9/10 Morning <NA> Panama PA Colón 1274
## 2 4879 5/28/13 <NA> <NA> Panama PA Colón 1274
## 3 6702 5/9/14 <NA> <NA> Panama PA Colón 1232
## 4 7450 9/7/15 <NA> <NA> Panama PA Colón 0
## 5 7451 7/2/15 <NA> <NA> Panama PA Colón 1146
## 6 4880 5/28/13 <NA> <NA> Panama PA Colón 3302
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_PA))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2795 | 12/9/10 | Morning | NA | Panama | PA | Colón | 1274 | Portobelo | 0.09491 | Deforested slope | 9.5493 | -79.6505 | (9.5493000000000006, -79.650499999999994) | Landslide | Mudslide | Medium | Downpour | NA | NA | 8 | Fox News Latino | http://latino.foxnews.com/latino/news/2010/12/09/heavy-rains-kill-panama-force-canal-close/ | 0.1872107 | 0.0936054 |
| 4879 | 5/28/13 | NA | NA | Panama | PA | Colón | 1274 | Portobelo | 2.67409 | NA | 9.5676 | -79.6667 | (9.5676000000000005, -79.666700000000006) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | www.newsroompanama.com | http://www.newsroompanama.com/panama/5804-rain-brings-floods-landslides-and-traffic-chaos-to-colon.html | 5.2746638 | 2.8245427 |
| 6702 | 5/9/14 | NA | NA | Panama | PA | Colón | 1232 | Nuevo San Juan | 4.74914 | Below road | 9.2924 | -79.7478 | (9.2924000000000007, -79.747799999999998) | Landslide | Landslide | Small | Downpour | NA | 0 | 0 | NEXtv | http://www.nexpanama.com/videos/deslizamiento-de-tierra-en-carretera-boyd-roosevelt-3800 | 9.3677165 | 10.1457328 |
| 7450 | 9/7/15 | NA | NA | Panama | PA | Colón | 0 | Nueva Providencia | 0.18619 | Unknown | 9.2619 | -79.8164 | (9.2619000000000007, -79.816400000000002) | Landslide | Landslide | Medium | Downpour | NA | 0 | 0 | Panamá América | http://www.panamaamerica.com.pa/provincias/un-colegio-y-20-casas-afectadas-por-las-lluvias-en-colon-991260 | 0.3672613 | 15.0132217 |
| 7451 | 7/2/15 | NA | NA | Panama | PA | Colón | 1146 | María Chiquita | 2.28589 | Mine construction | 9.4405 | -79.7754 | (9.4405000000000001, -79.775400000000005) | Landslide | Other | Medium | Construction | NA | 0 | 1 | El Siglo | http://elsiglo.com/panama/alud-tierra-obrero-colon-muere/23876592 | 4.5089363 | 17.4513205 |
| 4880 | 5/28/13 | NA | NA | Panama | PA | Colón | 3302 | Margarita | 0.74760 | NA | 9.3381 | -79.8897 | (9.3381000000000007, -79.889700000000005) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | NA | 1.4746470 | 20.4431121 |
stem(df_PA$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 00001112235
## 1 |
## 2 |
## 3 | 6stem(df_PA$"distance", scale = 2)##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 0000111223
## 0 | 5
## 1 |
## 1 |
## 2 |
## 2 |
## 3 |
## 3 | 6Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.09491 | 1 | 8.3 | 8.3 | 8.3 | 8.3 |
| 0.16894 | 1 | 8.3 | 8.3 | 16.7 | 16.7 |
| 0.18619 | 1 | 8.3 | 8.3 | 25.0 | 25.0 |
| 0.20365 | 1 | 8.3 | 8.3 | 33.3 | 33.3 |
| 0.63948 | 1 | 8.3 | 8.3 | 41.7 | 41.7 |
| 0.7476 | 1 | 8.3 | 8.3 | 50.0 | 50.0 |
| 0.7674 | 1 | 8.3 | 8.3 | 58.3 | 58.3 |
| 1.8033 | 1 | 8.3 | 8.3 | 66.7 | 66.7 |
| 2.28589 | 1 | 8.3 | 8.3 | 75.0 | 75.0 |
| 2.67409 | 1 | 8.3 | 8.3 | 83.3 | 83.3 |
| 4.74914 | 1 | 8.3 | 8.3 | 91.7 | 91.7 |
| 36.37629 | 1 | 8.3 | 8.3 | 100.0 | 100.0 |
| Total | 12 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 13 obs. of 5 variables:
## $ n : num 1 1 1 1 1 1 1 1 1 1 ...
## $ % : num 8.3 8.3 8.3 8.3 8.3 8.3 8.3 8.3 8.3 8.3 ...
## $ val% : num 8.3 8.3 8.3 8.3 8.3 8.3 8.3 8.3 8.3 8.3 ...
## $ %cum : num 8.3 16.7 25 33.3 41.7 50 58.3 66.7 75 83.3 ...
## $ val%cum: num 8.3 16.7 25 33.3 41.7 50 58.3 66.7 75 83.3 ...x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.09491 | 1 |
| 0.16894 | 1 |
| 0.18619 | 1 |
| 0.20365 | 1 |
| 0.63948 | 1 |
| 0.7476 | 1 |
| 0.7674 | 1 |
| 1.8033 | 1 |
| 2.28589 | 1 |
| 2.67409 | 1 |
| 4.74914 | 1 |
| 36.37629 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.09491 8.09491 16.09491 24.09491 32.09491 40.09491distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.0949,8.09] | 10 | 0.9090909 | 10 |
| (8.09,16.1] | 0 | 0.0000000 | 10 |
| (16.1,24.1] | 0 | 0.0000000 | 10 |
| (24.1,32.1] | 0 | 0.0000000 | 10 |
| (32.1,40.1] | 1 | 0.0909091 | 11 |
str(Freq_table)## 'data.frame': 5 obs. of 4 variables:
## $ distance: Factor w/ 5 levels "(0.0949,8.09]",..: 1 2 3 4 5
## $ Freq : int 10 0 0 0 1
## $ Rel_Freq: num 0.9091 0 0 0 0.0909
## $ Cum_Freq: int 10 10 10 10 11df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.0949,8.09] | 10 |
| (8.09,16.1] | 0 |
| (16.1,24.1] | 0 |
| (24.1,32.1] | 0 |
| (32.1,40.1] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_PA)## id date time continent_code country_name country_code
## nbr.val 1.200000e+01 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 2.652000e+03 NA NA NA NA NA
## max 7.452000e+03 NA NA NA NA NA
## range 4.800000e+03 NA NA NA NA NA
## sum 6.181400e+04 NA NA NA NA NA
## median 4.880500e+03 NA NA NA NA NA
## mean 5.151167e+03 NA NA NA NA NA
## SE.mean 5.231425e+02 NA NA NA NA NA
## CI.mean.0.95 1.151429e+03 NA NA NA NA NA
## var 3.284136e+06 NA NA NA NA NA
## std.dev 1.812219e+03 NA NA NA NA NA
## coef.var 3.518074e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 1.200000e+01 NA 12.000000 NA
## nbr.null NA 1.000000e+00 NA 0.000000 NA
## nbr.na NA 0.000000e+00 NA 0.000000 NA
## min NA 0.000000e+00 NA 0.094910 NA
## max NA 7.664300e+04 NA 36.376290 NA
## range NA 7.664300e+04 NA 36.281380 NA
## sum NA 1.971740e+05 NA 50.696880 NA
## median NA 1.375500e+03 NA 0.757500 NA
## mean NA 1.643117e+04 NA 4.224740 NA
## SE.mean NA 8.446243e+03 NA 2.950226 NA
## CI.mean.0.95 NA 1.859006e+04 NA 6.493404 NA
## var NA 8.560683e+08 NA 104.446004 NA
## std.dev NA 2.925864e+04 NA 10.219883 NA
## coef.var NA 1.780680e+00 NA 2.419056 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 12.0000000 12.00000000 NA NA NA
## nbr.null 0.0000000 0.00000000 NA NA NA
## nbr.na 0.0000000 0.00000000 NA NA NA
## min 9.2332000 -85.26500000 NA NA NA
## max 15.5227000 -79.65050000 NA NA NA
## range 6.2895000 5.61450000 NA NA NA
## sum 118.6112000 -963.01940000 NA NA NA
## median 9.3590500 -79.81925000 NA NA NA
## mean 9.8842667 -80.25161667 NA NA NA
## SE.mean 0.5134407 0.45651767 NA NA NA
## CI.mean.0.95 1.1300754 1.00478862 NA NA NA
## var 3.1634562 2.50090061 NA NA NA
## std.dev 1.7786107 1.58142360 NA NA NA
## coef.var 0.1799436 -0.01970582 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 4 12.0000000 NA
## nbr.null NA NA NA 4 8.0000000 NA
## nbr.na NA NA NA 8 0.0000000 NA
## min NA NA NA 0 0.0000000 NA
## max NA NA NA 0 8.0000000 NA
## range NA NA NA 0 8.0000000 NA
## sum NA NA NA 0 15.0000000 NA
## median NA NA NA 0 0.0000000 NA
## mean NA NA NA 0 1.2500000 NA
## SE.mean NA NA NA 0 0.7084447 NA
## CI.mean.0.95 NA NA NA 0 1.5592763 NA
## var NA NA NA 0 6.0227273 NA
## std.dev NA NA NA 0 2.4541245 NA
## coef.var NA NA NA NaN 1.9632996 NA
## source_link prop ypos
## nbr.val NA 12.0000000 1.200000e+01
## nbr.null NA 0.0000000 0.000000e+00
## nbr.na NA 0.0000000 0.000000e+00
## min NA 0.1872107 9.360537e-02
## max NA 71.7525220 9.936931e+01
## range NA 71.5653113 9.927570e+01
## sum NA 100.0000000 4.705863e+02
## median NA 1.4941748 2.119020e+01
## mean NA 8.3333333 3.921552e+01
## SE.mean NA 5.8193444 1.127004e+01
## CI.mean.0.95 NA 12.8082906 2.480520e+01
## var NA 406.3772270 1.524167e+03
## std.dev NA 20.1588002 3.904058e+01
## coef.var NA 2.4190560 9.955389e-01boxplot(data, horizontal=TRUE, col='green')
Gráfico para Los Santos (Panama)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_PA<- subset(df, state == "Los Santos")
knitr::kable(head(df_PA))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 3167 | 3/2/11 | Night | NA | Panama | PA | Los Santos | 1283 | La Palma | 13.40535 | NA | 7.5955 | -80.38 | (7.5955000000000004, -80.38) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.newsroompanama.com/panama/2434-off-season-rain-creating-crop-worries-and-landslides.html |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_PA, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_PA, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_PA, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_PA <- df_PA %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_PA$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_PA, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_PA$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 13.40535 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()## geom_path: Each group consists of only one observation. Do you need to adjust
## the group aesthetic?
Diagrama de pareto
library(qcc)
distance <- df_PA$distance
names(distance) <- df_PA$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## La Palma 13.40535 13.40535 100.00000 100.00000stem(df_PA$"distance")
head(df_PA)## # A tibble: 1 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 3167 3/2/11 Night <NA> Panama PA Los Santos 1283
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_PA))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 3167 | 3/2/11 | Night | NA | Panama | PA | Los Santos | 1283 | La Palma | 13.40535 | NA | 7.5955 | -80.38 | (7.5955000000000004, -80.38) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.newsroompanama.com/panama/2434-off-season-rain-creating-crop-worries-and-landslides.html | 100 | 50 |
stem(df_PA$"distance")
stem(df_PA$"distance", scale = 2)Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 13.40535 | 1 | 100 | 100 | 100 | 100 |
| Total | 1 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 2 obs. of 5 variables:
## $ n : num 1 1
## $ % : num 100 100
## $ val% : num 100 100
## $ %cum : num 100 100
## $ val%cum: num 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 13.40535 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 13.40535distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (13.392,13.394] | 0 | 0 | 0 |
| (13.394,13.396] | 0 | 0 | 0 |
| (13.396,13.398] | 0 | 0 | 0 |
| (13.398,13.4] | 0 | 0 | 0 |
| (13.4,13.402] | 0 | 0 | 0 |
| (13.402,13.404] | 0 | 0 | 0 |
| (13.404,13.406] | 1 | 1 | 1 |
| (13.406,13.408] | 0 | 0 | 1 |
| (13.408,13.411] | 0 | 0 | 1 |
| (13.411,13.413] | 0 | 0 | 1 |
| (13.413,13.415] | 0 | 0 | 1 |
| (13.415,13.417] | 0 | 0 | 1 |
| (13.417,13.419] | 0 | 0 | 1 |
str(Freq_table)## 'data.frame': 13 obs. of 4 variables:
## $ distance: Factor w/ 13 levels "(13.392,13.394]",..: 1 2 3 4 5 6 7 8 9 10 ...
## $ Freq : int 0 0 0 0 0 0 1 0 0 0 ...
## $ Rel_Freq: num 0 0 0 0 0 0 1 0 0 0 ...
## $ Cum_Freq: int 0 0 0 0 0 0 1 1 1 1 ...df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (13.392,13.394] | 0 |
| (13.394,13.396] | 0 |
| (13.396,13.398] | 0 |
| (13.398,13.4] | 0 |
| (13.4,13.402] | 0 |
| (13.402,13.404] | 0 |
| (13.404,13.406] | 1 |
| (13.406,13.408] | 0 |
| (13.408,13.411] | 0 |
| (13.411,13.413] | 0 |
| (13.413,13.415] | 0 |
| (13.415,13.417] | 0 |
| (13.417,13.419] | 0 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_PA)## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced
## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced
## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced
## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced
## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## Warning in min(x): ningún argumento finito para min; retornando Inf## Warning in max(x): ningun argumento finito para max; retornando -Inf## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced
## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced
## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced
## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code state
## nbr.val 1 NA NA NA NA NA NA
## nbr.null 0 NA NA NA NA NA NA
## nbr.na 0 NA NA NA NA NA NA
## min 3167 NA NA NA NA NA NA
## max 3167 NA NA NA NA NA NA
## range 0 NA NA NA NA NA NA
## sum 3167 NA NA NA NA NA NA
## median 3167 NA NA NA NA NA NA
## mean 3167 NA NA NA NA NA NA
## SE.mean NA NA NA NA NA NA NA
## CI.mean.0.95 NaN NA NA NA NA NA NA
## var NA NA NA NA NA NA NA
## std.dev NA NA NA NA NA NA NA
## coef.var NA NA NA NA NA NA NA
## population city distance location_description latitude longitude
## nbr.val 1 NA 1.00000 NA 1.0000 1.00
## nbr.null 0 NA 0.00000 NA 0.0000 0.00
## nbr.na 0 NA 0.00000 NA 0.0000 0.00
## min 1283 NA 13.40535 NA 7.5955 -80.38
## max 1283 NA 13.40535 NA 7.5955 -80.38
## range 0 NA 0.00000 NA 0.0000 0.00
## sum 1283 NA 13.40535 NA 7.5955 -80.38
## median 1283 NA 13.40535 NA 7.5955 -80.38
## mean 1283 NA 13.40535 NA 7.5955 -80.38
## SE.mean NA NA NA NA NA NA
## CI.mean.0.95 NaN NA NaN NA NaN NaN
## var NA NA NA NA NA NA
## std.dev NA NA NA NA NA NA
## coef.var NA NA NA NA NA NA
## geolocation hazard_type landslide_type landslide_size trigger
## nbr.val NA NA NA NA NA
## nbr.null NA NA NA NA NA
## nbr.na NA NA NA NA NA
## min NA NA NA NA NA
## max NA NA NA NA NA
## range NA NA NA NA NA
## sum NA NA NA NA NA
## median NA NA NA NA NA
## mean NA NA NA NA NA
## SE.mean NA NA NA NA NA
## CI.mean.0.95 NA NA NA NA NA
## var NA NA NA NA NA
## std.dev NA NA NA NA NA
## coef.var NA NA NA NA NA
## storm_name injuries fatalities source_name source_link prop ypos
## nbr.val NA 0 1 NA NA 1 1
## nbr.null NA 0 1 NA NA 0 0
## nbr.na NA 1 0 NA NA 0 0
## min NA Inf 0 NA NA 100 50
## max NA -Inf 0 NA NA 100 50
## range NA -Inf 0 NA NA 0 0
## sum NA 0 0 NA NA 100 50
## median NA NA 0 NA NA 100 50
## mean NA NaN 0 NA NA 100 50
## SE.mean NA NA NA NA NA NA NA
## CI.mean.0.95 NA NaN NaN NA NA NaN NaN
## var NA NA NA NA NA NA NA
## std.dev NA NA NA NA NA NA NA
## coef.var NA NA NA NA NA NA NAboxplot(data, horizontal=TRUE, col='green')
Gráfico para Panamá (Panama)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_PA<- subset(df, state == "Panamá")
knitr::kable(head(df_PA))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 750 | 8/26/08 | NA | NA | Panama | PA | Panamá | 1287 | Cerro Azul | 1.84596 | NA | 9.1559 | -79.4295 | (9.1559000000000008, -79.429500000000004) | Landslide | Landslide | Medium | Downpour | NA | NA | NA | NA | http://news.xinhuanet.com/english/2008-08/27/content_9721298.htm |
| 5562 | 9/29/13 | NA | NA | Panama | PA | Panamá | 69102 | Las Cumbres | 2.81479 | NA | 9.0655 | -79.5516 | (9.0655000000000001, -79.551599999999993) | Landslide | Landslide | Medium | Downpour | NA | NA | NA | www.newsroompanama.com | http://www.newsroompanama.com/panama/6467--nearly-800-affeccted-by-floods-in-panama-city-region.html |
| 6701 | 9/14/14 | Morning | NA | Panama | PA | Panamá | 19782 | Alcaldedíaz | 1.41526 | Urban area | 9.1139 | -79.5626 | (9.1138999999999992, -79.562600000000003) | Landslide | Other | Small | Rain | NA | 0 | 0 | Estrella de Panama | http://laestrella.com.pa/panama/nacional/colapsa-pared-vivienda-alcade-diaz/23804690/foto/50372 |
| 6703 | 6/17/14 | NA | NA | Panama | PA | Panamá | 321501 | San Miguelito | 4.18074 | Unknown | 9.0329 | -79.5380 | (9.0328999999999997, -79.537999999999997) | Landslide | Mudslide | Medium | Unknown | NA | 0 | 0 | PanamaAmerica | http://www.panamaamerica.com.pa/nacion/reportan-deslizamiento-en-autopista-panama-colon# |
| 6705 | 6/24/14 | NA | NA | Panama | PA | Panamá | 9169 | Ancón | 2.24069 | Below road | 8.9763 | -79.5391 | (8.9763000000000002, -79.539100000000005) | Landslide | Landslide | Small | Unknown | NA | 0 | 0 | Ministerio de Obras Públicas de Panamá | http://www.mop.gob.pa/poste-electrico-de-la-avenida-frangipany-cae-sobre-camion-del-mop/ |
| 7453 | 6/5/15 | Afternoon | NA | Panama | PA | Panamá | 0 | Las Margaritas | 0.48725 | Above road | 9.1805 | -79.0896 | (9.1805000000000003, -79.089600000000004) | Landslide | Landslide | Medium | Downpour | NA | 0 | 0 | La Estrella de Panama | http://laestrella.com.pa/panama/nacional/deslizamiento-tierra-bayano-inundaciones-colon/23870997/foto/136658 |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_PA, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_PA, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_PA, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_PA <- df_PA %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_PA$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_PA, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_PA$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 4.18074 |
| 2.57852 |
| 2.59449 |
| 3.30848 |
| 3.54386 |
| 0.48725 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_PA$distance
names(distance) <- df_PA$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## San Miguelito 4.180740 4.180740 15.591951 15.591951
## San Miguelito 3.543860 7.724600 13.216725 28.808676
## San Miguelito 3.308480 11.033080 12.338882 41.147558
## Las Cumbres 2.814790 13.847870 10.497679 51.645238
## San Miguelito 2.594490 16.442360 9.676077 61.321314
## San Miguelito 2.578520 19.020880 9.616517 70.937832
## Ancón 2.240690 21.261570 8.356590 79.294421
## Cerro Azul 1.845960 23.107530 6.884455 86.178877
## Arraiján 1.803410 24.910940 6.725766 92.904643
## Alcaldedíaz 1.415260 26.326200 5.278172 98.182815
## Las Margaritas 0.487250 26.813450 1.817185 100.000000stem(df_PA$"distance")##
## The decimal point is at the |
##
## 0 | 5
## 1 | 488
## 2 | 2668
## 3 | 35
## 4 | 2head(df_PA)## # A tibble: 6 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 6703 6/17/14 <NA> <NA> Panama PA Panamá 321501
## 2 7506 9/10/15 <NA> <NA> Panama PA Panamá 321501
## 3 7509 9/10/15 <NA> <NA> Panama PA Panamá 321501
## 4 7510 8/31/15 <NA> <NA> Panama PA Panamá 321501
## 5 7511 8/31/15 <NA> <NA> Panama PA Panamá 321501
## 6 7453 6/5/15 Afternoon <NA> Panama PA Panamá 0
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_PA))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 6703 | 6/17/14 | NA | NA | Panama | PA | Panamá | 321501 | San Miguelito | 4.18074 | Unknown | 9.0329 | -79.5380 | (9.0328999999999997, -79.537999999999997) | Landslide | Mudslide | Medium | Unknown | NA | 0 | 0 | PanamaAmerica | http://www.panamaamerica.com.pa/nacion/reportan-deslizamiento-en-autopista-panama-colon# | 15.591951 | 7.795975 |
| 7506 | 9/10/15 | NA | NA | Panama | PA | Panamá | 321501 | San Miguelito | 2.57852 | Unknown | 9.0539 | -79.4945 | (9.0539000000000005, -79.494500000000002) | Landslide | Landslide | Large | Downpour | NA | 45 | 0 | IDAAN | http://www.idaan.gob.pa/noticias/idaan-prest%C3%B3-apoyo-los-afectados-por-inundaciones-y-deslizamientos-de-tierra | 9.616517 | 20.400210 |
| 7509 | 9/10/15 | NA | NA | Panama | PA | Panamá | 321501 | San Miguelito | 2.59449 | Urban area | 9.0417 | -79.4487 | (9.0417000000000005, -79.448700000000002) | Landslide | Landslide | Large | Downpour | NA | 0 | 0 | Cuerpos de Bomberos | http://www.bomberos.gob.pa/2015/09/gobierno-de-panama-reitera-el-apoyo-a-todos-los-afectados-por-inundaciones-en-el-pais/ | 9.676077 | 30.046506 |
| 7510 | 8/31/15 | NA | NA | Panama | PA | Panamá | 321501 | San Miguelito | 3.30848 | Urban area | 9.0688 | -79.4944 | (9.0687999999999995, -79.494399999999999) | Landslide | Landslide | Medium | Downpour | NA | 0 | 0 | Critica | http://www.critica.com.pa/nacional/deslizamientos-de-tierra-causan-afectaciones-3-casas-404174 | 12.338882 | 41.053986 |
| 7511 | 8/31/15 | NA | NA | Panama | PA | Panamá | 321501 | San Miguelito | 3.54386 | Urban area | 9.0772 | -79.4882 | (9.0771999999999995, -79.488200000000006) | Landslide | Landslide | Medium | Downpour | NA | 0 | 0 | Critica | http://www.critica.com.pa/nacional/deslizamientos-de-tierra-causan-afectaciones-3-casas-404174 | 13.216725 | 53.831790 |
| 7453 | 6/5/15 | Afternoon | NA | Panama | PA | Panamá | 0 | Las Margaritas | 0.48725 | Above road | 9.1805 | -79.0896 | (9.1805000000000003, -79.089600000000004) | Landslide | Landslide | Medium | Downpour | NA | 0 | 0 | La Estrella de Panama | http://laestrella.com.pa/panama/nacional/deslizamiento-tierra-bayano-inundaciones-colon/23870997/foto/136658 | 1.817185 | 61.348745 |
stem(df_PA$"distance")##
## The decimal point is at the |
##
## 0 | 5
## 1 | 488
## 2 | 2668
## 3 | 35
## 4 | 2stem(df_PA$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 |
## 0 | 5
## 1 | 4
## 1 | 88
## 2 | 2
## 2 | 668
## 3 | 3
## 3 | 5
## 4 | 2Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.48725 | 1 | 9.1 | 9.1 | 9.1 | 9.1 |
| 1.41526 | 1 | 9.1 | 9.1 | 18.2 | 18.2 |
| 1.80341 | 1 | 9.1 | 9.1 | 27.3 | 27.3 |
| 1.84596 | 1 | 9.1 | 9.1 | 36.4 | 36.4 |
| 2.24069 | 1 | 9.1 | 9.1 | 45.5 | 45.5 |
| 2.57852 | 1 | 9.1 | 9.1 | 54.5 | 54.5 |
| 2.59449 | 1 | 9.1 | 9.1 | 63.6 | 63.6 |
| 2.81479 | 1 | 9.1 | 9.1 | 72.7 | 72.7 |
| 3.30848 | 1 | 9.1 | 9.1 | 81.8 | 81.8 |
| 3.54386 | 1 | 9.1 | 9.1 | 90.9 | 90.9 |
| 4.18074 | 1 | 9.1 | 9.1 | 100.0 | 100.0 |
| Total | 11 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 12 obs. of 5 variables:
## $ n : num 1 1 1 1 1 1 1 1 1 1 ...
## $ % : num 9.1 9.1 9.1 9.1 9.1 9.1 9.1 9.1 9.1 9.1 ...
## $ val% : num 9.1 9.1 9.1 9.1 9.1 9.1 9.1 9.1 9.1 9.1 ...
## $ %cum : num 9.1 18.2 27.3 36.4 45.5 54.5 63.6 72.7 81.8 90.9 ...
## $ val%cum: num 9.1 18.2 27.3 36.4 45.5 54.5 63.6 72.7 81.8 90.9 ...x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.48725 | 1 |
| 1.41526 | 1 |
| 1.80341 | 1 |
| 1.84596 | 1 |
| 2.24069 | 1 |
| 2.57852 | 1 |
| 2.59449 | 1 |
| 2.81479 | 1 |
| 3.30848 | 1 |
| 3.54386 | 1 |
| 4.18074 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.48725 1.48725 2.48725 3.48725 4.48725distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.487,1.49] | 1 | 0.1 | 1 |
| (1.49,2.49] | 3 | 0.3 | 4 |
| (2.49,3.49] | 4 | 0.4 | 8 |
| (3.49,4.49] | 2 | 0.2 | 10 |
str(Freq_table)## 'data.frame': 4 obs. of 4 variables:
## $ distance: Factor w/ 4 levels "(0.487,1.49]",..: 1 2 3 4
## $ Freq : int 1 3 4 2
## $ Rel_Freq: num 0.1 0.3 0.4 0.2
## $ Cum_Freq: int 1 4 8 10df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.487,1.49] | 1 |
| (1.49,2.49] | 3 |
| (2.49,3.49] | 4 |
| (3.49,4.49] | 2 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_PA)## id date time continent_code country_name country_code
## nbr.val 1.100000e+01 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 7.500000e+02 NA NA NA NA NA
## max 7.512000e+03 NA NA NA NA NA
## range 6.762000e+03 NA NA NA NA NA
## sum 7.142200e+04 NA NA NA NA NA
## median 7.453000e+03 NA NA NA NA NA
## mean 6.492909e+03 NA NA NA NA NA
## SE.mean 6.035510e+02 NA NA NA NA NA
## CI.mean.0.95 1.344795e+03 NA NA NA NA NA
## var 4.007012e+06 NA NA NA NA NA
## std.dev 2.001752e+03 NA NA NA NA NA
## coef.var 3.082982e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 1.100000e+01 NA 11.0000000 NA
## nbr.null NA 1.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 0.000000e+00 NA 0.4872500 NA
## max NA 3.215010e+05 NA 4.1807400 NA
## range NA 3.215010e+05 NA 3.6934900 NA
## sum NA 1.783660e+06 NA 26.8134500 NA
## median NA 7.681500e+04 NA 2.5785200 NA
## mean NA 1.621509e+05 NA 2.4375864 NA
## SE.mean NA 4.658766e+04 NA 0.3140292 NA
## CI.mean.0.95 NA 1.038038e+05 NA 0.6997007 NA
## var NA 2.387451e+10 NA 1.0847578 NA
## std.dev NA 1.545138e+05 NA 1.0415171 NA
## coef.var NA 9.529011e-01 NA 0.4272739 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 11.000000000 1.100000e+01 NA NA NA
## nbr.null 0.000000000 0.000000e+00 NA NA NA
## nbr.na 0.000000000 0.000000e+00 NA NA NA
## min 8.949600000 -7.963360e+01 NA NA NA
## max 9.180500000 -7.908960e+01 NA NA NA
## range 0.230900000 5.440000e-01 NA NA NA
## sum 99.716200000 -8.742698e+02 NA NA NA
## median 9.065500000 -7.949450e+01 NA NA NA
## mean 9.065109091 -7.947907e+01 NA NA NA
## SE.mean 0.020679157 4.251380e-02 NA NA NA
## CI.mean.0.95 0.046076033 9.472666e-02 NA NA NA
## var 0.004703903 1.988166e-02 NA NA NA
## std.dev 0.068585005 1.410023e-01 NA NA NA
## coef.var 0.007565822 -1.774081e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 9.00000 9 NA
## nbr.null NA NA NA 8.00000 9 NA
## nbr.na NA NA NA 2.00000 2 NA
## min NA NA NA 0.00000 0 NA
## max NA NA NA 45.00000 0 NA
## range NA NA NA 45.00000 0 NA
## sum NA NA NA 45.00000 0 NA
## median NA NA NA 0.00000 0 NA
## mean NA NA NA 5.00000 0 NA
## SE.mean NA NA NA 5.00000 0 NA
## CI.mean.0.95 NA NA NA 11.53002 0 NA
## var NA NA NA 225.00000 0 NA
## std.dev NA NA NA 15.00000 0 NA
## coef.var NA NA NA 3.00000 NaN NA
## source_link prop ypos
## nbr.val NA 11.0000000 11.0000000
## nbr.null NA 0.0000000 0.0000000
## nbr.na NA 0.0000000 0.0000000
## min NA 1.8171850 7.7959755
## max NA 15.5919511 97.3609140
## range NA 13.7747660 89.5649385
## sum NA 100.0000000 629.0874356
## median NA 9.6165171 61.3487448
## mean NA 9.0909091 57.1897669
## SE.mean NA 1.1711630 8.8826226
## CI.mean.0.95 NA 2.6095138 19.7917165
## var NA 15.0878511 867.9108284
## std.dev NA 3.8843083 29.4603263
## coef.var NA 0.4272739 0.5151328boxplot(data, horizontal=TRUE, col='green')
Gráfico para Mexico
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_MX <- subset(df, country_name == "Mexico")
knitr::kable(head(df_MX)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 115 | 7/4/07 | NA | NA | Mexico | MX | Veracruz-Llave | 1947 | Laguna Chica (Pueblo Nuevo) | 9.51003 | NA | 18.5369 | -96.8229 | (18.536899999999999, -96.822900000000004) | Landslide | Landslide | Medium | Rain | NA | NA | 7 | nytimes.com | http://www.nytimes.com/2007/07/04/world/americas/04cnd-mexico.html?_r=1&hp&oref=slogin |
| 201 | 8/23/07 | NA | NA | Mexico | MX | Puebla | 1414 | Xochitlaxco (San Baltazar) | 1.68294 | NA | 19.9333 | -97.8500 | (19.933299999999999, -97.85) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Dean | NA | 6 | Inquirer.com | http://newsinfo.inquirer.net/breakingnews/world/view_article.php?article_id=84452 |
| 225 | 9/2/07 | NA | NA | Mexico | MX | Sinaloa | 3191 | El Limón de los Ramos | 10.88351 | NA | 24.9531 | -107.6220 | (24.953099999999999, -107.622) | Landslide | Complex | Medium | Tropical cyclone | Tropical Storm Henrietta | NA | 3 | NA | NA |
| 284 | 9/28/07 | NA | NA | Mexico | MX | Puebla | 3761 | Xaltepuxtla | 7.93258 | NA | 20.2000 | -97.9000 | (20.2, -97.9) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Lorenzo | NA | 1 | PressTV.ir | http://www.presstv.ir/detail.aspx?id=25037§ionid=3510207 |
| 342 | 10/31/07 | NA | NA | Mexico | MX | Tabasco | 4468 | Buenavista | 4.19108 | NA | 17.9493 | -92.5534 | (17.949300000000001, -92.553399999999996) | Landslide | Landslide | Medium | Rain | NA | NA | 18 | CapeTimes | http://www.capetimes.co.za/?fArticleId=4109453 |
| 346 | 11/4/07 | NA | NA | Mexico | MX | Chiapas | 3183 | Ostuacán | 3.74149 | NA | 17.3900 | -93.3060 | (17.39, -93.305999999999997) | Landslide | Mudslide | Very_large | Rain | NA | NA | 5 | Reuters - AlertNet.org | http://news.monstersandcritics.com/americas/news/article_1371436.php/Mudslide_is_latest_disaster_for_hard-hit_Mexico__2nd_Roundup_ |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(fill=state, y=distance, x=country_name)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(fill=state, y=distance, x=country_name)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(x=country_name, y=distance, fill=state)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_MX <- df_MX %>%
arrange(desc(state)) %>%
mutate(prop = distance / sum(df_MX$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_MX, aes(x=country_name, y = prop, fill=state)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4## Warning in RColorBrewer::brewer.pal(n, pal): n too large, allowed maximum for palette Greens is 9
## Returning the palette you asked for with that many colors
Grafico de series temporales
library(forecast)
data<- ts(df_MX$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 9.51003 |
| 8.28739 |
| 1.27837 |
| 1.52983 |
| 2.85382 |
| 3.73160 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_MX$distance
names(distance) <- df_MX$state
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por estados"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Guerrero 32.12708000 32.12708000 7.76637116 7.76637116
## Oaxaca 24.67589000 56.80297000 5.96512725 13.73149841
## Nayarit 21.80060000 78.60357000 5.27005726 19.00155566
## Nayarit 19.41353000 98.01710000 4.69300912 23.69456478
## Oaxaca 16.16369000 114.18079000 3.90739575 27.60196053
## Oaxaca 15.74984000 129.93063000 3.80735203 31.40931256
## Tabasco 15.22260000 145.15323000 3.67989751 35.08921007
## Guerrero 14.04274000 159.19597000 3.39467922 38.48388929
## Baja California 12.53758000 171.73355000 3.03082321 41.51471249
## Baja California 12.36500000 184.09855000 2.98910388 44.50381637
## Guerrero 12.33417000 196.43272000 2.98165106 47.48546743
## Oaxaca 11.83490000 208.26762000 2.86095798 50.34642541
## Sinaloa 10.88351000 219.15113000 2.63096983 52.97739524
## Hidalgo 9.78251000 228.93364000 2.36481509 55.34221033
## Oaxaca 9.56829000 238.50193000 2.31302974 57.65524007
## Veracruz-Llave 9.51003000 248.01196000 2.29894602 59.95418609
## Tabasco 8.93271000 256.94467000 2.15938521 62.11357130
## Chiapas 8.46579000 265.41046000 2.04651239 64.16008369
## Veracruz-Llave 8.28739000 273.69785000 2.00338614 66.16346982
## Chiapas 7.93996000 281.63781000 1.91939872 68.08286855
## Puebla 7.93258000 289.57039000 1.91761469 70.00048324
## Guerrero 7.07138000 296.64177000 1.70942898 71.70991222
## Guerrero 6.80950000 303.45127000 1.64612235 73.35603457
## Baja California 6.46156000 309.91283000 1.56201165 74.91804622
## Puebla 5.24855000 315.16138000 1.26877971 76.18682593
## Tabasco 4.81680000 319.97818000 1.16440886 77.35123479
## Chiapas 4.68443000 324.66261000 1.13240986 78.48364465
## Veracruz-Llave 4.51820000 329.18081000 1.09222557 79.57587021
## México 4.40801000 333.58882000 1.06558834 80.64145855
## Tabasco 4.32007000 337.90889000 1.04432980 81.68578835
## Tabasco 4.19108000 342.09997000 1.01314787 82.69893622
## Michoacán 4.18059000 346.28056000 1.01061203 83.70954826
## Guerrero 4.10830000 350.38886000 0.99313671 84.70268497
## Chiapas 3.74149000 354.13035000 0.90446440 85.60714937
## Veracruz-Llave 3.73160000 357.86195000 0.90207360 86.50922296
## Oaxaca 3.64682000 361.50877000 0.88157896 87.39080192
## The Federal District 3.49173000 365.00050000 0.84408764 88.23488956
## Michoacán 3.42740000 368.42790000 0.82853656 89.06342613
## Michoacán 3.36905000 371.79695000 0.81443109 89.87785721
## Nuevo León 3.30074000 375.09769000 0.79791789 90.67577511
## Chihuahua 3.05542000 378.15311000 0.73861446 91.41438956
## Veracruz-Llave 2.85382000 381.00693000 0.68987986 92.10426942
## México 2.59637000 383.60330000 0.62764413 92.73191355
## Baja California 2.49770000 386.10100000 0.60379173 93.33570528
## Veracruz 2.47800000 388.57900000 0.59902947 93.93473475
## Tabasco 2.15703000 390.73603000 0.52143847 94.45617322
## Chiapas 2.06743000 392.80346000 0.49977865 94.95595187
## Veracruz 1.93516000 394.73862000 0.46780382 95.42375570
## Chiapas 1.73469000 396.47331000 0.41934239 95.84309808
## Michoacán 1.69508000 398.16839000 0.40976710 96.25286518
## Puebla 1.68294000 399.85133000 0.40683239 96.65969757
## Veracruz-Llave 1.52983000 401.38116000 0.36981972 97.02951729
## Chiapas 1.41805000 402.79921000 0.34279812 97.37231541
## Veracruz-Llave 1.27837000 404.07758000 0.30903200 97.68134741
## México 1.06048000 405.13806000 0.25635947 97.93770688
## Chiapas 0.94118000 406.07924000 0.22752000 98.16522688
## Guerrero 0.90692000 406.98616000 0.21923802 98.38446490
## Guerrero 0.88149000 407.86765000 0.21309059 98.59755549
## Oaxaca 0.78340000 408.65105000 0.18937840 98.78693390
## Chiapas 0.76257000 409.41362000 0.18434298 98.97127688
## México 0.66626000 410.07988000 0.16106109 99.13233796
## Hidalgo 0.64483000 410.72471000 0.15588062 99.28821858
## Oaxaca 0.63550000 411.36021000 0.15362519 99.44184377
## Veracruz-Llave 0.50188000 411.86209000 0.12132402 99.56316779
## Colima 0.36051000 412.22260000 0.08714936 99.65031715
## Chiapas 0.31118000 412.53378000 0.07522437 99.72554152
## Puebla 0.30326000 412.83704000 0.07330980 99.79885132
## Oaxaca 0.28905000 413.12609000 0.06987468 99.86872600
## The Federal District 0.15208000 413.27817000 0.03676368 99.90548968
## The Federal District 0.15208000 413.43025000 0.03676368 99.94225337
## Veracruz-Llave 0.09971000 413.52996000 0.02410380 99.96635717
## Jalisco 0.08269000 413.61265000 0.01998941 99.98634658
## Baja California Sur 0.05648000 413.66913000 0.01365342 100.00000000stem(df_MX$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 000000000111111111111222222222333333344444444
## 0 | 555567788889
## 1 | 000122234
## 1 | 5669
## 2 | 2
## 2 | 5
## 3 | 2head(df_MX)## # A tibble: 6 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 115 7/4/07 <NA> <NA> Mexico MX Vera~ 1947
## 2 2438 9/17/10 <NA> <NA> Mexico MX Vera~ 1324
## 3 3684 7/1/11 <NA> <NA> Mexico MX Vera~ 425148
## 4 5403 8/26/13 20:20:00 <NA> Mexico MX Vera~ 30607
## 5 5405 8/26/13 <NA> <NA> Mexico MX Vera~ 15800
## 6 5406 8/26/13 <NA> <NA> Mexico MX Vera~ 3198
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_MX))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 115 | 7/4/07 | NA | NA | Mexico | MX | Veracruz-Llave | 1947 | Laguna Chica (Pueblo Nuevo) | 9.51003 | NA | 18.5369 | -96.8229 | (18.536899999999999, -96.822900000000004) | Landslide | Landslide | Medium | Rain | NA | NA | 7 | nytimes.com | http://www.nytimes.com/2007/07/04/world/americas/04cnd-mexico.html?_r=1&hp&oref=slogin | 2.2989460 | 1.149473 |
| 2438 | 9/17/10 | NA | NA | Mexico | MX | Veracruz-Llave | 1324 | El Hatito | 8.28739 | NA | 19.2818 | -96.3149 | (19.2818, -96.314899999999994) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Karl | NA | 2 | NA | http://www.lfpress.com/news/world/2010/09/17/15382976-reuters.html | 2.0033861 | 3.300639 |
| 3684 | 7/1/11 | NA | NA | Mexico | MX | Veracruz-Llave | 425148 | Xalapa de Enríquez | 1.27837 | NA | 19.5426 | -96.9137 | (19.5426, -96.913700000000006) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Storm Arlene | NA | 0 | NA | http://edition.cnn.com/2011/WORLD/americas/07/04/mexico.arlene.deaths/ | 0.3090320 | 4.456848 |
| 5403 | 8/26/13 | 20:20:00 | NA | Mexico | MX | Veracruz-Llave | 30607 | Coatzintla | 1.52983 | NA | 20.5004 | -97.4647 | (20.500399999999999, -97.464699999999993) | Landslide | Landslide | Medium | Tropical cyclone | Fernand | NA | 3 | www.cbc.ca | http://www.cbc.ca/news/world/mexico-storm-related-landslides-kill-13-1.1370491 | 0.3698197 | 4.796274 |
| 5405 | 8/26/13 | NA | NA | Mexico | MX | Veracruz-Llave | 15800 | Altotonga | 2.85382 | NA | 19.7906 | -97.2428 | (19.790600000000001, -97.242800000000003) | Landslide | Landslide | Medium | Tropical cyclone | Fernand | NA | 1 | www.cbc.ca | http://www.cbc.ca/news/world/mexico-storm-related-landslides-kill-13-1.1370491 | 0.6898799 | 5.326124 |
| 5406 | 8/26/13 | NA | NA | Mexico | MX | Veracruz-Llave | 3198 | Yecuatla | 3.73160 | NA | 19.8413 | -96.8005 | (19.8413, -96.8005) | Landslide | Landslide | Medium | Downpour | NA | NA | 9 | www.cbc.ca | http://www.cbc.ca/news/world/mexico-storm-related-landslides-kill-13-1.1370491 | 0.9020736 | 6.122101 |
stem(df_MX$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 000000000111111111111222222222333333344444444
## 0 | 555567788889
## 1 | 000122234
## 1 | 5669
## 2 | 2
## 2 | 5
## 3 | 2stem(df_MX$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 11122333456678899913457779
## 2 | 12556913445677
## 4 | 122345782
## 6 | 58199
## 8 | 359568
## 10 | 98
## 12 | 345
## 14 | 027
## 16 | 2
## 18 | 4
## 20 | 8
## 22 |
## 24 | 7
## 26 |
## 28 |
## 30 |
## 32 | 1Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.15208 | 2 | 2.7 | 2.7 | 2.7 | 2.7 |
| 0.05648 | 1 | 1.4 | 1.4 | 4.1 | 4.1 |
| 0.08269 | 1 | 1.4 | 1.4 | 5.5 | 5.5 |
| 0.09971 | 1 | 1.4 | 1.4 | 6.8 | 6.8 |
| 0.28905 | 1 | 1.4 | 1.4 | 8.2 | 8.2 |
| 0.30326 | 1 | 1.4 | 1.4 | 9.6 | 9.6 |
| 0.31118 | 1 | 1.4 | 1.4 | 11.0 | 11.0 |
| 0.36051 | 1 | 1.4 | 1.4 | 12.3 | 12.3 |
| 0.50188 | 1 | 1.4 | 1.4 | 13.7 | 13.7 |
| 0.6355 | 1 | 1.4 | 1.4 | 15.1 | 15.1 |
| 0.64483 | 1 | 1.4 | 1.4 | 16.4 | 16.4 |
| 0.66626 | 1 | 1.4 | 1.4 | 17.8 | 17.8 |
| 0.76257 | 1 | 1.4 | 1.4 | 19.2 | 19.2 |
| 0.7834 | 1 | 1.4 | 1.4 | 20.5 | 20.5 |
| 0.88149 | 1 | 1.4 | 1.4 | 21.9 | 21.9 |
| 0.90692 | 1 | 1.4 | 1.4 | 23.3 | 23.3 |
| 0.94118 | 1 | 1.4 | 1.4 | 24.7 | 24.7 |
| 1.06048 | 1 | 1.4 | 1.4 | 26.0 | 26.0 |
| 1.27837 | 1 | 1.4 | 1.4 | 27.4 | 27.4 |
| 1.41805 | 1 | 1.4 | 1.4 | 28.8 | 28.8 |
| 1.52983 | 1 | 1.4 | 1.4 | 30.1 | 30.1 |
| 1.68294 | 1 | 1.4 | 1.4 | 31.5 | 31.5 |
| 1.69508 | 1 | 1.4 | 1.4 | 32.9 | 32.9 |
| 1.73469 | 1 | 1.4 | 1.4 | 34.2 | 34.2 |
| 1.93516 | 1 | 1.4 | 1.4 | 35.6 | 35.6 |
| 2.06743 | 1 | 1.4 | 1.4 | 37.0 | 37.0 |
| 2.15703 | 1 | 1.4 | 1.4 | 38.4 | 38.4 |
| 2.478 | 1 | 1.4 | 1.4 | 39.7 | 39.7 |
| 2.4977 | 1 | 1.4 | 1.4 | 41.1 | 41.1 |
| 2.59637 | 1 | 1.4 | 1.4 | 42.5 | 42.5 |
| 2.85382 | 1 | 1.4 | 1.4 | 43.8 | 43.8 |
| 3.05542 | 1 | 1.4 | 1.4 | 45.2 | 45.2 |
| 3.30074 | 1 | 1.4 | 1.4 | 46.6 | 46.6 |
| 3.36905 | 1 | 1.4 | 1.4 | 47.9 | 47.9 |
| 3.4274 | 1 | 1.4 | 1.4 | 49.3 | 49.3 |
| 3.49173 | 1 | 1.4 | 1.4 | 50.7 | 50.7 |
| 3.64682 | 1 | 1.4 | 1.4 | 52.1 | 52.1 |
| 3.7316 | 1 | 1.4 | 1.4 | 53.4 | 53.4 |
| 3.74149 | 1 | 1.4 | 1.4 | 54.8 | 54.8 |
| 4.1083 | 1 | 1.4 | 1.4 | 56.2 | 56.2 |
| 4.18059 | 1 | 1.4 | 1.4 | 57.5 | 57.5 |
| 4.19108 | 1 | 1.4 | 1.4 | 58.9 | 58.9 |
| 4.32007 | 1 | 1.4 | 1.4 | 60.3 | 60.3 |
| 4.40801 | 1 | 1.4 | 1.4 | 61.6 | 61.6 |
| 4.5182 | 1 | 1.4 | 1.4 | 63.0 | 63.0 |
| 4.68443 | 1 | 1.4 | 1.4 | 64.4 | 64.4 |
| 4.8168 | 1 | 1.4 | 1.4 | 65.8 | 65.8 |
| 5.24855 | 1 | 1.4 | 1.4 | 67.1 | 67.1 |
| 6.46156 | 1 | 1.4 | 1.4 | 68.5 | 68.5 |
| 6.8095 | 1 | 1.4 | 1.4 | 69.9 | 69.9 |
| 7.07138 | 1 | 1.4 | 1.4 | 71.2 | 71.2 |
| 7.93258 | 1 | 1.4 | 1.4 | 72.6 | 72.6 |
| 7.93996 | 1 | 1.4 | 1.4 | 74.0 | 74.0 |
| 8.28739 | 1 | 1.4 | 1.4 | 75.3 | 75.3 |
| 8.46579 | 1 | 1.4 | 1.4 | 76.7 | 76.7 |
| 8.93271 | 1 | 1.4 | 1.4 | 78.1 | 78.1 |
| 9.51003 | 1 | 1.4 | 1.4 | 79.5 | 79.5 |
| 9.56829 | 1 | 1.4 | 1.4 | 80.8 | 80.8 |
| 9.78251 | 1 | 1.4 | 1.4 | 82.2 | 82.2 |
| 10.88351 | 1 | 1.4 | 1.4 | 83.6 | 83.6 |
| 11.8349 | 1 | 1.4 | 1.4 | 84.9 | 84.9 |
| 12.33417 | 1 | 1.4 | 1.4 | 86.3 | 86.3 |
| 12.365 | 1 | 1.4 | 1.4 | 87.7 | 87.7 |
| 12.53758 | 1 | 1.4 | 1.4 | 89.0 | 89.0 |
| 14.04274 | 1 | 1.4 | 1.4 | 90.4 | 90.4 |
| 15.2226 | 1 | 1.4 | 1.4 | 91.8 | 91.8 |
| 15.74984 | 1 | 1.4 | 1.4 | 93.2 | 93.2 |
| 16.16369 | 1 | 1.4 | 1.4 | 94.5 | 94.5 |
| 19.41353 | 1 | 1.4 | 1.4 | 95.9 | 95.9 |
| 21.8006 | 1 | 1.4 | 1.4 | 97.3 | 97.3 |
| 24.67589 | 1 | 1.4 | 1.4 | 98.6 | 98.6 |
| 32.12708 | 1 | 1.4 | 1.4 | 100.0 | 100.0 |
| Total | 73 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 73 obs. of 5 variables:
## $ n : num 2 1 1 1 1 1 1 1 1 1 ...
## $ % : num 2.7 1.4 1.4 1.4 1.4 1.4 1.4 1.4 1.4 1.4 ...
## $ val% : num 2.7 1.4 1.4 1.4 1.4 1.4 1.4 1.4 1.4 1.4 ...
## $ %cum : num 2.7 4.1 5.5 6.8 8.2 9.6 11 12.3 13.7 15.1 ...
## $ val%cum: num 2.7 4.1 5.5 6.8 8.2 9.6 11 12.3 13.7 15.1 ...x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.15208 | 2 |
| 0.05648 | 1 |
| 0.08269 | 1 |
| 0.09971 | 1 |
| 0.28905 | 1 |
| 0.30326 | 1 |
| 0.31118 | 1 |
| 0.36051 | 1 |
| 0.50188 | 1 |
| 0.6355 | 1 |
| 0.64483 | 1 |
| 0.66626 | 1 |
| 0.76257 | 1 |
| 0.7834 | 1 |
| 0.88149 | 1 |
| 0.90692 | 1 |
| 0.94118 | 1 |
| 1.06048 | 1 |
| 1.27837 | 1 |
| 1.41805 | 1 |
| 1.52983 | 1 |
| 1.68294 | 1 |
| 1.69508 | 1 |
| 1.73469 | 1 |
| 1.93516 | 1 |
| 2.06743 | 1 |
| 2.15703 | 1 |
| 2.478 | 1 |
| 2.4977 | 1 |
| 2.59637 | 1 |
| 2.85382 | 1 |
| 3.05542 | 1 |
| 3.30074 | 1 |
| 3.36905 | 1 |
| 3.4274 | 1 |
| 3.49173 | 1 |
| 3.64682 | 1 |
| 3.7316 | 1 |
| 3.74149 | 1 |
| 4.1083 | 1 |
| 4.18059 | 1 |
| 4.19108 | 1 |
| 4.32007 | 1 |
| 4.40801 | 1 |
| 4.5182 | 1 |
| 4.68443 | 1 |
| 4.8168 | 1 |
| 5.24855 | 1 |
| 6.46156 | 1 |
| 6.8095 | 1 |
| 7.07138 | 1 |
| 7.93258 | 1 |
| 7.93996 | 1 |
| 8.28739 | 1 |
| 8.46579 | 1 |
| 8.93271 | 1 |
| 9.51003 | 1 |
| 9.56829 | 1 |
| 9.78251 | 1 |
| 10.88351 | 1 |
| 11.8349 | 1 |
| 12.33417 | 1 |
| 12.365 | 1 |
| 12.53758 | 1 |
| 14.04274 | 1 |
| 15.2226 | 1 |
| 15.74984 | 1 |
| 16.16369 | 1 |
| 19.41353 | 1 |
| 21.8006 | 1 |
| 24.67589 | 1 |
| 32.12708 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")+ theme(axis.text.x = element_text(angle = 90))
library(pastecs)
stat.desc(df_MX)## id date time continent_code country_name country_code
## nbr.val 7.300000e+01 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 1.150000e+02 NA NA NA NA NA
## max 7.518000e+03 NA NA NA NA NA
## range 7.403000e+03 NA NA NA NA NA
## sum 2.913040e+05 NA NA NA NA NA
## median 3.834000e+03 NA NA NA NA NA
## mean 3.990466e+03 NA NA NA NA NA
## SE.mean 2.764651e+02 NA NA NA NA NA
## CI.mean.0.95 5.511232e+02 NA NA NA NA NA
## var 5.579607e+06 NA NA NA NA NA
## std.dev 2.362119e+03 NA NA NA NA NA
## coef.var 5.919407e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 7.300000e+01 NA 73.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 1.005000e+03 NA 0.0564800 NA
## max NA 1.229419e+07 NA 32.1270800 NA
## range NA 1.229319e+07 NA 32.0706000 NA
## sum NA 3.298622e+07 NA 413.6691300 NA
## median NA 6.089000e+03 NA 3.4917300 NA
## mean NA 4.518661e+05 NA 5.6667004 NA
## SE.mean NA 2.369285e+05 NA 0.7442396 NA
## CI.mean.0.95 NA 4.723084e+05 NA 1.4836145 NA
## var NA 4.097865e+12 NA 40.4341560 NA
## std.dev NA 2.024318e+06 NA 6.3587857 NA
## coef.var NA 4.479908e+00 NA 1.1221320 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 73.0000000 7.300000e+01 NA NA NA
## nbr.null 0.0000000 0.000000e+00 NA NA NA
## nbr.na 0.0000000 0.000000e+00 NA NA NA
## min 15.0337000 -1.170898e+02 NA NA NA
## max 32.5755000 -9.129880e+01 NA NA NA
## range 17.5418000 2.579100e+01 NA NA NA
## sum 1427.3326000 -7.208526e+03 NA NA NA
## median 19.0294000 -9.749970e+01 NA NA NA
## mean 19.5525014 -9.874694e+01 NA NA NA
## SE.mean 0.4625032 6.876754e-01 NA NA NA
## CI.mean.0.95 0.9219832 1.370856e+00 NA NA NA
## var 15.6153711 3.452151e+01 NA NA NA
## std.dev 3.9516289 5.875501e+00 NA NA NA
## coef.var 0.2021035 -5.950059e-02 NA NA NA
## landslide_size trigger storm_name injuries fatalities
## nbr.val NA NA NA 19.0000000 70.000000
## nbr.null NA NA NA 15.0000000 27.000000
## nbr.na NA NA NA 54.0000000 3.000000
## min NA NA NA 0.0000000 0.000000
## max NA NA NA 8.0000000 71.000000
## range NA NA NA 8.0000000 71.000000
## sum NA NA NA 15.0000000 284.000000
## median NA NA NA 0.0000000 2.000000
## mean NA NA NA 0.7894737 4.057143
## SE.mean NA NA NA 0.4625062 1.098632
## CI.mean.0.95 NA NA NA 0.9716894 2.191711
## var NA NA NA 4.0643275 84.489441
## std.dev NA NA NA 2.0160177 9.191814
## coef.var NA NA NA 2.5536225 2.265588
## source_name source_link prop ypos
## nbr.val NA NA 73.00000000 73.0000000
## nbr.null NA NA 0.00000000 0.0000000
## nbr.na NA NA 0.00000000 0.0000000
## min NA NA 0.01365342 1.1494730
## max NA NA 7.76637116 99.2189942
## range NA NA 7.75271773 98.0695212
## sum NA NA 100.00000000 3545.1804284
## median NA NA 0.84408764 54.2381528
## mean NA NA 1.36986301 48.5641155
## SE.mean NA NA 0.17991180 3.7293810
## CI.mean.0.95 NA NA 0.35864762 7.4343851
## var NA NA 2.36288267 1015.3046257
## std.dev NA NA 1.53716709 31.8638451
## coef.var NA NA 1.12213198 0.6561191boxplot(data, horizontal=TRUE, col='green')
Gráfico para Baja California (Mexico)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_MX <- subset(df, country_name == "Mexico")
knitr::kable(head(df_MX)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 115 | 7/4/07 | NA | NA | Mexico | MX | Veracruz-Llave | 1947 | Laguna Chica (Pueblo Nuevo) | 9.51003 | NA | 18.5369 | -96.8229 | (18.536899999999999, -96.822900000000004) | Landslide | Landslide | Medium | Rain | NA | NA | 7 | nytimes.com | http://www.nytimes.com/2007/07/04/world/americas/04cnd-mexico.html?_r=1&hp&oref=slogin |
| 201 | 8/23/07 | NA | NA | Mexico | MX | Puebla | 1414 | Xochitlaxco (San Baltazar) | 1.68294 | NA | 19.9333 | -97.8500 | (19.933299999999999, -97.85) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Dean | NA | 6 | Inquirer.com | http://newsinfo.inquirer.net/breakingnews/world/view_article.php?article_id=84452 |
| 225 | 9/2/07 | NA | NA | Mexico | MX | Sinaloa | 3191 | El Limón de los Ramos | 10.88351 | NA | 24.9531 | -107.6220 | (24.953099999999999, -107.622) | Landslide | Complex | Medium | Tropical cyclone | Tropical Storm Henrietta | NA | 3 | NA | NA |
| 284 | 9/28/07 | NA | NA | Mexico | MX | Puebla | 3761 | Xaltepuxtla | 7.93258 | NA | 20.2000 | -97.9000 | (20.2, -97.9) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Lorenzo | NA | 1 | PressTV.ir | http://www.presstv.ir/detail.aspx?id=25037§ionid=3510207 |
| 342 | 10/31/07 | NA | NA | Mexico | MX | Tabasco | 4468 | Buenavista | 4.19108 | NA | 17.9493 | -92.5534 | (17.949300000000001, -92.553399999999996) | Landslide | Landslide | Medium | Rain | NA | NA | 18 | CapeTimes | http://www.capetimes.co.za/?fArticleId=4109453 |
| 346 | 11/4/07 | NA | NA | Mexico | MX | Chiapas | 3183 | Ostuacán | 3.74149 | NA | 17.3900 | -93.3060 | (17.39, -93.305999999999997) | Landslide | Mudslide | Very_large | Rain | NA | NA | 5 | Reuters - AlertNet.org | http://news.monstersandcritics.com/americas/news/article_1371436.php/Mudslide_is_latest_disaster_for_hard-hit_Mexico__2nd_Roundup_ |
library(dplyr)
df_MX <- subset(df, state == "Baja California")
knitr::kable(head(df_MX))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 417 | 1/7/08 | NA | NA | Mexico | MX | Baja California | 1376457 | Tijuana | 12.53758 | NA | 32.5755 | -116.9016 | (32.575499999999998, -116.9016) | Landslide | Landslide | Medium | Rain | NA | NA | 1 | NA | http://www.signonsandiego.com/news/mexico/tijuana/20080108-1858-bn08tj.html |
| 1838 | 5/5/10 | NA | NA | Mexico | MX | Baja California | 1376457 | Tijuana | 2.49770 | NA | 32.5250 | -116.9999 | (32.524999999999999, -116.9999) | Landslide | Mudslide | Medium | Rain | NA | NA | 0 | NA | http://hisz.rsoe.hu/alertmap/woalert_read.php?lang=eng&cid=25962&utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+RsoeEdis-EmergencyAndDisasterInformation+%28RSOE+EDIS+-+Emergency+and+Disaster+Information%29 |
| 5731 | 12/28/13 | 2:00:00 | NA | Mexico | MX | Baja California | 9085 | El Sauzal | 12.36500 | Below road | 31.9780 | -116.7776 | (31.978000000000002, -116.77760000000001) | Landslide | Mudslide | Medium | Downpour | NA | NA | 0 | www.globalpost.com | http://www.globalpost.com/dispatch/news/agencia-efe/131230/mudslide-closes-major-road-northwestern-mexico |
| 7056 | 5/17/15 | NA | NA | Mexico | MX | Baja California | 1173 | La Esperanza [Granjas Familiares] | 6.46156 | Urban area | 32.5196 | -117.0898 | (32.519599999999997, -117.0898) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | NA | NA |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_MX <- df_MX %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_MX$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_MX, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_MX$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 12.53758 |
| 2.49770 |
| 6.46156 |
| 12.36500 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_MX$distance
names(distance) <- df_MX$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Tijuana 12.53758 12.53758 37.02569 37.02569
## El Sauzal 12.36500 24.90258 36.51603 73.54172
## La Esperanza [Granjas Familiares] 6.46156 31.36414 19.08213 92.62385
## Tijuana 2.49770 33.86184 7.37615 100.00000stem(df_MX$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 2
## 0 | 6
## 1 | 23head(df_MX)## # A tibble: 4 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 417 1/7/08 <NA> <NA> Mexico MX Baja~ 1376457
## 2 1838 5/5/10 <NA> <NA> Mexico MX Baja~ 1376457
## 3 7056 5/17/15 <NA> <NA> Mexico MX Baja~ 1173
## 4 5731 12/28/13 2:00:00 <NA> Mexico MX Baja~ 9085
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_MX))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 417 | 1/7/08 | NA | NA | Mexico | MX | Baja California | 1376457 | Tijuana | 12.53758 | NA | 32.5755 | -116.9016 | (32.575499999999998, -116.9016) | Landslide | Landslide | Medium | Rain | NA | NA | 1 | NA | http://www.signonsandiego.com/news/mexico/tijuana/20080108-1858-bn08tj.html | 37.02569 | 18.51285 |
| 1838 | 5/5/10 | NA | NA | Mexico | MX | Baja California | 1376457 | Tijuana | 2.49770 | NA | 32.5250 | -116.9999 | (32.524999999999999, -116.9999) | Landslide | Mudslide | Medium | Rain | NA | NA | 0 | NA | http://hisz.rsoe.hu/alertmap/woalert_read.php?lang=eng&cid=25962&utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+RsoeEdis-EmergencyAndDisasterInformation+%28RSOE+EDIS+-+Emergency+and+Disaster+Information%29 | 7.37615 | 40.71377 |
| 7056 | 5/17/15 | NA | NA | Mexico | MX | Baja California | 1173 | La Esperanza [Granjas Familiares] | 6.46156 | Urban area | 32.5196 | -117.0898 | (32.519599999999997, -117.0898) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | NA | NA | 19.08213 | 53.94290 |
| 5731 | 12/28/13 | 2:00:00 | NA | Mexico | MX | Baja California | 9085 | El Sauzal | 12.36500 | Below road | 31.9780 | -116.7776 | (31.978000000000002, -116.77760000000001) | Landslide | Mudslide | Medium | Downpour | NA | NA | 0 | www.globalpost.com | http://www.globalpost.com/dispatch/news/agencia-efe/131230/mudslide-closes-major-road-northwestern-mexico | 36.51603 | 81.74198 |
stem(df_MX$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 2
## 0 | 6
## 1 | 23stem(df_MX$"distance", scale = 2)##
## The decimal point is at the |
##
## 2 | 5
## 4 |
## 6 | 5
## 8 |
## 10 |
## 12 | 45Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 2.4977 | 1 | 25 | 25 | 25 | 25 |
| 6.46156 | 1 | 25 | 25 | 50 | 50 |
| 12.365 | 1 | 25 | 25 | 75 | 75 |
| 12.53758 | 1 | 25 | 25 | 100 | 100 |
| Total | 4 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 5 obs. of 5 variables:
## $ n : num 1 1 1 1 4
## $ % : num 25 25 25 25 100
## $ val% : num 25 25 25 25 100
## $ %cum : num 25 50 75 100 100
## $ val%cum: num 25 50 75 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 2.4977 | 1 |
| 6.46156 | 1 |
| 12.365 | 1 |
| 12.53758 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 2.4977 6.4977 10.4977 14.4977distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (2.5,6.5] | 1 | 0.3333333 | 1 |
| (6.5,10.5] | 0 | 0.0000000 | 1 |
| (10.5,14.5] | 2 | 0.6666667 | 3 |
str(Freq_table)## 'data.frame': 3 obs. of 4 variables:
## $ distance: Factor w/ 3 levels "(2.5,6.5]","(6.5,10.5]",..: 1 2 3
## $ Freq : int 1 0 2
## $ Rel_Freq: num 0.333 0 0.667
## $ Cum_Freq: int 1 1 3df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (2.5,6.5] | 1 |
| (6.5,10.5] | 0 |
| (10.5,14.5] | 2 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_MX)## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 4.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 4.170000e+02 NA NA NA NA NA
## max 7.056000e+03 NA NA NA NA NA
## range 6.639000e+03 NA NA NA NA NA
## sum 1.504200e+04 NA NA NA NA NA
## median 3.784500e+03 NA NA NA NA NA
## mean 3.760500e+03 NA NA NA NA NA
## SE.mean 1.571045e+03 NA NA NA NA NA
## CI.mean.0.95 4.999766e+03 NA NA NA NA NA
## var 9.872730e+06 NA NA NA NA NA
## std.dev 3.142090e+03 NA NA NA NA NA
## coef.var 8.355511e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 4.000000e+00 NA 4.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 1.173000e+03 NA 2.4977000 NA
## max NA 1.376457e+06 NA 12.5375800 NA
## range NA 1.375284e+06 NA 10.0398800 NA
## sum NA 2.763172e+06 NA 33.8618400 NA
## median NA 6.927710e+05 NA 9.4132800 NA
## mean NA 6.907930e+05 NA 8.4654600 NA
## SE.mean NA 3.958716e+05 NA 2.4395756 NA
## CI.mean.0.95 NA 1.259840e+06 NA 7.7638183 NA
## var NA 6.268573e+11 NA 23.8061160 NA
## std.dev NA 7.917432e+05 NA 4.8791512 NA
## coef.var NA 1.146137e+00 NA 0.5763598 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 4.000000e+00 4.000000e+00 NA NA NA
## nbr.null 0.000000e+00 0.000000e+00 NA NA NA
## nbr.na 0.000000e+00 0.000000e+00 NA NA NA
## min 3.197800e+01 -1.170898e+02 NA NA NA
## max 3.257550e+01 -1.167776e+02 NA NA NA
## range 5.975000e-01 3.122000e-01 NA NA NA
## sum 1.295981e+02 -4.677689e+02 NA NA NA
## median 3.252230e+01 -1.169507e+02 NA NA NA
## mean 3.239952e+01 -1.169422e+02 NA NA NA
## SE.mean 1.410711e-01 6.699289e-02 NA NA NA
## CI.mean.0.95 4.489511e-01 2.132013e-01 NA NA NA
## var 7.960417e-02 1.795219e-02 NA NA NA
## std.dev 2.821421e-01 1.339858e-01 NA NA NA
## coef.var 8.708217e-03 -1.145743e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 1 4.0000000 NA
## nbr.null NA NA NA 1 3.0000000 NA
## nbr.na NA NA NA 3 0.0000000 NA
## min NA NA NA 0 0.0000000 NA
## max NA NA NA 0 1.0000000 NA
## range NA NA NA 0 1.0000000 NA
## sum NA NA NA 0 1.0000000 NA
## median NA NA NA 0 0.0000000 NA
## mean NA NA NA 0 0.2500000 NA
## SE.mean NA NA NA NA 0.2500000 NA
## CI.mean.0.95 NA NA NA NaN 0.7956116 NA
## var NA NA NA NA 0.2500000 NA
## std.dev NA NA NA NA 0.5000000 NA
## coef.var NA NA NA NA 2.0000000 NA
## source_link prop ypos
## nbr.val NA 4.0000000 4.0000000
## nbr.null NA 0.0000000 0.0000000
## nbr.na NA 0.0000000 0.0000000
## min NA 7.3761497 18.5128451
## max NA 37.0256903 81.7419845
## range NA 29.6495406 63.2291393
## sum NA 100.0000000 194.9114992
## median NA 27.7990800 47.3283348
## mean NA 25.0000000 48.7278748
## SE.mean NA 7.2044980 13.2107972
## CI.mean.0.95 NA 22.9279280 42.0426527
## var NA 207.6191648 698.1006481
## std.dev NA 14.4089960 26.4215944
## coef.var NA 0.5763598 0.5422275boxplot(data, horizontal=TRUE, col='green')
Gráfico para Chiapas (Mexico)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_MX <- subset(df, country_name == "Mexico")
knitr::kable(head(df_MX)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 115 | 7/4/07 | NA | NA | Mexico | MX | Veracruz-Llave | 1947 | Laguna Chica (Pueblo Nuevo) | 9.51003 | NA | 18.5369 | -96.8229 | (18.536899999999999, -96.822900000000004) | Landslide | Landslide | Medium | Rain | NA | NA | 7 | nytimes.com | http://www.nytimes.com/2007/07/04/world/americas/04cnd-mexico.html?_r=1&hp&oref=slogin |
| 201 | 8/23/07 | NA | NA | Mexico | MX | Puebla | 1414 | Xochitlaxco (San Baltazar) | 1.68294 | NA | 19.9333 | -97.8500 | (19.933299999999999, -97.85) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Dean | NA | 6 | Inquirer.com | http://newsinfo.inquirer.net/breakingnews/world/view_article.php?article_id=84452 |
| 225 | 9/2/07 | NA | NA | Mexico | MX | Sinaloa | 3191 | El Limón de los Ramos | 10.88351 | NA | 24.9531 | -107.6220 | (24.953099999999999, -107.622) | Landslide | Complex | Medium | Tropical cyclone | Tropical Storm Henrietta | NA | 3 | NA | NA |
| 284 | 9/28/07 | NA | NA | Mexico | MX | Puebla | 3761 | Xaltepuxtla | 7.93258 | NA | 20.2000 | -97.9000 | (20.2, -97.9) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Lorenzo | NA | 1 | PressTV.ir | http://www.presstv.ir/detail.aspx?id=25037§ionid=3510207 |
| 342 | 10/31/07 | NA | NA | Mexico | MX | Tabasco | 4468 | Buenavista | 4.19108 | NA | 17.9493 | -92.5534 | (17.949300000000001, -92.553399999999996) | Landslide | Landslide | Medium | Rain | NA | NA | 18 | CapeTimes | http://www.capetimes.co.za/?fArticleId=4109453 |
| 346 | 11/4/07 | NA | NA | Mexico | MX | Chiapas | 3183 | Ostuacán | 3.74149 | NA | 17.3900 | -93.3060 | (17.39, -93.305999999999997) | Landslide | Mudslide | Very_large | Rain | NA | NA | 5 | Reuters - AlertNet.org | http://news.monstersandcritics.com/americas/news/article_1371436.php/Mudslide_is_latest_disaster_for_hard-hit_Mexico__2nd_Roundup_ |
library(dplyr)
df_MX <- subset(df, state == "Chiapas")
knitr::kable(head(df_MX))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 346 | 11/4/07 | NA | NA | Mexico | MX | Chiapas | 3183 | Ostuacán | 3.74149 | NA | 17.3900 | -93.3060 | (17.39, -93.305999999999997) | Landslide | Mudslide | Very_large | Rain | NA | NA | 5 | Reuters - AlertNet.org | http://news.monstersandcritics.com/americas/news/article_1371436.php/Mudslide_is_latest_disaster_for_hard-hit_Mexico__2nd_Roundup_ |
| 2114 | 7/22/10 | Overnight | NA | Mexico | MX | Chiapas | 9570 | Escuintla | 1.41805 | NA | 15.3258 | -92.6698 | (15.325799999999999, -92.669799999999995) | Landslide | Mudslide | Medium | Downpour | NA | NA | 3 | NA | http://www.laht.com/article.asp?ArticleId=361041&CategoryId=14091 |
| 2115 | 7/22/10 | NA | NA | Mexico | MX | Chiapas | 128996 | San Cristóbal de las Casas | 0.94118 | NA | 16.7294 | -92.6389 | (16.729399999999998, -92.638900000000007) | Landslide | Rockfall | Small | Downpour | NA | NA | 0 | NA | http://www.laht.com/article.asp?ArticleId=361041&CategoryId=14091 |
| 2520 | 9/29/10 | NA | NA | Mexico | MX | Chiapas | 3947 | Amatán | 0.31118 | NA | 17.3738 | -92.8213 | (17.373799999999999, -92.821299999999994) | Landslide | Mudslide | Large | Tropical cyclone | Hurricane Karl and Tropical Storm Matthew | NA | 16 | NA | http://technews.tmcnet.com/topics/associated-press/articles/106209-death-toll-southern-mexico-mudslides-up-32.htm |
| 2521 | 9/29/10 | NA | NA | Mexico | MX | Chiapas | 1088 | Chihuahua | 8.46579 | NA | 16.0203 | -91.8946 | (16.020299999999999, -91.894599999999997) | Landslide | Complex | Medium | Tropical cyclone | Hurricane Karl and Tropical Storm Matthew | NA | 3 | NA | http://technews.tmcnet.com/topics/associated-press/articles/106209-death-toll-southern-mexico-mudslides-up-32.htm |
| 3832 | 7/22/11 | NA | NA | Mexico | MX | Chiapas | 1005 | Nueva Libertad | 7.93996 | NA | 16.1514 | -92.7704 | (16.151399999999999, -92.770399999999995) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Dora | NA | 0 | NA | http://www.china.org.cn/environment/2011-07/22/content_23044018.htm |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_MX <- df_MX %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_MX$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_MX, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4## Warning in RColorBrewer::brewer.pal(n, pal): n too large, allowed maximum for palette Greens is 9
## Returning the palette you asked for with that many colors
Grafico de series temporales
library(forecast)
data<- ts(df_MX$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 1.73469 |
| 0.76257 |
| 0.94118 |
| 3.74149 |
| 7.93996 |
| 2.06743 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_MX$distance
names(distance) <- df_MX$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Chihuahua 8.4657900 8.4657900 26.4005074 26.4005074
## Nueva Libertad 7.9399600 16.4057500 24.7607102 51.1612177
## Emiliano Zapata 4.6844300 21.0901800 14.6083625 65.7695802
## Ostuacán 3.7414900 24.8316700 11.6678106 77.4373908
## Motozintla de Mendoza 2.0674300 26.8991000 6.4472661 83.8846569
## Tila 1.7346900 28.6337900 5.4096187 89.2942757
## Escuintla 1.4180500 30.0518400 4.4221791 93.7164548
## San Cristóbal de las Casas 0.9411800 30.9930200 2.9350633 96.6515181
## Santo Domingo 0.7625700 31.7555900 2.3780693 99.0295873
## Amatán 0.3111800 32.0667700 0.9704127 100.0000000stem(df_MX$"distance")##
## The decimal point is at the |
##
## 0 | 38947
## 2 | 17
## 4 | 7
## 6 | 9
## 8 | 5head(df_MX)## # A tibble: 6 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 7517 9/12/15 <NA> <NA> Mexico MX Chiapas 6089
## 2 7514 5/23/15 <NA> <NA> Mexico MX Chiapas 3796
## 3 2115 7/22/10 <NA> <NA> Mexico MX Chiapas 128996
## 4 346 11/4/07 <NA> <NA> Mexico MX Chiapas 3183
## 5 3832 7/22/11 <NA> <NA> Mexico MX Chiapas 1005
## 6 7515 10/21/15 <NA> <NA> Mexico MX Chiapas 19092
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_MX))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 7517 | 9/12/15 | NA | NA | Mexico | MX | Chiapas | 6089 | Tila | 1.73469 | Below road | 17.3112 | -92.4393 | (17.311199999999999, -92.439300000000003) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | NVI noticias | http://www.noticiasnet.mx/portal/chiapas/general/agua/317470-lluvias-causan-deslaves-tramos-carreteros | 5.409619 | 2.704809 |
| 7514 | 5/23/15 | NA | NA | Mexico | MX | Chiapas | 3796 | Santo Domingo | 0.76257 | Below road | 15.0337 | -92.1124 | (15.0337, -92.112399999999994) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | Cuarto Poder | http://www.cuartopoder.mx/deslaveafectacarreteradejandouncarril-116564.html | 2.378069 | 6.598653 |
| 2115 | 7/22/10 | NA | NA | Mexico | MX | Chiapas | 128996 | San Cristóbal de las Casas | 0.94118 | NA | 16.7294 | -92.6389 | (16.729399999999998, -92.638900000000007) | Landslide | Rockfall | Small | Downpour | NA | NA | 0 | NA | http://www.laht.com/article.asp?ArticleId=361041&CategoryId=14091 | 2.935063 | 9.255220 |
| 346 | 11/4/07 | NA | NA | Mexico | MX | Chiapas | 3183 | Ostuacán | 3.74149 | NA | 17.3900 | -93.3060 | (17.39, -93.305999999999997) | Landslide | Mudslide | Very_large | Rain | NA | NA | 5 | Reuters - AlertNet.org | http://news.monstersandcritics.com/americas/news/article_1371436.php/Mudslide_is_latest_disaster_for_hard-hit_Mexico__2nd_Roundup_ | 11.667811 | 16.556657 |
| 3832 | 7/22/11 | NA | NA | Mexico | MX | Chiapas | 1005 | Nueva Libertad | 7.93996 | NA | 16.1514 | -92.7704 | (16.151399999999999, -92.770399999999995) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Dora | NA | 0 | NA | http://www.china.org.cn/environment/2011-07/22/content_23044018.htm | 24.760710 | 34.770917 |
| 7515 | 10/21/15 | NA | NA | Mexico | MX | Chiapas | 19092 | Motozintla de Mendoza | 2.06743 | Above road | 15.3482 | -92.2523 | (15.3482, -92.252300000000005) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | azteca noticias | http://www.aztecanoticias.com.mx/notas/estados/234140/suman-16-deslaves-por-lluvias-en-chiapas | 6.447266 | 50.374905 |
stem(df_MX$"distance")##
## The decimal point is at the |
##
## 0 | 38947
## 2 | 17
## 4 | 7
## 6 | 9
## 8 | 5stem(df_MX$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 389
## 1 | 47
## 2 | 1
## 3 | 7
## 4 | 7
## 5 |
## 6 |
## 7 | 9
## 8 | 5Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.31118 | 1 | 10 | 10 | 10 | 10 |
| 0.76257 | 1 | 10 | 10 | 20 | 20 |
| 0.94118 | 1 | 10 | 10 | 30 | 30 |
| 1.41805 | 1 | 10 | 10 | 40 | 40 |
| 1.73469 | 1 | 10 | 10 | 50 | 50 |
| 2.06743 | 1 | 10 | 10 | 60 | 60 |
| 3.74149 | 1 | 10 | 10 | 70 | 70 |
| 4.68443 | 1 | 10 | 10 | 80 | 80 |
| 7.93996 | 1 | 10 | 10 | 90 | 90 |
| 8.46579 | 1 | 10 | 10 | 100 | 100 |
| Total | 10 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 11 obs. of 5 variables:
## $ n : num 1 1 1 1 1 1 1 1 1 1 ...
## $ % : num 10 10 10 10 10 10 10 10 10 10 ...
## $ val% : num 10 10 10 10 10 10 10 10 10 10 ...
## $ %cum : num 10 20 30 40 50 60 70 80 90 100 ...
## $ val%cum: num 10 20 30 40 50 60 70 80 90 100 ...x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.31118 | 1 |
| 0.76257 | 1 |
| 0.94118 | 1 |
| 1.41805 | 1 |
| 1.73469 | 1 |
| 2.06743 | 1 |
| 3.74149 | 1 |
| 4.68443 | 1 |
| 7.93996 | 1 |
| 8.46579 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.31118 2.31118 4.31118 6.31118 8.31118 10.31118distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.311,2.31] | 5 | 0.5555556 | 5 |
| (2.31,4.31] | 1 | 0.1111111 | 6 |
| (4.31,6.31] | 1 | 0.1111111 | 7 |
| (6.31,8.31] | 1 | 0.1111111 | 8 |
| (8.31,10.3] | 1 | 0.1111111 | 9 |
str(Freq_table)## 'data.frame': 5 obs. of 4 variables:
## $ distance: Factor w/ 5 levels "(0.311,2.31]",..: 1 2 3 4 5
## $ Freq : int 5 1 1 1 1
## $ Rel_Freq: num 0.556 0.111 0.111 0.111 0.111
## $ Cum_Freq: int 5 6 7 8 9df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.311,2.31] | 5 |
| (2.31,4.31] | 1 |
| (4.31,6.31] | 1 |
| (6.31,8.31] | 1 |
| (8.31,10.3] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_MX)## id date time continent_code country_name country_code
## nbr.val 1.000000e+01 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 3.460000e+02 NA NA NA NA NA
## max 7.517000e+03 NA NA NA NA NA
## range 7.171000e+03 NA NA NA NA NA
## sum 4.351000e+04 NA NA NA NA NA
## median 3.176500e+03 NA NA NA NA NA
## mean 4.351000e+03 NA NA NA NA NA
## SE.mean 9.010547e+02 NA NA NA NA NA
## CI.mean.0.95 2.038327e+03 NA NA NA NA NA
## var 8.118995e+06 NA NA NA NA NA
## std.dev 2.849385e+03 NA NA NA NA NA
## coef.var 6.548805e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 1.000000e+01 NA 10.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 1.005000e+03 NA 0.3111800 NA
## max NA 1.289960e+05 NA 8.4657900 NA
## range NA 1.279910e+05 NA 8.1546100 NA
## sum NA 1.953740e+05 NA 32.0667700 NA
## median NA 5.018000e+03 NA 1.9010600 NA
## mean NA 1.953740e+04 NA 3.2066770 NA
## SE.mean NA 1.233991e+04 NA 0.9350334 NA
## CI.mean.0.95 NA 2.791482e+04 NA 2.1151925 NA
## var NA 1.522734e+09 NA 8.7428745 NA
## std.dev NA 3.902222e+04 NA 2.9568352 NA
## coef.var NA 1.997309e+00 NA 0.9220870 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 10.00000000 1.000000e+01 NA NA NA
## nbr.null 0.00000000 0.000000e+00 NA NA NA
## nbr.na 0.00000000 0.000000e+00 NA NA NA
## min 15.03370000 -9.330600e+01 NA NA NA
## max 17.70550000 -9.174160e+01 NA NA NA
## range 2.67180000 1.564400e+00 NA NA NA
## sum 164.38930000 -9.246466e+02 NA NA NA
## median 16.44040000 -9.253910e+01 NA NA NA
## mean 16.43893000 -9.246466e+01 NA NA NA
## SE.mean 0.31427677 1.497619e-01 NA NA NA
## CI.mean.0.95 0.71094344 3.387849e-01 NA NA NA
## var 0.98769885 2.242861e-01 NA NA NA
## std.dev 0.99383039 4.735886e-01 NA NA NA
## coef.var 0.06045591 -5.121833e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 4 10.000000 NA
## nbr.null NA NA NA 4 6.000000 NA
## nbr.na NA NA NA 6 0.000000 NA
## min NA NA NA 0 0.000000 NA
## max NA NA NA 0 16.000000 NA
## range NA NA NA 0 16.000000 NA
## sum NA NA NA 0 27.000000 NA
## median NA NA NA 0 0.000000 NA
## mean NA NA NA 0 2.700000 NA
## SE.mean NA NA NA 0 1.584999 NA
## CI.mean.0.95 NA NA NA 0 3.585517 NA
## var NA NA NA 0 25.122222 NA
## std.dev NA NA NA 0 5.012207 NA
## coef.var NA NA NA NaN 1.856373 NA
## source_link prop ypos
## nbr.val NA 10.0000000 10.0000000
## nbr.null NA 0.0000000 0.0000000
## nbr.na NA 0.0000000 0.0000000
## min NA 0.9704127 2.7048094
## max NA 26.4005074 99.5147937
## range NA 25.4300948 96.8099843
## sum NA 100.0000000 426.7398151
## median NA 5.9284424 42.5729111
## mean NA 10.0000000 42.6739815
## SE.mean NA 2.9158952 10.8517928
## CI.mean.0.95 NA 6.5962131 24.5484607
## var NA 85.0244464 1177.6140634
## std.dev NA 9.2208702 34.3163819
## coef.var NA 0.9220870 0.8041523boxplot(data, horizontal=TRUE, col='green')
Gráfico para Guerrero (Mexico)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_MX <- subset(df, country_name == "Mexico")
knitr::kable(head(df_MX)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 115 | 7/4/07 | NA | NA | Mexico | MX | Veracruz-Llave | 1947 | Laguna Chica (Pueblo Nuevo) | 9.51003 | NA | 18.5369 | -96.8229 | (18.536899999999999, -96.822900000000004) | Landslide | Landslide | Medium | Rain | NA | NA | 7 | nytimes.com | http://www.nytimes.com/2007/07/04/world/americas/04cnd-mexico.html?_r=1&hp&oref=slogin |
| 201 | 8/23/07 | NA | NA | Mexico | MX | Puebla | 1414 | Xochitlaxco (San Baltazar) | 1.68294 | NA | 19.9333 | -97.8500 | (19.933299999999999, -97.85) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Dean | NA | 6 | Inquirer.com | http://newsinfo.inquirer.net/breakingnews/world/view_article.php?article_id=84452 |
| 225 | 9/2/07 | NA | NA | Mexico | MX | Sinaloa | 3191 | El Limón de los Ramos | 10.88351 | NA | 24.9531 | -107.6220 | (24.953099999999999, -107.622) | Landslide | Complex | Medium | Tropical cyclone | Tropical Storm Henrietta | NA | 3 | NA | NA |
| 284 | 9/28/07 | NA | NA | Mexico | MX | Puebla | 3761 | Xaltepuxtla | 7.93258 | NA | 20.2000 | -97.9000 | (20.2, -97.9) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Lorenzo | NA | 1 | PressTV.ir | http://www.presstv.ir/detail.aspx?id=25037§ionid=3510207 |
| 342 | 10/31/07 | NA | NA | Mexico | MX | Tabasco | 4468 | Buenavista | 4.19108 | NA | 17.9493 | -92.5534 | (17.949300000000001, -92.553399999999996) | Landslide | Landslide | Medium | Rain | NA | NA | 18 | CapeTimes | http://www.capetimes.co.za/?fArticleId=4109453 |
| 346 | 11/4/07 | NA | NA | Mexico | MX | Chiapas | 3183 | Ostuacán | 3.74149 | NA | 17.3900 | -93.3060 | (17.39, -93.305999999999997) | Landslide | Mudslide | Very_large | Rain | NA | NA | 5 | Reuters - AlertNet.org | http://news.monstersandcritics.com/americas/news/article_1371436.php/Mudslide_is_latest_disaster_for_hard-hit_Mexico__2nd_Roundup_ |
library(dplyr)
df_MX <- subset(df, state == "Guerrero")
knitr::kable(head(df_MX))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 3834 | 7/22/11 | NA | NA | Mexico | MX | Guerrero | 165250 | Chilpancingo de los Bravos | 6.80950 | NA | 17.4974 | -99.5380 | (17.497399999999999, -99.537999999999997) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Dora | NA | 0 | NA | NA |
| 5530 | 9/15/13 | NA | NA | Mexico | MX | Guerrero | 652136 | Acapulco | 0.90692 | NA | 16.8638 | -99.8816 | (16.863800000000001, -99.881600000000006) | Landslide | Mudslide | Very_large | Downpour | NA | NA | NA | www.trust.org | http://www.trust.org/item/20131014162052-6ou24/?source=gep |
| 5534 | 9/16/13 | 15:30 | NA | Mexico | MX | Guerrero | 21407 | Atoyac de Álvarez | 32.12708 | Deforested slope | 17.3461 | -100.1681 | (17.3461, -100.1681) | Landslide | Mudslide | Medium | Tropical cyclone | Manuel | 4 | 71 | Vice News | https://news.vice.com/article/a-mexican-town-mourns-its-missing-one-year-after-being-engulfed-by-mud |
| 5538 | 9/16/13 | NA | NA | Mexico | MX | Guerrero | 1252 | San Pablo Atzompa | 14.04274 | NA | 17.2250 | -98.5000 | (17.225000000000001, -98.5) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | america.aljazeera.com | http://america.aljazeera.com/articles/2013/11/19/after-landslide-poorestofthepoorleftoutinthecoldinmexico.html |
| 5543 | 9/16/13 | NA | NA | Mexico | MX | Guerrero | 165250 | Chilpancingo de los Bravos | 0.88149 | NA | 17.5482 | -99.5137 | (17.548200000000001, -99.5137) | Landslide | Mudslide | Medium | Tropical cyclone | Ingrid | NA | 4 | www.washingtonpost.com | http://www.washingtonpost.com/world/two-storms-batter-mexico-killing-dozens/2013/09/17/5cd3d81e-1f8e-11e3-b7d1-7153ad47b549_gallery.html#photo=6 |
| 6269 | 10/18/14 | NA | NA | Mexico | MX | Guerrero | 1018 | Colonia Alborada | 4.10830 | Above road | 16.8850 | -99.8562 | (16.885000000000002, -99.856200000000001) | Landslide | Landslide | Small | Tropical cyclone | Trudy | 0 | 0 | Thomson Reuters Foundation | http://www.trust.org/item/20141018173449-r3rca/ |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_MX <- df_MX %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_MX$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_MX, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_MX$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 14.04274 |
| 12.33417 |
| 4.10830 |
| 6.80950 |
| 0.88149 |
| 32.12708 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_MX$distance
names(distance) <- df_MX$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Atoyac de Álvarez 32.127080 32.127080 41.040408 41.040408
## San Pablo Atzompa 14.042740 46.169820 17.938754 58.979162
## Pochutla 12.334170 58.503990 15.756159 74.735321
## Acapulco de Juárez 7.071380 65.575370 9.033262 83.768583
## Chilpancingo de los Bravos 6.809500 72.384870 8.698726 92.467308
## Colonia Alborada 4.108300 76.493170 5.248106 97.715414
## Acapulco 0.906920 77.400090 1.158536 98.873950
## Chilpancingo de los Bravos 0.881490 78.281580 1.126050 100.000000stem(df_MX$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 11477
## 1 | 24
## 2 |
## 3 | 2head(df_MX)## # A tibble: 6 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 5538 9/16/13 <NA> <NA> Mexico MX Guerrero 1252
## 2 7479 10/3/15 Night <NA> Mexico MX Guerrero 1201
## 3 6269 10/18/14 <NA> <NA> Mexico MX Guerrero 1018
## 4 3834 7/22/11 <NA> <NA> Mexico MX Guerrero 165250
## 5 5543 9/16/13 <NA> <NA> Mexico MX Guerrero 165250
## 6 5534 9/16/13 15:30 <NA> Mexico MX Guerrero 21407
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_MX))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 5538 | 9/16/13 | NA | NA | Mexico | MX | Guerrero | 1252 | San Pablo Atzompa | 14.04274 | NA | 17.2250 | -98.5000 | (17.225000000000001, -98.5) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | america.aljazeera.com | http://america.aljazeera.com/articles/2013/11/19/after-landslide-poorestofthepoorleftoutinthecoldinmexico.html | 17.938754 | 8.969377 |
| 7479 | 10/3/15 | Night | NA | Mexico | MX | Guerrero | 1201 | Pochutla | 12.33417 | Unknown | 17.5586 | -98.9483 | (17.558599999999998, -98.948300000000003) | Landslide | Landslide | Medium | Tropical cyclone | Marty | 0 | 0 | Tiempo | http://www.tiempoenlinea.com.mx/index.php/oaxaca-2/52715-deslave-afecta-62-viviendas-en-la-montana-de-guerrero | 15.756159 | 25.816833 |
| 6269 | 10/18/14 | NA | NA | Mexico | MX | Guerrero | 1018 | Colonia Alborada | 4.10830 | Above road | 16.8850 | -99.8562 | (16.885000000000002, -99.856200000000001) | Landslide | Landslide | Small | Tropical cyclone | Trudy | 0 | 0 | Thomson Reuters Foundation | http://www.trust.org/item/20141018173449-r3rca/ | 5.248106 | 36.318965 |
| 3834 | 7/22/11 | NA | NA | Mexico | MX | Guerrero | 165250 | Chilpancingo de los Bravos | 6.80950 | NA | 17.4974 | -99.5380 | (17.497399999999999, -99.537999999999997) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Dora | NA | 0 | NA | NA | 8.698726 | 43.292381 |
| 5543 | 9/16/13 | NA | NA | Mexico | MX | Guerrero | 165250 | Chilpancingo de los Bravos | 0.88149 | NA | 17.5482 | -99.5137 | (17.548200000000001, -99.5137) | Landslide | Mudslide | Medium | Tropical cyclone | Ingrid | NA | 4 | www.washingtonpost.com | http://www.washingtonpost.com/world/two-storms-batter-mexico-killing-dozens/2013/09/17/5cd3d81e-1f8e-11e3-b7d1-7153ad47b549_gallery.html#photo=6 | 1.126050 | 48.204769 |
| 5534 | 9/16/13 | 15:30 | NA | Mexico | MX | Guerrero | 21407 | Atoyac de Álvarez | 32.12708 | Deforested slope | 17.3461 | -100.1681 | (17.3461, -100.1681) | Landslide | Mudslide | Medium | Tropical cyclone | Manuel | 4 | 71 | Vice News | https://news.vice.com/article/a-mexican-town-mourns-its-missing-one-year-after-being-engulfed-by-mud | 41.040408 | 69.287999 |
stem(df_MX$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 11477
## 1 | 24
## 2 |
## 3 | 2stem(df_MX$"distance", scale = 2)##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 114
## 0 | 77
## 1 | 24
## 1 |
## 2 |
## 2 |
## 3 | 2Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.88149 | 1 | 12.5 | 12.5 | 12.5 | 12.5 |
| 0.90692 | 1 | 12.5 | 12.5 | 25.0 | 25.0 |
| 4.1083 | 1 | 12.5 | 12.5 | 37.5 | 37.5 |
| 6.8095 | 1 | 12.5 | 12.5 | 50.0 | 50.0 |
| 7.07138 | 1 | 12.5 | 12.5 | 62.5 | 62.5 |
| 12.33417 | 1 | 12.5 | 12.5 | 75.0 | 75.0 |
| 14.04274 | 1 | 12.5 | 12.5 | 87.5 | 87.5 |
| 32.12708 | 1 | 12.5 | 12.5 | 100.0 | 100.0 |
| Total | 8 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 9 obs. of 5 variables:
## $ n : num 1 1 1 1 1 1 1 1 8
## $ % : num 12.5 12.5 12.5 12.5 12.5 12.5 12.5 12.5 100
## $ val% : num 12.5 12.5 12.5 12.5 12.5 12.5 12.5 12.5 100
## $ %cum : num 12.5 25 37.5 50 62.5 75 87.5 100 100
## $ val%cum: num 12.5 25 37.5 50 62.5 75 87.5 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.88149 | 1 |
| 0.90692 | 1 |
| 4.1083 | 1 |
| 6.8095 | 1 |
| 7.07138 | 1 |
| 12.33417 | 1 |
| 14.04274 | 1 |
| 32.12708 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.88149 8.88149 16.88149 24.88149 32.88149distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.881,8.88] | 4 | 0.5714286 | 4 |
| (8.88,16.9] | 2 | 0.2857143 | 6 |
| (16.9,24.9] | 0 | 0.0000000 | 6 |
| (24.9,32.9] | 1 | 0.1428571 | 7 |
str(Freq_table)## 'data.frame': 4 obs. of 4 variables:
## $ distance: Factor w/ 4 levels "(0.881,8.88]",..: 1 2 3 4
## $ Freq : int 4 2 0 1
## $ Rel_Freq: num 0.571 0.286 0 0.143
## $ Cum_Freq: int 4 6 6 7df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.881,8.88] | 4 |
| (8.88,16.9] | 2 |
| (16.9,24.9] | 0 |
| (24.9,32.9] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_MX)## id date time continent_code country_name country_code
## nbr.val 8.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 3.834000e+03 NA NA NA NA NA
## max 7.479000e+03 NA NA NA NA NA
## range 3.645000e+03 NA NA NA NA NA
## sum 4.719200e+04 NA NA NA NA NA
## median 5.540500e+03 NA NA NA NA NA
## mean 5.899000e+03 NA NA NA NA NA
## SE.mean 4.199559e+02 NA NA NA NA NA
## CI.mean.0.95 9.930378e+02 NA NA NA NA NA
## var 1.410903e+06 NA NA NA NA NA
## std.dev 1.187815e+03 NA NA NA NA NA
## coef.var 2.013586e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 8.000000e+00 NA 8.000000 NA
## nbr.null NA 0.000000e+00 NA 0.000000 NA
## nbr.na NA 0.000000e+00 NA 0.000000 NA
## min NA 1.018000e+03 NA 0.881490 NA
## max NA 6.521360e+05 NA 32.127080 NA
## range NA 6.511180e+05 NA 31.245590 NA
## sum NA 1.659650e+06 NA 78.281580 NA
## median NA 9.332850e+04 NA 6.940440 NA
## mean NA 2.074563e+05 NA 9.785198 NA
## SE.mean NA 1.001192e+05 NA 3.611317 NA
## CI.mean.0.95 NA 2.367442e+05 NA 8.539408 NA
## var NA 8.019077e+10 NA 104.332887 NA
## std.dev NA 2.831797e+05 NA 10.214347 NA
## coef.var NA 1.365009e+00 NA 1.043857 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 8.00000000 8.000000e+00 NA NA NA
## nbr.null 0.00000000 0.000000e+00 NA NA NA
## nbr.na 0.00000000 0.000000e+00 NA NA NA
## min 16.86380000 -1.001681e+02 NA NA NA
## max 17.55860000 -9.850000e+01 NA NA NA
## range 0.69480000 1.668100e+00 NA NA NA
## sum 137.82300000 -7.963511e+02 NA NA NA
## median 17.28555000 -9.969710e+01 NA NA NA
## mean 17.22787500 -9.954389e+01 NA NA NA
## SE.mean 0.10831128 1.985507e-01 NA NA NA
## CI.mean.0.95 0.25611548 4.694978e-01 NA NA NA
## var 0.09385067 3.153790e-01 NA NA NA
## std.dev 0.30635057 5.615862e-01 NA NA NA
## coef.var 0.01778226 -5.641594e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 4.000000 7.000000 NA
## nbr.null NA NA NA 3.000000 5.000000 NA
## nbr.na NA NA NA 4.000000 1.000000 NA
## min NA NA NA 0.000000 0.000000 NA
## max NA NA NA 4.000000 71.000000 NA
## range NA NA NA 4.000000 71.000000 NA
## sum NA NA NA 4.000000 75.000000 NA
## median NA NA NA 0.000000 0.000000 NA
## mean NA NA NA 1.000000 10.714286 NA
## SE.mean NA NA NA 1.000000 10.063404 NA
## CI.mean.0.95 NA NA NA 3.182446 24.624264 NA
## var NA NA NA 4.000000 708.904762 NA
## std.dev NA NA NA 2.000000 26.625265 NA
## coef.var NA NA NA 2.000000 2.485025 NA
## source_link prop ypos
## nbr.val NA 8.000000 8.0000000
## nbr.null NA 0.000000 0.0000000
## nbr.na NA 0.000000 0.0000000
## min NA 1.126050 8.9693770
## max NA 41.040408 99.4207322
## range NA 39.914358 90.4513552
## sum NA 100.000000 425.6358903
## median NA 8.865994 45.7485752
## mean NA 12.500000 53.2044863
## SE.mean NA 4.613240 11.3394853
## CI.mean.0.95 NA 10.908579 26.8136220
## var NA 170.255856 1028.6714218
## std.dev NA 13.048213 32.0729079
## coef.var NA 1.043857 0.6028234boxplot(data, horizontal=TRUE, col='green')
Gráfico para Hidalgo (Mexico)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_MX <- subset(df, country_name == "Mexico")
knitr::kable(head(df_MX)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 115 | 7/4/07 | NA | NA | Mexico | MX | Veracruz-Llave | 1947 | Laguna Chica (Pueblo Nuevo) | 9.51003 | NA | 18.5369 | -96.8229 | (18.536899999999999, -96.822900000000004) | Landslide | Landslide | Medium | Rain | NA | NA | 7 | nytimes.com | http://www.nytimes.com/2007/07/04/world/americas/04cnd-mexico.html?_r=1&hp&oref=slogin |
| 201 | 8/23/07 | NA | NA | Mexico | MX | Puebla | 1414 | Xochitlaxco (San Baltazar) | 1.68294 | NA | 19.9333 | -97.8500 | (19.933299999999999, -97.85) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Dean | NA | 6 | Inquirer.com | http://newsinfo.inquirer.net/breakingnews/world/view_article.php?article_id=84452 |
| 225 | 9/2/07 | NA | NA | Mexico | MX | Sinaloa | 3191 | El Limón de los Ramos | 10.88351 | NA | 24.9531 | -107.6220 | (24.953099999999999, -107.622) | Landslide | Complex | Medium | Tropical cyclone | Tropical Storm Henrietta | NA | 3 | NA | NA |
| 284 | 9/28/07 | NA | NA | Mexico | MX | Puebla | 3761 | Xaltepuxtla | 7.93258 | NA | 20.2000 | -97.9000 | (20.2, -97.9) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Lorenzo | NA | 1 | PressTV.ir | http://www.presstv.ir/detail.aspx?id=25037§ionid=3510207 |
| 342 | 10/31/07 | NA | NA | Mexico | MX | Tabasco | 4468 | Buenavista | 4.19108 | NA | 17.9493 | -92.5534 | (17.949300000000001, -92.553399999999996) | Landslide | Landslide | Medium | Rain | NA | NA | 18 | CapeTimes | http://www.capetimes.co.za/?fArticleId=4109453 |
| 346 | 11/4/07 | NA | NA | Mexico | MX | Chiapas | 3183 | Ostuacán | 3.74149 | NA | 17.3900 | -93.3060 | (17.39, -93.305999999999997) | Landslide | Mudslide | Very_large | Rain | NA | NA | 5 | Reuters - AlertNet.org | http://news.monstersandcritics.com/americas/news/article_1371436.php/Mudslide_is_latest_disaster_for_hard-hit_Mexico__2nd_Roundup_ |
library(dplyr)
df_MX <- subset(df, state == "Hidalgo")
knitr::kable(head(df_MX))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 4874 | 5/26/13 | NA | NA | Mexico | MX | Hidalgo | 33196 | Tepeji de Ocampo | 0.64483 | NA | 19.9006 | -99.3417 | (19.900600000000001, -99.341700000000003) | Landslide | Landslide | Large | Rain | NA | NA | 7 | en.apa.az | http://en.apa.az/xeber_7_killed_in_landslide_in_central_mexico_193672.html |
| 5527 | 9/15/13 | NA | NA | Mexico | MX | Hidalgo | 1236 | Fontezuelas | 9.78251 | NA | 20.5402 | -98.9492 | (20.540199999999999, -98.949200000000005) | Landslide | Landslide | Very_large | Tropical cyclone | Ingrid | NA | 3 | www.recordonline.com | http://www.recordonline.com/apps/pbcs.dll/article?AID=/20130915/NEWS/130919814/-1/SITEMAP |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_MX <- df_MX %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_MX$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_MX, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_MX$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 0.64483 |
| 9.78251 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_MX$distance
names(distance) <- df_MX$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Fontezuelas 9.782510 9.782510 93.815968 93.815968
## Tepeji de Ocampo 0.644830 10.427340 6.184032 100.000000stem(df_MX$"distance")##
## The decimal point is at the |
##
## 0 | 6
## 2 |
## 4 |
## 6 |
## 8 | 8head(df_MX)## # A tibble: 2 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 4874 5/26/13 <NA> <NA> Mexico MX Hidalgo 33196
## 2 5527 9/15/13 <NA> <NA> Mexico MX Hidalgo 1236
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_MX))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 4874 | 5/26/13 | NA | NA | Mexico | MX | Hidalgo | 33196 | Tepeji de Ocampo | 0.64483 | NA | 19.9006 | -99.3417 | (19.900600000000001, -99.341700000000003) | Landslide | Landslide | Large | Rain | NA | NA | 7 | en.apa.az | http://en.apa.az/xeber_7_killed_in_landslide_in_central_mexico_193672.html | 6.184032 | 3.092016 |
| 5527 | 9/15/13 | NA | NA | Mexico | MX | Hidalgo | 1236 | Fontezuelas | 9.78251 | NA | 20.5402 | -98.9492 | (20.540199999999999, -98.949200000000005) | Landslide | Landslide | Very_large | Tropical cyclone | Ingrid | NA | 3 | www.recordonline.com | http://www.recordonline.com/apps/pbcs.dll/article?AID=/20130915/NEWS/130919814/-1/SITEMAP | 93.815968 | 53.092016 |
stem(df_MX$"distance")##
## The decimal point is at the |
##
## 0 | 6
## 2 |
## 4 |
## 6 |
## 8 | 8stem(df_MX$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 6
## 1 |
## 2 |
## 3 |
## 4 |
## 5 |
## 6 |
## 7 |
## 8 |
## 9 | 8Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.64483 | 1 | 50 | 50 | 50 | 50 |
| 9.78251 | 1 | 50 | 50 | 100 | 100 |
| Total | 2 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 3 obs. of 5 variables:
## $ n : num 1 1 2
## $ % : num 50 50 100
## $ val% : num 50 50 100
## $ %cum : num 50 100 100
## $ val%cum: num 50 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.64483 | 1 |
| 9.78251 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.64483 5.64483 10.64483distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.645,5.64] | 0 | 0 | 0 |
| (5.64,10.6] | 1 | 1 | 1 |
str(Freq_table)## 'data.frame': 2 obs. of 4 variables:
## $ distance: Factor w/ 2 levels "(0.645,5.64]",..: 1 2
## $ Freq : int 0 1
## $ Rel_Freq: num 0 1
## $ Cum_Freq: int 0 1df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.645,5.64] | 0 |
| (5.64,10.6] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_MX)## Warning in min(x): ningún argumento finito para min; retornando Inf## Warning in max(x): ningun argumento finito para max; retornando -Inf## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 2.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 4.874000e+03 NA NA NA NA NA
## max 5.527000e+03 NA NA NA NA NA
## range 6.530000e+02 NA NA NA NA NA
## sum 1.040100e+04 NA NA NA NA NA
## median 5.200500e+03 NA NA NA NA NA
## mean 5.200500e+03 NA NA NA NA NA
## SE.mean 3.265000e+02 NA NA NA NA NA
## CI.mean.0.95 4.148576e+03 NA NA NA NA NA
## var 2.132045e+05 NA NA NA NA NA
## std.dev 4.617407e+02 NA NA NA NA NA
## coef.var 8.878776e-02 NA NA NA NA NA
## state population city distance location_description latitude
## nbr.val NA 2.000000e+00 NA 2.000000 NA 2.00000000
## nbr.null NA 0.000000e+00 NA 0.000000 NA 0.00000000
## nbr.na NA 0.000000e+00 NA 0.000000 NA 0.00000000
## min NA 1.236000e+03 NA 0.644830 NA 19.90060000
## max NA 3.319600e+04 NA 9.782510 NA 20.54020000
## range NA 3.196000e+04 NA 9.137680 NA 0.63960000
## sum NA 3.443200e+04 NA 10.427340 NA 40.44080000
## median NA 1.721600e+04 NA 5.213670 NA 20.22040000
## mean NA 1.721600e+04 NA 5.213670 NA 20.22040000
## SE.mean NA 1.598000e+04 NA 4.568840 NA 0.31980000
## CI.mean.0.95 NA 2.030452e+05 NA 58.052616 NA 4.06344427
## var NA 5.107208e+08 NA 41.748598 NA 0.20454408
## std.dev NA 2.259913e+04 NA 6.461315 NA 0.45226550
## coef.var NA 1.312682e+00 NA 1.239303 NA 0.02236679
## longitude geolocation hazard_type landslide_type
## nbr.val 2.000000e+00 NA NA NA
## nbr.null 0.000000e+00 NA NA NA
## nbr.na 0.000000e+00 NA NA NA
## min -9.934170e+01 NA NA NA
## max -9.894920e+01 NA NA NA
## range 3.925000e-01 NA NA NA
## sum -1.982909e+02 NA NA NA
## median -9.914545e+01 NA NA NA
## mean -9.914545e+01 NA NA NA
## SE.mean 1.962500e-01 NA NA NA
## CI.mean.0.95 2.493593e+00 NA NA NA
## var 7.702812e-02 NA NA NA
## std.dev 2.775394e-01 NA NA NA
## coef.var -2.799316e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 0 2.0000000 NA
## nbr.null NA NA NA 0 0.0000000 NA
## nbr.na NA NA NA 2 0.0000000 NA
## min NA NA NA Inf 3.0000000 NA
## max NA NA NA -Inf 7.0000000 NA
## range NA NA NA -Inf 4.0000000 NA
## sum NA NA NA 0 10.0000000 NA
## median NA NA NA NA 5.0000000 NA
## mean NA NA NA NaN 5.0000000 NA
## SE.mean NA NA NA NA 2.0000000 NA
## CI.mean.0.95 NA NA NA NaN 25.4124095 NA
## var NA NA NA NA 8.0000000 NA
## std.dev NA NA NA NA 2.8284271 NA
## coef.var NA NA NA NA 0.5656854 NA
## source_link prop ypos
## nbr.val NA 2.000000 2.000000
## nbr.null NA 0.000000 0.000000
## nbr.na NA 0.000000 0.000000
## min NA 6.184032 3.092016
## max NA 93.815968 53.092016
## range NA 87.631937 50.000000
## sum NA 100.000000 56.184032
## median NA 50.000000 28.092016
## mean NA 50.000000 28.092016
## SE.mean NA 43.815968 25.000000
## CI.mean.0.95 NA 556.734665 317.655118
## var NA 3839.678175 1250.000000
## std.dev NA 61.965137 35.355339
## coef.var NA 1.239303 1.258555boxplot(data, horizontal=TRUE, col='green')
Gráfico para México (Mexico)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_MX <- subset(df, country_name == "Mexico")
knitr::kable(head(df_MX)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 115 | 7/4/07 | NA | NA | Mexico | MX | Veracruz-Llave | 1947 | Laguna Chica (Pueblo Nuevo) | 9.51003 | NA | 18.5369 | -96.8229 | (18.536899999999999, -96.822900000000004) | Landslide | Landslide | Medium | Rain | NA | NA | 7 | nytimes.com | http://www.nytimes.com/2007/07/04/world/americas/04cnd-mexico.html?_r=1&hp&oref=slogin |
| 201 | 8/23/07 | NA | NA | Mexico | MX | Puebla | 1414 | Xochitlaxco (San Baltazar) | 1.68294 | NA | 19.9333 | -97.8500 | (19.933299999999999, -97.85) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Dean | NA | 6 | Inquirer.com | http://newsinfo.inquirer.net/breakingnews/world/view_article.php?article_id=84452 |
| 225 | 9/2/07 | NA | NA | Mexico | MX | Sinaloa | 3191 | El Limón de los Ramos | 10.88351 | NA | 24.9531 | -107.6220 | (24.953099999999999, -107.622) | Landslide | Complex | Medium | Tropical cyclone | Tropical Storm Henrietta | NA | 3 | NA | NA |
| 284 | 9/28/07 | NA | NA | Mexico | MX | Puebla | 3761 | Xaltepuxtla | 7.93258 | NA | 20.2000 | -97.9000 | (20.2, -97.9) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Lorenzo | NA | 1 | PressTV.ir | http://www.presstv.ir/detail.aspx?id=25037§ionid=3510207 |
| 342 | 10/31/07 | NA | NA | Mexico | MX | Tabasco | 4468 | Buenavista | 4.19108 | NA | 17.9493 | -92.5534 | (17.949300000000001, -92.553399999999996) | Landslide | Landslide | Medium | Rain | NA | NA | 18 | CapeTimes | http://www.capetimes.co.za/?fArticleId=4109453 |
| 346 | 11/4/07 | NA | NA | Mexico | MX | Chiapas | 3183 | Ostuacán | 3.74149 | NA | 17.3900 | -93.3060 | (17.39, -93.305999999999997) | Landslide | Mudslide | Very_large | Rain | NA | NA | 5 | Reuters - AlertNet.org | http://news.monstersandcritics.com/americas/news/article_1371436.php/Mudslide_is_latest_disaster_for_hard-hit_Mexico__2nd_Roundup_ |
library(dplyr)
df_MX <- subset(df, state == "México")
knitr::kable(head(df_MX))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 744 | 8/25/08 | NA | NA | Mexico | MX | México | 7182 | San Francisco Chimalpa | 2.59637 | NA | 19.4360 | -99.3650 | (19.436, -99.364999999999995) | Landslide | Mudslide | Medium | Downpour | NA | NA | 1 | NA | http://www.alertnet.org/thenews/newsdesk/N26335664.htm |
| 1469 | 2/5/10 | NA | NA | Mexico | MX | México | 505881 | Toluca | 0.66626 | NA | 19.2880 | -99.6469 | (19.288, -99.646900000000002) | Landslide | Landslide | Large | Downpour | NA | NA | 11 | NA | http://www.trt.net.tr/trtinternational/en/newsDetail.aspx?HaberKodu=dc2169ea-80de-437d-a57a-eb11725c40e5 |
| 1477 | 2/4/10 | 22:00 | NA | Mexico | MX | México | 2968 | Zacazonapan | 4.40801 | Above road | 19.1927 | -99.8654 | (19.192699999999999, -99.865399999999994) | Landslide | Mudslide | Large | Downpour | NA | NA | 11 | News Daily | http://www.newsdaily.com/stories/tre6151we-us-mexico-mudslide/ |
| 2474 | 9/20/10 | Late night | NA | Mexico | MX | México | 9267 | Villa Guerrero | 1.06048 | NA | 18.9642 | -99.6511 | (18.964200000000002, -99.6511) | Landslide | Landslide | Large | Downpour | NA | NA | 8 | NA | http://www.alertnet.org/thenews/newsdesk/N21168920.htm |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_MX <- df_MX %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_MX$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_MX, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_MX$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 4.40801 |
| 1.06048 |
| 0.66626 |
| 2.59637 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_MX$distance
names(distance) <- df_MX$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Zacazonapan 4.408010 4.408010 50.486192 50.486192
## San Francisco Chimalpa 2.596370 7.004380 29.736964 80.223156
## Villa Guerrero 1.060480 8.064860 12.145979 92.369135
## Toluca 0.666260 8.731120 7.630865 100.000000stem(df_MX$"distance")##
## The decimal point is at the |
##
## 0 | 7
## 1 | 1
## 2 | 6
## 3 |
## 4 | 4head(df_MX)## # A tibble: 4 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 1477 2/4/10 22:00 <NA> Mexico MX México 2968
## 2 2474 9/20/10 Late night <NA> Mexico MX México 9267
## 3 1469 2/5/10 <NA> <NA> Mexico MX México 505881
## 4 744 8/25/08 <NA> <NA> Mexico MX México 7182
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_MX))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1477 | 2/4/10 | 22:00 | NA | Mexico | MX | México | 2968 | Zacazonapan | 4.40801 | Above road | 19.1927 | -99.8654 | (19.192699999999999, -99.865399999999994) | Landslide | Mudslide | Large | Downpour | NA | NA | 11 | News Daily | http://www.newsdaily.com/stories/tre6151we-us-mexico-mudslide/ | 50.486192 | 25.24310 |
| 2474 | 9/20/10 | Late night | NA | Mexico | MX | México | 9267 | Villa Guerrero | 1.06048 | NA | 18.9642 | -99.6511 | (18.964200000000002, -99.6511) | Landslide | Landslide | Large | Downpour | NA | NA | 8 | NA | http://www.alertnet.org/thenews/newsdesk/N21168920.htm | 12.145979 | 56.55918 |
| 1469 | 2/5/10 | NA | NA | Mexico | MX | México | 505881 | Toluca | 0.66626 | NA | 19.2880 | -99.6469 | (19.288, -99.646900000000002) | Landslide | Landslide | Large | Downpour | NA | NA | 11 | NA | http://www.trt.net.tr/trtinternational/en/newsDetail.aspx?HaberKodu=dc2169ea-80de-437d-a57a-eb11725c40e5 | 7.630865 | 66.44760 |
| 744 | 8/25/08 | NA | NA | Mexico | MX | México | 7182 | San Francisco Chimalpa | 2.59637 | NA | 19.4360 | -99.3650 | (19.436, -99.364999999999995) | Landslide | Mudslide | Medium | Downpour | NA | NA | 1 | NA | http://www.alertnet.org/thenews/newsdesk/N26335664.htm | 29.736964 | 85.13152 |
stem(df_MX$"distance")##
## The decimal point is at the |
##
## 0 | 7
## 1 | 1
## 2 | 6
## 3 |
## 4 | 4stem(df_MX$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 7
## 1 | 1
## 1 |
## 2 |
## 2 | 6
## 3 |
## 3 |
## 4 | 4Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.66626 | 1 | 25 | 25 | 25 | 25 |
| 1.06048 | 1 | 25 | 25 | 50 | 50 |
| 2.59637 | 1 | 25 | 25 | 75 | 75 |
| 4.40801 | 1 | 25 | 25 | 100 | 100 |
| Total | 4 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 5 obs. of 5 variables:
## $ n : num 1 1 1 1 4
## $ % : num 25 25 25 25 100
## $ val% : num 25 25 25 25 100
## $ %cum : num 25 50 75 100 100
## $ val%cum: num 25 50 75 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.66626 | 1 |
| 1.06048 | 1 |
| 2.59637 | 1 |
| 4.40801 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.66626 2.66626 4.66626distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.666,2.67] | 2 | 0.6666667 | 2 |
| (2.67,4.67] | 1 | 0.3333333 | 3 |
str(Freq_table)## 'data.frame': 2 obs. of 4 variables:
## $ distance: Factor w/ 2 levels "(0.666,2.67]",..: 1 2
## $ Freq : int 2 1
## $ Rel_Freq: num 0.667 0.333
## $ Cum_Freq: int 2 3df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.666,2.67] | 2 |
| (2.67,4.67] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_MX)## Warning in min(x): ningún argumento finito para min; retornando Inf## Warning in max(x): ningun argumento finito para max; retornando -Inf## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 4.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 7.440000e+02 NA NA NA NA NA
## max 2.474000e+03 NA NA NA NA NA
## range 1.730000e+03 NA NA NA NA NA
## sum 6.164000e+03 NA NA NA NA NA
## median 1.473000e+03 NA NA NA NA NA
## mean 1.541000e+03 NA NA NA NA NA
## SE.mean 3.553142e+02 NA NA NA NA NA
## CI.mean.0.95 1.130768e+03 NA NA NA NA NA
## var 5.049927e+05 NA NA NA NA NA
## std.dev 7.106284e+02 NA NA NA NA NA
## coef.var 4.611475e-01 NA NA NA NA NA
## state population city distance location_description latitude
## nbr.val NA 4.000000e+00 NA 4.0000000 NA 4.00000000
## nbr.null NA 0.000000e+00 NA 0.0000000 NA 0.00000000
## nbr.na NA 0.000000e+00 NA 0.0000000 NA 0.00000000
## min NA 2.968000e+03 NA 0.6662600 NA 18.96420000
## max NA 5.058810e+05 NA 4.4080100 NA 19.43600000
## range NA 5.029130e+05 NA 3.7417500 NA 0.47180000
## sum NA 5.252980e+05 NA 8.7311200 NA 76.88090000
## median NA 8.224500e+03 NA 1.8284250 NA 19.24035000
## mean NA 1.313245e+05 NA 2.1827800 NA 19.22022500
## SE.mean NA 1.248590e+05 NA 0.8505927 NA 0.09893547
## CI.mean.0.95 NA 3.973572e+05 NA 2.7069656 NA 0.31485682
## var NA 6.235912e+10 NA 2.8940318 NA 0.03915291
## std.dev NA 2.497181e+05 NA 1.7011854 NA 0.19787094
## coef.var NA 1.901535e+00 NA 0.7793664 NA 0.01029493
## longitude geolocation hazard_type landslide_type
## nbr.val 4.000000e+00 NA NA NA
## nbr.null 0.000000e+00 NA NA NA
## nbr.na 0.000000e+00 NA NA NA
## min -9.986540e+01 NA NA NA
## max -9.936500e+01 NA NA NA
## range 5.004000e-01 NA NA NA
## sum -3.985284e+02 NA NA NA
## median -9.964900e+01 NA NA NA
## mean -9.963210e+01 NA NA NA
## SE.mean 1.026123e-01 NA NA NA
## CI.mean.0.95 3.265580e-01 NA NA NA
## var 4.211711e-02 NA NA NA
## std.dev 2.052245e-01 NA NA NA
## coef.var -2.059824e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 0 4.0000000 NA
## nbr.null NA NA NA 0 0.0000000 NA
## nbr.na NA NA NA 4 0.0000000 NA
## min NA NA NA Inf 1.0000000 NA
## max NA NA NA -Inf 11.0000000 NA
## range NA NA NA -Inf 10.0000000 NA
## sum NA NA NA 0 31.0000000 NA
## median NA NA NA NA 9.5000000 NA
## mean NA NA NA NaN 7.7500000 NA
## SE.mean NA NA NA NA 2.3584953 NA
## CI.mean.0.95 NA NA NA NaN 7.5057846 NA
## var NA NA NA NA 22.2500000 NA
## std.dev NA NA NA NA 4.7169906 NA
## coef.var NA NA NA NA 0.6086439 NA
## source_link prop ypos
## nbr.val NA 4.0000000 4.0000000
## nbr.null NA 0.0000000 0.0000000
## nbr.na NA 0.0000000 0.0000000
## min NA 7.6308652 25.2430960
## max NA 50.4861919 85.1315181
## range NA 42.8553267 59.8884221
## sum NA 100.0000000 233.3813989
## median NA 20.9414714 61.5033925
## mean NA 25.0000000 58.3453497
## SE.mean NA 9.7420801 12.5236274
## CI.mean.0.95 NA 31.0036469 39.8557719
## var NA 379.6325015 627.3649774
## std.dev NA 19.4841603 25.0472549
## coef.var NA 0.7793664 0.4292931boxplot(data, horizontal=TRUE, col='green')
Gráfico para Michoacán (Mexico)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_MX <- subset(df, country_name == "Mexico")
knitr::kable(head(df_MX)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 115 | 7/4/07 | NA | NA | Mexico | MX | Veracruz-Llave | 1947 | Laguna Chica (Pueblo Nuevo) | 9.51003 | NA | 18.5369 | -96.8229 | (18.536899999999999, -96.822900000000004) | Landslide | Landslide | Medium | Rain | NA | NA | 7 | nytimes.com | http://www.nytimes.com/2007/07/04/world/americas/04cnd-mexico.html?_r=1&hp&oref=slogin |
| 201 | 8/23/07 | NA | NA | Mexico | MX | Puebla | 1414 | Xochitlaxco (San Baltazar) | 1.68294 | NA | 19.9333 | -97.8500 | (19.933299999999999, -97.85) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Dean | NA | 6 | Inquirer.com | http://newsinfo.inquirer.net/breakingnews/world/view_article.php?article_id=84452 |
| 225 | 9/2/07 | NA | NA | Mexico | MX | Sinaloa | 3191 | El Limón de los Ramos | 10.88351 | NA | 24.9531 | -107.6220 | (24.953099999999999, -107.622) | Landslide | Complex | Medium | Tropical cyclone | Tropical Storm Henrietta | NA | 3 | NA | NA |
| 284 | 9/28/07 | NA | NA | Mexico | MX | Puebla | 3761 | Xaltepuxtla | 7.93258 | NA | 20.2000 | -97.9000 | (20.2, -97.9) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Lorenzo | NA | 1 | PressTV.ir | http://www.presstv.ir/detail.aspx?id=25037§ionid=3510207 |
| 342 | 10/31/07 | NA | NA | Mexico | MX | Tabasco | 4468 | Buenavista | 4.19108 | NA | 17.9493 | -92.5534 | (17.949300000000001, -92.553399999999996) | Landslide | Landslide | Medium | Rain | NA | NA | 18 | CapeTimes | http://www.capetimes.co.za/?fArticleId=4109453 |
| 346 | 11/4/07 | NA | NA | Mexico | MX | Chiapas | 3183 | Ostuacán | 3.74149 | NA | 17.3900 | -93.3060 | (17.39, -93.305999999999997) | Landslide | Mudslide | Very_large | Rain | NA | NA | 5 | Reuters - AlertNet.org | http://news.monstersandcritics.com/americas/news/article_1371436.php/Mudslide_is_latest_disaster_for_hard-hit_Mexico__2nd_Roundup_ |
library(dplyr)
df_MX <- subset(df, state == "Michoacán")
knitr::kable(head(df_MX))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1470 | 2/5/10 | NA | NA | Mexico | MX | Michoacán | 78950 | Heroica Zitácuaro | 4.18059 | NA | 19.4000 | -100.3667 | (19.399999999999999, -100.36669999999999) | Landslide | Mudslide | Medium | Downpour | NA | NA | 2 | NA | http://www.sott.net/articles/show/202533-Mexico-rainstorms-leave-at-least-15-dead |
| 1471 | 2/5/10 | NA | NA | Mexico | MX | Michoacán | 2817 | Jarácuaro | 3.42740 | NA | 19.5670 | -101.7098 | (19.567, -101.7098) | Landslide | Mudslide | Medium | Downpour | NA | NA | 1 | NA | http://www.sott.net/articles/show/202533-Mexico-rainstorms-leave-at-least-15-dead |
| 1472 | 2/5/10 | NA | NA | Mexico | MX | Michoacán | 4943 | Mineral de Angangueo | 1.69508 | NA | 19.6167 | -100.3000 | (19.616700000000002, -100.3) | Landslide | Mudslide | Medium | Downpour | NA | NA | 3 | NA | http://www.aajtv.com/news/World/158635_detail.html |
| 3835 | 7/22/11 | NA | NA | Mexico | MX | Michoacán | 2817 | Jarácuaro | 3.36905 | NA | 19.5805 | -101.7023 | (19.580500000000001, -101.70229999999999) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Dora | NA | 0 | NA | NA |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_MX <- df_MX %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_MX$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_MX, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_MX$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 1.69508 |
| 3.42740 |
| 3.36905 |
| 4.18059 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_MX$distance
names(distance) <- df_MX$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Heroica Zitácuaro 4.18059 4.18059 32.99045 32.99045
## Jarácuaro 3.42740 7.60799 27.04678 60.03723
## Jarácuaro 3.36905 10.97704 26.58632 86.62355
## Mineral de Angangueo 1.69508 12.67212 13.37645 100.00000stem(df_MX$"distance")##
## The decimal point is at the |
##
## 1 | 7
## 2 |
## 2 |
## 3 | 44
## 3 |
## 4 | 2head(df_MX)## # A tibble: 4 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 1472 2/5/10 <NA> <NA> Mexico MX Michoacán 4943
## 2 1471 2/5/10 <NA> <NA> Mexico MX Michoacán 2817
## 3 3835 7/22/11 <NA> <NA> Mexico MX Michoacán 2817
## 4 1470 2/5/10 <NA> <NA> Mexico MX Michoacán 78950
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_MX))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1472 | 2/5/10 | NA | NA | Mexico | MX | Michoacán | 4943 | Mineral de Angangueo | 1.69508 | NA | 19.6167 | -100.3000 | (19.616700000000002, -100.3) | Landslide | Mudslide | Medium | Downpour | NA | NA | 3 | NA | http://www.aajtv.com/news/World/158635_detail.html | 13.37645 | 6.688226 |
| 1471 | 2/5/10 | NA | NA | Mexico | MX | Michoacán | 2817 | Jarácuaro | 3.42740 | NA | 19.5670 | -101.7098 | (19.567, -101.7098) | Landslide | Mudslide | Medium | Downpour | NA | NA | 1 | NA | http://www.sott.net/articles/show/202533-Mexico-rainstorms-leave-at-least-15-dead | 27.04678 | 26.899840 |
| 3835 | 7/22/11 | NA | NA | Mexico | MX | Michoacán | 2817 | Jarácuaro | 3.36905 | NA | 19.5805 | -101.7023 | (19.580500000000001, -101.70229999999999) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Dora | NA | 0 | NA | NA | 26.58632 | 53.716387 |
| 1470 | 2/5/10 | NA | NA | Mexico | MX | Michoacán | 78950 | Heroica Zitácuaro | 4.18059 | NA | 19.4000 | -100.3667 | (19.399999999999999, -100.36669999999999) | Landslide | Mudslide | Medium | Downpour | NA | NA | 2 | NA | http://www.sott.net/articles/show/202533-Mexico-rainstorms-leave-at-least-15-dead | 32.99045 | 83.504773 |
stem(df_MX$"distance")##
## The decimal point is at the |
##
## 1 | 7
## 2 |
## 2 |
## 3 | 44
## 3 |
## 4 | 2stem(df_MX$"distance", scale = 2)##
## The decimal point is at the |
##
## 1 | 7
## 2 |
## 2 |
## 3 | 44
## 3 |
## 4 | 2Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 1.69508 | 1 | 25 | 25 | 25 | 25 |
| 3.36905 | 1 | 25 | 25 | 50 | 50 |
| 3.4274 | 1 | 25 | 25 | 75 | 75 |
| 4.18059 | 1 | 25 | 25 | 100 | 100 |
| Total | 4 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 5 obs. of 5 variables:
## $ n : num 1 1 1 1 4
## $ % : num 25 25 25 25 100
## $ val% : num 25 25 25 25 100
## $ %cum : num 25 50 75 100 100
## $ val%cum: num 25 50 75 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 1.69508 | 1 |
| 3.36905 | 1 |
| 3.4274 | 1 |
| 4.18059 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 1.69508 2.69508 3.69508 4.69508distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (1.7,2.7] | 0 | 0.0000000 | 0 |
| (2.7,3.7] | 2 | 0.6666667 | 2 |
| (3.7,4.7] | 1 | 0.3333333 | 3 |
str(Freq_table)## 'data.frame': 3 obs. of 4 variables:
## $ distance: Factor w/ 3 levels "(1.7,2.7]","(2.7,3.7]",..: 1 2 3
## $ Freq : int 0 2 1
## $ Rel_Freq: num 0 0.667 0.333
## $ Cum_Freq: int 0 2 3df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (1.7,2.7] | 0 |
| (2.7,3.7] | 2 |
| (3.7,4.7] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_MX)## Warning in min(x): ningún argumento finito para min; retornando Inf## Warning in max(x): ningun argumento finito para max; retornando -Inf## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 4.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 1.470000e+03 NA NA NA NA NA
## max 3.835000e+03 NA NA NA NA NA
## range 2.365000e+03 NA NA NA NA NA
## sum 8.248000e+03 NA NA NA NA NA
## median 1.471500e+03 NA NA NA NA NA
## mean 2.062000e+03 NA NA NA NA NA
## SE.mean 5.910001e+02 NA NA NA NA NA
## CI.mean.0.95 1.880826e+03 NA NA NA NA NA
## var 1.397125e+06 NA NA NA NA NA
## std.dev 1.182000e+03 NA NA NA NA NA
## coef.var 5.732300e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 4.000000e+00 NA 4.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 2.817000e+03 NA 1.6950800 NA
## max NA 7.895000e+04 NA 4.1805900 NA
## range NA 7.613300e+04 NA 2.4855100 NA
## sum NA 8.952700e+04 NA 12.6721200 NA
## median NA 3.880000e+03 NA 3.3982250 NA
## mean NA 2.238175e+04 NA 3.1680300 NA
## SE.mean NA 1.886274e+04 NA 0.5246063 NA
## CI.mean.0.95 NA 6.002966e+04 NA 1.6695314 NA
## var NA 1.423212e+09 NA 1.1008471 NA
## std.dev NA 3.772548e+04 NA 1.0492126 NA
## coef.var NA 1.685547e+00 NA 0.3311877 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 4.000000000 4.000000e+00 NA NA NA
## nbr.null 0.000000000 0.000000e+00 NA NA NA
## nbr.na 0.000000000 0.000000e+00 NA NA NA
## min 19.400000000 -1.017098e+02 NA NA NA
## max 19.616700000 -1.003000e+02 NA NA NA
## range 0.216700000 1.409800e+00 NA NA NA
## sum 78.164200000 -4.040788e+02 NA NA NA
## median 19.573750000 -1.010345e+02 NA NA NA
## mean 19.541050000 -1.010197e+02 NA NA NA
## SE.mean 0.048173065 3.965011e-01 NA NA NA
## CI.mean.0.95 0.153308192 1.261844e+00 NA NA NA
## var 0.009282577 6.288526e-01 NA NA NA
## std.dev 0.096346129 7.930023e-01 NA NA NA
## coef.var 0.004930448 -7.849977e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 0 4.0000000 NA
## nbr.null NA NA NA 0 1.0000000 NA
## nbr.na NA NA NA 4 0.0000000 NA
## min NA NA NA Inf 0.0000000 NA
## max NA NA NA -Inf 3.0000000 NA
## range NA NA NA -Inf 3.0000000 NA
## sum NA NA NA 0 6.0000000 NA
## median NA NA NA NA 1.5000000 NA
## mean NA NA NA NaN 1.5000000 NA
## SE.mean NA NA NA NA 0.6454972 NA
## CI.mean.0.95 NA NA NA NaN 2.0542603 NA
## var NA NA NA NA 1.6666667 NA
## std.dev NA NA NA NA 1.2909944 NA
## coef.var NA NA NA NA 0.8606630 NA
## source_link prop ypos
## nbr.val NA 4.0000000 4.0000000
## nbr.null NA 0.0000000 0.0000000
## nbr.na NA 0.0000000 0.0000000
## min NA 13.3764516 6.6882258
## max NA 32.9904546 83.5047727
## range NA 19.6140030 76.8165469
## sum NA 100.0000000 170.8092253
## median NA 26.8165469 40.3081134
## mean NA 25.0000000 42.7023063
## SE.mean NA 4.1398464 16.6655412
## CI.mean.0.95 NA 13.1748389 53.0371901
## var NA 68.5533130 1110.9610564
## std.dev NA 8.2796928 33.3310824
## coef.var NA 0.3311877 0.7805453boxplot(data, horizontal=TRUE, col='green')
Gráfico para Nayarit (Mexico)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_MX <- subset(df, country_name == "Mexico")
knitr::kable(head(df_MX)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 115 | 7/4/07 | NA | NA | Mexico | MX | Veracruz-Llave | 1947 | Laguna Chica (Pueblo Nuevo) | 9.51003 | NA | 18.5369 | -96.8229 | (18.536899999999999, -96.822900000000004) | Landslide | Landslide | Medium | Rain | NA | NA | 7 | nytimes.com | http://www.nytimes.com/2007/07/04/world/americas/04cnd-mexico.html?_r=1&hp&oref=slogin |
| 201 | 8/23/07 | NA | NA | Mexico | MX | Puebla | 1414 | Xochitlaxco (San Baltazar) | 1.68294 | NA | 19.9333 | -97.8500 | (19.933299999999999, -97.85) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Dean | NA | 6 | Inquirer.com | http://newsinfo.inquirer.net/breakingnews/world/view_article.php?article_id=84452 |
| 225 | 9/2/07 | NA | NA | Mexico | MX | Sinaloa | 3191 | El Limón de los Ramos | 10.88351 | NA | 24.9531 | -107.6220 | (24.953099999999999, -107.622) | Landslide | Complex | Medium | Tropical cyclone | Tropical Storm Henrietta | NA | 3 | NA | NA |
| 284 | 9/28/07 | NA | NA | Mexico | MX | Puebla | 3761 | Xaltepuxtla | 7.93258 | NA | 20.2000 | -97.9000 | (20.2, -97.9) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Lorenzo | NA | 1 | PressTV.ir | http://www.presstv.ir/detail.aspx?id=25037§ionid=3510207 |
| 342 | 10/31/07 | NA | NA | Mexico | MX | Tabasco | 4468 | Buenavista | 4.19108 | NA | 17.9493 | -92.5534 | (17.949300000000001, -92.553399999999996) | Landslide | Landslide | Medium | Rain | NA | NA | 18 | CapeTimes | http://www.capetimes.co.za/?fArticleId=4109453 |
| 346 | 11/4/07 | NA | NA | Mexico | MX | Chiapas | 3183 | Ostuacán | 3.74149 | NA | 17.3900 | -93.3060 | (17.39, -93.305999999999997) | Landslide | Mudslide | Very_large | Rain | NA | NA | 5 | Reuters - AlertNet.org | http://news.monstersandcritics.com/americas/news/article_1371436.php/Mudslide_is_latest_disaster_for_hard-hit_Mexico__2nd_Roundup_ |
library(dplyr)
df_MX <- subset(df, state == "Nayarit")
knitr::kable(head(df_MX))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 3639 | 6/22/11 | NA | NA | Mexico | MX | Nayarit | 4463 | La Jarretadera | 21.80060 | NA | 21.9814 | -104.8381 | (21.981400000000001, -104.8381) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Beatriz | NA | 0 | NA | http://channel6newsonline.com/2011/06/missing-teen-found-dead-after-beatriz-slams-mexicos-pacific-coast/ |
| 3836 | 7/22/11 | NA | NA | Mexico | MX | Nayarit | 6361 | Puga | 19.41353 | NA | 21.7595 | -104.8334 | (21.759499999999999, -104.8334) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Dora | NA | 0 | NA | NA |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_MX <- df_MX %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_MX$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_MX, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_MX$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 19.41353 |
| 21.80060 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_MX$distance
names(distance) <- df_MX$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## La Jarretadera 21.80060 21.80060 52.89594 52.89594
## Puga 19.41353 41.21413 47.10406 100.00000stem(df_MX$"distance")##
## The decimal point is at the |
##
## 19 | 4
## 19 |
## 20 |
## 20 |
## 21 |
## 21 | 8head(df_MX)## # A tibble: 2 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 3836 7/22/11 <NA> <NA> Mexico MX Nayarit 6361
## 2 3639 6/22/11 <NA> <NA> Mexico MX Nayarit 4463
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_MX))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 3836 | 7/22/11 | NA | NA | Mexico | MX | Nayarit | 6361 | Puga | 19.41353 | NA | 21.7595 | -104.8334 | (21.759499999999999, -104.8334) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Dora | NA | 0 | NA | NA | 47.10406 | 23.55203 |
| 3639 | 6/22/11 | NA | NA | Mexico | MX | Nayarit | 4463 | La Jarretadera | 21.80060 | NA | 21.9814 | -104.8381 | (21.981400000000001, -104.8381) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Beatriz | NA | 0 | NA | http://channel6newsonline.com/2011/06/missing-teen-found-dead-after-beatriz-slams-mexicos-pacific-coast/ | 52.89594 | 73.55203 |
stem(df_MX$"distance")##
## The decimal point is at the |
##
## 19 | 4
## 19 |
## 20 |
## 20 |
## 21 |
## 21 | 8stem(df_MX$"distance", scale = 2)##
## The decimal point is at the |
##
## 19 | 4
## 19 |
## 20 |
## 20 |
## 21 |
## 21 | 8Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 19.41353 | 1 | 50 | 50 | 50 | 50 |
| 21.8006 | 1 | 50 | 50 | 100 | 100 |
| Total | 2 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 3 obs. of 5 variables:
## $ n : num 1 1 2
## $ % : num 50 50 100
## $ val% : num 50 50 100
## $ %cum : num 50 100 100
## $ val%cum: num 50 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 19.41353 | 1 |
| 21.8006 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 19.41353 21.41353 23.41353distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (19.4,21.4] | 0 | 0 | 0 |
| (21.4,23.4] | 1 | 1 | 1 |
str(Freq_table)## 'data.frame': 2 obs. of 4 variables:
## $ distance: Factor w/ 2 levels "(19.4,21.4]",..: 1 2
## $ Freq : int 0 1
## $ Rel_Freq: num 0 1
## $ Cum_Freq: int 0 1df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (19.4,21.4] | 0 |
| (21.4,23.4] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_MX)## Warning in min(x): ningún argumento finito para min; retornando Inf## Warning in max(x): ningun argumento finito para max; retornando -Inf## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 2.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 3.639000e+03 NA NA NA NA NA
## max 3.836000e+03 NA NA NA NA NA
## range 1.970000e+02 NA NA NA NA NA
## sum 7.475000e+03 NA NA NA NA NA
## median 3.737500e+03 NA NA NA NA NA
## mean 3.737500e+03 NA NA NA NA NA
## SE.mean 9.850000e+01 NA NA NA NA NA
## CI.mean.0.95 1.251561e+03 NA NA NA NA NA
## var 1.940450e+04 NA NA NA NA NA
## std.dev 1.393000e+02 NA NA NA NA NA
## coef.var 3.727091e-02 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 2.000000e+00 NA 2.00000000 NA
## nbr.null NA 0.000000e+00 NA 0.00000000 NA
## nbr.na NA 0.000000e+00 NA 0.00000000 NA
## min NA 4.463000e+03 NA 19.41353000 NA
## max NA 6.361000e+03 NA 21.80060000 NA
## range NA 1.898000e+03 NA 2.38707000 NA
## sum NA 1.082400e+04 NA 41.21413000 NA
## median NA 5.412000e+03 NA 20.60706500 NA
## mean NA 5.412000e+03 NA 20.60706500 NA
## SE.mean NA 9.490000e+02 NA 1.19353500 NA
## CI.mean.0.95 NA 1.205819e+04 NA 15.16530007 NA
## var NA 1.801202e+06 NA 2.84905159 NA
## std.dev NA 1.342089e+03 NA 1.68791338 NA
## coef.var NA 2.479839e-01 NA 0.08190945 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 2.000000000 2.000000e+00 NA NA NA
## nbr.null 0.000000000 0.000000e+00 NA NA NA
## nbr.na 0.000000000 0.000000e+00 NA NA NA
## min 21.759500000 -1.048381e+02 NA NA NA
## max 21.981400000 -1.048334e+02 NA NA NA
## range 0.221900000 4.700000e-03 NA NA NA
## sum 43.740900000 -2.096715e+02 NA NA NA
## median 21.870450000 -1.048357e+02 NA NA NA
## mean 21.870450000 -1.048357e+02 NA NA NA
## SE.mean 0.110950000 2.350000e-03 NA NA NA
## CI.mean.0.95 1.409753415 2.985958e-02 NA NA NA
## var 0.024619805 1.104500e-05 NA NA NA
## std.dev 0.156906995 3.323402e-03 NA NA NA
## coef.var 0.007174383 -3.170104e-05 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 0 2 NA
## nbr.null NA NA NA 0 2 NA
## nbr.na NA NA NA 2 0 NA
## min NA NA NA Inf 0 NA
## max NA NA NA -Inf 0 NA
## range NA NA NA -Inf 0 NA
## sum NA NA NA 0 0 NA
## median NA NA NA NA 0 NA
## mean NA NA NA NaN 0 NA
## SE.mean NA NA NA NA 0 NA
## CI.mean.0.95 NA NA NA NaN 0 NA
## var NA NA NA NA 0 NA
## std.dev NA NA NA NA 0 NA
## coef.var NA NA NA NA NaN NA
## source_link prop ypos
## nbr.val NA 2.00000000 2.0000000
## nbr.null NA 0.00000000 0.0000000
## nbr.na NA 0.00000000 0.0000000
## min NA 47.10406358 23.5520318
## max NA 52.89593642 73.5520318
## range NA 5.79187284 50.0000000
## sum NA 100.00000000 97.1040636
## median NA 50.00000000 48.5520318
## mean NA 50.00000000 48.5520318
## SE.mean NA 2.89593642 25.0000000
## CI.mean.0.95 NA 36.79636103 317.6551184
## var NA 16.77289547 1250.0000000
## std.dev NA 4.09547256 35.3553391
## coef.var NA 0.08190945 0.7281948boxplot(data, horizontal=TRUE, col='green')
Gráfico para Oaxaca (Mexico)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_MX <- subset(df, country_name == "Mexico")
knitr::kable(head(df_MX)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 115 | 7/4/07 | NA | NA | Mexico | MX | Veracruz-Llave | 1947 | Laguna Chica (Pueblo Nuevo) | 9.51003 | NA | 18.5369 | -96.8229 | (18.536899999999999, -96.822900000000004) | Landslide | Landslide | Medium | Rain | NA | NA | 7 | nytimes.com | http://www.nytimes.com/2007/07/04/world/americas/04cnd-mexico.html?_r=1&hp&oref=slogin |
| 201 | 8/23/07 | NA | NA | Mexico | MX | Puebla | 1414 | Xochitlaxco (San Baltazar) | 1.68294 | NA | 19.9333 | -97.8500 | (19.933299999999999, -97.85) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Dean | NA | 6 | Inquirer.com | http://newsinfo.inquirer.net/breakingnews/world/view_article.php?article_id=84452 |
| 225 | 9/2/07 | NA | NA | Mexico | MX | Sinaloa | 3191 | El Limón de los Ramos | 10.88351 | NA | 24.9531 | -107.6220 | (24.953099999999999, -107.622) | Landslide | Complex | Medium | Tropical cyclone | Tropical Storm Henrietta | NA | 3 | NA | NA |
| 284 | 9/28/07 | NA | NA | Mexico | MX | Puebla | 3761 | Xaltepuxtla | 7.93258 | NA | 20.2000 | -97.9000 | (20.2, -97.9) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Lorenzo | NA | 1 | PressTV.ir | http://www.presstv.ir/detail.aspx?id=25037§ionid=3510207 |
| 342 | 10/31/07 | NA | NA | Mexico | MX | Tabasco | 4468 | Buenavista | 4.19108 | NA | 17.9493 | -92.5534 | (17.949300000000001, -92.553399999999996) | Landslide | Landslide | Medium | Rain | NA | NA | 18 | CapeTimes | http://www.capetimes.co.za/?fArticleId=4109453 |
| 346 | 11/4/07 | NA | NA | Mexico | MX | Chiapas | 3183 | Ostuacán | 3.74149 | NA | 17.3900 | -93.3060 | (17.39, -93.305999999999997) | Landslide | Mudslide | Very_large | Rain | NA | NA | 5 | Reuters - AlertNet.org | http://news.monstersandcritics.com/americas/news/article_1371436.php/Mudslide_is_latest_disaster_for_hard-hit_Mexico__2nd_Roundup_ |
library(dplyr)
df_MX <- subset(df, state == "Oaxaca")
knitr::kable(head(df_MX))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2321 | 8/24/10 | Morning | NA | Mexico | MX | Oaxaca | 1099 | Santiago Choapam | 16.16369 | NA | 17.2568 | -96.0289 | (17.256799999999998, -96.028899999999993) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Frank | NA | 2 | NA | NA |
| 2322 | 8/24/10 | Morning | NA | Mexico | MX | Oaxaca | 1701 | Santa María la Asunción | 0.63550 | NA | 18.1060 | -96.8133 | (18.106000000000002, -96.813299999999998) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Frank | NA | 2 | NA | NA |
| 2514 | 9/28/10 | 4:00:00 | NA | Mexico | MX | Oaxaca | 1813 | Santo Domingo Tepuxtepec | 15.74984 | NA | 17.0977 | -96.0625 | (17.0977, -96.0625) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Karl and Tropical Storm Matthew | NA | 11 | NA | http://technews.tmcnet.com/topics/associated-press/articles/106209-death-toll-southern-mexico-mudslides-up-32.htm |
| 2524 | 9/30/10 | Morning | NA | Mexico | MX | Oaxaca | 1096 | Tanetze de Zaragoza | 24.67589 | NA | 17.1833 | -96.1833 | (17.183299999999999, -96.183300000000003) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Karl and Tropical Storm Matthew | NA | 2 | NA | http://technews.tmcnet.com/topics/associated-press/articles/106209-death-toll-southern-mexico-mudslides-up-32.htm |
| 3795 | 7/17/11 | NA | NA | Mexico | MX | Oaxaca | 73648 | Salina Cruz | 0.78340 | NA | 16.1863 | -95.1924 | (16.186299999999999, -95.192400000000006) | Landslide | Mudslide | Medium | Downpour | NA | NA | 0 | NA | http://latino.foxnews.com/latino/news/2011/07/18/3-die-180000-affected-by-rains-in-southern-mexico/ |
| 3796 | 7/17/11 | NA | NA | Mexico | MX | Oaxaca | 3294 | San José Chiltepec | 0.28905 | NA | 17.9484 | -96.1674 | (17.948399999999999, -96.167400000000001) | Landslide | Mudslide | Medium | Downpour | NA | NA | 0 | NA | http://www.thenews.com.pk/NewsDetail.aspx?ID=18895&title=Intense-rains-in-Mexico-affect-thousands |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_MX <- df_MX %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_MX$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_MX, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_MX$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 24.67589 |
| 15.74984 |
| 16.16369 |
| 0.63550 |
| 0.28905 |
| 11.83490 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_MX$distance
names(distance) <- df_MX$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Tanetze de Zaragoza 24.6758900 24.6758900 29.6060776 29.6060776
## Santiago Choapam 16.1636900 40.8395800 19.3931591 48.9992367
## Santo Domingo Tepuxtepec 15.7498400 56.5894200 18.8966228 67.8958595
## San Andrés Huayapam 11.8349000 68.4243200 14.1994865 82.0953460
## Paso Real de Sarabia 9.5682900 77.9926100 11.4800129 93.5753589
## Oaxaca 3.6468200 81.6394300 4.3754465 97.9508054
## Salina Cruz 0.7834000 82.4228300 0.9399216 98.8907270
## Santa María la Asunción 0.6355000 83.0583300 0.7624715 99.6531985
## San José Chiltepec 0.2890500 83.3473800 0.3468015 100.0000000stem(df_MX$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 0114
## 0 |
## 1 | 02
## 1 | 66
## 2 |
## 2 | 5head(df_MX)## # A tibble: 6 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 2524 9/30/10 Morning <NA> Mexico MX Oaxaca 1096
## 2 2514 9/28/10 4:00:00 <NA> Mexico MX Oaxaca 1813
## 3 2321 8/24/10 Morning <NA> Mexico MX Oaxaca 1099
## 4 2322 8/24/10 Morning <NA> Mexico MX Oaxaca 1701
## 5 3796 7/17/11 <NA> <NA> Mexico MX Oaxaca 3294
## 6 5526 9/14/13 <NA> <NA> Mexico MX Oaxaca 3630
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_MX))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2524 | 9/30/10 | Morning | NA | Mexico | MX | Oaxaca | 1096 | Tanetze de Zaragoza | 24.67589 | NA | 17.1833 | -96.1833 | (17.183299999999999, -96.183300000000003) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Karl and Tropical Storm Matthew | NA | 2 | NA | http://technews.tmcnet.com/topics/associated-press/articles/106209-death-toll-southern-mexico-mudslides-up-32.htm | 29.6060776 | 14.80304 |
| 2514 | 9/28/10 | 4:00:00 | NA | Mexico | MX | Oaxaca | 1813 | Santo Domingo Tepuxtepec | 15.74984 | NA | 17.0977 | -96.0625 | (17.0977, -96.0625) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Karl and Tropical Storm Matthew | NA | 11 | NA | http://technews.tmcnet.com/topics/associated-press/articles/106209-death-toll-southern-mexico-mudslides-up-32.htm | 18.8966228 | 39.05439 |
| 2321 | 8/24/10 | Morning | NA | Mexico | MX | Oaxaca | 1099 | Santiago Choapam | 16.16369 | NA | 17.2568 | -96.0289 | (17.256799999999998, -96.028899999999993) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Frank | NA | 2 | NA | NA | 19.3931591 | 58.19928 |
| 2322 | 8/24/10 | Morning | NA | Mexico | MX | Oaxaca | 1701 | Santa María la Asunción | 0.63550 | NA | 18.1060 | -96.8133 | (18.106000000000002, -96.813299999999998) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Frank | NA | 2 | NA | NA | 0.7624715 | 68.27710 |
| 3796 | 7/17/11 | NA | NA | Mexico | MX | Oaxaca | 3294 | San José Chiltepec | 0.28905 | NA | 17.9484 | -96.1674 | (17.948399999999999, -96.167400000000001) | Landslide | Mudslide | Medium | Downpour | NA | NA | 0 | NA | http://www.thenews.com.pk/NewsDetail.aspx?ID=18895&title=Intense-rains-in-Mexico-affect-thousands | 0.3468015 | 68.83173 |
| 5526 | 9/14/13 | NA | NA | Mexico | MX | Oaxaca | 3630 | San Andrés Huayapam | 11.83490 | NA | 17.1933 | -96.6045 | (17.193300000000001, -96.604500000000002) | Landslide | Landslide | Very_large | Tropical cyclone | Ingrid | NA | 1 | www.recordonline.com | http://www.recordonline.com/apps/pbcs.dll/article?AID=/20130915/NEWS/130919814/-1/SITEMAP | 14.1994865 | 76.10488 |
stem(df_MX$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 0114
## 0 |
## 1 | 02
## 1 | 66
## 2 |
## 2 | 5stem(df_MX$"distance", scale = 2)##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 0114
## 0 |
## 1 | 02
## 1 | 66
## 2 |
## 2 | 5Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.28905 | 1 | 11.1 | 11.1 | 11.1 | 11.1 |
| 0.6355 | 1 | 11.1 | 11.1 | 22.2 | 22.2 |
| 0.7834 | 1 | 11.1 | 11.1 | 33.3 | 33.3 |
| 3.64682 | 1 | 11.1 | 11.1 | 44.4 | 44.4 |
| 9.56829 | 1 | 11.1 | 11.1 | 55.6 | 55.6 |
| 11.8349 | 1 | 11.1 | 11.1 | 66.7 | 66.7 |
| 15.74984 | 1 | 11.1 | 11.1 | 77.8 | 77.8 |
| 16.16369 | 1 | 11.1 | 11.1 | 88.9 | 88.9 |
| 24.67589 | 1 | 11.1 | 11.1 | 100.0 | 100.0 |
| Total | 9 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 10 obs. of 5 variables:
## $ n : num 1 1 1 1 1 1 1 1 1 9
## $ % : num 11.1 11.1 11.1 11.1 11.1 11.1 11.1 11.1 11.1 100
## $ val% : num 11.1 11.1 11.1 11.1 11.1 11.1 11.1 11.1 11.1 100
## $ %cum : num 11.1 22.2 33.3 44.4 55.6 66.7 77.8 88.9 100 100
## $ val%cum: num 11.1 22.2 33.3 44.4 55.6 66.7 77.8 88.9 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.28905 | 1 |
| 0.6355 | 1 |
| 0.7834 | 1 |
| 3.64682 | 1 |
| 9.56829 | 1 |
| 11.8349 | 1 |
| 15.74984 | 1 |
| 16.16369 | 1 |
| 24.67589 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.28905 5.28905 10.28905 15.28905 20.28905 25.28905distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.289,5.29] | 3 | 0.375 | 3 |
| (5.29,10.3] | 1 | 0.125 | 4 |
| (10.3,15.3] | 1 | 0.125 | 5 |
| (15.3,20.3] | 2 | 0.250 | 7 |
| (20.3,25.3] | 1 | 0.125 | 8 |
str(Freq_table)## 'data.frame': 5 obs. of 4 variables:
## $ distance: Factor w/ 5 levels "(0.289,5.29]",..: 1 2 3 4 5
## $ Freq : int 3 1 1 2 1
## $ Rel_Freq: num 0.375 0.125 0.125 0.25 0.125
## $ Cum_Freq: int 3 4 5 7 8df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.289,5.29] | 3 |
| (5.29,10.3] | 1 |
| (10.3,15.3] | 1 |
| (15.3,20.3] | 2 |
| (20.3,25.3] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_MX)## Warning in min(x): ningún argumento finito para min; retornando Inf## Warning in max(x): ningun argumento finito para max; retornando -Inf## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 9.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 2.321000e+03 NA NA NA NA NA
## max 5.526000e+03 NA NA NA NA NA
## range 3.205000e+03 NA NA NA NA NA
## sum 3.100700e+04 NA NA NA NA NA
## median 3.795000e+03 NA NA NA NA NA
## mean 3.445222e+03 NA NA NA NA NA
## SE.mean 3.703370e+02 NA NA NA NA NA
## CI.mean.0.95 8.539986e+02 NA NA NA NA NA
## var 1.234345e+06 NA NA NA NA NA
## std.dev 1.111011e+03 NA NA NA NA NA
## coef.var 3.224787e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 9.000000e+00 NA 9.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 1.019000e+03 NA 0.2890500 NA
## max NA 2.625660e+05 NA 24.6758900 NA
## range NA 2.615470e+05 NA 24.3868400 NA
## sum NA 3.498660e+05 NA 83.3473800 NA
## median NA 1.813000e+03 NA 9.5682900 NA
## mean NA 3.887400e+04 NA 9.2608200 NA
## SE.mean NA 2.905882e+04 NA 2.8683480 NA
## CI.mean.0.95 NA 6.700977e+04 NA 6.6144223 NA
## var NA 7.599737e+09 NA 74.0467814 NA
## std.dev NA 8.717647e+04 NA 8.6050440 NA
## coef.var NA 2.242539e+00 NA 0.9291881 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 9.00000000 9.000000e+00 NA NA NA
## nbr.null 0.00000000 0.000000e+00 NA NA NA
## nbr.na 0.00000000 0.000000e+00 NA NA NA
## min 16.18630000 -9.681330e+01 NA NA NA
## max 18.10600000 -9.500000e+01 NA NA NA
## range 1.91970000 1.813300e+00 NA NA NA
## sum 155.05720000 -8.648023e+02 NA NA NA
## median 17.18330000 -9.616740e+01 NA NA NA
## mean 17.22857778 -9.608914e+01 NA NA NA
## SE.mean 0.18515476 2.120154e-01 NA NA NA
## CI.mean.0.95 0.42696764 4.889083e-01 NA NA NA
## var 0.30854056 4.045547e-01 NA NA NA
## std.dev 0.55546428 6.360461e-01 NA NA NA
## coef.var 0.03224087 -6.619334e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 0 9.000000 NA
## nbr.null NA NA NA 0 2.000000 NA
## nbr.na NA NA NA 9 0.000000 NA
## min NA NA NA Inf 0.000000 NA
## max NA NA NA -Inf 11.000000 NA
## range NA NA NA -Inf 11.000000 NA
## sum NA NA NA 0 23.000000 NA
## median NA NA NA NA 2.000000 NA
## mean NA NA NA NaN 2.555556 NA
## SE.mean NA NA NA NA 1.106937 NA
## CI.mean.0.95 NA NA NA NaN 2.552600 NA
## var NA NA NA NA 11.027778 NA
## std.dev NA NA NA NA 3.320810 NA
## coef.var NA NA NA NA 1.299447 NA
## source_link prop ypos
## nbr.val NA 9.0000000 9.0000000
## nbr.null NA 0.0000000 0.0000000
## nbr.na NA 0.0000000 0.0000000
## min NA 0.3468015 14.8030388
## max NA 29.6060776 97.8122768
## range NA 29.2592761 83.0092380
## sum NA 100.0000000 596.6418141
## median NA 11.4800129 68.8317317
## mean NA 11.1111111 66.2935349
## SE.mean NA 3.4414375 8.6742485
## CI.mean.0.95 NA 7.9359691 20.0028529
## var NA 106.5914281 677.1832815
## std.dev NA 10.3243125 26.0227455
## coef.var NA 0.9291881 0.3925382boxplot(data, horizontal=TRUE, col='green')
Gráfico para Puebla (Mexico)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_MX <- subset(df, country_name == "Mexico")
knitr::kable(head(df_MX)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 115 | 7/4/07 | NA | NA | Mexico | MX | Veracruz-Llave | 1947 | Laguna Chica (Pueblo Nuevo) | 9.51003 | NA | 18.5369 | -96.8229 | (18.536899999999999, -96.822900000000004) | Landslide | Landslide | Medium | Rain | NA | NA | 7 | nytimes.com | http://www.nytimes.com/2007/07/04/world/americas/04cnd-mexico.html?_r=1&hp&oref=slogin |
| 201 | 8/23/07 | NA | NA | Mexico | MX | Puebla | 1414 | Xochitlaxco (San Baltazar) | 1.68294 | NA | 19.9333 | -97.8500 | (19.933299999999999, -97.85) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Dean | NA | 6 | Inquirer.com | http://newsinfo.inquirer.net/breakingnews/world/view_article.php?article_id=84452 |
| 225 | 9/2/07 | NA | NA | Mexico | MX | Sinaloa | 3191 | El Limón de los Ramos | 10.88351 | NA | 24.9531 | -107.6220 | (24.953099999999999, -107.622) | Landslide | Complex | Medium | Tropical cyclone | Tropical Storm Henrietta | NA | 3 | NA | NA |
| 284 | 9/28/07 | NA | NA | Mexico | MX | Puebla | 3761 | Xaltepuxtla | 7.93258 | NA | 20.2000 | -97.9000 | (20.2, -97.9) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Lorenzo | NA | 1 | PressTV.ir | http://www.presstv.ir/detail.aspx?id=25037§ionid=3510207 |
| 342 | 10/31/07 | NA | NA | Mexico | MX | Tabasco | 4468 | Buenavista | 4.19108 | NA | 17.9493 | -92.5534 | (17.949300000000001, -92.553399999999996) | Landslide | Landslide | Medium | Rain | NA | NA | 18 | CapeTimes | http://www.capetimes.co.za/?fArticleId=4109453 |
| 346 | 11/4/07 | NA | NA | Mexico | MX | Chiapas | 3183 | Ostuacán | 3.74149 | NA | 17.3900 | -93.3060 | (17.39, -93.305999999999997) | Landslide | Mudslide | Very_large | Rain | NA | NA | 5 | Reuters - AlertNet.org | http://news.monstersandcritics.com/americas/news/article_1371436.php/Mudslide_is_latest_disaster_for_hard-hit_Mexico__2nd_Roundup_ |
library(dplyr)
df_MX <- subset(df, state == "Puebla")
knitr::kable(head(df_MX))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 201 | 8/23/07 | NA | NA | Mexico | MX | Puebla | 1414 | Xochitlaxco (San Baltazar) | 1.68294 | NA | 19.9333 | -97.8500 | (19.933299999999999, -97.85) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Dean | NA | 6 | Inquirer.com | http://newsinfo.inquirer.net/breakingnews/world/view_article.php?article_id=84452 |
| 284 | 9/28/07 | NA | NA | Mexico | MX | Puebla | 3761 | Xaltepuxtla | 7.93258 | NA | 20.2000 | -97.9000 | (20.2, -97.9) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Lorenzo | NA | 1 | PressTV.ir | http://www.presstv.ir/detail.aspx?id=25037§ionid=3510207 |
| 5528 | 9/15/13 | NA | NA | Mexico | MX | Puebla | 9720 | Tlatlauquitepec | 0.30326 | NA | 19.8490 | -97.4997 | (19.849, -97.499700000000004) | Landslide | Landslide | Very_large | Tropical cyclone | Ingrid | 1 | 3 | www.recordonline.com | http://www.recordonline.com/apps/pbcs.dll/article?AID=/20130915/NEWS/130919814/-1/SITEMAP |
| 5539 | 9/16/13 | NA | NA | Mexico | MX | Puebla | 1123 | Atzala | 5.24855 | NA | 18.5938 | -98.5539 | (18.593800000000002, -98.553899999999999) | Landslide | Landslide | Medium | Tropical cyclone | Manyi | NA | 0 | america.aljazeera.com | http://america.aljazeera.com/articles/2013/11/19/after-landslide-poorestofthepoorleftoutinthecoldinmexico.html |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_MX <- df_MX %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_MX$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_MX, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_MX$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 1.68294 |
| 7.93258 |
| 0.30326 |
| 5.24855 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_MX$distance
names(distance) <- df_MX$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Xaltepuxtla 7.932580 7.932580 52.300438 52.300438
## Atzala 5.248550 13.181130 34.604311 86.904749
## Xochitlaxco (San Baltazar) 1.682940 14.864070 11.095822 98.000571
## Tlatlauquitepec 0.303260 15.167330 1.999429 100.000000stem(df_MX$"distance")##
## The decimal point is at the |
##
## 0 | 37
## 2 |
## 4 | 2
## 6 | 9head(df_MX)## # A tibble: 4 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 201 8/23/07 <NA> <NA> Mexico MX Puebla 1414
## 2 284 9/28/07 <NA> <NA> Mexico MX Puebla 3761
## 3 5528 9/15/13 <NA> <NA> Mexico MX Puebla 9720
## 4 5539 9/16/13 <NA> <NA> Mexico MX Puebla 1123
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_MX))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 201 | 8/23/07 | NA | NA | Mexico | MX | Puebla | 1414 | Xochitlaxco (San Baltazar) | 1.68294 | NA | 19.9333 | -97.8500 | (19.933299999999999, -97.85) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Dean | NA | 6 | Inquirer.com | http://newsinfo.inquirer.net/breakingnews/world/view_article.php?article_id=84452 | 11.095822 | 5.547911 |
| 284 | 9/28/07 | NA | NA | Mexico | MX | Puebla | 3761 | Xaltepuxtla | 7.93258 | NA | 20.2000 | -97.9000 | (20.2, -97.9) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Lorenzo | NA | 1 | PressTV.ir | http://www.presstv.ir/detail.aspx?id=25037§ionid=3510207 | 52.300438 | 37.246041 |
| 5528 | 9/15/13 | NA | NA | Mexico | MX | Puebla | 9720 | Tlatlauquitepec | 0.30326 | NA | 19.8490 | -97.4997 | (19.849, -97.499700000000004) | Landslide | Landslide | Very_large | Tropical cyclone | Ingrid | 1 | 3 | www.recordonline.com | http://www.recordonline.com/apps/pbcs.dll/article?AID=/20130915/NEWS/130919814/-1/SITEMAP | 1.999429 | 64.395975 |
| 5539 | 9/16/13 | NA | NA | Mexico | MX | Puebla | 1123 | Atzala | 5.24855 | NA | 18.5938 | -98.5539 | (18.593800000000002, -98.553899999999999) | Landslide | Landslide | Medium | Tropical cyclone | Manyi | NA | 0 | america.aljazeera.com | http://america.aljazeera.com/articles/2013/11/19/after-landslide-poorestofthepoorleftoutinthecoldinmexico.html | 34.604311 | 82.697845 |
stem(df_MX$"distance")##
## The decimal point is at the |
##
## 0 | 37
## 2 |
## 4 | 2
## 6 | 9stem(df_MX$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 3
## 1 | 7
## 2 |
## 3 |
## 4 |
## 5 | 2
## 6 |
## 7 | 9Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.30326 | 1 | 25 | 25 | 25 | 25 |
| 1.68294 | 1 | 25 | 25 | 50 | 50 |
| 5.24855 | 1 | 25 | 25 | 75 | 75 |
| 7.93258 | 1 | 25 | 25 | 100 | 100 |
| Total | 4 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 5 obs. of 5 variables:
## $ n : num 1 1 1 1 4
## $ % : num 25 25 25 25 100
## $ val% : num 25 25 25 25 100
## $ %cum : num 25 50 75 100 100
## $ val%cum: num 25 50 75 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.30326 | 1 |
| 1.68294 | 1 |
| 5.24855 | 1 |
| 7.93258 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.30326 3.30326 6.30326 9.30326distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.303,3.3] | 1 | 0.3333333 | 1 |
| (3.3,6.3] | 1 | 0.3333333 | 2 |
| (6.3,9.3] | 1 | 0.3333333 | 3 |
str(Freq_table)## 'data.frame': 3 obs. of 4 variables:
## $ distance: Factor w/ 3 levels "(0.303,3.3]",..: 1 2 3
## $ Freq : int 1 1 1
## $ Rel_Freq: num 0.333 0.333 0.333
## $ Cum_Freq: int 1 2 3df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.303,3.3] | 1 |
| (3.3,6.3] | 1 |
| (6.3,9.3] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_MX)## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 4.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 2.010000e+02 NA NA NA NA NA
## max 5.539000e+03 NA NA NA NA NA
## range 5.338000e+03 NA NA NA NA NA
## sum 1.155200e+04 NA NA NA NA NA
## median 2.906000e+03 NA NA NA NA NA
## mean 2.888000e+03 NA NA NA NA NA
## SE.mean 1.527476e+03 NA NA NA NA NA
## CI.mean.0.95 4.861110e+03 NA NA NA NA NA
## var 9.332729e+06 NA NA NA NA NA
## std.dev 3.054951e+03 NA NA NA NA NA
## coef.var 1.057809e+00 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 4.000000e+00 NA 4.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 1.123000e+03 NA 0.3032600 NA
## max NA 9.720000e+03 NA 7.9325800 NA
## range NA 8.597000e+03 NA 7.6293200 NA
## sum NA 1.601800e+04 NA 15.1673300 NA
## median NA 2.587500e+03 NA 3.4657450 NA
## mean NA 4.004500e+03 NA 3.7918325 NA
## SE.mean NA 1.994575e+03 NA 1.7292913 NA
## CI.mean.0.95 NA 6.347629e+03 NA 5.5033768 NA
## var NA 1.591332e+07 NA 11.9617938 NA
## std.dev NA 3.989150e+03 NA 3.4585826 NA
## coef.var NA 9.961669e-01 NA 0.9121138 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 4.00000000 4.000000e+00 NA NA NA
## nbr.null 0.00000000 0.000000e+00 NA NA NA
## nbr.na 0.00000000 0.000000e+00 NA NA NA
## min 18.59380000 -9.855390e+01 NA NA NA
## max 20.20000000 -9.749970e+01 NA NA NA
## range 1.60620000 1.054200e+00 NA NA NA
## sum 78.57610000 -3.918036e+02 NA NA NA
## median 19.89115000 -9.787500e+01 NA NA NA
## mean 19.64402500 -9.795090e+01 NA NA NA
## SE.mean 0.35797760 2.198412e-01 NA NA NA
## CI.mean.0.95 1.13924448 6.996329e-01 NA NA NA
## var 0.51259184 1.933207e-01 NA NA NA
## std.dev 0.71595520 4.396825e-01 NA NA NA
## coef.var 0.03644646 -4.488805e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 1 4.000000 NA
## nbr.null NA NA NA 0 1.000000 NA
## nbr.na NA NA NA 3 0.000000 NA
## min NA NA NA 1 0.000000 NA
## max NA NA NA 1 6.000000 NA
## range NA NA NA 0 6.000000 NA
## sum NA NA NA 1 10.000000 NA
## median NA NA NA 1 2.000000 NA
## mean NA NA NA 1 2.500000 NA
## SE.mean NA NA NA NA 1.322876 NA
## CI.mean.0.95 NA NA NA NaN 4.209981 NA
## var NA NA NA NA 7.000000 NA
## std.dev NA NA NA NA 2.645751 NA
## coef.var NA NA NA NA 1.058301 NA
## source_link prop ypos
## nbr.val NA 4.0000000 4.0000000
## nbr.null NA 0.0000000 0.0000000
## nbr.na NA 0.0000000 0.0000000
## min NA 1.9994290 5.5479112
## max NA 52.3004378 82.6978446
## range NA 50.3010088 77.1499334
## sum NA 100.0000000 189.8877719
## median NA 22.8500666 50.8210080
## mean NA 25.0000000 47.4719430
## SE.mean NA 11.4014221 16.8064484
## CI.mean.0.95 NA 36.2844136 53.4856197
## var NA 519.9697034 1129.8268351
## std.dev NA 22.8028442 33.6128969
## coef.var NA 0.9121138 0.7080582boxplot(data, horizontal=TRUE, col='green')
Gráfico para Tabasco (Mexico)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_MX <- subset(df, country_name == "Mexico")
knitr::kable(head(df_MX)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 115 | 7/4/07 | NA | NA | Mexico | MX | Veracruz-Llave | 1947 | Laguna Chica (Pueblo Nuevo) | 9.51003 | NA | 18.5369 | -96.8229 | (18.536899999999999, -96.822900000000004) | Landslide | Landslide | Medium | Rain | NA | NA | 7 | nytimes.com | http://www.nytimes.com/2007/07/04/world/americas/04cnd-mexico.html?_r=1&hp&oref=slogin |
| 201 | 8/23/07 | NA | NA | Mexico | MX | Puebla | 1414 | Xochitlaxco (San Baltazar) | 1.68294 | NA | 19.9333 | -97.8500 | (19.933299999999999, -97.85) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Dean | NA | 6 | Inquirer.com | http://newsinfo.inquirer.net/breakingnews/world/view_article.php?article_id=84452 |
| 225 | 9/2/07 | NA | NA | Mexico | MX | Sinaloa | 3191 | El Limón de los Ramos | 10.88351 | NA | 24.9531 | -107.6220 | (24.953099999999999, -107.622) | Landslide | Complex | Medium | Tropical cyclone | Tropical Storm Henrietta | NA | 3 | NA | NA |
| 284 | 9/28/07 | NA | NA | Mexico | MX | Puebla | 3761 | Xaltepuxtla | 7.93258 | NA | 20.2000 | -97.9000 | (20.2, -97.9) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Lorenzo | NA | 1 | PressTV.ir | http://www.presstv.ir/detail.aspx?id=25037§ionid=3510207 |
| 342 | 10/31/07 | NA | NA | Mexico | MX | Tabasco | 4468 | Buenavista | 4.19108 | NA | 17.9493 | -92.5534 | (17.949300000000001, -92.553399999999996) | Landslide | Landslide | Medium | Rain | NA | NA | 18 | CapeTimes | http://www.capetimes.co.za/?fArticleId=4109453 |
| 346 | 11/4/07 | NA | NA | Mexico | MX | Chiapas | 3183 | Ostuacán | 3.74149 | NA | 17.3900 | -93.3060 | (17.39, -93.305999999999997) | Landslide | Mudslide | Very_large | Rain | NA | NA | 5 | Reuters - AlertNet.org | http://news.monstersandcritics.com/americas/news/article_1371436.php/Mudslide_is_latest_disaster_for_hard-hit_Mexico__2nd_Roundup_ |
library(dplyr)
df_MX <- subset(df, state == "Tabasco")
knitr::kable(head(df_MX))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 342 | 10/31/07 | NA | NA | Mexico | MX | Tabasco | 4468 | Buenavista | 4.19108 | NA | 17.9493 | -92.5534 | (17.949300000000001, -92.553399999999996) | Landslide | Landslide | Medium | Rain | NA | NA | 18 | CapeTimes | http://www.capetimes.co.za/?fArticleId=4109453 |
| 5693 | 12/16/13 | NA | NA | Mexico | MX | Tabasco | 1732 | Olcuatitán | 4.32007 | NA | 18.1563 | -92.9790 | (18.156300000000002, -92.978999999999999) | Landslide | Landslide | Medium | Continuous rain | NA | NA | NA | www.aljazeera.com | http://www.aljazeera.com/weather/2013/12/rain-snow-floods-hit-mexico-20131229105245837299.html |
| 7430 | 10/7/15 | NA | NA | Mexico | MX | Tabasco | 1042 | Libertad | 4.81680 | Unknown | 17.3768 | -92.7439 | (17.376799999999999, -92.743899999999996) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | Tabasco Hoy | http://www.tabascohoy.com/2/notas/273505/dejan-lluvias-deslizamientos-e-inundaciones-en-la-sierra |
| 7431 | 10/7/15 | NA | NA | Mexico | MX | Tabasco | 2500 | Huapinol | 2.15703 | Unknown | 17.9100 | -92.8956 | (17.91, -92.895600000000002) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | Tabasco Hoy | http://www.tabascohoy.com/2/notas/273505/dejan-lluvias-deslizamientos-e-inundaciones-en-la-sierra |
| 7469 | 12/16/15 | NA | NA | Mexico | MX | Tabasco | 1732 | Olcuatitán | 8.93271 | Below road | 18.2341 | -92.8901 | (18.234100000000002, -92.890100000000004) | Landslide | Riverbank collapse | Medium | Flooding | NA | 0 | 0 | Diario Presente | http://www.diariopresente.com.mx/noticia/tabasco/145872/deslave-carretera-punto-dejar-incomunicados-comunidades-nacajuca/ |
| 7518 | 10/15/15 | NA | NA | Mexico | MX | Tabasco | 32415 | Tenosique de Pino Suárez | 15.22260 | Below road | 17.4054 | -91.2988 | (17.4054, -91.2988) | Landslide | Landslide | Medium | Flooding | NA | 0 | 0 | ver tiente global | http://vertienteglobal.com/?p=49401 |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_MX <- df_MX %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_MX$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_MX, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_MX$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 15.22260 |
| 4.32007 |
| 8.93271 |
| 4.81680 |
| 2.15703 |
| 4.19108 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_MX$distance
names(distance) <- df_MX$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Tenosique de Pino Suárez 15.222600 15.222600 38.401838 38.401838
## Olcuatitán 8.932710 24.155310 22.534421 60.936260
## Libertad 4.816800 28.972110 12.151273 73.087533
## Olcuatitán 4.320070 33.292180 10.898180 83.985713
## Buenavista 4.191080 37.483260 10.572778 94.558491
## Huapinol 2.157030 39.640290 5.441509 100.000000stem(df_MX$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 244
## 0 | 59
## 1 |
## 1 | 5head(df_MX)## # A tibble: 6 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 7518 10/15/15 <NA> <NA> Mexico MX Tabasco 32415
## 2 5693 12/16/13 <NA> <NA> Mexico MX Tabasco 1732
## 3 7469 12/16/15 <NA> <NA> Mexico MX Tabasco 1732
## 4 7430 10/7/15 <NA> <NA> Mexico MX Tabasco 1042
## 5 7431 10/7/15 <NA> <NA> Mexico MX Tabasco 2500
## 6 342 10/31/07 <NA> <NA> Mexico MX Tabasco 4468
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_MX))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 7518 | 10/15/15 | NA | NA | Mexico | MX | Tabasco | 32415 | Tenosique de Pino Suárez | 15.22260 | Below road | 17.4054 | -91.2988 | (17.4054, -91.2988) | Landslide | Landslide | Medium | Flooding | NA | 0 | 0 | ver tiente global | http://vertienteglobal.com/?p=49401 | 38.401838 | 19.20092 |
| 5693 | 12/16/13 | NA | NA | Mexico | MX | Tabasco | 1732 | Olcuatitán | 4.32007 | NA | 18.1563 | -92.9790 | (18.156300000000002, -92.978999999999999) | Landslide | Landslide | Medium | Continuous rain | NA | NA | NA | www.aljazeera.com | http://www.aljazeera.com/weather/2013/12/rain-snow-floods-hit-mexico-20131229105245837299.html | 10.898180 | 43.85093 |
| 7469 | 12/16/15 | NA | NA | Mexico | MX | Tabasco | 1732 | Olcuatitán | 8.93271 | Below road | 18.2341 | -92.8901 | (18.234100000000002, -92.890100000000004) | Landslide | Riverbank collapse | Medium | Flooding | NA | 0 | 0 | Diario Presente | http://www.diariopresente.com.mx/noticia/tabasco/145872/deslave-carretera-punto-dejar-incomunicados-comunidades-nacajuca/ | 22.534421 | 60.56723 |
| 7430 | 10/7/15 | NA | NA | Mexico | MX | Tabasco | 1042 | Libertad | 4.81680 | Unknown | 17.3768 | -92.7439 | (17.376799999999999, -92.743899999999996) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | Tabasco Hoy | http://www.tabascohoy.com/2/notas/273505/dejan-lluvias-deslizamientos-e-inundaciones-en-la-sierra | 12.151273 | 77.91008 |
| 7431 | 10/7/15 | NA | NA | Mexico | MX | Tabasco | 2500 | Huapinol | 2.15703 | Unknown | 17.9100 | -92.8956 | (17.91, -92.895600000000002) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | Tabasco Hoy | http://www.tabascohoy.com/2/notas/273505/dejan-lluvias-deslizamientos-e-inundaciones-en-la-sierra | 5.441509 | 86.70647 |
| 342 | 10/31/07 | NA | NA | Mexico | MX | Tabasco | 4468 | Buenavista | 4.19108 | NA | 17.9493 | -92.5534 | (17.949300000000001, -92.553399999999996) | Landslide | Landslide | Medium | Rain | NA | NA | 18 | CapeTimes | http://www.capetimes.co.za/?fArticleId=4109453 | 10.572778 | 94.71361 |
stem(df_MX$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 244
## 0 | 59
## 1 |
## 1 | 5stem(df_MX$"distance", scale = 2)##
## The decimal point is at the |
##
## 2 | 2
## 4 | 238
## 6 |
## 8 | 9
## 10 |
## 12 |
## 14 | 2Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 2.15703 | 1 | 16.7 | 16.7 | 16.7 | 16.7 |
| 4.19108 | 1 | 16.7 | 16.7 | 33.3 | 33.3 |
| 4.32007 | 1 | 16.7 | 16.7 | 50.0 | 50.0 |
| 4.8168 | 1 | 16.7 | 16.7 | 66.7 | 66.7 |
| 8.93271 | 1 | 16.7 | 16.7 | 83.3 | 83.3 |
| 15.2226 | 1 | 16.7 | 16.7 | 100.0 | 100.0 |
| Total | 6 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 7 obs. of 5 variables:
## $ n : num 1 1 1 1 1 1 6
## $ % : num 16.7 16.7 16.7 16.7 16.7 16.7 100
## $ val% : num 16.7 16.7 16.7 16.7 16.7 16.7 100
## $ %cum : num 16.7 33.3 50 66.7 83.3 100 100
## $ val%cum: num 16.7 33.3 50 66.7 83.3 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 2.15703 | 1 |
| 4.19108 | 1 |
| 4.32007 | 1 |
| 4.8168 | 1 |
| 8.93271 | 1 |
| 15.2226 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 2.15703 7.15703 12.15703 17.15703distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (2.16,7.16] | 3 | 0.6 | 3 |
| (7.16,12.2] | 1 | 0.2 | 4 |
| (12.2,17.2] | 1 | 0.2 | 5 |
str(Freq_table)## 'data.frame': 3 obs. of 4 variables:
## $ distance: Factor w/ 3 levels "(2.16,7.16]",..: 1 2 3
## $ Freq : int 3 1 1
## $ Rel_Freq: num 0.6 0.2 0.2
## $ Cum_Freq: int 3 4 5df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (2.16,7.16] | 3 |
| (7.16,12.2] | 1 |
| (12.2,17.2] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_MX)## id date time continent_code country_name country_code
## nbr.val 6.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 3.420000e+02 NA NA NA NA NA
## max 7.518000e+03 NA NA NA NA NA
## range 7.176000e+03 NA NA NA NA NA
## sum 3.588300e+04 NA NA NA NA NA
## median 7.430500e+03 NA NA NA NA NA
## mean 5.980500e+03 NA NA NA NA NA
## SE.mean 1.164186e+03 NA NA NA NA NA
## CI.mean.0.95 2.992636e+03 NA NA NA NA NA
## var 8.131976e+06 NA NA NA NA NA
## std.dev 2.851662e+03 NA NA NA NA NA
## coef.var 4.768267e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 6.000000e+00 NA 6.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 1.042000e+03 NA 2.1570300 NA
## max NA 3.241500e+04 NA 15.2226000 NA
## range NA 3.137300e+04 NA 13.0655700 NA
## sum NA 4.388900e+04 NA 39.6402900 NA
## median NA 2.116000e+03 NA 4.5684350 NA
## mean NA 7.314833e+03 NA 6.6067150 NA
## SE.mean NA 5.043114e+03 NA 1.9468886 NA
## CI.mean.0.95 NA 1.296374e+04 NA 5.0046365 NA
## var NA 1.525980e+08 NA 22.7422514 NA
## std.dev NA 1.235306e+04 NA 4.7688837 NA
## coef.var NA 1.688768e+00 NA 0.7218237 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 6.00000000 6.000000e+00 NA NA NA
## nbr.null 0.00000000 0.000000e+00 NA NA NA
## nbr.na 0.00000000 0.000000e+00 NA NA NA
## min 17.37680000 -9.297900e+01 NA NA NA
## max 18.23410000 -9.129880e+01 NA NA NA
## range 0.85730000 1.680200e+00 NA NA NA
## sum 107.03190000 -5.553608e+02 NA NA NA
## median 17.92965000 -9.281700e+01 NA NA NA
## mean 17.83865000 -9.256013e+01 NA NA NA
## SE.mean 0.15006970 2.595921e-01 NA NA NA
## CI.mean.0.95 0.38576645 6.673029e-01 NA NA NA
## var 0.13512549 4.043285e-01 NA NA NA
## std.dev 0.36759419 6.358683e-01 NA NA NA
## coef.var 0.02060662 -6.869786e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 4 5.000000 NA
## nbr.null NA NA NA 4 4.000000 NA
## nbr.na NA NA NA 2 1.000000 NA
## min NA NA NA 0 0.000000 NA
## max NA NA NA 0 18.000000 NA
## range NA NA NA 0 18.000000 NA
## sum NA NA NA 0 18.000000 NA
## median NA NA NA 0 0.000000 NA
## mean NA NA NA 0 3.600000 NA
## SE.mean NA NA NA 0 3.600000 NA
## CI.mean.0.95 NA NA NA 0 9.995202 NA
## var NA NA NA 0 64.800000 NA
## std.dev NA NA NA 0 8.049845 NA
## coef.var NA NA NA NaN 2.236068 NA
## source_link prop ypos
## nbr.val NA 6.0000000 6.0000000
## nbr.null NA 0.0000000 0.0000000
## nbr.na NA 0.0000000 0.0000000
## min NA 5.4415091 19.2009191
## max NA 38.4018381 94.7136108
## range NA 32.9603290 75.5126918
## sum NA 100.0000000 382.9492292
## median NA 11.5247265 69.2386521
## mean NA 16.6666667 63.8248715
## SE.mean NA 4.9113884 11.6575332
## CI.mean.0.95 NA 12.6251258 29.9666431
## var NA 144.7304161 815.3884811
## std.dev NA 12.0303955 28.5550080
## coef.var NA 0.7218237 0.4473962boxplot(data, horizontal=TRUE, col='green')
Gráfico para The Federal District (Mexico)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_MX <- subset(df, country_name == "Mexico")
knitr::kable(head(df_MX)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 115 | 7/4/07 | NA | NA | Mexico | MX | Veracruz-Llave | 1947 | Laguna Chica (Pueblo Nuevo) | 9.51003 | NA | 18.5369 | -96.8229 | (18.536899999999999, -96.822900000000004) | Landslide | Landslide | Medium | Rain | NA | NA | 7 | nytimes.com | http://www.nytimes.com/2007/07/04/world/americas/04cnd-mexico.html?_r=1&hp&oref=slogin |
| 201 | 8/23/07 | NA | NA | Mexico | MX | Puebla | 1414 | Xochitlaxco (San Baltazar) | 1.68294 | NA | 19.9333 | -97.8500 | (19.933299999999999, -97.85) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Dean | NA | 6 | Inquirer.com | http://newsinfo.inquirer.net/breakingnews/world/view_article.php?article_id=84452 |
| 225 | 9/2/07 | NA | NA | Mexico | MX | Sinaloa | 3191 | El Limón de los Ramos | 10.88351 | NA | 24.9531 | -107.6220 | (24.953099999999999, -107.622) | Landslide | Complex | Medium | Tropical cyclone | Tropical Storm Henrietta | NA | 3 | NA | NA |
| 284 | 9/28/07 | NA | NA | Mexico | MX | Puebla | 3761 | Xaltepuxtla | 7.93258 | NA | 20.2000 | -97.9000 | (20.2, -97.9) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Lorenzo | NA | 1 | PressTV.ir | http://www.presstv.ir/detail.aspx?id=25037§ionid=3510207 |
| 342 | 10/31/07 | NA | NA | Mexico | MX | Tabasco | 4468 | Buenavista | 4.19108 | NA | 17.9493 | -92.5534 | (17.949300000000001, -92.553399999999996) | Landslide | Landslide | Medium | Rain | NA | NA | 18 | CapeTimes | http://www.capetimes.co.za/?fArticleId=4109453 |
| 346 | 11/4/07 | NA | NA | Mexico | MX | Chiapas | 3183 | Ostuacán | 3.74149 | NA | 17.3900 | -93.3060 | (17.39, -93.305999999999997) | Landslide | Mudslide | Very_large | Rain | NA | NA | 5 | Reuters - AlertNet.org | http://news.monstersandcritics.com/americas/news/article_1371436.php/Mudslide_is_latest_disaster_for_hard-hit_Mexico__2nd_Roundup_ |
library(dplyr)
df_MX <- subset(df, state == "The Federal District")
knitr::kable(head(df_MX))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 975 | 1/22/09 | NA | NA | Mexico | MX | The Federal District | 12294193 | Mexico City | 0.15208 | NA | 19.4271 | -99.1276 | (19.427099999999999, -99.127600000000001) | Landslide | Landslide | Medium | Downpour | NA | NA | 2 | NA | NA |
| 1167 | 9/15/09 | NA | NA | Mexico | MX | The Federal District | 228927 | Magdalena Contreras | 3.49173 | NA | 19.3161 | -99.2398 | (19.316099999999999, -99.239800000000002) | Landslide | Mudslide | Medium | Downpour | NA | NA | 3 | NA | http://edition.cnn.com/2009/WORLD/americas/09/16/mexico.mudslide.deaths/ |
| 2191 | 8/2/10 | NA | NA | Mexico | MX | The Federal District | 12294193 | Mexico City | 0.15208 | NA | 19.4270 | -99.1276 | (19.427, -99.127600000000001) | Landslide | Mudslide | Medium | Construction | NA | NA | 2 | NA | NA |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_MX <- df_MX %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_MX$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_MX, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_MX$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 0.15208 |
| 0.15208 |
| 3.49173 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_MX$distance
names(distance) <- df_MX$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Magdalena Contreras 3.491730 3.491730 91.987123 91.987123
## Mexico City 0.152080 3.643810 4.006439 95.993561
## Mexico City 0.152080 3.795890 4.006439 100.000000stem(df_MX$"distance")##
## The decimal point is at the |
##
## 0 | 22
## 1 |
## 2 |
## 3 | 5head(df_MX)## # A tibble: 3 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 975 1/22/09 <NA> <NA> Mexico MX The F~ 12294193
## 2 2191 8/2/10 <NA> <NA> Mexico MX The F~ 12294193
## 3 1167 9/15/09 <NA> <NA> Mexico MX The F~ 228927
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_MX))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 975 | 1/22/09 | NA | NA | Mexico | MX | The Federal District | 12294193 | Mexico City | 0.15208 | NA | 19.4271 | -99.1276 | (19.427099999999999, -99.127600000000001) | Landslide | Landslide | Medium | Downpour | NA | NA | 2 | NA | NA | 4.006438 | 2.003219 |
| 2191 | 8/2/10 | NA | NA | Mexico | MX | The Federal District | 12294193 | Mexico City | 0.15208 | NA | 19.4270 | -99.1276 | (19.427, -99.127600000000001) | Landslide | Mudslide | Medium | Construction | NA | NA | 2 | NA | NA | 4.006438 | 6.009658 |
| 1167 | 9/15/09 | NA | NA | Mexico | MX | The Federal District | 228927 | Magdalena Contreras | 3.49173 | NA | 19.3161 | -99.2398 | (19.316099999999999, -99.239800000000002) | Landslide | Mudslide | Medium | Downpour | NA | NA | 3 | NA | http://edition.cnn.com/2009/WORLD/americas/09/16/mexico.mudslide.deaths/ | 91.987123 | 54.006439 |
stem(df_MX$"distance")##
## The decimal point is at the |
##
## 0 | 22
## 1 |
## 2 |
## 3 | 5stem(df_MX$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 22
## 0 |
## 1 |
## 1 |
## 2 |
## 2 |
## 3 |
## 3 | 5Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.15208 | 2 | 66.7 | 66.7 | 66.7 | 66.7 |
| 3.49173 | 1 | 33.3 | 33.3 | 100.0 | 100.0 |
| Total | 3 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 3 obs. of 5 variables:
## $ n : num 2 1 3
## $ % : num 66.7 33.3 100
## $ val% : num 66.7 33.3 100
## $ %cum : num 66.7 100 100
## $ val%cum: num 66.7 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.15208 | 2 |
| 3.49173 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.15208 2.15208 4.15208distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.152,2.15] | 0 | 0 | 0 |
| (2.15,4.15] | 1 | 1 | 1 |
str(Freq_table)## 'data.frame': 2 obs. of 4 variables:
## $ distance: Factor w/ 2 levels "(0.152,2.15]",..: 1 2
## $ Freq : int 0 1
## $ Rel_Freq: num 0 1
## $ Cum_Freq: int 0 1df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.152,2.15] | 0 |
| (2.15,4.15] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_MX)## Warning in min(x): ningún argumento finito para min; retornando Inf## Warning in max(x): ningun argumento finito para max; retornando -Inf## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 3.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 9.750000e+02 NA NA NA NA NA
## max 2.191000e+03 NA NA NA NA NA
## range 1.216000e+03 NA NA NA NA NA
## sum 4.333000e+03 NA NA NA NA NA
## median 1.167000e+03 NA NA NA NA NA
## mean 1.444333e+03 NA NA NA NA NA
## SE.mean 3.774252e+02 NA NA NA NA NA
## CI.mean.0.95 1.623930e+03 NA NA NA NA NA
## var 4.273493e+05 NA NA NA NA NA
## std.dev 6.537196e+02 NA NA NA NA NA
## coef.var 4.526099e-01 NA NA NA NA NA
## state population city distance location_description latitude
## nbr.val NA 3.000000e+00 NA 3.000000 NA 3.000000000
## nbr.null NA 0.000000e+00 NA 0.000000 NA 0.000000000
## nbr.na NA 0.000000e+00 NA 0.000000 NA 0.000000000
## min NA 2.289270e+05 NA 0.152080 NA 19.316100000
## max NA 1.229419e+07 NA 3.491730 NA 19.427100000
## range NA 1.206527e+07 NA 3.339650 NA 0.111000000
## sum NA 2.481731e+07 NA 3.795890 NA 58.170200000
## median NA 1.229419e+07 NA 0.152080 NA 19.427000000
## mean NA 8.272438e+06 NA 1.265297 NA 19.390066667
## SE.mean NA 4.021755e+06 NA 1.113217 NA 0.036983345
## CI.mean.0.95 NA 1.730422e+07 NA 4.789785 NA 0.159126489
## var NA 4.852355e+13 NA 3.717754 NA 0.004103303
## std.dev NA 6.965885e+06 NA 1.928148 NA 0.064057032
## coef.var NA 8.420595e-01 NA 1.523870 NA 0.003303600
## longitude geolocation hazard_type landslide_type
## nbr.val 3.000000e+00 NA NA NA
## nbr.null 0.000000e+00 NA NA NA
## nbr.na 0.000000e+00 NA NA NA
## min -9.923980e+01 NA NA NA
## max -9.912760e+01 NA NA NA
## range 1.122000e-01 NA NA NA
## sum -2.974950e+02 NA NA NA
## median -9.912760e+01 NA NA NA
## mean -9.916500e+01 NA NA NA
## SE.mean 3.740000e-02 NA NA NA
## CI.mean.0.95 1.609192e-01 NA NA NA
## var 4.196280e-03 NA NA NA
## std.dev 6.477870e-02 NA NA NA
## coef.var -6.532416e-04 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 0 3.0000000 NA
## nbr.null NA NA NA 0 0.0000000 NA
## nbr.na NA NA NA 3 0.0000000 NA
## min NA NA NA Inf 2.0000000 NA
## max NA NA NA -Inf 3.0000000 NA
## range NA NA NA -Inf 1.0000000 NA
## sum NA NA NA 0 7.0000000 NA
## median NA NA NA NA 2.0000000 NA
## mean NA NA NA NaN 2.3333333 NA
## SE.mean NA NA NA NA 0.3333333 NA
## CI.mean.0.95 NA NA NA NaN 1.4342176 NA
## var NA NA NA NA 0.3333333 NA
## std.dev NA NA NA NA 0.5773503 NA
## coef.var NA NA NA NA 0.2474358 NA
## source_link prop ypos
## nbr.val NA 3.000000 3.000000
## nbr.null NA 0.000000 0.000000
## nbr.na NA 0.000000 0.000000
## min NA 4.006439 2.003219
## max NA 91.987123 54.006439
## range NA 87.980684 52.003219
## sum NA 100.000000 62.019316
## median NA 4.006439 6.009658
## mean NA 33.333333 20.673105
## SE.mean NA 29.326895 16.706747
## CI.mean.0.95 NA 126.183444 71.883332
## var NA 2580.200274 837.346221
## std.dev NA 50.795672 28.936935
## coef.var NA 1.523870 1.399738boxplot(data, horizontal=TRUE, col='green')
Gráfico para Veracruz (Mexico)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_MX <- subset(df, country_name == "Mexico")
knitr::kable(head(df_MX)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 115 | 7/4/07 | NA | NA | Mexico | MX | Veracruz-Llave | 1947 | Laguna Chica (Pueblo Nuevo) | 9.51003 | NA | 18.5369 | -96.8229 | (18.536899999999999, -96.822900000000004) | Landslide | Landslide | Medium | Rain | NA | NA | 7 | nytimes.com | http://www.nytimes.com/2007/07/04/world/americas/04cnd-mexico.html?_r=1&hp&oref=slogin |
| 201 | 8/23/07 | NA | NA | Mexico | MX | Puebla | 1414 | Xochitlaxco (San Baltazar) | 1.68294 | NA | 19.9333 | -97.8500 | (19.933299999999999, -97.85) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Dean | NA | 6 | Inquirer.com | http://newsinfo.inquirer.net/breakingnews/world/view_article.php?article_id=84452 |
| 225 | 9/2/07 | NA | NA | Mexico | MX | Sinaloa | 3191 | El Limón de los Ramos | 10.88351 | NA | 24.9531 | -107.6220 | (24.953099999999999, -107.622) | Landslide | Complex | Medium | Tropical cyclone | Tropical Storm Henrietta | NA | 3 | NA | NA |
| 284 | 9/28/07 | NA | NA | Mexico | MX | Puebla | 3761 | Xaltepuxtla | 7.93258 | NA | 20.2000 | -97.9000 | (20.2, -97.9) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Lorenzo | NA | 1 | PressTV.ir | http://www.presstv.ir/detail.aspx?id=25037§ionid=3510207 |
| 342 | 10/31/07 | NA | NA | Mexico | MX | Tabasco | 4468 | Buenavista | 4.19108 | NA | 17.9493 | -92.5534 | (17.949300000000001, -92.553399999999996) | Landslide | Landslide | Medium | Rain | NA | NA | 18 | CapeTimes | http://www.capetimes.co.za/?fArticleId=4109453 |
| 346 | 11/4/07 | NA | NA | Mexico | MX | Chiapas | 3183 | Ostuacán | 3.74149 | NA | 17.3900 | -93.3060 | (17.39, -93.305999999999997) | Landslide | Mudslide | Very_large | Rain | NA | NA | 5 | Reuters - AlertNet.org | http://news.monstersandcritics.com/americas/news/article_1371436.php/Mudslide_is_latest_disaster_for_hard-hit_Mexico__2nd_Roundup_ |
library(dplyr)
df_MX <- subset(df, state == "Veracruz")
knitr::kable(head(df_MX))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 6688 | 1/5/14 | Night | NA | Mexico | MX | Veracruz | 9277 | Chocaman | 1.93516 | Unknown | 19.0294 | -97.0355 | (19.029399999999999, -97.035499999999999) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | Calor | http://www.alcalorpolitico.com/informacion/saldo-blanco-en-deslave-de-chocaman-familias-salieron-a-tiempo-maza-limon-139202.html#.VLfpVPnF98E |
| 7445 | 9/17/15 | NA | NA | Mexico | MX | Veracruz | 1005 | Cruz Verde | 2.47800 | Deforested slope | 19.1331 | -97.1317 | (19.133099999999999, -97.131699999999995) | Landslide | Landslide | Medium | Rain | NA | 0 | 6 | El Diario | http://www.eldiariony.com/2015/09/17/deslizamiento-de-cerro-en-veracruz-deja-seis-muertos/ |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_MX <- df_MX %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_MX$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_MX, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_MX$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 2.47800 |
| 1.93516 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_MX$distance
names(distance) <- df_MX$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Cruz Verde 2.47800 2.47800 56.15024 56.15024
## Chocaman 1.93516 4.41316 43.84976 100.00000stem(df_MX$"distance")##
## The decimal point is 1 digit(s) to the left of the |
##
## 18 | 4
## 20 |
## 22 |
## 24 | 8head(df_MX)## # A tibble: 2 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 7445 9/17/15 <NA> <NA> Mexico MX Veracruz 1005
## 2 6688 1/5/14 Night <NA> Mexico MX Veracruz 9277
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_MX))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 7445 | 9/17/15 | NA | NA | Mexico | MX | Veracruz | 1005 | Cruz Verde | 2.47800 | Deforested slope | 19.1331 | -97.1317 | (19.133099999999999, -97.131699999999995) | Landslide | Landslide | Medium | Rain | NA | 0 | 6 | El Diario | http://www.eldiariony.com/2015/09/17/deslizamiento-de-cerro-en-veracruz-deja-seis-muertos/ | 56.15024 | 28.07512 |
| 6688 | 1/5/14 | Night | NA | Mexico | MX | Veracruz | 9277 | Chocaman | 1.93516 | Unknown | 19.0294 | -97.0355 | (19.029399999999999, -97.035499999999999) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | Calor | http://www.alcalorpolitico.com/informacion/saldo-blanco-en-deslave-de-chocaman-familias-salieron-a-tiempo-maza-limon-139202.html#.VLfpVPnF98E | 43.84976 | 78.07512 |
stem(df_MX$"distance")##
## The decimal point is 1 digit(s) to the left of the |
##
## 18 | 4
## 20 |
## 22 |
## 24 | 8stem(df_MX$"distance", scale = 2)##
## The decimal point is 1 digit(s) to the left of the |
##
## 19 | 4
## 20 |
## 21 |
## 22 |
## 23 |
## 24 | 8Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 1.93516 | 1 | 50 | 50 | 50 | 50 |
| 2.478 | 1 | 50 | 50 | 100 | 100 |
| Total | 2 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 3 obs. of 5 variables:
## $ n : num 1 1 2
## $ % : num 50 50 100
## $ val% : num 50 50 100
## $ %cum : num 50 100 100
## $ val%cum: num 50 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 1.93516 | 1 |
| 2.478 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 1.93516 2.93516distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (1.94,2.94] | 1 | 1 | 1 |
str(Freq_table)## 'data.frame': 1 obs. of 4 variables:
## $ distance: Factor w/ 1 level "(1.94,2.94]": 1
## $ Freq : int 1
## $ Rel_Freq: num 1
## $ Cum_Freq: int 1df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (1.94,2.94] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_MX)## id date time continent_code country_name country_code
## nbr.val 2.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 6.688000e+03 NA NA NA NA NA
## max 7.445000e+03 NA NA NA NA NA
## range 7.570000e+02 NA NA NA NA NA
## sum 1.413300e+04 NA NA NA NA NA
## median 7.066500e+03 NA NA NA NA NA
## mean 7.066500e+03 NA NA NA NA NA
## SE.mean 3.785000e+02 NA NA NA NA NA
## CI.mean.0.95 4.809298e+03 NA NA NA NA NA
## var 2.865245e+05 NA NA NA NA NA
## std.dev 5.352798e+02 NA NA NA NA NA
## coef.var 7.574893e-02 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 2.000000e+00 NA 2.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 1.005000e+03 NA 1.9351600 NA
## max NA 9.277000e+03 NA 2.4780000 NA
## range NA 8.272000e+03 NA 0.5428400 NA
## sum NA 1.028200e+04 NA 4.4131600 NA
## median NA 5.141000e+03 NA 2.2065800 NA
## mean NA 5.141000e+03 NA 2.2065800 NA
## SE.mean NA 4.136000e+03 NA 0.2714200 NA
## CI.mean.0.95 NA 5.255286e+04 NA 3.4487181 NA
## var NA 3.421299e+07 NA 0.1473376 NA
## std.dev NA 5.849187e+03 NA 0.3838458 NA
## coef.var NA 1.137753e+00 NA 0.1739551 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 2.000000000 2.000000e+00 NA NA NA
## nbr.null 0.000000000 0.000000e+00 NA NA NA
## nbr.na 0.000000000 0.000000e+00 NA NA NA
## min 19.029400000 -9.713170e+01 NA NA NA
## max 19.133100000 -9.703550e+01 NA NA NA
## range 0.103700000 9.620000e-02 NA NA NA
## sum 38.162500000 -1.941672e+02 NA NA NA
## median 19.081250000 -9.708360e+01 NA NA NA
## mean 19.081250000 -9.708360e+01 NA NA NA
## SE.mean 0.051850000 4.810000e-02 NA NA NA
## CI.mean.0.95 0.658816716 6.111684e-01 NA NA NA
## var 0.005376845 4.627220e-03 NA NA NA
## std.dev 0.073326973 6.802367e-02 NA NA NA
## coef.var 0.003842881 -7.006711e-04 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 2 2.000000 NA
## nbr.null NA NA NA 2 1.000000 NA
## nbr.na NA NA NA 0 0.000000 NA
## min NA NA NA 0 0.000000 NA
## max NA NA NA 0 6.000000 NA
## range NA NA NA 0 6.000000 NA
## sum NA NA NA 0 6.000000 NA
## median NA NA NA 0 3.000000 NA
## mean NA NA NA 0 3.000000 NA
## SE.mean NA NA NA 0 3.000000 NA
## CI.mean.0.95 NA NA NA 0 38.118614 NA
## var NA NA NA 0 18.000000 NA
## std.dev NA NA NA 0 4.242641 NA
## coef.var NA NA NA NaN 1.414214 NA
## source_link prop ypos
## nbr.val NA 2.0000000 2.0000000
## nbr.null NA 0.0000000 0.0000000
## nbr.na NA 0.0000000 0.0000000
## min NA 43.8497584 28.0751208
## max NA 56.1502416 78.0751208
## range NA 12.3004831 50.0000000
## sum NA 100.0000000 106.1502416
## median NA 50.0000000 53.0751208
## mean NA 50.0000000 53.0751208
## SE.mean NA 6.1502416 25.0000000
## CI.mean.0.95 NA 78.1462283 317.6551184
## var NA 75.6509423 1250.0000000
## std.dev NA 8.6977550 35.3553391
## coef.var NA 0.1739551 0.6661377boxplot(data, horizontal=TRUE, col='green')
Gráfico para Veracruz-Llave (Mexico)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_MX <- subset(df, country_name == "Mexico")
knitr::kable(head(df_MX)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 115 | 7/4/07 | NA | NA | Mexico | MX | Veracruz-Llave | 1947 | Laguna Chica (Pueblo Nuevo) | 9.51003 | NA | 18.5369 | -96.8229 | (18.536899999999999, -96.822900000000004) | Landslide | Landslide | Medium | Rain | NA | NA | 7 | nytimes.com | http://www.nytimes.com/2007/07/04/world/americas/04cnd-mexico.html?_r=1&hp&oref=slogin |
| 201 | 8/23/07 | NA | NA | Mexico | MX | Puebla | 1414 | Xochitlaxco (San Baltazar) | 1.68294 | NA | 19.9333 | -97.8500 | (19.933299999999999, -97.85) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Dean | NA | 6 | Inquirer.com | http://newsinfo.inquirer.net/breakingnews/world/view_article.php?article_id=84452 |
| 225 | 9/2/07 | NA | NA | Mexico | MX | Sinaloa | 3191 | El Limón de los Ramos | 10.88351 | NA | 24.9531 | -107.6220 | (24.953099999999999, -107.622) | Landslide | Complex | Medium | Tropical cyclone | Tropical Storm Henrietta | NA | 3 | NA | NA |
| 284 | 9/28/07 | NA | NA | Mexico | MX | Puebla | 3761 | Xaltepuxtla | 7.93258 | NA | 20.2000 | -97.9000 | (20.2, -97.9) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Lorenzo | NA | 1 | PressTV.ir | http://www.presstv.ir/detail.aspx?id=25037§ionid=3510207 |
| 342 | 10/31/07 | NA | NA | Mexico | MX | Tabasco | 4468 | Buenavista | 4.19108 | NA | 17.9493 | -92.5534 | (17.949300000000001, -92.553399999999996) | Landslide | Landslide | Medium | Rain | NA | NA | 18 | CapeTimes | http://www.capetimes.co.za/?fArticleId=4109453 |
| 346 | 11/4/07 | NA | NA | Mexico | MX | Chiapas | 3183 | Ostuacán | 3.74149 | NA | 17.3900 | -93.3060 | (17.39, -93.305999999999997) | Landslide | Mudslide | Very_large | Rain | NA | NA | 5 | Reuters - AlertNet.org | http://news.monstersandcritics.com/americas/news/article_1371436.php/Mudslide_is_latest_disaster_for_hard-hit_Mexico__2nd_Roundup_ |
library(dplyr)
df_MX <- subset(df, state == "Veracruz-Llave")
knitr::kable(head(df_MX))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 115 | 7/4/07 | NA | NA | Mexico | MX | Veracruz-Llave | 1947 | Laguna Chica (Pueblo Nuevo) | 9.51003 | NA | 18.5369 | -96.8229 | (18.536899999999999, -96.822900000000004) | Landslide | Landslide | Medium | Rain | NA | NA | 7 | nytimes.com | http://www.nytimes.com/2007/07/04/world/americas/04cnd-mexico.html?_r=1&hp&oref=slogin |
| 2438 | 9/17/10 | NA | NA | Mexico | MX | Veracruz-Llave | 1324 | El Hatito | 8.28739 | NA | 19.2818 | -96.3149 | (19.2818, -96.314899999999994) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Karl | NA | 2 | NA | http://www.lfpress.com/news/world/2010/09/17/15382976-reuters.html |
| 3684 | 7/1/11 | NA | NA | Mexico | MX | Veracruz-Llave | 425148 | Xalapa de Enríquez | 1.27837 | NA | 19.5426 | -96.9137 | (19.5426, -96.913700000000006) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Storm Arlene | NA | 0 | NA | http://edition.cnn.com/2011/WORLD/americas/07/04/mexico.arlene.deaths/ |
| 5403 | 8/26/13 | 20:20:00 | NA | Mexico | MX | Veracruz-Llave | 30607 | Coatzintla | 1.52983 | NA | 20.5004 | -97.4647 | (20.500399999999999, -97.464699999999993) | Landslide | Landslide | Medium | Tropical cyclone | Fernand | NA | 3 | www.cbc.ca | http://www.cbc.ca/news/world/mexico-storm-related-landslides-kill-13-1.1370491 |
| 5405 | 8/26/13 | NA | NA | Mexico | MX | Veracruz-Llave | 15800 | Altotonga | 2.85382 | NA | 19.7906 | -97.2428 | (19.790600000000001, -97.242800000000003) | Landslide | Landslide | Medium | Tropical cyclone | Fernand | NA | 1 | www.cbc.ca | http://www.cbc.ca/news/world/mexico-storm-related-landslides-kill-13-1.1370491 |
| 5406 | 8/26/13 | NA | NA | Mexico | MX | Veracruz-Llave | 3198 | Yecuatla | 3.73160 | NA | 19.8413 | -96.8005 | (19.8413, -96.8005) | Landslide | Landslide | Medium | Downpour | NA | NA | 9 | www.cbc.ca | http://www.cbc.ca/news/world/mexico-storm-related-landslides-kill-13-1.1370491 |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_MX, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_MX <- df_MX %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_MX$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_MX, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_MX$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 3.73160 |
| 1.27837 |
| 4.51820 |
| 9.51003 |
| 0.09971 |
| 8.28739 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_MX$distance
names(distance) <- df_MX$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage
## Laguna Chica (Pueblo Nuevo) 9.5100300 9.5100300 29.4329486
## El Hatito 8.2873900 17.7974200 25.6489542
## Tetlaxco 4.5182000 22.3156200 13.9835467
## Yecuatla 3.7316000 26.0472200 11.5490688
## Altotonga 2.8538200 28.9010400 8.8323946
## Coatzintla 1.5298300 30.4308700 4.7347283
## Xalapa de Enríquez 1.2783700 31.7092400 3.9564753
## Altotonga 0.5018800 32.2111200 1.5532872
## Heroica Coscomatepec de Bravo 0.0997100 32.3108300 0.3085962
##
## Pareto chart analysis for distance
## Cum.Percent.
## Laguna Chica (Pueblo Nuevo) 29.4329486
## El Hatito 55.0819029
## Tetlaxco 69.0654496
## Yecuatla 80.6145184
## Altotonga 89.4469130
## Coatzintla 94.1816413
## Xalapa de Enríquez 98.1381165
## Altotonga 99.6914038
## Heroica Coscomatepec de Bravo 100.0000000stem(df_MX$"distance")##
## The decimal point is at the |
##
## 0 | 1535
## 2 | 97
## 4 | 5
## 6 |
## 8 | 35head(df_MX)## # A tibble: 6 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 5406 8/26/13 <NA> <NA> Mexico MX Verac~ 3198
## 2 3684 7/1/11 <NA> <NA> Mexico MX Verac~ 425148
## 3 5542 9/16/13 <NA> <NA> Mexico MX Verac~ 1543
## 4 115 7/4/07 <NA> <NA> Mexico MX Verac~ 1947
## 5 5486 9/9/13 Night <NA> Mexico MX Verac~ 12920
## 6 2438 9/17/10 <NA> <NA> Mexico MX Verac~ 1324
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_MX))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 5406 | 8/26/13 | NA | NA | Mexico | MX | Veracruz-Llave | 3198 | Yecuatla | 3.73160 | NA | 19.8413 | -96.8005 | (19.8413, -96.8005) | Landslide | Landslide | Medium | Downpour | NA | NA | 9 | www.cbc.ca | http://www.cbc.ca/news/world/mexico-storm-related-landslides-kill-13-1.1370491 | 11.5490688 | 5.774534 |
| 3684 | 7/1/11 | NA | NA | Mexico | MX | Veracruz-Llave | 425148 | Xalapa de Enríquez | 1.27837 | NA | 19.5426 | -96.9137 | (19.5426, -96.913700000000006) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Storm Arlene | NA | 0 | NA | http://edition.cnn.com/2011/WORLD/americas/07/04/mexico.arlene.deaths/ | 3.9564753 | 13.527306 |
| 5542 | 9/16/13 | NA | NA | Mexico | MX | Veracruz-Llave | 1543 | Tetlaxco | 4.51820 | NA | 19.0603 | -97.1009 | (19.060300000000002, -97.100899999999996) | Landslide | Landslide | Medium | Tropical cyclone | Manuel | NA | 13 | www.raymondvillechroniclenews.com | http://www.raymondvillechroniclenews.com/news/2013-09-18/News/Mexican_village_buries_13_victims_of_mudslide.html | 13.9835467 | 22.497318 |
| 115 | 7/4/07 | NA | NA | Mexico | MX | Veracruz-Llave | 1947 | Laguna Chica (Pueblo Nuevo) | 9.51003 | NA | 18.5369 | -96.8229 | (18.536899999999999, -96.822900000000004) | Landslide | Landslide | Medium | Rain | NA | NA | 7 | nytimes.com | http://www.nytimes.com/2007/07/04/world/americas/04cnd-mexico.html?_r=1&hp&oref=slogin | 29.4329486 | 44.205565 |
| 5486 | 9/9/13 | Night | NA | Mexico | MX | Veracruz-Llave | 12920 | Heroica Coscomatepec de Bravo | 0.09971 | NA | 19.0719 | -97.0474 | (19.071899999999999, -97.047399999999996) | Landslide | Landslide | Medium | Downpour | NA | 2 | 14 | infosurhoy.com | http://infosurhoy.com/en_GB/articles/saii/newsbriefs/2013/09/12/newsbrief-03 | 0.3085962 | 59.076338 |
| 2438 | 9/17/10 | NA | NA | Mexico | MX | Veracruz-Llave | 1324 | El Hatito | 8.28739 | NA | 19.2818 | -96.3149 | (19.2818, -96.314899999999994) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Karl | NA | 2 | NA | http://www.lfpress.com/news/world/2010/09/17/15382976-reuters.html | 25.6489542 | 72.055113 |
stem(df_MX$"distance")##
## The decimal point is at the |
##
## 0 | 1535
## 2 | 97
## 4 | 5
## 6 |
## 8 | 35stem(df_MX$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 15
## 1 | 35
## 2 | 9
## 3 | 7
## 4 | 5
## 5 |
## 6 |
## 7 |
## 8 | 3
## 9 | 5Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.09971 | 1 | 11.1 | 11.1 | 11.1 | 11.1 |
| 0.50188 | 1 | 11.1 | 11.1 | 22.2 | 22.2 |
| 1.27837 | 1 | 11.1 | 11.1 | 33.3 | 33.3 |
| 1.52983 | 1 | 11.1 | 11.1 | 44.4 | 44.4 |
| 2.85382 | 1 | 11.1 | 11.1 | 55.6 | 55.6 |
| 3.7316 | 1 | 11.1 | 11.1 | 66.7 | 66.7 |
| 4.5182 | 1 | 11.1 | 11.1 | 77.8 | 77.8 |
| 8.28739 | 1 | 11.1 | 11.1 | 88.9 | 88.9 |
| 9.51003 | 1 | 11.1 | 11.1 | 100.0 | 100.0 |
| Total | 9 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 10 obs. of 5 variables:
## $ n : num 1 1 1 1 1 1 1 1 1 9
## $ % : num 11.1 11.1 11.1 11.1 11.1 11.1 11.1 11.1 11.1 100
## $ val% : num 11.1 11.1 11.1 11.1 11.1 11.1 11.1 11.1 11.1 100
## $ %cum : num 11.1 22.2 33.3 44.4 55.6 66.7 77.8 88.9 100 100
## $ val%cum: num 11.1 22.2 33.3 44.4 55.6 66.7 77.8 88.9 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.09971 | 1 |
| 0.50188 | 1 |
| 1.27837 | 1 |
| 1.52983 | 1 |
| 2.85382 | 1 |
| 3.7316 | 1 |
| 4.5182 | 1 |
| 8.28739 | 1 |
| 9.51003 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.09971 2.09971 4.09971 6.09971 8.09971 10.09971distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.0997,2.1] | 3 | 0.375 | 3 |
| (2.1,4.1] | 2 | 0.250 | 5 |
| (4.1,6.1] | 1 | 0.125 | 6 |
| (6.1,8.1] | 0 | 0.000 | 6 |
| (8.1,10.1] | 2 | 0.250 | 8 |
str(Freq_table)## 'data.frame': 5 obs. of 4 variables:
## $ distance: Factor w/ 5 levels "(0.0997,2.1]",..: 1 2 3 4 5
## $ Freq : int 3 2 1 0 2
## $ Rel_Freq: num 0.375 0.25 0.125 0 0.25
## $ Cum_Freq: int 3 5 6 6 8df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.0997,2.1] | 3 |
| (2.1,4.1] | 2 |
| (4.1,6.1] | 1 |
| (6.1,8.1] | 0 |
| (8.1,10.1] | 2 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_MX)## id date time continent_code country_name country_code
## nbr.val 9.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 1.150000e+02 NA NA NA NA NA
## max 5.542000e+03 NA NA NA NA NA
## range 5.427000e+03 NA NA NA NA NA
## sum 3.901100e+04 NA NA NA NA NA
## median 5.405000e+03 NA NA NA NA NA
## mean 4.334556e+03 NA NA NA NA NA
## SE.mean 6.398549e+02 NA NA NA NA NA
## CI.mean.0.95 1.475508e+03 NA NA NA NA NA
## var 3.684729e+06 NA NA NA NA NA
## std.dev 1.919565e+03 NA NA NA NA NA
## coef.var 4.428516e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 9.000000e+00 NA 9.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 1.324000e+03 NA 0.0997100 NA
## max NA 4.251480e+05 NA 9.5100300 NA
## range NA 4.238240e+05 NA 9.4103200 NA
## sum NA 5.082870e+05 NA 32.3108300 NA
## median NA 1.292000e+04 NA 2.8538200 NA
## mean NA 5.647633e+04 NA 3.5900922 NA
## SE.mean NA 4.619791e+04 NA 1.1170543 NA
## CI.mean.0.95 NA 1.065326e+05 NA 2.5759318 NA
## var NA 1.920822e+10 NA 11.2302922 NA
## std.dev NA 1.385937e+05 NA 3.3511628 NA
## coef.var NA 2.454014e+00 NA 0.9334476 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 9.00000000 9.000000e+00 NA NA NA
## nbr.null 0.00000000 0.000000e+00 NA NA NA
## nbr.na 0.00000000 0.000000e+00 NA NA NA
## min 18.53690000 -9.746470e+01 NA NA NA
## max 20.50040000 -9.631490e+01 NA NA NA
## range 1.96350000 1.149800e+00 NA NA NA
## sum 175.38730000 -8.729500e+02 NA NA NA
## median 19.54260000 -9.704740e+01 NA NA NA
## mean 19.48747778 -9.699444e+01 NA NA NA
## SE.mean 0.19084238 1.114103e-01 NA NA NA
## CI.mean.0.95 0.44008331 2.569127e-01 NA NA NA
## var 0.32778731 1.117104e-01 NA NA NA
## std.dev 0.57252713 3.342310e-01 NA NA NA
## coef.var 0.02937923 -3.445878e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities
## nbr.val NA NA NA 2.0000000 9.0000000
## nbr.null NA NA NA 0.0000000 1.0000000
## nbr.na NA NA NA 7.0000000 0.0000000
## min NA NA NA 2.0000000 0.0000000
## max NA NA NA 8.0000000 14.0000000
## range NA NA NA 6.0000000 14.0000000
## sum NA NA NA 10.0000000 61.0000000
## median NA NA NA 5.0000000 7.0000000
## mean NA NA NA 5.0000000 6.7777778
## SE.mean NA NA NA 3.0000000 1.8240506
## CI.mean.0.95 NA NA NA 38.1186142 4.2062682
## var NA NA NA 18.0000000 29.9444444
## std.dev NA NA NA 4.2426407 5.4721517
## coef.var NA NA NA 0.8485281 0.8073666
## source_name source_link prop ypos
## nbr.val NA NA 9.0000000 9.0000000
## nbr.null NA NA 0.0000000 0.0000000
## nbr.na NA NA 0.0000000 0.0000000
## min NA NA 0.3085962 5.7745344
## max NA NA 29.4329486 99.2233564
## range NA NA 29.1243524 93.4488220
## sum NA NA 100.0000000 497.6369997
## median NA NA 8.8323946 59.0763376
## mean NA NA 11.1111111 55.2930000
## SE.mean NA NA 3.4572132 11.8683450
## CI.mean.0.95 NA NA 7.9723479 27.3684527
## var NA NA 107.5709066 1267.7185196
## std.dev NA NA 10.3716395 35.6050350
## coef.var NA NA 0.9334476 0.6439339boxplot(data, horizontal=TRUE, col='green')
Gráfico para El Salvador
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_ES <- subset(df, country_name == "El Salvador")
knitr::kable(head(df_ES))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 230 | 9/5/07 | NA | NA | El Salvador | SV | Ahuachapán | 7797 | Concepción de Ataco | 0.00273 | NA | 13.8703 | -89.8486 | (13.8703, -89.848600000000005) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Felix | NA | NA | Azcentral.com | http://www.azcentral.com/news/articles/1108sr-fhsistercity1109-ON.html |
| 564 | 6/2/08 | NA | NA | El Salvador | SV | La Libertad | 124694 | Santa Tecla | 4.96416 | NA | 13.7205 | -89.2687 | (13.720499999999999, -89.268699999999995) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Arthur | NA | NA | NA | http://news.xinhuanet.com/english/2008-06/04/content_8310737.htm |
| 1285 | 11/8/09 | NA | NA | El Salvador | SV | San Vicente | 41504 | San Vicente | 7.60946 | NA | 13.6409 | -88.8699 | (13.6409, -88.869900000000001) | Landslide | Complex | Very_large | Tropical cyclone | Tropical Cyclone Ida | NA | 23 | NA | http://www.google.com/hostednews/ap/article/ALeqM5j0XCCb1n12DyhoBoDzGj_hTyEtrAD9BRKPRG0 |
| 1286 | 11/8/09 | NA | NA | El Salvador | SV | La Libertad | 33767 | Antiguo Cuscatlán | 4.86219 | NA | 13.7156 | -89.2521 | (13.7156, -89.252099999999999) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Cyclone Ida | NA | 4 | NA | http://www.google.com/hostednews/ap/article/ALeqM5j0XCCb1n12DyhoBoDzGj_hTyEtrAD9BRKPRG0 |
| 1287 | 11/8/09 | NA | NA | El Salvador | SV | San Vicente | 41504 | San Vicente | 5.90726 | NA | 13.6094 | -88.8488 | (13.609400000000001, -88.848799999999997) | Landslide | Rockfall | Medium | Tropical cyclone | Tropical Cyclone Ida | NA | NA | NA | http://news.bbc.co.uk/2/hi/in_depth/8349333.stm |
| 1288 | 11/8/09 | NA | NA | El Salvador | SV | San Vicente | 41504 | San Vicente | 4.03125 | NA | 13.6466 | -88.8347 | (13.646599999999999, -88.834699999999998) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Cyclone Ida | NA | NA | NA | http://news.yahoo.com/s/afp/20091109/wl_afp/salvadorweatherstorm_20091109100952 |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_ES, aes(fill= state, y=distance, x=country_name)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_ES, aes(fill=state, y=distance, x=country_name)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_ES, aes(x=country_name, y=distance, fill=state)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_ES <- df_ES %>%
arrange(desc(state)) %>%
mutate(prop = distance / sum(df_ES$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_ES, aes(x=country_name, y=prop, fill=state)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_ES$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 4.23875 |
| 3.22235 |
| 0.49346 |
| 8.83210 |
| 1.15810 |
| 7.60946 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_ES$distance
names(distance) <- df_ES$state
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por estados"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## San Miguel 1.006695e+01 1.006695e+01 8.974011e+00 8.974011e+00
## San Miguel 9.972270e+00 2.003922e+01 8.889610e+00 1.786362e+01
## La Libertad 9.875530e+00 2.991475e+01 8.803373e+00 2.666699e+01
## Santa Ana 8.832100e+00 3.874685e+01 7.873225e+00 3.454022e+01
## Cabañas 8.825250e+00 4.757210e+01 7.867118e+00 4.240734e+01
## San Vicente 7.609460e+00 5.518156e+01 6.783323e+00 4.919066e+01
## San Miguel 6.945360e+00 6.212692e+01 6.191323e+00 5.538198e+01
## San Vicente 5.907260e+00 6.803418e+01 5.265926e+00 6.064791e+01
## Ahuachapán 5.299010e+00 7.333319e+01 4.723712e+00 6.537162e+01
## La Libertad 4.964160e+00 7.829735e+01 4.425216e+00 6.979684e+01
## La Libertad 4.862190e+00 8.315954e+01 4.334316e+00 7.413115e+01
## La Libertad 4.677220e+00 8.783676e+01 4.169428e+00 7.830058e+01
## La Libertad 4.606550e+00 9.244331e+01 4.106430e+00 8.240701e+01
## Sonsonate 4.238750e+00 9.668206e+01 3.778561e+00 8.618557e+01
## San Vicente 4.031250e+00 1.007133e+02 3.593589e+00 8.977916e+01
## San Salvador 3.252270e+00 1.039656e+02 2.899181e+00 9.267834e+01
## Sonsonate 3.222350e+00 1.071879e+02 2.872509e+00 9.555085e+01
## San Salvador 3.017390e+00 1.102053e+02 2.689801e+00 9.824065e+01
## Santa Ana 1.158100e+00 1.113634e+02 1.032368e+00 9.927302e+01
## Sonsonate 4.934600e-01 1.118569e+02 4.398865e-01 9.971291e+01
## La Paz 3.193300e-01 1.121762e+02 2.846613e-01 9.999757e+01
## Ahuachapán 2.730000e-03 1.121789e+02 2.433612e-03 1.000000e+02stem(df_ES$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 000133344
## 0 | 5555567899
## 1 | 000head(df_ES)## # A tibble: 6 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 6681 10/15/14 <NA> <NA> El Salvador SV Sons~ 7358
## 2 6682 10/15/14 <NA> <NA> El Salvador SV Sons~ 15446
## 3 7442 10/19/15 <NA> <NA> El Salvador SV Sons~ 9936
## 4 6685 10/12/14 <NA> <NA> El Salvador SV Sant~ 5773
## 5 7438 7/18/15 <NA> <NA> El Salvador SV Sant~ 10095
## 6 1285 11/8/09 <NA> <NA> El Salvador SV San ~ 41504
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_ES))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 6681 | 10/15/14 | NA | NA | El Salvador | SV | Sonsonate | 7358 | Nahuizalco | 4.23875 | Unknown | 13.7895 | -89.7739 | (13.7895, -89.773899999999998) | Landslide | Landslide | Medium | Continuous rain | NA | 0 | 0 | reliefweb | http://reliefweb.int/report/el-salvador/lluvias-causan-estragos-en-seis-departamentos | 3.7785613 | 1.889281 |
| 6682 | 10/15/14 | NA | NA | El Salvador | SV | Sonsonate | 15446 | Sonzacate | 3.22235 | Unknown | 13.7135 | -89.6938 | (13.7135, -89.693799999999996) | Landslide | Landslide | Medium | Continuous rain | NA | 0 | 0 | reliefweb | http://reliefweb.int/report/el-salvador/lluvias-causan-estragos-en-seis-departamentos | 2.8725089 | 5.214816 |
| 7442 | 10/19/15 | NA | NA | El Salvador | SV | Sonsonate | 9936 | Juayúa | 0.49346 | Unknown | 13.8457 | -89.7445 | (13.845700000000001, -89.744500000000002) | Landslide | Landslide | Medium | Downpour | NA | 1 | 0 | El Heraldo | http://www.elheraldo.hn/mundo/892045-217/cuatro-muertos-por-persistentes-lluvias-en-el-salvador | 0.4398865 | 6.871013 |
| 6685 | 10/12/14 | NA | NA | El Salvador | SV | Santa Ana | 5773 | Coatepeque | 8.83210 | Unknown | 14.0007 | -89.4691 | (14.0007, -89.469099999999997) | Landslide | Landslide | Medium | Rain | NA | 2 | 3 | Mexicano | http://www.oem.com.mx/elmexicano/notas/n3569793.htm | 7.8732247 | 11.027569 |
| 7438 | 7/18/15 | NA | NA | El Salvador | SV | Santa Ana | 10095 | Ciudad Arce | 1.15810 | Above road | 13.8464 | -89.4502 | (13.846399999999999, -89.450199999999995) | Landslide | Landslide | Small | Rain | NA | 0 | 0 | La Prensa | http://www.laprensagrafica.com/2015/07/18/lluvias-causan-derrumbe-en-carretera-a-santa-ana | 1.0323685 | 15.480366 |
| 1285 | 11/8/09 | NA | NA | El Salvador | SV | San Vicente | 41504 | San Vicente | 7.60946 | NA | 13.6409 | -88.8699 | (13.6409, -88.869900000000001) | Landslide | Complex | Very_large | Tropical cyclone | Tropical Cyclone Ida | NA | 23 | NA | http://www.google.com/hostednews/ap/article/ALeqM5j0XCCb1n12DyhoBoDzGj_hTyEtrAD9BRKPRG0 | 6.7833231 | 19.388211 |
stem(df_ES$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 000133344
## 0 | 5555567899
## 1 | 000stem(df_ES$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 0352
## 2 | 023
## 4 | 02679039
## 6 | 96
## 8 | 889
## 10 | 01Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.00273 | 1 | 4.5 | 4.5 | 4.5 | 4.5 |
| 0.31933 | 1 | 4.5 | 4.5 | 9.1 | 9.1 |
| 0.49346 | 1 | 4.5 | 4.5 | 13.6 | 13.6 |
| 1.1581 | 1 | 4.5 | 4.5 | 18.2 | 18.2 |
| 3.01739 | 1 | 4.5 | 4.5 | 22.7 | 22.7 |
| 3.22235 | 1 | 4.5 | 4.5 | 27.3 | 27.3 |
| 3.25227 | 1 | 4.5 | 4.5 | 31.8 | 31.8 |
| 4.03125 | 1 | 4.5 | 4.5 | 36.4 | 36.4 |
| 4.23875 | 1 | 4.5 | 4.5 | 40.9 | 40.9 |
| 4.60655 | 1 | 4.5 | 4.5 | 45.5 | 45.5 |
| 4.67722 | 1 | 4.5 | 4.5 | 50.0 | 50.0 |
| 4.86219 | 1 | 4.5 | 4.5 | 54.5 | 54.5 |
| 4.96416 | 1 | 4.5 | 4.5 | 59.1 | 59.1 |
| 5.29901 | 1 | 4.5 | 4.5 | 63.6 | 63.6 |
| 5.90726 | 1 | 4.5 | 4.5 | 68.2 | 68.2 |
| 6.94536 | 1 | 4.5 | 4.5 | 72.7 | 72.7 |
| 7.60946 | 1 | 4.5 | 4.5 | 77.3 | 77.3 |
| 8.82525 | 1 | 4.5 | 4.5 | 81.8 | 81.8 |
| 8.8321 | 1 | 4.5 | 4.5 | 86.4 | 86.4 |
| 9.87553 | 1 | 4.5 | 4.5 | 90.9 | 90.9 |
| 9.97227 | 1 | 4.5 | 4.5 | 95.5 | 95.5 |
| 10.06695 | 1 | 4.5 | 4.5 | 100.0 | 100.0 |
| Total | 22 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 23 obs. of 5 variables:
## $ n : num 1 1 1 1 1 1 1 1 1 1 ...
## $ % : num 4.5 4.5 4.5 4.5 4.5 4.5 4.5 4.5 4.5 4.5 ...
## $ val% : num 4.5 4.5 4.5 4.5 4.5 4.5 4.5 4.5 4.5 4.5 ...
## $ %cum : num 4.5 9.1 13.6 18.2 22.7 27.3 31.8 36.4 40.9 45.5 ...
## $ val%cum: num 4.5 9.1 13.6 18.2 22.7 27.3 31.8 36.4 40.9 45.5 ...x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.00273 | 1 |
| 0.31933 | 1 |
| 0.49346 | 1 |
| 1.1581 | 1 |
| 3.01739 | 1 |
| 3.22235 | 1 |
| 3.25227 | 1 |
| 4.03125 | 1 |
| 4.23875 | 1 |
| 4.60655 | 1 |
| 4.67722 | 1 |
| 4.86219 | 1 |
| 4.96416 | 1 |
| 5.29901 | 1 |
| 5.90726 | 1 |
| 6.94536 | 1 |
| 7.60946 | 1 |
| 8.82525 | 1 |
| 8.8321 | 1 |
| 9.87553 | 1 |
| 9.97227 | 1 |
| 10.06695 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.00273 3.00273 6.00273 9.00273 12.00273distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.00273,3] | 3 | 0.1428571 | 3 |
| (3,6] | 11 | 0.5238095 | 14 |
| (6,9] | 4 | 0.1904762 | 18 |
| (9,12] | 3 | 0.1428571 | 21 |
str(Freq_table)## 'data.frame': 4 obs. of 4 variables:
## $ distance: Factor w/ 4 levels "(0.00273,3]",..: 1 2 3 4
## $ Freq : int 3 11 4 3
## $ Rel_Freq: num 0.143 0.524 0.19 0.143
## $ Cum_Freq: int 3 14 18 21df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.00273,3] | 3 |
| (3,6] | 11 |
| (6,9] | 4 |
| (9,12] | 3 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_ES)## id date time continent_code country_name country_code
## nbr.val 2.200000e+01 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 2.300000e+02 NA NA NA NA NA
## max 7.442000e+03 NA NA NA NA NA
## range 7.212000e+03 NA NA NA NA NA
## sum 1.086050e+05 NA NA NA NA NA
## median 6.680000e+03 NA NA NA NA NA
## mean 4.936591e+03 NA NA NA NA NA
## SE.mean 5.803080e+02 NA NA NA NA NA
## CI.mean.0.95 1.206817e+03 NA NA NA NA NA
## var 7.408663e+06 NA NA NA NA NA
## std.dev 2.721886e+03 NA NA NA NA NA
## coef.var 5.513696e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 2.200000e+01 NA 22.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 2.654000e+03 NA 0.0027300 NA
## max NA 1.246940e+05 NA 10.0669500 NA
## range NA 1.220400e+05 NA 10.0642200 NA
## sum NA 9.383360e+05 NA 112.1789400 NA
## median NA 2.643100e+04 NA 4.7697050 NA
## mean NA 4.265164e+04 NA 5.0990427 NA
## SE.mean NA 9.849090e+03 NA 0.6720603 NA
## CI.mean.0.95 NA 2.048230e+04 NA 1.3976259 NA
## var NA 2.134100e+09 NA 9.9366315 NA
## std.dev NA 4.619633e+04 NA 3.1522423 NA
## coef.var NA 1.083108e+00 NA 0.6182028 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 22.00000000 2.200000e+01 NA NA NA
## nbr.null 0.00000000 0.000000e+00 NA NA NA
## nbr.na 0.00000000 0.000000e+00 NA NA NA
## min 13.28170000 -8.990440e+01 NA NA NA
## max 14.00070000 -8.808430e+01 NA NA NA
## range 0.71900000 1.820100e+00 NA NA NA
## sum 301.25530000 -1.961688e+03 NA NA NA
## median 13.71515000 -8.926030e+01 NA NA NA
## mean 13.69342273 -8.916765e+01 NA NA NA
## SE.mean 0.03809807 1.112458e-01 NA NA NA
## CI.mean.0.95 0.07922927 2.313484e-01 NA NA NA
## var 0.03193218 2.722640e-01 NA NA NA
## std.dev 0.17869578 5.217892e-01 NA NA NA
## coef.var 0.01304975 -5.851777e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities
## nbr.val NA NA NA 14.0000000 18.000000
## nbr.null NA NA NA 10.0000000 13.000000
## nbr.na NA NA NA 8.0000000 4.000000
## min NA NA NA 0.0000000 0.000000
## max NA NA NA 2.0000000 32.000000
## range NA NA NA 2.0000000 32.000000
## sum NA NA NA 6.0000000 63.000000
## median NA NA NA 0.0000000 0.000000
## mean NA NA NA 0.4285714 3.500000
## SE.mean NA NA NA 0.2020305 2.107022
## CI.mean.0.95 NA NA NA 0.4364604 4.445428
## var NA NA NA 0.5714286 79.911765
## std.dev NA NA NA 0.7559289 8.939338
## coef.var NA NA NA 1.7638342 2.554097
## source_name source_link prop ypos
## nbr.val NA NA 2.200000e+01 22.0000000
## nbr.null NA NA 0.000000e+00 0.0000000
## nbr.na NA NA 0.000000e+00 0.0000000
## min NA NA 2.433612e-03 1.8892806
## max NA NA 8.974011e+00 97.6381440
## range NA NA 8.971577e+00 95.7488634
## sum NA NA 1.000000e+02 1038.4834890
## median NA NA 4.251872e+00 44.1153638
## mean NA NA 4.545455e+00 47.2037950
## SE.mean NA NA 5.990967e-01 6.6246536
## CI.mean.0.95 NA NA 1.245890e+00 13.7767213
## var NA NA 7.896171e+00 965.4927696
## std.dev NA NA 2.810013e+00 31.0723795
## coef.var NA NA 6.182028e-01 0.6582602boxplot(data, horizontal=TRUE, col='green')
Gráfico para La Libertad (El Salvador)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_ES <- subset(df, country_name == "El Salvador")
knitr::kable(head(df_ES)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 230 | 9/5/07 | NA | NA | El Salvador | SV | Ahuachapán | 7797 | Concepción de Ataco | 0.00273 | NA | 13.8703 | -89.8486 | (13.8703, -89.848600000000005) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Felix | NA | NA | Azcentral.com | http://www.azcentral.com/news/articles/1108sr-fhsistercity1109-ON.html |
| 564 | 6/2/08 | NA | NA | El Salvador | SV | La Libertad | 124694 | Santa Tecla | 4.96416 | NA | 13.7205 | -89.2687 | (13.720499999999999, -89.268699999999995) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Arthur | NA | NA | NA | http://news.xinhuanet.com/english/2008-06/04/content_8310737.htm |
| 1285 | 11/8/09 | NA | NA | El Salvador | SV | San Vicente | 41504 | San Vicente | 7.60946 | NA | 13.6409 | -88.8699 | (13.6409, -88.869900000000001) | Landslide | Complex | Very_large | Tropical cyclone | Tropical Cyclone Ida | NA | 23 | NA | http://www.google.com/hostednews/ap/article/ALeqM5j0XCCb1n12DyhoBoDzGj_hTyEtrAD9BRKPRG0 |
| 1286 | 11/8/09 | NA | NA | El Salvador | SV | La Libertad | 33767 | Antiguo Cuscatlán | 4.86219 | NA | 13.7156 | -89.2521 | (13.7156, -89.252099999999999) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Cyclone Ida | NA | 4 | NA | http://www.google.com/hostednews/ap/article/ALeqM5j0XCCb1n12DyhoBoDzGj_hTyEtrAD9BRKPRG0 |
| 1287 | 11/8/09 | NA | NA | El Salvador | SV | San Vicente | 41504 | San Vicente | 5.90726 | NA | 13.6094 | -88.8488 | (13.609400000000001, -88.848799999999997) | Landslide | Rockfall | Medium | Tropical cyclone | Tropical Cyclone Ida | NA | NA | NA | http://news.bbc.co.uk/2/hi/in_depth/8349333.stm |
| 1288 | 11/8/09 | NA | NA | El Salvador | SV | San Vicente | 41504 | San Vicente | 4.03125 | NA | 13.6466 | -88.8347 | (13.646599999999999, -88.834699999999998) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Cyclone Ida | NA | NA | NA | http://news.yahoo.com/s/afp/20091109/wl_afp/salvadorweatherstorm_20091109100952 |
library(dplyr)
df_ES <- subset(df, state == "La Libertad")
knitr::kable(head(df_ES))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 564 | 6/2/08 | NA | NA | El Salvador | SV | La Libertad | 124694 | Santa Tecla | 4.96416 | NA | 13.7205 | -89.2687 | (13.720499999999999, -89.268699999999995) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Arthur | NA | NA | NA | http://news.xinhuanet.com/english/2008-06/04/content_8310737.htm |
| 1004 | 4/14/09 | NA | SA | Peru | PE | La Libertad | 0 | Parcoy | 9.64894 | NA | -7.9589 | -77.5239 | (-7.9588999999999999, -77.523899999999998) | Landslide | Mudslide | Medium | Downpour | NA | NA | 12 | NA | http://rawstory.com/news/afp/Nine_dead_in_Peru_mudslides_04142009.html |
| 1005 | 4/14/09 | NA | SA | Peru | PE | La Libertad | 0 | Aricapampa | 0.00442 | NA | -7.8058 | -77.7172 | (-7.8057999999999996, -77.717200000000005) | Landslide | Mudslide | Medium | Downpour | NA | NA | 0 | NA | http://rawstory.com/news/afp/Nine_dead_in_Peru_mudslides_04142009.html |
| 1286 | 11/8/09 | NA | NA | El Salvador | SV | La Libertad | 33767 | Antiguo Cuscatlán | 4.86219 | NA | 13.7156 | -89.2521 | (13.7156, -89.252099999999999) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Cyclone Ida | NA | 4 | NA | http://www.google.com/hostednews/ap/article/ALeqM5j0XCCb1n12DyhoBoDzGj_hTyEtrAD9BRKPRG0 |
| 6686 | 10/12/14 | NA | NA | El Salvador | SV | La Libertad | 124694 | Santa Tecla | 4.60655 | Above road | 13.6905 | -89.3200 | (13.6905, -89.32) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | Mexicano | http://www.oem.com.mx/elmexicano/notas/n3569793.htm |
| 7440 | 11/3/15 | 1:00 | NA | El Salvador | SV | La Libertad | 124694 | Santa Tecla | 4.67722 | Unknown | 13.7178 | -89.2685 | (13.7178, -89.268500000000003) | Landslide | Mudslide | Medium | Rain | NA | 0 | 0 | El Salvador Noticias | http://www.elsalvadornoticias.net/2015/11/03/deslave-en-colonia-escalon-por-desborde-quebrada-las-lajas/ |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_ES, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_ES, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_ES, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_ES <- df_ES %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_ES$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_ES, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_ES$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 4.96416 |
| 4.60655 |
| 4.67722 |
| 9.87553 |
| 9.64894 |
| 0.00442 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_ES$distance
names(distance) <- df_ES$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Santa Tecla 9.87553000 9.87553000 25.55844469 25.55844469
## Parcoy 9.64894000 19.52447000 24.97201662 50.53046131
## Santa Tecla 4.96416000 24.48863000 12.84753414 63.37799545
## Antiguo Cuscatlán 4.86219000 29.35082000 12.58362986 75.96162531
## Santa Tecla 4.67722000 34.02804000 12.10491677 88.06654208
## Santa Tecla 4.60655000 38.63459000 11.92201871 99.98856078
## Aricapampa 0.00442000 38.63901000 0.01143922 100.00000000stem(df_ES$"distance")##
## The decimal point is at the |
##
## 0 | 0
## 2 |
## 4 | 6790
## 6 |
## 8 | 69head(df_ES)## # A tibble: 6 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 564 6/2/08 <NA> <NA> El Salvador SV La L~ 124694
## 2 6686 10/12/14 <NA> <NA> El Salvador SV La L~ 124694
## 3 7440 11/3/15 1:00 <NA> El Salvador SV La L~ 124694
## 4 7441 11/4/15 <NA> <NA> El Salvador SV La L~ 124694
## 5 1004 4/14/09 <NA> SA Peru PE La L~ 0
## 6 1005 4/14/09 <NA> SA Peru PE La L~ 0
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_ES))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 564 | 6/2/08 | NA | NA | El Salvador | SV | La Libertad | 124694 | Santa Tecla | 4.96416 | NA | 13.7205 | -89.2687 | (13.720499999999999, -89.268699999999995) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Arthur | NA | NA | NA | http://news.xinhuanet.com/english/2008-06/04/content_8310737.htm | 12.8475341 | 6.423767 |
| 6686 | 10/12/14 | NA | NA | El Salvador | SV | La Libertad | 124694 | Santa Tecla | 4.60655 | Above road | 13.6905 | -89.3200 | (13.6905, -89.32) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | Mexicano | http://www.oem.com.mx/elmexicano/notas/n3569793.htm | 11.9220187 | 18.808543 |
| 7440 | 11/3/15 | 1:00 | NA | El Salvador | SV | La Libertad | 124694 | Santa Tecla | 4.67722 | Unknown | 13.7178 | -89.2685 | (13.7178, -89.268500000000003) | Landslide | Mudslide | Medium | Rain | NA | 0 | 0 | El Salvador Noticias | http://www.elsalvadornoticias.net/2015/11/03/deslave-en-colonia-escalon-por-desborde-quebrada-las-lajas/ | 12.1049168 | 30.822011 |
| 7441 | 11/4/15 | NA | NA | El Salvador | SV | La Libertad | 124694 | Santa Tecla | 9.87553 | Retaining wall | 13.7147 | -89.3625 | (13.714700000000001, -89.362499999999997) | Landslide | Other | Small | Rain | NA | 1 | 0 | Tele El Salvador | http://www.teleelsalvador.com/noticias/deslaves-en-colonia-escalon-dejan-carros-danados-y-calles-cerradas/ | 25.5584447 | 49.653692 |
| 1004 | 4/14/09 | NA | SA | Peru | PE | La Libertad | 0 | Parcoy | 9.64894 | NA | -7.9589 | -77.5239 | (-7.9588999999999999, -77.523899999999998) | Landslide | Mudslide | Medium | Downpour | NA | NA | 12 | NA | http://rawstory.com/news/afp/Nine_dead_in_Peru_mudslides_04142009.html | 24.9720166 | 74.918923 |
| 1005 | 4/14/09 | NA | SA | Peru | PE | La Libertad | 0 | Aricapampa | 0.00442 | NA | -7.8058 | -77.7172 | (-7.8057999999999996, -77.717200000000005) | Landslide | Mudslide | Medium | Downpour | NA | NA | 0 | NA | http://rawstory.com/news/afp/Nine_dead_in_Peru_mudslides_04142009.html | 0.0114392 | 87.410651 |
stem(df_ES$"distance")##
## The decimal point is at the |
##
## 0 | 0
## 2 |
## 4 | 6790
## 6 |
## 8 | 69stem(df_ES$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 0
## 1 |
## 2 |
## 3 |
## 4 | 679
## 5 | 0
## 6 |
## 7 |
## 8 |
## 9 | 69Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.00442 | 1 | 14.3 | 14.3 | 14.3 | 14.3 |
| 4.60655 | 1 | 14.3 | 14.3 | 28.6 | 28.6 |
| 4.67722 | 1 | 14.3 | 14.3 | 42.9 | 42.9 |
| 4.86219 | 1 | 14.3 | 14.3 | 57.1 | 57.1 |
| 4.96416 | 1 | 14.3 | 14.3 | 71.4 | 71.4 |
| 9.64894 | 1 | 14.3 | 14.3 | 85.7 | 85.7 |
| 9.87553 | 1 | 14.3 | 14.3 | 100.0 | 100.0 |
| Total | 7 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 8 obs. of 5 variables:
## $ n : num 1 1 1 1 1 1 1 7
## $ % : num 14.3 14.3 14.3 14.3 14.3 14.3 14.3 100
## $ val% : num 14.3 14.3 14.3 14.3 14.3 14.3 14.3 100
## $ %cum : num 14.3 28.6 42.9 57.1 71.4 85.7 100 100
## $ val%cum: num 14.3 28.6 42.9 57.1 71.4 85.7 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.00442 | 1 |
| 4.60655 | 1 |
| 4.67722 | 1 |
| 4.86219 | 1 |
| 4.96416 | 1 |
| 9.64894 | 1 |
| 9.87553 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.00442 4.00442 8.00442 12.00442distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.00442,4] | 0 | 0.0000000 | 0 |
| (4,8] | 4 | 0.6666667 | 4 |
| (8,12] | 2 | 0.3333333 | 6 |
str(Freq_table)## 'data.frame': 3 obs. of 4 variables:
## $ distance: Factor w/ 3 levels "(0.00442,4]",..: 1 2 3
## $ Freq : int 0 4 2
## $ Rel_Freq: num 0 0.667 0.333
## $ Cum_Freq: int 0 4 6df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.00442,4] | 0 |
| (4,8] | 4 |
| (8,12] | 2 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_ES)## id date time continent_code country_name country_code
## nbr.val 7.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 5.640000e+02 NA NA NA NA NA
## max 7.441000e+03 NA NA NA NA NA
## range 6.877000e+03 NA NA NA NA NA
## sum 2.542600e+04 NA NA NA NA NA
## median 1.286000e+03 NA NA NA NA NA
## mean 3.632286e+03 NA NA NA NA NA
## SE.mean 1.263594e+03 NA NA NA NA NA
## CI.mean.0.95 3.091903e+03 NA NA NA NA NA
## var 1.117669e+07 NA NA NA NA NA
## std.dev 3.343155e+03 NA NA NA NA NA
## coef.var 9.203998e-01 NA NA NA NA NA
## state population city distance location_description latitude
## nbr.val NA 7.000000e+00 NA 7.0000000 NA 7.000000
## nbr.null NA 2.000000e+00 NA 0.0000000 NA 0.000000
## nbr.na NA 0.000000e+00 NA 0.0000000 NA 0.000000
## min NA 0.000000e+00 NA 0.0044200 NA -7.958900
## max NA 1.246940e+05 NA 9.8755300 NA 13.720500
## range NA 1.246940e+05 NA 9.8711100 NA 21.679400
## sum NA 5.325430e+05 NA 38.6390100 NA 52.794400
## median NA 1.246940e+05 NA 4.8621900 NA 13.714700
## mean NA 7.607757e+04 NA 5.5198586 NA 7.542057
## SE.mean NA 2.330952e+04 NA 1.2791994 NA 3.982602
## CI.mean.0.95 NA 5.703633e+04 NA 3.1300883 NA 9.745075
## var NA 3.803334e+09 NA 11.4544585 NA 111.027808
## std.dev NA 6.167118e+04 NA 3.3844436 NA 10.536973
## coef.var NA 8.106355e-01 NA 0.6131395 NA 1.397095
## longitude geolocation hazard_type landslide_type
## nbr.val 7.00000000 NA NA NA
## nbr.null 0.00000000 NA NA NA
## nbr.na 0.00000000 NA NA NA
## min -89.36250000 NA NA NA
## max -77.52390000 NA NA NA
## range 11.83860000 NA NA NA
## sum -601.71290000 NA NA NA
## median -89.26850000 NA NA NA
## mean -85.95898571 NA NA NA
## SE.mean 2.15312466 NA NA NA
## CI.mean.0.95 5.26850626 NA NA NA
## var 32.45162074 NA NA NA
## std.dev 5.69663240 NA NA NA
## coef.var -0.06627152 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 3.0000000 6.000000 NA
## nbr.null NA NA NA 2.0000000 4.000000 NA
## nbr.na NA NA NA 4.0000000 1.000000 NA
## min NA NA NA 0.0000000 0.000000 NA
## max NA NA NA 1.0000000 12.000000 NA
## range NA NA NA 1.0000000 12.000000 NA
## sum NA NA NA 1.0000000 16.000000 NA
## median NA NA NA 0.0000000 0.000000 NA
## mean NA NA NA 0.3333333 2.666667 NA
## SE.mean NA NA NA 0.3333333 1.977653 NA
## CI.mean.0.95 NA NA NA 1.4342176 5.083719 NA
## var NA NA NA 0.3333333 23.466667 NA
## std.dev NA NA NA 0.5773503 4.844241 NA
## coef.var NA NA NA 1.7320508 1.816590 NA
## source_link prop ypos
## nbr.val NA 7.00000000 7.0000000
## nbr.null NA 0.00000000 0.0000000
## nbr.na NA 0.00000000 0.0000000
## min NA 0.01143922 6.4237671
## max NA 25.55844469 93.7081851
## range NA 25.54700547 87.2844180
## sum NA 100.00000000 361.7457720
## median NA 12.58362986 49.6536920
## mean NA 14.28571429 51.6779674
## SE.mean NA 3.31064238 13.0483680
## CI.mean.0.95 NA 8.10085008 31.9282063
## var NA 76.72247089 1191.8193525
## std.dev NA 8.75913642 34.5227367
## coef.var NA 0.61313955 0.6680359boxplot(data, horizontal=TRUE, col='green')
Gráfico para La Paz (El Salvador)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_ES <- subset(df, country_name == "El Salvador")
knitr::kable(head(df_ES)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 230 | 9/5/07 | NA | NA | El Salvador | SV | Ahuachapán | 7797 | Concepción de Ataco | 0.00273 | NA | 13.8703 | -89.8486 | (13.8703, -89.848600000000005) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Felix | NA | NA | Azcentral.com | http://www.azcentral.com/news/articles/1108sr-fhsistercity1109-ON.html |
| 564 | 6/2/08 | NA | NA | El Salvador | SV | La Libertad | 124694 | Santa Tecla | 4.96416 | NA | 13.7205 | -89.2687 | (13.720499999999999, -89.268699999999995) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Arthur | NA | NA | NA | http://news.xinhuanet.com/english/2008-06/04/content_8310737.htm |
| 1285 | 11/8/09 | NA | NA | El Salvador | SV | San Vicente | 41504 | San Vicente | 7.60946 | NA | 13.6409 | -88.8699 | (13.6409, -88.869900000000001) | Landslide | Complex | Very_large | Tropical cyclone | Tropical Cyclone Ida | NA | 23 | NA | http://www.google.com/hostednews/ap/article/ALeqM5j0XCCb1n12DyhoBoDzGj_hTyEtrAD9BRKPRG0 |
| 1286 | 11/8/09 | NA | NA | El Salvador | SV | La Libertad | 33767 | Antiguo Cuscatlán | 4.86219 | NA | 13.7156 | -89.2521 | (13.7156, -89.252099999999999) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Cyclone Ida | NA | 4 | NA | http://www.google.com/hostednews/ap/article/ALeqM5j0XCCb1n12DyhoBoDzGj_hTyEtrAD9BRKPRG0 |
| 1287 | 11/8/09 | NA | NA | El Salvador | SV | San Vicente | 41504 | San Vicente | 5.90726 | NA | 13.6094 | -88.8488 | (13.609400000000001, -88.848799999999997) | Landslide | Rockfall | Medium | Tropical cyclone | Tropical Cyclone Ida | NA | NA | NA | http://news.bbc.co.uk/2/hi/in_depth/8349333.stm |
| 1288 | 11/8/09 | NA | NA | El Salvador | SV | San Vicente | 41504 | San Vicente | 4.03125 | NA | 13.6466 | -88.8347 | (13.646599999999999, -88.834699999999998) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Cyclone Ida | NA | NA | NA | http://news.yahoo.com/s/afp/20091109/wl_afp/salvadorweatherstorm_20091109100952 |
library(dplyr)
df_ES <- subset(df, state == "La Paz")
knitr::kable(head(df_ES))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 6683 | 10/15/14 | NA | NA | El Salvador | SV | La Paz | 2654 | San Pedro Masahuat | 0.31933 | Above river | 13.5461 | -89.0401 | (13.546099999999999, -89.040099999999995) | Landslide | Landslide | Medium | Continuous rain | NA | 0 | 0 | reliefweb | http://reliefweb.int/report/el-salvador/lluvias-causan-estragos-en-seis-departamentos |
| 7460 | 9/25/15 | NA | NA | Honduras | HN | La Paz | 1463 | San José | 4.69133 | Unknown | 14.2801 | -87.9369 | (14.280099999999999, -87.936899999999994) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | Tiempo | http://www.tiempo.hn/lluvias-comienzan-a-causar-deslizamientos-en-carreteras-del-occidente-de-honduras/ |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_ES, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_ES, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_ES, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_ES <- df_ES %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_ES$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_ES, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_ES$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 0.31933 |
| 4.69133 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_ES$distance
names(distance) <- df_ES$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## San José 4.691330 4.691330 93.626987 93.626987
## San Pedro Masahuat 0.319330 5.010660 6.373013 100.000000stem(df_ES$"distance")##
## The decimal point is at the |
##
## 0 | 3
## 1 |
## 2 |
## 3 |
## 4 | 7head(df_ES)## # A tibble: 2 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 6683 10/15/14 <NA> <NA> El Salvador SV La Paz 2654
## 2 7460 9/25/15 <NA> <NA> Honduras HN La Paz 1463
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_ES))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 6683 | 10/15/14 | NA | NA | El Salvador | SV | La Paz | 2654 | San Pedro Masahuat | 0.31933 | Above river | 13.5461 | -89.0401 | (13.546099999999999, -89.040099999999995) | Landslide | Landslide | Medium | Continuous rain | NA | 0 | 0 | reliefweb | http://reliefweb.int/report/el-salvador/lluvias-causan-estragos-en-seis-departamentos | 6.373013 | 3.186506 |
| 7460 | 9/25/15 | NA | NA | Honduras | HN | La Paz | 1463 | San José | 4.69133 | Unknown | 14.2801 | -87.9369 | (14.280099999999999, -87.936899999999994) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | Tiempo | http://www.tiempo.hn/lluvias-comienzan-a-causar-deslizamientos-en-carreteras-del-occidente-de-honduras/ | 93.626987 | 53.186506 |
stem(df_ES$"distance")##
## The decimal point is at the |
##
## 0 | 3
## 1 |
## 2 |
## 3 |
## 4 | 7stem(df_ES$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 3
## 0 |
## 1 |
## 1 |
## 2 |
## 2 |
## 3 |
## 3 |
## 4 |
## 4 | 7Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.31933 | 1 | 50 | 50 | 50 | 50 |
| 4.69133 | 1 | 50 | 50 | 100 | 100 |
| Total | 2 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 3 obs. of 5 variables:
## $ n : num 1 1 2
## $ % : num 50 50 100
## $ val% : num 50 50 100
## $ %cum : num 50 100 100
## $ val%cum: num 50 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.31933 | 1 |
| 4.69133 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.31933 3.31933 6.31933distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.319,3.32] | 0 | 0 | 0 |
| (3.32,6.32] | 1 | 1 | 1 |
str(Freq_table)## 'data.frame': 2 obs. of 4 variables:
## $ distance: Factor w/ 2 levels "(0.319,3.32]",..: 1 2
## $ Freq : int 0 1
## $ Rel_Freq: num 0 1
## $ Cum_Freq: int 0 1df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.319,3.32] | 0 |
| (3.32,6.32] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_ES)## id date time continent_code country_name country_code
## nbr.val 2.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 6.683000e+03 NA NA NA NA NA
## max 7.460000e+03 NA NA NA NA NA
## range 7.770000e+02 NA NA NA NA NA
## sum 1.414300e+04 NA NA NA NA NA
## median 7.071500e+03 NA NA NA NA NA
## mean 7.071500e+03 NA NA NA NA NA
## SE.mean 3.885000e+02 NA NA NA NA NA
## CI.mean.0.95 4.936361e+03 NA NA NA NA NA
## var 3.018645e+05 NA NA NA NA NA
## std.dev 5.494220e+02 NA NA NA NA NA
## coef.var 7.769525e-02 NA NA NA NA NA
## state population city distance location_description latitude
## nbr.val NA 2.000000e+00 NA 2.000000 NA 2.00000000
## nbr.null NA 0.000000e+00 NA 0.000000 NA 0.00000000
## nbr.na NA 0.000000e+00 NA 0.000000 NA 0.00000000
## min NA 1.463000e+03 NA 0.319330 NA 13.54610000
## max NA 2.654000e+03 NA 4.691330 NA 14.28010000
## range NA 1.191000e+03 NA 4.372000 NA 0.73400000
## sum NA 4.117000e+03 NA 5.010660 NA 27.82620000
## median NA 2.058500e+03 NA 2.505330 NA 13.91310000
## mean NA 2.058500e+03 NA 2.505330 NA 13.91310000
## SE.mean NA 5.955000e+02 NA 2.186000 NA 0.36700000
## CI.mean.0.95 NA 7.566545e+03 NA 27.775764 NA 4.66317714
## var NA 7.092405e+05 NA 9.557192 NA 0.26937800
## std.dev NA 8.421642e+02 NA 3.091471 NA 0.51901638
## coef.var NA 4.091155e-01 NA 1.233958 NA 0.03730415
## longitude geolocation hazard_type landslide_type
## nbr.val 2.000000e+00 NA NA NA
## nbr.null 0.000000e+00 NA NA NA
## nbr.na 0.000000e+00 NA NA NA
## min -8.904010e+01 NA NA NA
## max -8.793690e+01 NA NA NA
## range 1.103200e+00 NA NA NA
## sum -1.769770e+02 NA NA NA
## median -8.848850e+01 NA NA NA
## mean -8.848850e+01 NA NA NA
## SE.mean 5.516000e-01 NA NA NA
## CI.mean.0.95 7.008743e+00 NA NA NA
## var 6.085251e-01 NA NA NA
## std.dev 7.800802e-01 NA NA NA
## coef.var -8.815611e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 2 2 NA
## nbr.null NA NA NA 2 2 NA
## nbr.na NA NA NA 0 0 NA
## min NA NA NA 0 0 NA
## max NA NA NA 0 0 NA
## range NA NA NA 0 0 NA
## sum NA NA NA 0 0 NA
## median NA NA NA 0 0 NA
## mean NA NA NA 0 0 NA
## SE.mean NA NA NA 0 0 NA
## CI.mean.0.95 NA NA NA 0 0 NA
## var NA NA NA 0 0 NA
## std.dev NA NA NA 0 0 NA
## coef.var NA NA NA NaN NaN NA
## source_link prop ypos
## nbr.val NA 2.000000 2.000000
## nbr.null NA 0.000000 0.000000
## nbr.na NA 0.000000 0.000000
## min NA 6.373013 3.186506
## max NA 93.626987 53.186506
## range NA 87.253975 50.000000
## sum NA 100.000000 56.373013
## median NA 50.000000 28.186506
## mean NA 50.000000 28.186506
## SE.mean NA 43.626987 25.000000
## CI.mean.0.95 NA 554.333432 317.655118
## var NA 3806.628035 1250.000000
## std.dev NA 61.697877 35.355339
## coef.var NA 1.233958 1.254336boxplot(data, horizontal=TRUE, col='green')
Gráfico para San Miguel (El Salvador)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_ES <- subset(df, country_name == "El Salvador")
knitr::kable(head(df_ES)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 230 | 9/5/07 | NA | NA | El Salvador | SV | Ahuachapán | 7797 | Concepción de Ataco | 0.00273 | NA | 13.8703 | -89.8486 | (13.8703, -89.848600000000005) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Felix | NA | NA | Azcentral.com | http://www.azcentral.com/news/articles/1108sr-fhsistercity1109-ON.html |
| 564 | 6/2/08 | NA | NA | El Salvador | SV | La Libertad | 124694 | Santa Tecla | 4.96416 | NA | 13.7205 | -89.2687 | (13.720499999999999, -89.268699999999995) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Arthur | NA | NA | NA | http://news.xinhuanet.com/english/2008-06/04/content_8310737.htm |
| 1285 | 11/8/09 | NA | NA | El Salvador | SV | San Vicente | 41504 | San Vicente | 7.60946 | NA | 13.6409 | -88.8699 | (13.6409, -88.869900000000001) | Landslide | Complex | Very_large | Tropical cyclone | Tropical Cyclone Ida | NA | 23 | NA | http://www.google.com/hostednews/ap/article/ALeqM5j0XCCb1n12DyhoBoDzGj_hTyEtrAD9BRKPRG0 |
| 1286 | 11/8/09 | NA | NA | El Salvador | SV | La Libertad | 33767 | Antiguo Cuscatlán | 4.86219 | NA | 13.7156 | -89.2521 | (13.7156, -89.252099999999999) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Cyclone Ida | NA | 4 | NA | http://www.google.com/hostednews/ap/article/ALeqM5j0XCCb1n12DyhoBoDzGj_hTyEtrAD9BRKPRG0 |
| 1287 | 11/8/09 | NA | NA | El Salvador | SV | San Vicente | 41504 | San Vicente | 5.90726 | NA | 13.6094 | -88.8488 | (13.609400000000001, -88.848799999999997) | Landslide | Rockfall | Medium | Tropical cyclone | Tropical Cyclone Ida | NA | NA | NA | http://news.bbc.co.uk/2/hi/in_depth/8349333.stm |
| 1288 | 11/8/09 | NA | NA | El Salvador | SV | San Vicente | 41504 | San Vicente | 4.03125 | NA | 13.6466 | -88.8347 | (13.646599999999999, -88.834699999999998) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Cyclone Ida | NA | NA | NA | http://news.yahoo.com/s/afp/20091109/wl_afp/salvadorweatherstorm_20091109100952 |
library(dplyr)
df_ES <- subset(df, state == "San Miguel")
knitr::kable(head(df_ES))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 6251 | 10/13/14 | Night | NA | El Salvador | SV | San Miguel | 6393 | Chirilagua | 6.94536 | Above road | 13.2817 | -88.1253 | (13.281700000000001, -88.125299999999996) | Landslide | Rockfall | Small | Earthquake | NA | 0 | 0 | elsalvador.com | http://www.elsalvador.com/mwedh/nota/nota_completa.asp?idCat=47859&idArt=9167407 |
| 6675 | 5/22/14 | Night | NA | El Salvador | SV | San Miguel | 19095 | San Rafael Oriente | 10.06695 | Unknown | 13.4379 | -88.2756 | (13.437900000000001, -88.275599999999997) | Landslide | Debris flow | Medium | Rain | NA | 0 | 0 | Mundo | http://elmundo.com.sv/comunidades-aledanas-al-chaparrastique-afectadas-por-escombros-tras-lluvias |
| 6684 | 10/15/14 | NA | NA | El Salvador | SV | San Miguel | 6393 | Chirilagua | 9.97227 | Other | 13.2930 | -88.0843 | (13.292999999999999, -88.084299999999999) | Landslide | Landslide | Medium | Continuous rain | NA | 0 | 0 | reliefweb | http://reliefweb.int/report/el-salvador/lluvias-causan-estragos-en-seis-departamentos |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_ES, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_ES, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_ES, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_ES <- df_ES %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_ES$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_ES, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_ES$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 10.06695 |
| 6.94536 |
| 9.97227 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_ES$distance
names(distance) <- df_ES$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## San Rafael Oriente 10.06695 10.06695 37.30631 37.30631
## Chirilagua 9.97227 20.03922 36.95544 74.26175
## Chirilagua 6.94536 26.98458 25.73825 100.00000stem(df_ES$"distance")##
## The decimal point is at the |
##
## 6 | 9
## 7 |
## 8 |
## 9 |
## 10 | 01head(df_ES)## # A tibble: 3 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 6675 5/22/14 Night <NA> El Salvador SV San Miguel 19095
## 2 6251 10/13/14 Night <NA> El Salvador SV San Miguel 6393
## 3 6684 10/15/14 <NA> <NA> El Salvador SV San Miguel 6393
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_ES))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 6675 | 5/22/14 | Night | NA | El Salvador | SV | San Miguel | 19095 | San Rafael Oriente | 10.06695 | Unknown | 13.4379 | -88.2756 | (13.437900000000001, -88.275599999999997) | Landslide | Debris flow | Medium | Rain | NA | 0 | 0 | Mundo | http://elmundo.com.sv/comunidades-aledanas-al-chaparrastique-afectadas-por-escombros-tras-lluvias | 37.30631 | 18.65315 |
| 6251 | 10/13/14 | Night | NA | El Salvador | SV | San Miguel | 6393 | Chirilagua | 6.94536 | Above road | 13.2817 | -88.1253 | (13.281700000000001, -88.125299999999996) | Landslide | Rockfall | Small | Earthquake | NA | 0 | 0 | elsalvador.com | http://www.elsalvador.com/mwedh/nota/nota_completa.asp?idCat=47859&idArt=9167407 | 25.73825 | 50.17543 |
| 6684 | 10/15/14 | NA | NA | El Salvador | SV | San Miguel | 6393 | Chirilagua | 9.97227 | Other | 13.2930 | -88.0843 | (13.292999999999999, -88.084299999999999) | Landslide | Landslide | Medium | Continuous rain | NA | 0 | 0 | reliefweb | http://reliefweb.int/report/el-salvador/lluvias-causan-estragos-en-seis-departamentos | 36.95544 | 81.52228 |
stem(df_ES$"distance")##
## The decimal point is at the |
##
## 6 | 9
## 7 |
## 8 |
## 9 |
## 10 | 01stem(df_ES$"distance", scale = 2)##
## The decimal point is at the |
##
## 6 | 9
## 7 |
## 7 |
## 8 |
## 8 |
## 9 |
## 9 |
## 10 | 01Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 6.94536 | 1 | 33.3 | 33.3 | 33.3 | 33.3 |
| 9.97227 | 1 | 33.3 | 33.3 | 66.7 | 66.7 |
| 10.06695 | 1 | 33.3 | 33.3 | 100.0 | 100.0 |
| Total | 3 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 4 obs. of 5 variables:
## $ n : num 1 1 1 3
## $ % : num 33.3 33.3 33.3 100
## $ val% : num 33.3 33.3 33.3 100
## $ %cum : num 33.3 66.7 100 100
## $ val%cum: num 33.3 66.7 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 6.94536 | 1 |
| 9.97227 | 1 |
| 10.06695 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 6.94536 8.94536 10.94536distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (6.95,8.95] | 0 | 0 | 0 |
| (8.95,10.9] | 2 | 1 | 2 |
str(Freq_table)## 'data.frame': 2 obs. of 4 variables:
## $ distance: Factor w/ 2 levels "(6.95,8.95]",..: 1 2
## $ Freq : int 0 2
## $ Rel_Freq: num 0 1
## $ Cum_Freq: int 0 2df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (6.95,8.95] | 0 |
| (8.95,10.9] | 2 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_ES)## id date time continent_code country_name country_code
## nbr.val 3.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 6.251000e+03 NA NA NA NA NA
## max 6.684000e+03 NA NA NA NA NA
## range 4.330000e+02 NA NA NA NA NA
## sum 1.961000e+04 NA NA NA NA NA
## median 6.675000e+03 NA NA NA NA NA
## mean 6.536667e+03 NA NA NA NA NA
## SE.mean 1.428570e+02 NA NA NA NA NA
## CI.mean.0.95 6.146639e+02 NA NA NA NA NA
## var 6.122433e+04 NA NA NA NA NA
## std.dev 2.474355e+02 NA NA NA NA NA
## coef.var 3.785347e-02 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 3.000000e+00 NA 3.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 6.393000e+03 NA 6.9453600 NA
## max NA 1.909500e+04 NA 10.0669500 NA
## range NA 1.270200e+04 NA 3.1215900 NA
## sum NA 3.188100e+04 NA 26.9845800 NA
## median NA 6.393000e+03 NA 9.9722700 NA
## mean NA 1.062700e+04 NA 8.9948600 NA
## SE.mean NA 4.234000e+03 NA 1.0251144 NA
## CI.mean.0.95 NA 1.821743e+04 NA 4.4107114 NA
## var NA 5.378027e+07 NA 3.1525788 NA
## std.dev NA 7.333503e+03 NA 1.7755503 NA
## coef.var NA 6.900822e-01 NA 0.1973961 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 3.000000000 3.000000e+00 NA NA NA
## nbr.null 0.000000000 0.000000e+00 NA NA NA
## nbr.na 0.000000000 0.000000e+00 NA NA NA
## min 13.281700000 -8.827560e+01 NA NA NA
## max 13.437900000 -8.808430e+01 NA NA NA
## range 0.156200000 1.913000e-01 NA NA NA
## sum 40.012600000 -2.644852e+02 NA NA NA
## median 13.293000000 -8.812530e+01 NA NA NA
## mean 13.337533333 -8.816173e+01 NA NA NA
## SE.mean 0.050289241 5.815056e-02 NA NA NA
## CI.mean.0.95 0.216377141 2.502017e-01 NA NA NA
## var 0.007587023 1.014446e-02 NA NA NA
## std.dev 0.087103521 1.007197e-01 NA NA NA
## coef.var 0.006530707 -1.142443e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 3 3 NA
## nbr.null NA NA NA 3 3 NA
## nbr.na NA NA NA 0 0 NA
## min NA NA NA 0 0 NA
## max NA NA NA 0 0 NA
## range NA NA NA 0 0 NA
## sum NA NA NA 0 0 NA
## median NA NA NA 0 0 NA
## mean NA NA NA 0 0 NA
## SE.mean NA NA NA 0 0 NA
## CI.mean.0.95 NA NA NA 0 0 NA
## var NA NA NA 0 0 NA
## std.dev NA NA NA 0 0 NA
## coef.var NA NA NA NaN NaN NA
## source_link prop ypos
## nbr.val NA 3.0000000 3.0000000
## nbr.null NA 0.0000000 0.0000000
## nbr.na NA 0.0000000 0.0000000
## min NA 25.7382550 18.6531530
## max NA 37.3063060 81.5222805
## range NA 11.5680511 62.8691275
## sum NA 100.0000000 150.3508671
## median NA 36.9554390 50.1754335
## mean NA 33.3333333 50.1169557
## SE.mean NA 3.7988897 18.1487774
## CI.mean.0.95 NA 16.3453031 78.0878866
## var NA 43.2946886 988.1343623
## std.dev NA 6.5798699 31.4346045
## coef.var NA 0.1973961 0.6272249boxplot(data, horizontal=TRUE, col='green')
Gráfico para San Salvador (El Salvador)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_ES <- subset(df, country_name == "El Salvador")
knitr::kable(head(df_ES)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 230 | 9/5/07 | NA | NA | El Salvador | SV | Ahuachapán | 7797 | Concepción de Ataco | 0.00273 | NA | 13.8703 | -89.8486 | (13.8703, -89.848600000000005) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Felix | NA | NA | Azcentral.com | http://www.azcentral.com/news/articles/1108sr-fhsistercity1109-ON.html |
| 564 | 6/2/08 | NA | NA | El Salvador | SV | La Libertad | 124694 | Santa Tecla | 4.96416 | NA | 13.7205 | -89.2687 | (13.720499999999999, -89.268699999999995) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Arthur | NA | NA | NA | http://news.xinhuanet.com/english/2008-06/04/content_8310737.htm |
| 1285 | 11/8/09 | NA | NA | El Salvador | SV | San Vicente | 41504 | San Vicente | 7.60946 | NA | 13.6409 | -88.8699 | (13.6409, -88.869900000000001) | Landslide | Complex | Very_large | Tropical cyclone | Tropical Cyclone Ida | NA | 23 | NA | http://www.google.com/hostednews/ap/article/ALeqM5j0XCCb1n12DyhoBoDzGj_hTyEtrAD9BRKPRG0 |
| 1286 | 11/8/09 | NA | NA | El Salvador | SV | La Libertad | 33767 | Antiguo Cuscatlán | 4.86219 | NA | 13.7156 | -89.2521 | (13.7156, -89.252099999999999) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Cyclone Ida | NA | 4 | NA | http://www.google.com/hostednews/ap/article/ALeqM5j0XCCb1n12DyhoBoDzGj_hTyEtrAD9BRKPRG0 |
| 1287 | 11/8/09 | NA | NA | El Salvador | SV | San Vicente | 41504 | San Vicente | 5.90726 | NA | 13.6094 | -88.8488 | (13.609400000000001, -88.848799999999997) | Landslide | Rockfall | Medium | Tropical cyclone | Tropical Cyclone Ida | NA | NA | NA | http://news.bbc.co.uk/2/hi/in_depth/8349333.stm |
| 1288 | 11/8/09 | NA | NA | El Salvador | SV | San Vicente | 41504 | San Vicente | 4.03125 | NA | 13.6466 | -88.8347 | (13.646599999999999, -88.834699999999998) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Cyclone Ida | NA | NA | NA | http://news.yahoo.com/s/afp/20091109/wl_afp/salvadorweatherstorm_20091109100952 |
library(dplyr)
df_ES <- subset(df, state == "San Salvador")
knitr::kable(head(df_ES))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 4008 | 10/10/11 | NA | NA | El Salvador | SV | San Salvador | 112158 | Apopa | 3.01739 | NA | 13.7874 | -89.1600 | (13.7874, -89.16) | Landslide | Landslide | Very_large | Downpour | NA | NA | 32 | NA | http://www.utsandiego.com/news/2011/oct/17/heavy-rains-kill-at-least-84-in-central-america/ |
| 6687 | 10/12/14 | NA | NA | El Salvador | SV | San Salvador | 33767 | Antiguo Cuscatlán | 3.25227 | Retaining wall | 13.6891 | -89.2361 | (13.6891, -89.236099999999993) | Landslide | Other | Small | Rain | NA | 0 | 0 | Mexicano | http://www.oem.com.mx/elmexicano/notas/n3569793.htm |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_ES, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_ES, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_ES, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_ES <- df_ES %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_ES$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_ES, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_ES$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 3.01739 |
| 3.25227 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_ES$distance
names(distance) <- df_ES$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Antiguo Cuscatlán 3.25227 3.25227 51.87315 51.87315
## Apopa 3.01739 6.26966 48.12685 100.00000stem(df_ES$"distance")##
## The decimal point is 1 digit(s) to the left of the |
##
## 30 | 2
## 30 |
## 31 |
## 31 |
## 32 |
## 32 | 5head(df_ES)## # A tibble: 2 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 4008 10/10/11 <NA> <NA> El Salvador SV San ~ 112158
## 2 6687 10/12/14 <NA> <NA> El Salvador SV San ~ 33767
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_ES))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 4008 | 10/10/11 | NA | NA | El Salvador | SV | San Salvador | 112158 | Apopa | 3.01739 | NA | 13.7874 | -89.1600 | (13.7874, -89.16) | Landslide | Landslide | Very_large | Downpour | NA | NA | 32 | NA | http://www.utsandiego.com/news/2011/oct/17/heavy-rains-kill-at-least-84-in-central-america/ | 48.12685 | 24.06343 |
| 6687 | 10/12/14 | NA | NA | El Salvador | SV | San Salvador | 33767 | Antiguo Cuscatlán | 3.25227 | Retaining wall | 13.6891 | -89.2361 | (13.6891, -89.236099999999993) | Landslide | Other | Small | Rain | NA | 0 | 0 | Mexicano | http://www.oem.com.mx/elmexicano/notas/n3569793.htm | 51.87315 | 74.06343 |
stem(df_ES$"distance")##
## The decimal point is 1 digit(s) to the left of the |
##
## 30 | 2
## 30 |
## 31 |
## 31 |
## 32 |
## 32 | 5stem(df_ES$"distance", scale = 2)##
## The decimal point is 1 digit(s) to the left of the |
##
## 30 | 2
## 30 |
## 31 |
## 31 |
## 32 |
## 32 | 5Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 3.01739 | 1 | 50 | 50 | 50 | 50 |
| 3.25227 | 1 | 50 | 50 | 100 | 100 |
| Total | 2 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 3 obs. of 5 variables:
## $ n : num 1 1 2
## $ % : num 50 50 100
## $ val% : num 50 50 100
## $ %cum : num 50 100 100
## $ val%cum: num 50 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 3.01739 | 1 |
| 3.25227 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 3.01739 4.01739distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (3.02,4.02] | 1 | 1 | 1 |
str(Freq_table)## 'data.frame': 1 obs. of 4 variables:
## $ distance: Factor w/ 1 level "(3.02,4.02]": 1
## $ Freq : int 1
## $ Rel_Freq: num 1
## $ Cum_Freq: int 1df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (3.02,4.02] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_ES)## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 2.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 4.008000e+03 NA NA NA NA NA
## max 6.687000e+03 NA NA NA NA NA
## range 2.679000e+03 NA NA NA NA NA
## sum 1.069500e+04 NA NA NA NA NA
## median 5.347500e+03 NA NA NA NA NA
## mean 5.347500e+03 NA NA NA NA NA
## SE.mean 1.339500e+03 NA NA NA NA NA
## CI.mean.0.95 1.701996e+04 NA NA NA NA NA
## var 3.588521e+06 NA NA NA NA NA
## std.dev 1.894339e+03 NA NA NA NA NA
## coef.var 3.542476e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 2.000000e+00 NA 2.00000000 NA
## nbr.null NA 0.000000e+00 NA 0.00000000 NA
## nbr.na NA 0.000000e+00 NA 0.00000000 NA
## min NA 3.376700e+04 NA 3.01739000 NA
## max NA 1.121580e+05 NA 3.25227000 NA
## range NA 7.839100e+04 NA 0.23488000 NA
## sum NA 1.459250e+05 NA 6.26966000 NA
## median NA 7.296250e+04 NA 3.13483000 NA
## mean NA 7.296250e+04 NA 3.13483000 NA
## SE.mean NA 3.919550e+04 NA 0.11744000 NA
## CI.mean.0.95 NA 4.980260e+05 NA 1.49221668 NA
## var NA 3.072574e+09 NA 0.02758431 NA
## std.dev NA 5.543081e+04 NA 0.16608524 NA
## coef.var NA 7.597164e-01 NA 0.05298062 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 2.000000000 2.000000e+00 NA NA NA
## nbr.null 0.000000000 0.000000e+00 NA NA NA
## nbr.na 0.000000000 0.000000e+00 NA NA NA
## min 13.689100000 -8.923610e+01 NA NA NA
## max 13.787400000 -8.916000e+01 NA NA NA
## range 0.098300000 7.610000e-02 NA NA NA
## sum 27.476500000 -1.783961e+02 NA NA NA
## median 13.738250000 -8.919805e+01 NA NA NA
## mean 13.738250000 -8.919805e+01 NA NA NA
## SE.mean 0.049150000 3.805000e-02 NA NA NA
## CI.mean.0.95 0.624509963 4.834711e-01 NA NA NA
## var 0.004831445 2.895605e-03 NA NA NA
## std.dev 0.069508597 5.381083e-02 NA NA NA
## coef.var 0.005059494 -6.032736e-04 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 1 2.000000 NA
## nbr.null NA NA NA 1 1.000000 NA
## nbr.na NA NA NA 1 0.000000 NA
## min NA NA NA 0 0.000000 NA
## max NA NA NA 0 32.000000 NA
## range NA NA NA 0 32.000000 NA
## sum NA NA NA 0 32.000000 NA
## median NA NA NA 0 16.000000 NA
## mean NA NA NA 0 16.000000 NA
## SE.mean NA NA NA NA 16.000000 NA
## CI.mean.0.95 NA NA NA NaN 203.299276 NA
## var NA NA NA NA 512.000000 NA
## std.dev NA NA NA NA 22.627417 NA
## coef.var NA NA NA NA 1.414214 NA
## source_link prop ypos
## nbr.val NA 2.00000000 2.0000000
## nbr.null NA 0.00000000 0.0000000
## nbr.na NA 0.00000000 0.0000000
## min NA 48.12685217 24.0634261
## max NA 51.87314783 74.0634261
## range NA 3.74629565 50.0000000
## sum NA 100.00000000 98.1268522
## median NA 50.00000000 49.0634261
## mean NA 50.00000000 49.0634261
## SE.mean NA 1.87314783 25.0000000
## CI.mean.0.95 NA 23.80059978 317.6551184
## var NA 7.01736556 1250.0000000
## std.dev NA 2.64903106 35.3553391
## coef.var NA 0.05298062 0.7206048boxplot(data, horizontal=TRUE, col='green')
Gráfico para Santa Ana (El Salvador)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_ES <- subset(df, country_name == "El Salvador")
knitr::kable(head(df_ES)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 230 | 9/5/07 | NA | NA | El Salvador | SV | Ahuachapán | 7797 | Concepción de Ataco | 0.00273 | NA | 13.8703 | -89.8486 | (13.8703, -89.848600000000005) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Felix | NA | NA | Azcentral.com | http://www.azcentral.com/news/articles/1108sr-fhsistercity1109-ON.html |
| 564 | 6/2/08 | NA | NA | El Salvador | SV | La Libertad | 124694 | Santa Tecla | 4.96416 | NA | 13.7205 | -89.2687 | (13.720499999999999, -89.268699999999995) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Arthur | NA | NA | NA | http://news.xinhuanet.com/english/2008-06/04/content_8310737.htm |
| 1285 | 11/8/09 | NA | NA | El Salvador | SV | San Vicente | 41504 | San Vicente | 7.60946 | NA | 13.6409 | -88.8699 | (13.6409, -88.869900000000001) | Landslide | Complex | Very_large | Tropical cyclone | Tropical Cyclone Ida | NA | 23 | NA | http://www.google.com/hostednews/ap/article/ALeqM5j0XCCb1n12DyhoBoDzGj_hTyEtrAD9BRKPRG0 |
| 1286 | 11/8/09 | NA | NA | El Salvador | SV | La Libertad | 33767 | Antiguo Cuscatlán | 4.86219 | NA | 13.7156 | -89.2521 | (13.7156, -89.252099999999999) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Cyclone Ida | NA | 4 | NA | http://www.google.com/hostednews/ap/article/ALeqM5j0XCCb1n12DyhoBoDzGj_hTyEtrAD9BRKPRG0 |
| 1287 | 11/8/09 | NA | NA | El Salvador | SV | San Vicente | 41504 | San Vicente | 5.90726 | NA | 13.6094 | -88.8488 | (13.609400000000001, -88.848799999999997) | Landslide | Rockfall | Medium | Tropical cyclone | Tropical Cyclone Ida | NA | NA | NA | http://news.bbc.co.uk/2/hi/in_depth/8349333.stm |
| 1288 | 11/8/09 | NA | NA | El Salvador | SV | San Vicente | 41504 | San Vicente | 4.03125 | NA | 13.6466 | -88.8347 | (13.646599999999999, -88.834699999999998) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Cyclone Ida | NA | NA | NA | http://news.yahoo.com/s/afp/20091109/wl_afp/salvadorweatherstorm_20091109100952 |
library(dplyr)
df_ES <- subset(df, state == "Santa Ana")
knitr::kable(head(df_ES))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 6685 | 10/12/14 | NA | NA | El Salvador | SV | Santa Ana | 5773 | Coatepeque | 8.8321 | Unknown | 14.0007 | -89.4691 | (14.0007, -89.469099999999997) | Landslide | Landslide | Medium | Rain | NA | 2 | 3 | Mexicano | http://www.oem.com.mx/elmexicano/notas/n3569793.htm |
| 7438 | 7/18/15 | NA | NA | El Salvador | SV | Santa Ana | 10095 | Ciudad Arce | 1.1581 | Above road | 13.8464 | -89.4502 | (13.846399999999999, -89.450199999999995) | Landslide | Landslide | Small | Rain | NA | 0 | 0 | La Prensa | http://www.laprensagrafica.com/2015/07/18/lluvias-causan-derrumbe-en-carretera-a-santa-ana |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_ES, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_ES, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_ES, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_ES <- df_ES %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_ES$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_ES, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_ES$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 8.8321 |
| 1.1581 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_ES$distance
names(distance) <- df_ES$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Coatepeque 8.83210 8.83210 88.40764 88.40764
## Ciudad Arce 1.15810 9.99020 11.59236 100.00000stem(df_ES$"distance")##
## The decimal point is at the |
##
## 0 | 2
## 2 |
## 4 |
## 6 |
## 8 | 8head(df_ES)## # A tibble: 2 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 6685 10/12/14 <NA> <NA> El Salvador SV Santa Ana 5773
## 2 7438 7/18/15 <NA> <NA> El Salvador SV Santa Ana 10095
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_ES))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 6685 | 10/12/14 | NA | NA | El Salvador | SV | Santa Ana | 5773 | Coatepeque | 8.8321 | Unknown | 14.0007 | -89.4691 | (14.0007, -89.469099999999997) | Landslide | Landslide | Medium | Rain | NA | 2 | 3 | Mexicano | http://www.oem.com.mx/elmexicano/notas/n3569793.htm | 88.40764 | 44.20382 |
| 7438 | 7/18/15 | NA | NA | El Salvador | SV | Santa Ana | 10095 | Ciudad Arce | 1.1581 | Above road | 13.8464 | -89.4502 | (13.846399999999999, -89.450199999999995) | Landslide | Landslide | Small | Rain | NA | 0 | 0 | La Prensa | http://www.laprensagrafica.com/2015/07/18/lluvias-causan-derrumbe-en-carretera-a-santa-ana | 11.59236 | 94.20382 |
stem(df_ES$"distance")##
## The decimal point is at the |
##
## 0 | 2
## 2 |
## 4 |
## 6 |
## 8 | 8stem(df_ES$"distance", scale = 2)##
## The decimal point is at the |
##
## 1 | 2
## 2 |
## 3 |
## 4 |
## 5 |
## 6 |
## 7 |
## 8 | 8Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 1.1581 | 1 | 50 | 50 | 50 | 50 |
| 8.8321 | 1 | 50 | 50 | 100 | 100 |
| Total | 2 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 3 obs. of 5 variables:
## $ n : num 1 1 2
## $ % : num 50 50 100
## $ val% : num 50 50 100
## $ %cum : num 50 100 100
## $ val%cum: num 50 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 1.1581 | 1 |
| 8.8321 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 1.1581 5.1581 9.1581distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (1.16,5.16] | 0 | 0 | 0 |
| (5.16,9.16] | 1 | 1 | 1 |
str(Freq_table)## 'data.frame': 2 obs. of 4 variables:
## $ distance: Factor w/ 2 levels "(1.16,5.16]",..: 1 2
## $ Freq : int 0 1
## $ Rel_Freq: num 0 1
## $ Cum_Freq: int 0 1df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (1.16,5.16] | 0 |
| (5.16,9.16] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_ES)## id date time continent_code country_name country_code
## nbr.val 2.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 6.685000e+03 NA NA NA NA NA
## max 7.438000e+03 NA NA NA NA NA
## range 7.530000e+02 NA NA NA NA NA
## sum 1.412300e+04 NA NA NA NA NA
## median 7.061500e+03 NA NA NA NA NA
## mean 7.061500e+03 NA NA NA NA NA
## SE.mean 3.765000e+02 NA NA NA NA NA
## CI.mean.0.95 4.783886e+03 NA NA NA NA NA
## var 2.835045e+05 NA NA NA NA NA
## std.dev 5.324514e+02 NA NA NA NA NA
## coef.var 7.540203e-02 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 2.000000e+00 NA 2.000000 NA
## nbr.null NA 0.000000e+00 NA 0.000000 NA
## nbr.na NA 0.000000e+00 NA 0.000000 NA
## min NA 5.773000e+03 NA 1.158100 NA
## max NA 1.009500e+04 NA 8.832100 NA
## range NA 4.322000e+03 NA 7.674000 NA
## sum NA 1.586800e+04 NA 9.990200 NA
## median NA 7.934000e+03 NA 4.995100 NA
## mean NA 7.934000e+03 NA 4.995100 NA
## SE.mean NA 2.161000e+03 NA 3.837000 NA
## CI.mean.0.95 NA 2.745811e+04 NA 48.753708 NA
## var NA 9.339842e+06 NA 29.445138 NA
## std.dev NA 3.056116e+03 NA 5.426337 NA
## coef.var NA 3.851923e-01 NA 1.086332 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 2.000000000 2.000000e+00 NA NA NA
## nbr.null 0.000000000 0.000000e+00 NA NA NA
## nbr.na 0.000000000 0.000000e+00 NA NA NA
## min 13.846400000 -8.946910e+01 NA NA NA
## max 14.000700000 -8.945020e+01 NA NA NA
## range 0.154300000 1.890000e-02 NA NA NA
## sum 27.847100000 -1.789193e+02 NA NA NA
## median 13.923550000 -8.945965e+01 NA NA NA
## mean 13.923550000 -8.945965e+01 NA NA NA
## SE.mean 0.077150000 9.450000e-03 NA NA NA
## CI.mean.0.95 0.980283695 1.200736e-01 NA NA NA
## var 0.011904245 1.786050e-04 NA NA NA
## std.dev 0.109106576 1.336432e-02 NA NA NA
## coef.var 0.007836118 -1.493893e-04 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 2.000000 2.000000 NA
## nbr.null NA NA NA 1.000000 1.000000 NA
## nbr.na NA NA NA 0.000000 0.000000 NA
## min NA NA NA 0.000000 0.000000 NA
## max NA NA NA 2.000000 3.000000 NA
## range NA NA NA 2.000000 3.000000 NA
## sum NA NA NA 2.000000 3.000000 NA
## median NA NA NA 1.000000 1.500000 NA
## mean NA NA NA 1.000000 1.500000 NA
## SE.mean NA NA NA 1.000000 1.500000 NA
## CI.mean.0.95 NA NA NA 12.706205 19.059307 NA
## var NA NA NA 2.000000 4.500000 NA
## std.dev NA NA NA 1.414214 2.121320 NA
## coef.var NA NA NA 1.414214 1.414214 NA
## source_link prop ypos
## nbr.val NA 2.000000 2.0000000
## nbr.null NA 0.000000 0.0000000
## nbr.na NA 0.000000 0.0000000
## min NA 11.592361 44.2038197
## max NA 88.407639 94.2038197
## range NA 76.815279 50.0000000
## sum NA 100.000000 138.4076395
## median NA 50.000000 69.2038197
## mean NA 50.000000 69.2038197
## SE.mean NA 38.407639 25.0000000
## CI.mean.0.95 NA 488.015331 317.6551184
## var NA 2950.293542 1250.0000000
## std.dev NA 54.316605 35.3553391
## coef.var NA 1.086332 0.5108871boxplot(data, horizontal=TRUE, col='green')
Gráfico para Sonsonate (El Salvador)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_ES <- subset(df, country_name == "El Salvador")
knitr::kable(head(df_ES)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 230 | 9/5/07 | NA | NA | El Salvador | SV | Ahuachapán | 7797 | Concepción de Ataco | 0.00273 | NA | 13.8703 | -89.8486 | (13.8703, -89.848600000000005) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Felix | NA | NA | Azcentral.com | http://www.azcentral.com/news/articles/1108sr-fhsistercity1109-ON.html |
| 564 | 6/2/08 | NA | NA | El Salvador | SV | La Libertad | 124694 | Santa Tecla | 4.96416 | NA | 13.7205 | -89.2687 | (13.720499999999999, -89.268699999999995) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Arthur | NA | NA | NA | http://news.xinhuanet.com/english/2008-06/04/content_8310737.htm |
| 1285 | 11/8/09 | NA | NA | El Salvador | SV | San Vicente | 41504 | San Vicente | 7.60946 | NA | 13.6409 | -88.8699 | (13.6409, -88.869900000000001) | Landslide | Complex | Very_large | Tropical cyclone | Tropical Cyclone Ida | NA | 23 | NA | http://www.google.com/hostednews/ap/article/ALeqM5j0XCCb1n12DyhoBoDzGj_hTyEtrAD9BRKPRG0 |
| 1286 | 11/8/09 | NA | NA | El Salvador | SV | La Libertad | 33767 | Antiguo Cuscatlán | 4.86219 | NA | 13.7156 | -89.2521 | (13.7156, -89.252099999999999) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Cyclone Ida | NA | 4 | NA | http://www.google.com/hostednews/ap/article/ALeqM5j0XCCb1n12DyhoBoDzGj_hTyEtrAD9BRKPRG0 |
| 1287 | 11/8/09 | NA | NA | El Salvador | SV | San Vicente | 41504 | San Vicente | 5.90726 | NA | 13.6094 | -88.8488 | (13.609400000000001, -88.848799999999997) | Landslide | Rockfall | Medium | Tropical cyclone | Tropical Cyclone Ida | NA | NA | NA | http://news.bbc.co.uk/2/hi/in_depth/8349333.stm |
| 1288 | 11/8/09 | NA | NA | El Salvador | SV | San Vicente | 41504 | San Vicente | 4.03125 | NA | 13.6466 | -88.8347 | (13.646599999999999, -88.834699999999998) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Cyclone Ida | NA | NA | NA | http://news.yahoo.com/s/afp/20091109/wl_afp/salvadorweatherstorm_20091109100952 |
library(dplyr)
df_ES <- subset(df, state == "Sonsonate")
knitr::kable(head(df_ES))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 6681 | 10/15/14 | NA | NA | El Salvador | SV | Sonsonate | 7358 | Nahuizalco | 4.23875 | Unknown | 13.7895 | -89.7739 | (13.7895, -89.773899999999998) | Landslide | Landslide | Medium | Continuous rain | NA | 0 | 0 | reliefweb | http://reliefweb.int/report/el-salvador/lluvias-causan-estragos-en-seis-departamentos |
| 6682 | 10/15/14 | NA | NA | El Salvador | SV | Sonsonate | 15446 | Sonzacate | 3.22235 | Unknown | 13.7135 | -89.6938 | (13.7135, -89.693799999999996) | Landslide | Landslide | Medium | Continuous rain | NA | 0 | 0 | reliefweb | http://reliefweb.int/report/el-salvador/lluvias-causan-estragos-en-seis-departamentos |
| 7442 | 10/19/15 | NA | NA | El Salvador | SV | Sonsonate | 9936 | Juayúa | 0.49346 | Unknown | 13.8457 | -89.7445 | (13.845700000000001, -89.744500000000002) | Landslide | Landslide | Medium | Downpour | NA | 1 | 0 | El Heraldo | http://www.elheraldo.hn/mundo/892045-217/cuatro-muertos-por-persistentes-lluvias-en-el-salvador |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_ES, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_ES, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_ES, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_ES <- df_ES %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_ES$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_ES, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_ES$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 3.22235 |
| 4.23875 |
| 0.49346 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_ES$distance
names(distance) <- df_ES$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Nahuizalco 4.238750 4.238750 53.287045 53.287045
## Sonzacate 3.222350 7.461100 40.509469 93.796514
## Juayúa 0.493460 7.954560 6.203486 100.000000stem(df_ES$"distance")##
## The decimal point is at the |
##
## 0 | 5
## 1 |
## 2 |
## 3 | 2
## 4 | 2head(df_ES)## # A tibble: 3 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 6682 10/15/14 <NA> <NA> El Salvador SV Sonsonate 15446
## 2 6681 10/15/14 <NA> <NA> El Salvador SV Sonsonate 7358
## 3 7442 10/19/15 <NA> <NA> El Salvador SV Sonsonate 9936
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_ES))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 6682 | 10/15/14 | NA | NA | El Salvador | SV | Sonsonate | 15446 | Sonzacate | 3.22235 | Unknown | 13.7135 | -89.6938 | (13.7135, -89.693799999999996) | Landslide | Landslide | Medium | Continuous rain | NA | 0 | 0 | reliefweb | http://reliefweb.int/report/el-salvador/lluvias-causan-estragos-en-seis-departamentos | 40.509469 | 20.25473 |
| 6681 | 10/15/14 | NA | NA | El Salvador | SV | Sonsonate | 7358 | Nahuizalco | 4.23875 | Unknown | 13.7895 | -89.7739 | (13.7895, -89.773899999999998) | Landslide | Landslide | Medium | Continuous rain | NA | 0 | 0 | reliefweb | http://reliefweb.int/report/el-salvador/lluvias-causan-estragos-en-seis-departamentos | 53.287045 | 67.15299 |
| 7442 | 10/19/15 | NA | NA | El Salvador | SV | Sonsonate | 9936 | Juayúa | 0.49346 | Unknown | 13.8457 | -89.7445 | (13.845700000000001, -89.744500000000002) | Landslide | Landslide | Medium | Downpour | NA | 1 | 0 | El Heraldo | http://www.elheraldo.hn/mundo/892045-217/cuatro-muertos-por-persistentes-lluvias-en-el-salvador | 6.203486 | 96.89826 |
stem(df_ES$"distance")##
## The decimal point is at the |
##
## 0 | 5
## 1 |
## 2 |
## 3 | 2
## 4 | 2stem(df_ES$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 |
## 0 | 5
## 1 |
## 1 |
## 2 |
## 2 |
## 3 | 2
## 3 |
## 4 | 2Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.49346 | 1 | 33.3 | 33.3 | 33.3 | 33.3 |
| 3.22235 | 1 | 33.3 | 33.3 | 66.7 | 66.7 |
| 4.23875 | 1 | 33.3 | 33.3 | 100.0 | 100.0 |
| Total | 3 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 4 obs. of 5 variables:
## $ n : num 1 1 1 3
## $ % : num 33.3 33.3 33.3 100
## $ val% : num 33.3 33.3 33.3 100
## $ %cum : num 33.3 66.7 100 100
## $ val%cum: num 33.3 66.7 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.49346 | 1 |
| 3.22235 | 1 |
| 4.23875 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.49346 2.49346 4.49346distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.493,2.49] | 0 | 0 | 0 |
| (2.49,4.49] | 2 | 1 | 2 |
str(Freq_table)## 'data.frame': 2 obs. of 4 variables:
## $ distance: Factor w/ 2 levels "(0.493,2.49]",..: 1 2
## $ Freq : int 0 2
## $ Rel_Freq: num 0 1
## $ Cum_Freq: int 0 2df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.493,2.49] | 0 |
| (2.49,4.49] | 2 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_ES)## id date time continent_code country_name country_code
## nbr.val 3.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 6.681000e+03 NA NA NA NA NA
## max 7.442000e+03 NA NA NA NA NA
## range 7.610000e+02 NA NA NA NA NA
## sum 2.080500e+04 NA NA NA NA NA
## median 6.682000e+03 NA NA NA NA NA
## mean 6.935000e+03 NA NA NA NA NA
## SE.mean 2.535002e+02 NA NA NA NA NA
## CI.mean.0.95 1.090723e+03 NA NA NA NA NA
## var 1.927870e+05 NA NA NA NA NA
## std.dev 4.390752e+02 NA NA NA NA NA
## coef.var 6.331293e-02 NA NA NA NA NA
## state population city distance location_description latitude
## nbr.val NA 3.000000e+00 NA 3.000000 NA 3.000000000
## nbr.null NA 0.000000e+00 NA 0.000000 NA 0.000000000
## nbr.na NA 0.000000e+00 NA 0.000000 NA 0.000000000
## min NA 7.358000e+03 NA 0.493460 NA 13.713500000
## max NA 1.544600e+04 NA 4.238750 NA 13.845700000
## range NA 8.088000e+03 NA 3.745290 NA 0.132200000
## sum NA 3.274000e+04 NA 7.954560 NA 41.348700000
## median NA 9.936000e+03 NA 3.222350 NA 13.789500000
## mean NA 1.091333e+04 NA 2.651520 NA 13.782900000
## SE.mean NA 2.385395e+03 NA 1.118211 NA 0.038305265
## CI.mean.0.95 NA 1.026352e+04 NA 4.811272 NA 0.164814253
## var NA 1.707032e+07 NA 3.751184 NA 0.004401880
## std.dev NA 4.131625e+03 NA 1.936797 NA 0.066346665
## coef.var NA 3.785850e-01 NA 0.730448 NA 0.004813694
## longitude geolocation hazard_type landslide_type
## nbr.val 3.000000e+00 NA NA NA
## nbr.null 0.000000e+00 NA NA NA
## nbr.na 0.000000e+00 NA NA NA
## min -8.977390e+01 NA NA NA
## max -8.969380e+01 NA NA NA
## range 8.010000e-02 NA NA NA
## sum -2.692122e+02 NA NA NA
## median -8.974450e+01 NA NA NA
## mean -8.973740e+01 NA NA NA
## SE.mean 2.339380e-02 NA NA NA
## CI.mean.0.95 1.006554e-01 NA NA NA
## var 1.641810e-03 NA NA NA
## std.dev 4.051925e-02 NA NA NA
## coef.var -4.515314e-04 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 3.0000000 3 NA
## nbr.null NA NA NA 2.0000000 3 NA
## nbr.na NA NA NA 0.0000000 0 NA
## min NA NA NA 0.0000000 0 NA
## max NA NA NA 1.0000000 0 NA
## range NA NA NA 1.0000000 0 NA
## sum NA NA NA 1.0000000 0 NA
## median NA NA NA 0.0000000 0 NA
## mean NA NA NA 0.3333333 0 NA
## SE.mean NA NA NA 0.3333333 0 NA
## CI.mean.0.95 NA NA NA 1.4342176 0 NA
## var NA NA NA 0.3333333 0 NA
## std.dev NA NA NA 0.5773503 0 NA
## coef.var NA NA NA 1.7320508 NaN NA
## source_link prop ypos
## nbr.val NA 3.000000 3.0000000
## nbr.null NA 0.000000 0.0000000
## nbr.na NA 0.000000 0.0000000
## min NA 6.203486 20.2547344
## max NA 53.287045 96.8982571
## range NA 47.083560 76.6435227
## sum NA 100.000000 184.3059830
## median NA 40.509469 67.1529915
## mean NA 33.333333 61.4353277
## SE.mean NA 14.057478 22.3090128
## CI.mean.0.95 NA 60.484447 95.9879347
## var NA 592.838087 1493.0761531
## std.dev NA 24.348267 38.6403436
## coef.var NA 0.730448 0.6289597boxplot(data, horizontal=TRUE, col='green')
Gráfico para Guatemala
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_GT <- subset(df, country_name == "El Salvador")
knitr::kable(head(df_GT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 230 | 9/5/07 | NA | NA | El Salvador | SV | Ahuachapán | 7797 | Concepción de Ataco | 0.00273 | NA | 13.8703 | -89.8486 | (13.8703, -89.848600000000005) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Felix | NA | NA | Azcentral.com | http://www.azcentral.com/news/articles/1108sr-fhsistercity1109-ON.html |
| 564 | 6/2/08 | NA | NA | El Salvador | SV | La Libertad | 124694 | Santa Tecla | 4.96416 | NA | 13.7205 | -89.2687 | (13.720499999999999, -89.268699999999995) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Arthur | NA | NA | NA | http://news.xinhuanet.com/english/2008-06/04/content_8310737.htm |
| 1285 | 11/8/09 | NA | NA | El Salvador | SV | San Vicente | 41504 | San Vicente | 7.60946 | NA | 13.6409 | -88.8699 | (13.6409, -88.869900000000001) | Landslide | Complex | Very_large | Tropical cyclone | Tropical Cyclone Ida | NA | 23 | NA | http://www.google.com/hostednews/ap/article/ALeqM5j0XCCb1n12DyhoBoDzGj_hTyEtrAD9BRKPRG0 |
| 1286 | 11/8/09 | NA | NA | El Salvador | SV | La Libertad | 33767 | Antiguo Cuscatlán | 4.86219 | NA | 13.7156 | -89.2521 | (13.7156, -89.252099999999999) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Cyclone Ida | NA | 4 | NA | http://www.google.com/hostednews/ap/article/ALeqM5j0XCCb1n12DyhoBoDzGj_hTyEtrAD9BRKPRG0 |
| 1287 | 11/8/09 | NA | NA | El Salvador | SV | San Vicente | 41504 | San Vicente | 5.90726 | NA | 13.6094 | -88.8488 | (13.609400000000001, -88.848799999999997) | Landslide | Rockfall | Medium | Tropical cyclone | Tropical Cyclone Ida | NA | NA | NA | http://news.bbc.co.uk/2/hi/in_depth/8349333.stm |
| 1288 | 11/8/09 | NA | NA | El Salvador | SV | San Vicente | 41504 | San Vicente | 4.03125 | NA | 13.6466 | -88.8347 | (13.646599999999999, -88.834699999999998) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Cyclone Ida | NA | NA | NA | http://news.yahoo.com/s/afp/20091109/wl_afp/salvadorweatherstorm_20091109100952 |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_GT, aes(fill= state, y=distance, x=country_name)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_GT, aes(fill=state, y=distance, x=country_name)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_GT, aes(x=country_name, y=distance, fill=state)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_GT <- df_GT %>%
arrange(desc(state)) %>%
mutate(prop = distance / sum(df_GT$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_GT, aes(x=country_name, y=prop, fill=state)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_GT$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 4.23875 |
| 3.22235 |
| 0.49346 |
| 8.83210 |
| 1.15810 |
| 7.60946 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_GT$distance
names(distance) <- df_GT$state
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por estados"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## San Miguel 1.006695e+01 1.006695e+01 8.974011e+00 8.974011e+00
## San Miguel 9.972270e+00 2.003922e+01 8.889610e+00 1.786362e+01
## La Libertad 9.875530e+00 2.991475e+01 8.803373e+00 2.666699e+01
## Santa Ana 8.832100e+00 3.874685e+01 7.873225e+00 3.454022e+01
## Cabañas 8.825250e+00 4.757210e+01 7.867118e+00 4.240734e+01
## San Vicente 7.609460e+00 5.518156e+01 6.783323e+00 4.919066e+01
## San Miguel 6.945360e+00 6.212692e+01 6.191323e+00 5.538198e+01
## San Vicente 5.907260e+00 6.803418e+01 5.265926e+00 6.064791e+01
## Ahuachapán 5.299010e+00 7.333319e+01 4.723712e+00 6.537162e+01
## La Libertad 4.964160e+00 7.829735e+01 4.425216e+00 6.979684e+01
## La Libertad 4.862190e+00 8.315954e+01 4.334316e+00 7.413115e+01
## La Libertad 4.677220e+00 8.783676e+01 4.169428e+00 7.830058e+01
## La Libertad 4.606550e+00 9.244331e+01 4.106430e+00 8.240701e+01
## Sonsonate 4.238750e+00 9.668206e+01 3.778561e+00 8.618557e+01
## San Vicente 4.031250e+00 1.007133e+02 3.593589e+00 8.977916e+01
## San Salvador 3.252270e+00 1.039656e+02 2.899181e+00 9.267834e+01
## Sonsonate 3.222350e+00 1.071879e+02 2.872509e+00 9.555085e+01
## San Salvador 3.017390e+00 1.102053e+02 2.689801e+00 9.824065e+01
## Santa Ana 1.158100e+00 1.113634e+02 1.032368e+00 9.927302e+01
## Sonsonate 4.934600e-01 1.118569e+02 4.398865e-01 9.971291e+01
## La Paz 3.193300e-01 1.121762e+02 2.846613e-01 9.999757e+01
## Ahuachapán 2.730000e-03 1.121789e+02 2.433612e-03 1.000000e+02stem(df_GT$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 000133344
## 0 | 5555567899
## 1 | 000head(df_GT)## # A tibble: 6 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 6681 10/15/14 <NA> <NA> El Salvador SV Sons~ 7358
## 2 6682 10/15/14 <NA> <NA> El Salvador SV Sons~ 15446
## 3 7442 10/19/15 <NA> <NA> El Salvador SV Sons~ 9936
## 4 6685 10/12/14 <NA> <NA> El Salvador SV Sant~ 5773
## 5 7438 7/18/15 <NA> <NA> El Salvador SV Sant~ 10095
## 6 1285 11/8/09 <NA> <NA> El Salvador SV San ~ 41504
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_GT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 6681 | 10/15/14 | NA | NA | El Salvador | SV | Sonsonate | 7358 | Nahuizalco | 4.23875 | Unknown | 13.7895 | -89.7739 | (13.7895, -89.773899999999998) | Landslide | Landslide | Medium | Continuous rain | NA | 0 | 0 | reliefweb | http://reliefweb.int/report/el-salvador/lluvias-causan-estragos-en-seis-departamentos | 3.7785613 | 1.889281 |
| 6682 | 10/15/14 | NA | NA | El Salvador | SV | Sonsonate | 15446 | Sonzacate | 3.22235 | Unknown | 13.7135 | -89.6938 | (13.7135, -89.693799999999996) | Landslide | Landslide | Medium | Continuous rain | NA | 0 | 0 | reliefweb | http://reliefweb.int/report/el-salvador/lluvias-causan-estragos-en-seis-departamentos | 2.8725089 | 5.214816 |
| 7442 | 10/19/15 | NA | NA | El Salvador | SV | Sonsonate | 9936 | Juayúa | 0.49346 | Unknown | 13.8457 | -89.7445 | (13.845700000000001, -89.744500000000002) | Landslide | Landslide | Medium | Downpour | NA | 1 | 0 | El Heraldo | http://www.elheraldo.hn/mundo/892045-217/cuatro-muertos-por-persistentes-lluvias-en-el-salvador | 0.4398865 | 6.871013 |
| 6685 | 10/12/14 | NA | NA | El Salvador | SV | Santa Ana | 5773 | Coatepeque | 8.83210 | Unknown | 14.0007 | -89.4691 | (14.0007, -89.469099999999997) | Landslide | Landslide | Medium | Rain | NA | 2 | 3 | Mexicano | http://www.oem.com.mx/elmexicano/notas/n3569793.htm | 7.8732247 | 11.027569 |
| 7438 | 7/18/15 | NA | NA | El Salvador | SV | Santa Ana | 10095 | Ciudad Arce | 1.15810 | Above road | 13.8464 | -89.4502 | (13.846399999999999, -89.450199999999995) | Landslide | Landslide | Small | Rain | NA | 0 | 0 | La Prensa | http://www.laprensagrafica.com/2015/07/18/lluvias-causan-derrumbe-en-carretera-a-santa-ana | 1.0323685 | 15.480366 |
| 1285 | 11/8/09 | NA | NA | El Salvador | SV | San Vicente | 41504 | San Vicente | 7.60946 | NA | 13.6409 | -88.8699 | (13.6409, -88.869900000000001) | Landslide | Complex | Very_large | Tropical cyclone | Tropical Cyclone Ida | NA | 23 | NA | http://www.google.com/hostednews/ap/article/ALeqM5j0XCCb1n12DyhoBoDzGj_hTyEtrAD9BRKPRG0 | 6.7833231 | 19.388211 |
stem(df_GT$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 000133344
## 0 | 5555567899
## 1 | 000stem(df_GT$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 0352
## 2 | 023
## 4 | 02679039
## 6 | 96
## 8 | 889
## 10 | 01Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.00273 | 1 | 4.5 | 4.5 | 4.5 | 4.5 |
| 0.31933 | 1 | 4.5 | 4.5 | 9.1 | 9.1 |
| 0.49346 | 1 | 4.5 | 4.5 | 13.6 | 13.6 |
| 1.1581 | 1 | 4.5 | 4.5 | 18.2 | 18.2 |
| 3.01739 | 1 | 4.5 | 4.5 | 22.7 | 22.7 |
| 3.22235 | 1 | 4.5 | 4.5 | 27.3 | 27.3 |
| 3.25227 | 1 | 4.5 | 4.5 | 31.8 | 31.8 |
| 4.03125 | 1 | 4.5 | 4.5 | 36.4 | 36.4 |
| 4.23875 | 1 | 4.5 | 4.5 | 40.9 | 40.9 |
| 4.60655 | 1 | 4.5 | 4.5 | 45.5 | 45.5 |
| 4.67722 | 1 | 4.5 | 4.5 | 50.0 | 50.0 |
| 4.86219 | 1 | 4.5 | 4.5 | 54.5 | 54.5 |
| 4.96416 | 1 | 4.5 | 4.5 | 59.1 | 59.1 |
| 5.29901 | 1 | 4.5 | 4.5 | 63.6 | 63.6 |
| 5.90726 | 1 | 4.5 | 4.5 | 68.2 | 68.2 |
| 6.94536 | 1 | 4.5 | 4.5 | 72.7 | 72.7 |
| 7.60946 | 1 | 4.5 | 4.5 | 77.3 | 77.3 |
| 8.82525 | 1 | 4.5 | 4.5 | 81.8 | 81.8 |
| 8.8321 | 1 | 4.5 | 4.5 | 86.4 | 86.4 |
| 9.87553 | 1 | 4.5 | 4.5 | 90.9 | 90.9 |
| 9.97227 | 1 | 4.5 | 4.5 | 95.5 | 95.5 |
| 10.06695 | 1 | 4.5 | 4.5 | 100.0 | 100.0 |
| Total | 22 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 23 obs. of 5 variables:
## $ n : num 1 1 1 1 1 1 1 1 1 1 ...
## $ % : num 4.5 4.5 4.5 4.5 4.5 4.5 4.5 4.5 4.5 4.5 ...
## $ val% : num 4.5 4.5 4.5 4.5 4.5 4.5 4.5 4.5 4.5 4.5 ...
## $ %cum : num 4.5 9.1 13.6 18.2 22.7 27.3 31.8 36.4 40.9 45.5 ...
## $ val%cum: num 4.5 9.1 13.6 18.2 22.7 27.3 31.8 36.4 40.9 45.5 ...x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.00273 | 1 |
| 0.31933 | 1 |
| 0.49346 | 1 |
| 1.1581 | 1 |
| 3.01739 | 1 |
| 3.22235 | 1 |
| 3.25227 | 1 |
| 4.03125 | 1 |
| 4.23875 | 1 |
| 4.60655 | 1 |
| 4.67722 | 1 |
| 4.86219 | 1 |
| 4.96416 | 1 |
| 5.29901 | 1 |
| 5.90726 | 1 |
| 6.94536 | 1 |
| 7.60946 | 1 |
| 8.82525 | 1 |
| 8.8321 | 1 |
| 9.87553 | 1 |
| 9.97227 | 1 |
| 10.06695 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.00273 3.00273 6.00273 9.00273 12.00273distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.00273,3] | 3 | 0.1428571 | 3 |
| (3,6] | 11 | 0.5238095 | 14 |
| (6,9] | 4 | 0.1904762 | 18 |
| (9,12] | 3 | 0.1428571 | 21 |
str(Freq_table)## 'data.frame': 4 obs. of 4 variables:
## $ distance: Factor w/ 4 levels "(0.00273,3]",..: 1 2 3 4
## $ Freq : int 3 11 4 3
## $ Rel_Freq: num 0.143 0.524 0.19 0.143
## $ Cum_Freq: int 3 14 18 21df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.00273,3] | 3 |
| (3,6] | 11 |
| (6,9] | 4 |
| (9,12] | 3 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_GT)## id date time continent_code country_name country_code
## nbr.val 2.200000e+01 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 2.300000e+02 NA NA NA NA NA
## max 7.442000e+03 NA NA NA NA NA
## range 7.212000e+03 NA NA NA NA NA
## sum 1.086050e+05 NA NA NA NA NA
## median 6.680000e+03 NA NA NA NA NA
## mean 4.936591e+03 NA NA NA NA NA
## SE.mean 5.803080e+02 NA NA NA NA NA
## CI.mean.0.95 1.206817e+03 NA NA NA NA NA
## var 7.408663e+06 NA NA NA NA NA
## std.dev 2.721886e+03 NA NA NA NA NA
## coef.var 5.513696e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 2.200000e+01 NA 22.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 2.654000e+03 NA 0.0027300 NA
## max NA 1.246940e+05 NA 10.0669500 NA
## range NA 1.220400e+05 NA 10.0642200 NA
## sum NA 9.383360e+05 NA 112.1789400 NA
## median NA 2.643100e+04 NA 4.7697050 NA
## mean NA 4.265164e+04 NA 5.0990427 NA
## SE.mean NA 9.849090e+03 NA 0.6720603 NA
## CI.mean.0.95 NA 2.048230e+04 NA 1.3976259 NA
## var NA 2.134100e+09 NA 9.9366315 NA
## std.dev NA 4.619633e+04 NA 3.1522423 NA
## coef.var NA 1.083108e+00 NA 0.6182028 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 22.00000000 2.200000e+01 NA NA NA
## nbr.null 0.00000000 0.000000e+00 NA NA NA
## nbr.na 0.00000000 0.000000e+00 NA NA NA
## min 13.28170000 -8.990440e+01 NA NA NA
## max 14.00070000 -8.808430e+01 NA NA NA
## range 0.71900000 1.820100e+00 NA NA NA
## sum 301.25530000 -1.961688e+03 NA NA NA
## median 13.71515000 -8.926030e+01 NA NA NA
## mean 13.69342273 -8.916765e+01 NA NA NA
## SE.mean 0.03809807 1.112458e-01 NA NA NA
## CI.mean.0.95 0.07922927 2.313484e-01 NA NA NA
## var 0.03193218 2.722640e-01 NA NA NA
## std.dev 0.17869578 5.217892e-01 NA NA NA
## coef.var 0.01304975 -5.851777e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities
## nbr.val NA NA NA 14.0000000 18.000000
## nbr.null NA NA NA 10.0000000 13.000000
## nbr.na NA NA NA 8.0000000 4.000000
## min NA NA NA 0.0000000 0.000000
## max NA NA NA 2.0000000 32.000000
## range NA NA NA 2.0000000 32.000000
## sum NA NA NA 6.0000000 63.000000
## median NA NA NA 0.0000000 0.000000
## mean NA NA NA 0.4285714 3.500000
## SE.mean NA NA NA 0.2020305 2.107022
## CI.mean.0.95 NA NA NA 0.4364604 4.445428
## var NA NA NA 0.5714286 79.911765
## std.dev NA NA NA 0.7559289 8.939338
## coef.var NA NA NA 1.7638342 2.554097
## source_name source_link prop ypos
## nbr.val NA NA 2.200000e+01 22.0000000
## nbr.null NA NA 0.000000e+00 0.0000000
## nbr.na NA NA 0.000000e+00 0.0000000
## min NA NA 2.433612e-03 1.8892806
## max NA NA 8.974011e+00 97.6381440
## range NA NA 8.971577e+00 95.7488634
## sum NA NA 1.000000e+02 1038.4834890
## median NA NA 4.251872e+00 44.1153638
## mean NA NA 4.545455e+00 47.2037950
## SE.mean NA NA 5.990967e-01 6.6246536
## CI.mean.0.95 NA NA 1.245890e+00 13.7767213
## var NA NA 7.896171e+00 965.4927696
## std.dev NA NA 2.810013e+00 31.0723795
## coef.var NA NA 6.182028e-01 0.6582602boxplot(data, horizontal=TRUE, col='green')
Gráfico para Alta Verapaz (Guatemala)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_GT <- subset(df, country_name == "Guatemala")
knitr::kable(head(df_GT)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 165 | 8/9/07 | NA | NA | Guatemala | GT | Guatemala | 47247 | San José Pinula | 4.74385 | NA | 14.5667 | -90.4500 | (14.566700000000001, -90.45) | Landslide | Mudslide | Medium | Rain | NA | NA | 5 | International Herald | http://www.iht.com/articles/ap/2007/08/09/america/LA-GEN-Guatemala-Deadly-Mudslide.php |
| 198 | 8/21/07 | NA | NA | Guatemala | GT | Alta Verapaz | 2006 | Lanquín | 13.39817 | NA | 15.6046 | -90.0853 | (15.6046, -90.085300000000004) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Dean | NA | NA | United Nations Development Programme - Relief Web | http://www.reliefweb.int/rw/RWB.NSF/db900SID/EDIS-76BSG6?OpenDocument |
| 199 | 8/21/07 | NA | NA | Guatemala | GT | Izabal | 18994 | Morales | 12.55184 | NA | 15.5163 | -88.9286 | (15.516299999999999, -88.928600000000003) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Dean | NA | NA | United Nations Development Programme - Relief Web | http://www.reliefweb.int/rw/RWB.NSF/db900SID/EDIS-76BSG6?OpenDocument |
| 277 | 9/22/07 | NA | NA | Guatemala | GT | Guatemala | 994938 | Guatemala City | 2.79113 | NA | 14.6229 | -90.5316 | (14.6229, -90.531599999999997) | Landslide | Mudslide | Medium | Rain | NA | NA | 3 | Fox News | http://www.foxnews.com/story/0,2933,297714,00.html |
| 563 | 6/1/08 | NA | NA | Guatemala | GT | Escuintla | 31329 | Palín | 3.10150 | NA | 14.4226 | -90.6755 | (14.422599999999999, -90.6755) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Storm Arthur | NA | 1 | NA | http://209.85.215.104/search?q=cache:QU_lPxNfk78J:www.plenglish.com/article.asp?ID=%7B1D4A74F7-CDCA-49D0-ABD4-D2E0FD9D2130%7D&language=EN+Colom+said+the+declaration+came+after+a+death+in+Palin+and+40+houses+partially&hl=en&ct=clnk&cd=1&gl=us&c |
| 591 | 6/18/08 | NA | NA | Guatemala | GT | Guatemala | 994938 | Guatemala City | 3.12614 | NA | 14.6510 | -90.5403 | (14.651, -90.540300000000002) | Landslide | Complex | Medium | Rain | NA | NA | 8 | NA | http://cnnwire.blogs.cnn.com/2008/06/20/8-dead-in-rough-weather-in-guatemala/ |
library(dplyr)
df_GT <- subset(df, state == "Alta Verapaz")
knitr::kable(head(df_GT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 198 | 8/21/07 | NA | NA | Guatemala | GT | Alta Verapaz | 2006 | Lanquín | 13.39817 | NA | 15.6046 | -90.0853 | (15.6046, -90.085300000000004) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Dean | NA | NA | United Nations Development Programme - Relief Web | http://www.reliefweb.int/rw/RWB.NSF/db900SID/EDIS-76BSG6?OpenDocument |
| 2354 | 8/28/10 | NA | NA | Guatemala | GT | Alta Verapaz | 5633 | Senahú | 2.30104 | NA | 15.4168 | -89.8207 | (15.4168, -89.820700000000002) | Landslide | Mudslide | Medium | Downpour | NA | NA | 2 | NA | NA |
| 7433 | 10/15/15 | NA | NA | Guatemala | GT | Alta Verapaz | 4671 | Cahabón | 5.14479 | Unknown | 15.5779 | -89.7321 | (15.5779, -89.732100000000003) | Landslide | Landslide | Medium | Rain | NA | 0 | 1 | El Periodico | http://elperiodico.com.gt/2015/10/20/pais/para-insivumeh-lluvia-es-fuerte-pero-diferente-a-la-del-mitch/ |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_GT, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_GT, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_GT, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_GT <- df_GT %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_GT$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_GT, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_GT$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 2.30104 |
| 13.39817 |
| 5.14479 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_GT$distance
names(distance) <- df_GT$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Lanquín 13.39817 13.39817 64.27831 64.27831
## Cahabón 5.14479 18.54296 24.68235 88.96066
## Senahú 2.30104 20.84400 11.03934 100.00000stem(df_GT$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 2
## 0 | 5
## 1 | 3head(df_GT)## # A tibble: 3 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 2354 8/28/10 <NA> <NA> Guatemala GT Alta~ 5633
## 2 198 8/21/07 <NA> <NA> Guatemala GT Alta~ 2006
## 3 7433 10/15/15 <NA> <NA> Guatemala GT Alta~ 4671
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_GT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2354 | 8/28/10 | NA | NA | Guatemala | GT | Alta Verapaz | 5633 | Senahú | 2.30104 | NA | 15.4168 | -89.8207 | (15.4168, -89.820700000000002) | Landslide | Mudslide | Medium | Downpour | NA | NA | 2 | NA | NA | 11.03934 | 5.51967 |
| 198 | 8/21/07 | NA | NA | Guatemala | GT | Alta Verapaz | 2006 | Lanquín | 13.39817 | NA | 15.6046 | -90.0853 | (15.6046, -90.085300000000004) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Dean | NA | NA | United Nations Development Programme - Relief Web | http://www.reliefweb.int/rw/RWB.NSF/db900SID/EDIS-76BSG6?OpenDocument | 64.27831 | 43.17849 |
| 7433 | 10/15/15 | NA | NA | Guatemala | GT | Alta Verapaz | 4671 | Cahabón | 5.14479 | Unknown | 15.5779 | -89.7321 | (15.5779, -89.732100000000003) | Landslide | Landslide | Medium | Rain | NA | 0 | 1 | El Periodico | http://elperiodico.com.gt/2015/10/20/pais/para-insivumeh-lluvia-es-fuerte-pero-diferente-a-la-del-mitch/ | 24.68235 | 87.65882 |
stem(df_GT$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 2
## 0 | 5
## 1 | 3stem(df_GT$"distance", scale = 2)##
## The decimal point is at the |
##
## 2 | 3
## 4 | 1
## 6 |
## 8 |
## 10 |
## 12 | 4Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 2.30104 | 1 | 33.3 | 33.3 | 33.3 | 33.3 |
| 5.14479 | 1 | 33.3 | 33.3 | 66.7 | 66.7 |
| 13.39817 | 1 | 33.3 | 33.3 | 100.0 | 100.0 |
| Total | 3 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 4 obs. of 5 variables:
## $ n : num 1 1 1 3
## $ % : num 33.3 33.3 33.3 100
## $ val% : num 33.3 33.3 33.3 100
## $ %cum : num 33.3 66.7 100 100
## $ val%cum: num 33.3 66.7 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 2.30104 | 1 |
| 5.14479 | 1 |
| 13.39817 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 2.30104 6.30104 10.30104 14.30104distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (2.3,6.3] | 1 | 0.5 | 1 |
| (6.3,10.3] | 0 | 0.0 | 1 |
| (10.3,14.3] | 1 | 0.5 | 2 |
str(Freq_table)## 'data.frame': 3 obs. of 4 variables:
## $ distance: Factor w/ 3 levels "(2.3,6.3]","(6.3,10.3]",..: 1 2 3
## $ Freq : int 1 0 1
## $ Rel_Freq: num 0.5 0 0.5
## $ Cum_Freq: int 1 1 2df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (2.3,6.3] | 1 |
| (6.3,10.3] | 0 |
| (10.3,14.3] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_GT)## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 3.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 1.980000e+02 NA NA NA NA NA
## max 7.433000e+03 NA NA NA NA NA
## range 7.235000e+03 NA NA NA NA NA
## sum 9.985000e+03 NA NA NA NA NA
## median 2.354000e+03 NA NA NA NA NA
## mean 3.328333e+03 NA NA NA NA NA
## SE.mean 2.144629e+03 NA NA NA NA NA
## CI.mean.0.95 9.227594e+03 NA NA NA NA NA
## var 1.379830e+07 NA NA NA NA NA
## std.dev 3.714606e+03 NA NA NA NA NA
## coef.var 1.116056e+00 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 3.000000e+00 NA 3.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 2.006000e+03 NA 2.3010400 NA
## max NA 5.633000e+03 NA 13.3981700 NA
## range NA 3.627000e+03 NA 11.0971300 NA
## sum NA 1.231000e+04 NA 20.8440000 NA
## median NA 4.671000e+03 NA 5.1447900 NA
## mean NA 4.103333e+03 NA 6.9480000 NA
## SE.mean NA 1.084814e+03 NA 3.3279247 NA
## CI.mean.0.95 NA 4.667579e+03 NA 14.3189043 NA
## var NA 3.530466e+06 NA 33.2252483 NA
## std.dev NA 1.878954e+03 NA 5.7641347 NA
## coef.var NA 4.579091e-01 NA 0.8296106 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 3.000000000 3.000000e+00 NA NA NA
## nbr.null 0.000000000 0.000000e+00 NA NA NA
## nbr.na 0.000000000 0.000000e+00 NA NA NA
## min 15.416800000 -9.008530e+01 NA NA NA
## max 15.604600000 -8.973210e+01 NA NA NA
## range 0.187800000 3.532000e-01 NA NA NA
## sum 46.599300000 -2.696381e+02 NA NA NA
## median 15.577900000 -8.982070e+01 NA NA NA
## mean 15.533100000 -8.987937e+01 NA NA NA
## SE.mean 0.058658588 1.060957e-01 NA NA NA
## CI.mean.0.95 0.252387536 4.564930e-01 NA NA NA
## var 0.010322490 3.376889e-02 NA NA NA
## std.dev 0.101599656 1.837631e-01 NA NA NA
## coef.var 0.006540849 -2.044553e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 1 2.0000000 NA
## nbr.null NA NA NA 1 0.0000000 NA
## nbr.na NA NA NA 2 1.0000000 NA
## min NA NA NA 0 1.0000000 NA
## max NA NA NA 0 2.0000000 NA
## range NA NA NA 0 1.0000000 NA
## sum NA NA NA 0 3.0000000 NA
## median NA NA NA 0 1.5000000 NA
## mean NA NA NA 0 1.5000000 NA
## SE.mean NA NA NA NA 0.5000000 NA
## CI.mean.0.95 NA NA NA NaN 6.3531024 NA
## var NA NA NA NA 0.5000000 NA
## std.dev NA NA NA NA 0.7071068 NA
## coef.var NA NA NA NA 0.4714045 NA
## source_link prop ypos
## nbr.val NA 3.0000000 3.0000000
## nbr.null NA 0.0000000 0.0000000
## nbr.na NA 0.0000000 0.0000000
## min NA 11.0393399 5.5196699
## max NA 64.2783055 87.6588227
## range NA 53.2389656 82.1391528
## sum NA 100.0000000 136.3569852
## median NA 24.6823546 43.1784926
## mean NA 33.3333333 45.4523284
## SE.mean NA 15.9658640 23.7387717
## CI.mean.0.95 NA 68.6955683 102.1396910
## var NA 764.7264402 1690.5878507
## std.dev NA 27.6536876 41.1167588
## coef.var NA 0.8296106 0.9046128boxplot(data, horizontal=TRUE, col='green')
Gráfico para Chimaltenango (Guatemala)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_GT <- subset(df, country_name == "Guatemala")
knitr::kable(head(df_GT)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 165 | 8/9/07 | NA | NA | Guatemala | GT | Guatemala | 47247 | San José Pinula | 4.74385 | NA | 14.5667 | -90.4500 | (14.566700000000001, -90.45) | Landslide | Mudslide | Medium | Rain | NA | NA | 5 | International Herald | http://www.iht.com/articles/ap/2007/08/09/america/LA-GEN-Guatemala-Deadly-Mudslide.php |
| 198 | 8/21/07 | NA | NA | Guatemala | GT | Alta Verapaz | 2006 | Lanquín | 13.39817 | NA | 15.6046 | -90.0853 | (15.6046, -90.085300000000004) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Dean | NA | NA | United Nations Development Programme - Relief Web | http://www.reliefweb.int/rw/RWB.NSF/db900SID/EDIS-76BSG6?OpenDocument |
| 199 | 8/21/07 | NA | NA | Guatemala | GT | Izabal | 18994 | Morales | 12.55184 | NA | 15.5163 | -88.9286 | (15.516299999999999, -88.928600000000003) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Dean | NA | NA | United Nations Development Programme - Relief Web | http://www.reliefweb.int/rw/RWB.NSF/db900SID/EDIS-76BSG6?OpenDocument |
| 277 | 9/22/07 | NA | NA | Guatemala | GT | Guatemala | 994938 | Guatemala City | 2.79113 | NA | 14.6229 | -90.5316 | (14.6229, -90.531599999999997) | Landslide | Mudslide | Medium | Rain | NA | NA | 3 | Fox News | http://www.foxnews.com/story/0,2933,297714,00.html |
| 563 | 6/1/08 | NA | NA | Guatemala | GT | Escuintla | 31329 | Palín | 3.10150 | NA | 14.4226 | -90.6755 | (14.422599999999999, -90.6755) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Storm Arthur | NA | 1 | NA | http://209.85.215.104/search?q=cache:QU_lPxNfk78J:www.plenglish.com/article.asp?ID=%7B1D4A74F7-CDCA-49D0-ABD4-D2E0FD9D2130%7D&language=EN+Colom+said+the+declaration+came+after+a+death+in+Palin+and+40+houses+partially&hl=en&ct=clnk&cd=1&gl=us&c |
| 591 | 6/18/08 | NA | NA | Guatemala | GT | Guatemala | 994938 | Guatemala City | 3.12614 | NA | 14.6510 | -90.5403 | (14.651, -90.540300000000002) | Landslide | Complex | Medium | Rain | NA | NA | 8 | NA | http://cnnwire.blogs.cnn.com/2008/06/20/8-dead-in-rough-weather-in-guatemala/ |
library(dplyr)
df_GT <- subset(df, state == "Chimaltenango")
knitr::kable(head(df_GT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 852 | 10/18/08 | NA | NA | Guatemala | GT | Chimaltenango | 5987 | San José Poaquil | 5.31511 | NA | 14.8667 | -90.9167 | (14.8667, -90.916700000000006) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Depression 16 | NA | NA | NA | http://www.reliefweb.int/rw/rwb.nsf/db900SID/KSAI-7KM5GH?OpenDocument |
| 1921 | 5/30/10 | NA | NA | Guatemala | GT | Chimaltenango | 2396 | Santa Apolonia | 0.99952 | NA | 14.7833 | -90.9667 | (14.783300000000001, -90.966700000000003) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Cyclone Agatha | NA | 11 | NA | http://www.cbc.ca/world/story/2010/06/01/central-america-agatha.html |
| 2388 | 9/4/10 | NA | NA | Guatemala | GT | Chimaltenango | 82370 | Chimaltenango | 1.36473 | NA | 14.6510 | -90.8267 | (14.651, -90.826700000000002) | Landslide | Landslide | Medium | Downpour | NA | NA | 10 | NA | http://www.google.com/hostednews/afp/article/ALeqM5hL3jdiAHX4wFkaLtnQWfIwxDhHBQ |
| 7413 | 9/27/15 | NA | NA | Guatemala | GT | Chimaltenango | 16494 | Patzicía | 5.52205 | Above road | 14.6614 | -90.9681 | (14.6614, -90.968100000000007) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | CONRED | http://www.redhum.org/documento_detail/conred-boletin-informativo-no-4038-lluvias-del-domingo-generaron-22-incidentes-en-6-departamentos |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_GT, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_GT, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_GT, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_GT <- df_GT %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_GT$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_GT, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_GT$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 0.99952 |
| 5.31511 |
| 5.52205 |
| 1.36473 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_GT$distance
names(distance) <- df_GT$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Patzicía 5.522050 5.522050 41.829244 41.829244
## San José Poaquil 5.315110 10.837160 40.261684 82.090928
## Chimaltenango 1.364730 12.201890 10.337759 92.428688
## Santa Apolonia 0.999520 13.201410 7.571312 100.000000stem(df_GT$"distance")##
## The decimal point is at the |
##
## 0 |
## 1 | 04
## 2 |
## 3 |
## 4 |
## 5 | 35head(df_GT)## # A tibble: 4 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 1921 5/30/10 <NA> <NA> Guatemala GT Chim~ 2396
## 2 852 10/18/08 <NA> <NA> Guatemala GT Chim~ 5987
## 3 7413 9/27/15 <NA> <NA> Guatemala GT Chim~ 16494
## 4 2388 9/4/10 <NA> <NA> Guatemala GT Chim~ 82370
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_GT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1921 | 5/30/10 | NA | NA | Guatemala | GT | Chimaltenango | 2396 | Santa Apolonia | 0.99952 | NA | 14.7833 | -90.9667 | (14.783300000000001, -90.966700000000003) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Cyclone Agatha | NA | 11 | NA | http://www.cbc.ca/world/story/2010/06/01/central-america-agatha.html | 7.571313 | 3.785656 |
| 852 | 10/18/08 | NA | NA | Guatemala | GT | Chimaltenango | 5987 | San José Poaquil | 5.31511 | NA | 14.8667 | -90.9167 | (14.8667, -90.916700000000006) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Depression 16 | NA | NA | NA | http://www.reliefweb.int/rw/rwb.nsf/db900SID/KSAI-7KM5GH?OpenDocument | 40.261684 | 27.702154 |
| 7413 | 9/27/15 | NA | NA | Guatemala | GT | Chimaltenango | 16494 | Patzicía | 5.52205 | Above road | 14.6614 | -90.9681 | (14.6614, -90.968100000000007) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | CONRED | http://www.redhum.org/documento_detail/conred-boletin-informativo-no-4038-lluvias-del-domingo-generaron-22-incidentes-en-6-departamentos | 41.829244 | 68.747619 |
| 2388 | 9/4/10 | NA | NA | Guatemala | GT | Chimaltenango | 82370 | Chimaltenango | 1.36473 | NA | 14.6510 | -90.8267 | (14.651, -90.826700000000002) | Landslide | Landslide | Medium | Downpour | NA | NA | 10 | NA | http://www.google.com/hostednews/afp/article/ALeqM5hL3jdiAHX4wFkaLtnQWfIwxDhHBQ | 10.337759 | 94.831120 |
stem(df_GT$"distance")##
## The decimal point is at the |
##
## 0 |
## 1 | 04
## 2 |
## 3 |
## 4 |
## 5 | 35stem(df_GT$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 |
## 1 | 04
## 1 |
## 2 |
## 2 |
## 3 |
## 3 |
## 4 |
## 4 |
## 5 | 3
## 5 | 5Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.99952 | 1 | 25 | 25 | 25 | 25 |
| 1.36473 | 1 | 25 | 25 | 50 | 50 |
| 5.31511 | 1 | 25 | 25 | 75 | 75 |
| 5.52205 | 1 | 25 | 25 | 100 | 100 |
| Total | 4 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 5 obs. of 5 variables:
## $ n : num 1 1 1 1 4
## $ % : num 25 25 25 25 100
## $ val% : num 25 25 25 25 100
## $ %cum : num 25 50 75 100 100
## $ val%cum: num 25 50 75 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.99952 | 1 |
| 1.36473 | 1 |
| 5.31511 | 1 |
| 5.52205 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.99952 2.99952 4.99952 6.99952distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (1,3] | 1 | 0.3333333 | 1 |
| (3,5] | 0 | 0.0000000 | 1 |
| (5,7] | 2 | 0.6666667 | 3 |
str(Freq_table)## 'data.frame': 3 obs. of 4 variables:
## $ distance: Factor w/ 3 levels "(1,3]","(3,5]",..: 1 2 3
## $ Freq : int 1 0 2
## $ Rel_Freq: num 0.333 0 0.667
## $ Cum_Freq: int 1 1 3df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (1,3] | 1 |
| (3,5] | 0 |
| (5,7] | 2 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_GT)## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 4.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 8.520000e+02 NA NA NA NA NA
## max 7.413000e+03 NA NA NA NA NA
## range 6.561000e+03 NA NA NA NA NA
## sum 1.257400e+04 NA NA NA NA NA
## median 2.154500e+03 NA NA NA NA NA
## mean 3.143500e+03 NA NA NA NA NA
## SE.mean 1.459020e+03 NA NA NA NA NA
## CI.mean.0.95 4.643254e+03 NA NA NA NA NA
## var 8.514963e+06 NA NA NA NA NA
## std.dev 2.918041e+03 NA NA NA NA NA
## coef.var 9.282777e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 4.000000e+00 NA 4.000000 NA
## nbr.null NA 0.000000e+00 NA 0.000000 NA
## nbr.na NA 0.000000e+00 NA 0.000000 NA
## min NA 2.396000e+03 NA 0.999520 NA
## max NA 8.237000e+04 NA 5.522050 NA
## range NA 7.997400e+04 NA 4.522530 NA
## sum NA 1.072470e+05 NA 13.201410 NA
## median NA 1.124050e+04 NA 3.339920 NA
## mean NA 2.681175e+04 NA 3.300352 NA
## SE.mean NA 1.875938e+04 NA 1.225957 NA
## CI.mean.0.95 NA 5.970073e+04 NA 3.901543 NA
## var NA 1.407658e+09 NA 6.011884 NA
## std.dev NA 3.751877e+04 NA 2.451914 NA
## coef.var NA 1.399341e+00 NA 0.742925 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 4.000000000 4.000000e+00 NA NA NA
## nbr.null 0.000000000 0.000000e+00 NA NA NA
## nbr.na 0.000000000 0.000000e+00 NA NA NA
## min 14.651000000 -9.096810e+01 NA NA NA
## max 14.866700000 -9.082670e+01 NA NA NA
## range 0.215700000 1.414000e-01 NA NA NA
## sum 58.962400000 -3.636782e+02 NA NA NA
## median 14.722350000 -9.094170e+01 NA NA NA
## mean 14.740600000 -9.091955e+01 NA NA NA
## SE.mean 0.051660188 3.317814e-02 NA NA NA
## CI.mean.0.95 0.164405774 1.055877e-01 NA NA NA
## var 0.010675100 4.403157e-03 NA NA NA
## std.dev 0.103320376 6.635629e-02 NA NA NA
## coef.var 0.007009238 -7.298352e-04 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 1 3.0000000 NA
## nbr.null NA NA NA 1 1.0000000 NA
## nbr.na NA NA NA 3 1.0000000 NA
## min NA NA NA 0 0.0000000 NA
## max NA NA NA 0 11.0000000 NA
## range NA NA NA 0 11.0000000 NA
## sum NA NA NA 0 21.0000000 NA
## median NA NA NA 0 10.0000000 NA
## mean NA NA NA 0 7.0000000 NA
## SE.mean NA NA NA NA 3.5118846 NA
## CI.mean.0.95 NA NA NA NaN 15.1104198 NA
## var NA NA NA NA 37.0000000 NA
## std.dev NA NA NA NA 6.0827625 NA
## coef.var NA NA NA NA 0.8689661 NA
## source_link prop ypos
## nbr.val NA 4.000000 4.0000000
## nbr.null NA 0.000000 0.0000000
## nbr.na NA 0.000000 0.0000000
## min NA 7.571312 3.7856562
## max NA 41.829244 94.8311203
## range NA 34.257932 91.0454641
## sum NA 100.000000 195.0665497
## median NA 25.299722 48.2248866
## mean NA 25.000000 48.7666374
## SE.mean NA 9.286562 20.3882673
## CI.mean.0.95 NA 29.553986 64.8845658
## var NA 344.960969 1662.7257673
## std.dev NA 18.573125 40.7765345
## coef.var NA 0.742925 0.8361564boxplot(data, horizontal=TRUE, col='green')
Gráfico para Escuintla (Guatemala)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_GT <- subset(df, country_name == "Guatemala")
knitr::kable(head(df_GT)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 165 | 8/9/07 | NA | NA | Guatemala | GT | Guatemala | 47247 | San José Pinula | 4.74385 | NA | 14.5667 | -90.4500 | (14.566700000000001, -90.45) | Landslide | Mudslide | Medium | Rain | NA | NA | 5 | International Herald | http://www.iht.com/articles/ap/2007/08/09/america/LA-GEN-Guatemala-Deadly-Mudslide.php |
| 198 | 8/21/07 | NA | NA | Guatemala | GT | Alta Verapaz | 2006 | Lanquín | 13.39817 | NA | 15.6046 | -90.0853 | (15.6046, -90.085300000000004) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Dean | NA | NA | United Nations Development Programme - Relief Web | http://www.reliefweb.int/rw/RWB.NSF/db900SID/EDIS-76BSG6?OpenDocument |
| 199 | 8/21/07 | NA | NA | Guatemala | GT | Izabal | 18994 | Morales | 12.55184 | NA | 15.5163 | -88.9286 | (15.516299999999999, -88.928600000000003) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Dean | NA | NA | United Nations Development Programme - Relief Web | http://www.reliefweb.int/rw/RWB.NSF/db900SID/EDIS-76BSG6?OpenDocument |
| 277 | 9/22/07 | NA | NA | Guatemala | GT | Guatemala | 994938 | Guatemala City | 2.79113 | NA | 14.6229 | -90.5316 | (14.6229, -90.531599999999997) | Landslide | Mudslide | Medium | Rain | NA | NA | 3 | Fox News | http://www.foxnews.com/story/0,2933,297714,00.html |
| 563 | 6/1/08 | NA | NA | Guatemala | GT | Escuintla | 31329 | Palín | 3.10150 | NA | 14.4226 | -90.6755 | (14.422599999999999, -90.6755) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Storm Arthur | NA | 1 | NA | http://209.85.215.104/search?q=cache:QU_lPxNfk78J:www.plenglish.com/article.asp?ID=%7B1D4A74F7-CDCA-49D0-ABD4-D2E0FD9D2130%7D&language=EN+Colom+said+the+declaration+came+after+a+death+in+Palin+and+40+houses+partially&hl=en&ct=clnk&cd=1&gl=us&c |
| 591 | 6/18/08 | NA | NA | Guatemala | GT | Guatemala | 994938 | Guatemala City | 3.12614 | NA | 14.6510 | -90.5403 | (14.651, -90.540300000000002) | Landslide | Complex | Medium | Rain | NA | NA | 8 | NA | http://cnnwire.blogs.cnn.com/2008/06/20/8-dead-in-rough-weather-in-guatemala/ |
library(dplyr)
df_GT <- subset(df, state == "Escuintla")
knitr::kable(head(df_GT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 563 | 6/1/08 | NA | NA | Guatemala | GT | Escuintla | 31329 | Palín | 3.10150 | NA | 14.4226 | -90.6755 | (14.422599999999999, -90.6755) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Storm Arthur | NA | 1 | NA | http://209.85.215.104/search?q=cache:QU_lPxNfk78J:www.plenglish.com/article.asp?ID=%7B1D4A74F7-CDCA-49D0-ABD4-D2E0FD9D2130%7D&language=EN+Colom+said+the+declaration+came+after+a+death+in+Palin+and+40+houses+partially&hl=en&ct=clnk&cd=1&gl=us&c |
| 1914 | 5/29/10 | NA | NA | Guatemala | GT | Escuintla | 31329 | Palín | 0.18542 | NA | 14.4039 | -90.6986 | (14.4039, -90.698599999999999) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Cyclone Agatha | NA | 0 | NA | http://www.odt.co.nz/news/dunedin/108264/landslide-shunts-camp-building |
| 7434 | 5/4/15 | 13:32 | NA | Guatemala | GT | Escuintla | 11121 | Nueva Concepción | 8.25465 | Above road | 14.2202 | -91.2264 | (14.2202, -91.226399999999998) | Landslide | Landslide | Medium | Unknown | NA | 0 | 0 | Prensa Libre | http://www.prensalibre.com/guatemala/escuintla/deslizamiento-afecto-servicio-de-energia-electrica |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_GT, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_GT, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_GT, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_GT <- df_GT %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_GT$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_GT, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_GT$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 3.10150 |
| 0.18542 |
| 8.25465 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_GT$distance
names(distance) <- df_GT$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Nueva Concepción 8.254650 8.254650 71.521032 71.521032
## Palín 3.101500 11.356150 26.872427 98.393459
## Palín 0.185420 11.541570 1.606541 100.000000stem(df_GT$"distance")##
## The decimal point is at the |
##
## 0 | 2
## 2 | 1
## 4 |
## 6 |
## 8 | 3head(df_GT)## # A tibble: 3 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 563 6/1/08 <NA> <NA> Guatemala GT Escuintla 31329
## 2 1914 5/29/10 <NA> <NA> Guatemala GT Escuintla 31329
## 3 7434 5/4/15 13:32 <NA> Guatemala GT Escuintla 11121
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_GT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 563 | 6/1/08 | NA | NA | Guatemala | GT | Escuintla | 31329 | Palín | 3.10150 | NA | 14.4226 | -90.6755 | (14.422599999999999, -90.6755) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Storm Arthur | NA | 1 | NA | http://209.85.215.104/search?q=cache:QU_lPxNfk78J:www.plenglish.com/article.asp?ID=%7B1D4A74F7-CDCA-49D0-ABD4-D2E0FD9D2130%7D&language=EN+Colom+said+the+declaration+came+after+a+death+in+Palin+and+40+houses+partially&hl=en&ct=clnk&cd=1&gl=us&c | 26.87243 | 13.43621 |
| 1914 | 5/29/10 | NA | NA | Guatemala | GT | Escuintla | 31329 | Palín | 0.18542 | NA | 14.4039 | -90.6986 | (14.4039, -90.698599999999999) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Cyclone Agatha | NA | 0 | NA | http://www.odt.co.nz/news/dunedin/108264/landslide-shunts-camp-building | 1.60654 | 27.67570 |
| 7434 | 5/4/15 | 13:32 | NA | Guatemala | GT | Escuintla | 11121 | Nueva Concepción | 8.25465 | Above road | 14.2202 | -91.2264 | (14.2202, -91.226399999999998) | Landslide | Landslide | Medium | Unknown | NA | 0 | 0 | Prensa Libre | http://www.prensalibre.com/guatemala/escuintla/deslizamiento-afecto-servicio-de-energia-electrica | 71.52103 | 64.23948 |
stem(df_GT$"distance")##
## The decimal point is at the |
##
## 0 | 2
## 2 | 1
## 4 |
## 6 |
## 8 | 3stem(df_GT$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 2
## 1 |
## 2 |
## 3 | 1
## 4 |
## 5 |
## 6 |
## 7 |
## 8 | 3Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.18542 | 1 | 33.3 | 33.3 | 33.3 | 33.3 |
| 3.1015 | 1 | 33.3 | 33.3 | 66.7 | 66.7 |
| 8.25465 | 1 | 33.3 | 33.3 | 100.0 | 100.0 |
| Total | 3 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 4 obs. of 5 variables:
## $ n : num 1 1 1 3
## $ % : num 33.3 33.3 33.3 100
## $ val% : num 33.3 33.3 33.3 100
## $ %cum : num 33.3 66.7 100 100
## $ val%cum: num 33.3 66.7 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.18542 | 1 |
| 3.1015 | 1 |
| 8.25465 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.18542 3.18542 6.18542 9.18542distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.185,3.19] | 1 | 0.5 | 1 |
| (3.19,6.19] | 0 | 0.0 | 1 |
| (6.19,9.19] | 1 | 0.5 | 2 |
str(Freq_table)## 'data.frame': 3 obs. of 4 variables:
## $ distance: Factor w/ 3 levels "(0.185,3.19]",..: 1 2 3
## $ Freq : int 1 0 1
## $ Rel_Freq: num 0.5 0 0.5
## $ Cum_Freq: int 1 1 2df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.185,3.19] | 1 |
| (3.19,6.19] | 0 |
| (6.19,9.19] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_GT)## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 3.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 5.630000e+02 NA NA NA NA NA
## max 7.434000e+03 NA NA NA NA NA
## range 6.871000e+03 NA NA NA NA NA
## sum 9.911000e+03 NA NA NA NA NA
## median 1.914000e+03 NA NA NA NA NA
## mean 3.303667e+03 NA NA NA NA NA
## SE.mean 2.101669e+03 NA NA NA NA NA
## CI.mean.0.95 9.042753e+03 NA NA NA NA NA
## var 1.325104e+07 NA NA NA NA NA
## std.dev 3.640198e+03 NA NA NA NA NA
## coef.var 1.101866e+00 NA NA NA NA NA
## state population city distance location_description latitude
## nbr.val NA 3.000000e+00 NA 3.000000 NA 3.00000000
## nbr.null NA 0.000000e+00 NA 0.000000 NA 0.00000000
## nbr.na NA 0.000000e+00 NA 0.000000 NA 0.00000000
## min NA 1.112100e+04 NA 0.185420 NA 14.22020000
## max NA 3.132900e+04 NA 8.254650 NA 14.42260000
## range NA 2.020800e+04 NA 8.069230 NA 0.20240000
## sum NA 7.377900e+04 NA 11.541570 NA 43.04670000
## median NA 3.132900e+04 NA 3.101500 NA 14.40390000
## mean NA 2.459300e+04 NA 3.847190 NA 14.34890000
## SE.mean NA 6.736000e+03 NA 2.359036 NA 0.06457603
## CI.mean.0.95 NA 2.898267e+04 NA 10.150114 NA 0.27784822
## var NA 1.361211e+08 NA 16.695158 NA 0.01251019
## std.dev NA 1.166709e+04 NA 4.085971 NA 0.11184896
## coef.var NA 4.744071e-01 NA 1.062066 NA 0.00779495
## longitude geolocation hazard_type landslide_type
## nbr.val 3.000000e+00 NA NA NA
## nbr.null 0.000000e+00 NA NA NA
## nbr.na 0.000000e+00 NA NA NA
## min -9.122640e+01 NA NA NA
## max -9.067550e+01 NA NA NA
## range 5.509000e-01 NA NA NA
## sum -2.726005e+02 NA NA NA
## median -9.069860e+01 NA NA NA
## mean -9.086683e+01 NA NA NA
## SE.mean 1.799070e-01 NA NA NA
## CI.mean.0.95 7.740772e-01 NA NA NA
## var 9.709954e-02 NA NA NA
## std.dev 3.116080e-01 NA NA NA
## coef.var -3.429282e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 1 3.0000000 NA
## nbr.null NA NA NA 1 2.0000000 NA
## nbr.na NA NA NA 2 0.0000000 NA
## min NA NA NA 0 0.0000000 NA
## max NA NA NA 0 1.0000000 NA
## range NA NA NA 0 1.0000000 NA
## sum NA NA NA 0 1.0000000 NA
## median NA NA NA 0 0.0000000 NA
## mean NA NA NA 0 0.3333333 NA
## SE.mean NA NA NA NA 0.3333333 NA
## CI.mean.0.95 NA NA NA NaN 1.4342176 NA
## var NA NA NA NA 0.3333333 NA
## std.dev NA NA NA NA 0.5773503 NA
## coef.var NA NA NA NA 1.7320508 NA
## source_link prop ypos
## nbr.val NA 3.000000 3.0000000
## nbr.null NA 0.000000 0.0000000
## nbr.na NA 0.000000 0.0000000
## min NA 1.606541 13.4362136
## max NA 71.521032 64.2394839
## range NA 69.914492 50.8032703
## sum NA 100.000000 105.3513950
## median NA 26.872427 27.6756975
## mean NA 33.333333 35.1171317
## SE.mean NA 20.439476 15.1302597
## CI.mean.0.95 NA 87.943967 65.1002531
## var NA 1253.316518 686.7742743
## std.dev NA 35.402211 26.2063785
## coef.var NA 1.062066 0.7462562boxplot(data, horizontal=TRUE, col='green')
Gráfico para Guatemala (Guatemala)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_GT <- subset(df, country_name == "Guatemala")
knitr::kable(head(df_GT)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 165 | 8/9/07 | NA | NA | Guatemala | GT | Guatemala | 47247 | San José Pinula | 4.74385 | NA | 14.5667 | -90.4500 | (14.566700000000001, -90.45) | Landslide | Mudslide | Medium | Rain | NA | NA | 5 | International Herald | http://www.iht.com/articles/ap/2007/08/09/america/LA-GEN-Guatemala-Deadly-Mudslide.php |
| 198 | 8/21/07 | NA | NA | Guatemala | GT | Alta Verapaz | 2006 | Lanquín | 13.39817 | NA | 15.6046 | -90.0853 | (15.6046, -90.085300000000004) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Dean | NA | NA | United Nations Development Programme - Relief Web | http://www.reliefweb.int/rw/RWB.NSF/db900SID/EDIS-76BSG6?OpenDocument |
| 199 | 8/21/07 | NA | NA | Guatemala | GT | Izabal | 18994 | Morales | 12.55184 | NA | 15.5163 | -88.9286 | (15.516299999999999, -88.928600000000003) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Dean | NA | NA | United Nations Development Programme - Relief Web | http://www.reliefweb.int/rw/RWB.NSF/db900SID/EDIS-76BSG6?OpenDocument |
| 277 | 9/22/07 | NA | NA | Guatemala | GT | Guatemala | 994938 | Guatemala City | 2.79113 | NA | 14.6229 | -90.5316 | (14.6229, -90.531599999999997) | Landslide | Mudslide | Medium | Rain | NA | NA | 3 | Fox News | http://www.foxnews.com/story/0,2933,297714,00.html |
| 563 | 6/1/08 | NA | NA | Guatemala | GT | Escuintla | 31329 | Palín | 3.10150 | NA | 14.4226 | -90.6755 | (14.422599999999999, -90.6755) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Storm Arthur | NA | 1 | NA | http://209.85.215.104/search?q=cache:QU_lPxNfk78J:www.plenglish.com/article.asp?ID=%7B1D4A74F7-CDCA-49D0-ABD4-D2E0FD9D2130%7D&language=EN+Colom+said+the+declaration+came+after+a+death+in+Palin+and+40+houses+partially&hl=en&ct=clnk&cd=1&gl=us&c |
| 591 | 6/18/08 | NA | NA | Guatemala | GT | Guatemala | 994938 | Guatemala City | 3.12614 | NA | 14.6510 | -90.5403 | (14.651, -90.540300000000002) | Landslide | Complex | Medium | Rain | NA | NA | 8 | NA | http://cnnwire.blogs.cnn.com/2008/06/20/8-dead-in-rough-weather-in-guatemala/ |
library(dplyr)
df_GT <- subset(df, state == "Guatemala")
knitr::kable(head(df_GT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 165 | 8/9/07 | NA | NA | Guatemala | GT | Guatemala | 47247 | San José Pinula | 4.74385 | NA | 14.5667 | -90.4500 | (14.566700000000001, -90.45) | Landslide | Mudslide | Medium | Rain | NA | NA | 5 | International Herald | http://www.iht.com/articles/ap/2007/08/09/america/LA-GEN-Guatemala-Deadly-Mudslide.php |
| 277 | 9/22/07 | NA | NA | Guatemala | GT | Guatemala | 994938 | Guatemala City | 2.79113 | NA | 14.6229 | -90.5316 | (14.6229, -90.531599999999997) | Landslide | Mudslide | Medium | Rain | NA | NA | 3 | Fox News | http://www.foxnews.com/story/0,2933,297714,00.html |
| 591 | 6/18/08 | NA | NA | Guatemala | GT | Guatemala | 994938 | Guatemala City | 3.12614 | NA | 14.6510 | -90.5403 | (14.651, -90.540300000000002) | Landslide | Complex | Medium | Rain | NA | NA | 8 | NA | http://cnnwire.blogs.cnn.com/2008/06/20/8-dead-in-rough-weather-in-guatemala/ |
| 1915 | 5/29/10 | NA | NA | Guatemala | GT | Guatemala | 71836 | Amatitlán | 2.02891 | NA | 14.4789 | -90.6319 | (14.478899999999999, -90.631900000000002) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Cyclone Agatha | NA | 0 | NA | http://news.xinhuanet.com/english2010/china/2010-05/30/c_13323403.htm |
| 1916 | 5/29/10 | NA | NA | Guatemala | GT | Guatemala | 97172 | Chinautla | 0.44764 | Urban area | 14.6969 | -90.4440 | (14.696899999999999, -90.444000000000003) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Cyclone Agatha | NA | 11 | Boston Globe | http://www.boston.com/bigpicture/2010/06/a_rough_week_for_guatemala.html#photo17 |
| 1919 | 5/30/10 | NA | NA | Guatemala | GT | Guatemala | 994938 | Guatemala City | 4.07930 | NA | 14.6066 | -90.5276 | (14.6066, -90.527600000000007) | Landslide | Landslide | Large | Tropical cyclone | Tropical Cyclone Agatha | NA | 17 | NA | http://worldnews.hometips4u.com/central-america-storm-kills-86-more-victims-feared |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_GT, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_GT, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_GT, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_GT <- df_GT %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_GT$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_GT, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_GT$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 0.65744 |
| 2.81128 |
| 2.70053 |
| 0.94245 |
| 3.96161 |
| 4.74385 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_GT$distance
names(distance) <- df_GT$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Fraijanes 6.1921800 6.1921800 7.1121567 7.1121567
## Chinautla 5.9453500 12.1375300 6.8286550 13.9408116
## San José Pinula 4.7438500 16.8813800 5.4486472 19.3894589
## Petapa 4.2072600 21.0886400 4.8323357 24.2217945
## Guatemala City 4.0793000 25.1679400 4.6853646 28.9071591
## Santa Catarina Pinula 3.9616100 29.1295500 4.5501893 33.4573483
## Chinautla 3.8564800 32.9860300 4.4294400 37.8867884
## Guatemala City 3.8031200 36.7891500 4.3681523 42.2549407
## Mixco 3.6474900 40.4366400 4.1894002 46.4443409
## Guatemala City 3.4934100 43.9300500 4.0124285 50.4567693
## Guatemala City 3.2567500 47.1868000 3.7406077 54.1973771
## Guatemala City 3.1261400 50.3129400 3.5905929 57.7879699
## Guatemala City 3.0031400 53.3160800 3.4493187 61.2372886
## Santa Catarina Pinula 2.8112800 56.1273600 3.2289539 64.4662425
## Guatemala City 2.7911300 58.9184900 3.2058102 67.6720527
## Santa Catarina Pinula 2.7005300 61.6190200 3.1017497 70.7738024
## Chinautla 2.6635800 64.2826000 3.0593100 73.8331124
## Guatemala City 2.5962000 66.8788000 2.9819193 76.8150318
## Chinautla 2.3637600 69.2425600 2.7149455 79.5299773
## Mixco 2.1041800 71.3467400 2.4167995 81.9467768
## Guatemala City 2.0842500 73.4309900 2.3939085 84.3406854
## Amatitlán 2.0289100 75.4599000 2.3303466 86.6710320
## Mixco 1.8700900 77.3299900 2.1479306 88.8189626
## Guatemala City 1.8386300 79.1686200 2.1117966 90.9307592
## Guatemala City 1.7014700 80.8700900 1.9542586 92.8850178
## Guatemala City 1.6829000 82.5529900 1.9329297 94.8179475
## Guatemala City 1.5738100 84.1268000 1.8076321 96.6255796
## Santa Catarina Pinula 0.9424500 85.0692500 1.0824705 97.7080501
## San José Pinula 0.8904000 85.9596500 1.0226874 98.7307375
## Villa Canales 0.6574400 86.6170900 0.7551163 99.4858538
## Chinautla 0.4476400 87.0647300 0.5141462 100.0000000stem(df_GT$"distance")##
## The decimal point is at the |
##
## 0 | 4799
## 1 | 67789
## 2 | 011467788
## 3 | 0135689
## 4 | 0127
## 5 | 9
## 6 | 2head(df_GT)## # A tibble: 6 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 7435 11/24/15 <NA> <NA> Guatemala GT Guatemala 122194
## 2 2350 8/28/10 <NA> <NA> Guatemala GT Guatemala 67994
## 3 6661 9/23/14 14:30 <NA> Guatemala GT Guatemala 67994
## 4 7343 10/1/15 21:30 <NA> Guatemala GT Guatemala 67994
## 5 7345 10/19/15 <NA> <NA> Guatemala GT Guatemala 67994
## 6 165 8/9/07 <NA> <NA> Guatemala GT Guatemala 47247
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_GT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 7435 | 11/24/15 | NA | NA | Guatemala | GT | Guatemala | 122194 | Villa Canales | 0.65744 | Retaining wall | 14.4758 | -90.5312 | (14.4758, -90.531199999999998) | Landslide | Landslide | Small | Rain | NA | 0 | 0 | Prensa Libre | http://www.prensalibre.com/guatemala/comunitario/madre-alcanzo-a-empujar-a-su-hija-para-salvarla-de-deslizamiento | 0.7551163 | 0.3775582 |
| 2350 | 8/28/10 | NA | NA | Guatemala | GT | Guatemala | 67994 | Santa Catarina Pinula | 2.81128 | NA | 14.5624 | -90.5205 | (14.5624, -90.520499999999998) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | NA | 3.2289539 | 2.3695933 |
| 6661 | 9/23/14 | 14:30 | NA | Guatemala | GT | Guatemala | 67994 | Santa Catarina Pinula | 2.70053 | Unknown | 14.5932 | -90.4979 | (14.5932, -90.497900000000001) | Landslide | Landslide | Medium | Rain | NA | 0 | 3 | Reliefweb | http://reliefweb.int/report/guatemala/deslizamiento-mata-esposos-e-hijo-de-3-os | 3.1017497 | 5.5349451 |
| 7343 | 10/1/15 | 21:30 | NA | Guatemala | GT | Guatemala | 67994 | Santa Catarina Pinula | 0.94245 | Urban area | 14.5755 | -90.4959 | (14.5755, -90.495900000000006) | Landslide | Mudslide | Medium | Rain | NA | 0 | 280 | CNN | http://www.cnn.com/2015/10/04/americas/guatemala-landslide-dead-missing/ | 1.0824705 | 7.6270552 |
| 7345 | 10/19/15 | NA | NA | Guatemala | GT | Guatemala | 67994 | Santa Catarina Pinula | 3.96161 | Above road | 14.5572 | -90.5300 | (14.5572, -90.53) | Landslide | Mudslide | Small | Tropical cyclone | NA | 0 | 0 | Prensa Libre | http://www.prensalibre.com/guatemala/comunitario/lluvia-causa-estragos-en-las-principales-rutas-del-pais | 4.5501893 | 10.4433851 |
| 165 | 8/9/07 | NA | NA | Guatemala | GT | Guatemala | 47247 | San José Pinula | 4.74385 | NA | 14.5667 | -90.4500 | (14.566700000000001, -90.45) | Landslide | Mudslide | Medium | Rain | NA | NA | 5 | International Herald | http://www.iht.com/articles/ap/2007/08/09/america/LA-GEN-Guatemala-Deadly-Mudslide.php | 5.4486472 | 15.4428033 |
stem(df_GT$"distance")##
## The decimal point is at the |
##
## 0 | 4799
## 1 | 67789
## 2 | 011467788
## 3 | 0135689
## 4 | 0127
## 5 | 9
## 6 | 2stem(df_GT$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 4
## 0 | 799
## 1 |
## 1 | 67789
## 2 | 0114
## 2 | 67788
## 3 | 013
## 3 | 5689
## 4 | 012
## 4 | 7
## 5 |
## 5 | 9
## 6 | 2Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.44764 | 1 | 3.2 | 3.2 | 3.2 | 3.2 |
| 0.65744 | 1 | 3.2 | 3.2 | 6.5 | 6.5 |
| 0.8904 | 1 | 3.2 | 3.2 | 9.7 | 9.7 |
| 0.94245 | 1 | 3.2 | 3.2 | 12.9 | 12.9 |
| 1.57381 | 1 | 3.2 | 3.2 | 16.1 | 16.1 |
| 1.6829 | 1 | 3.2 | 3.2 | 19.4 | 19.4 |
| 1.70147 | 1 | 3.2 | 3.2 | 22.6 | 22.6 |
| 1.83863 | 1 | 3.2 | 3.2 | 25.8 | 25.8 |
| 1.87009 | 1 | 3.2 | 3.2 | 29.0 | 29.0 |
| 2.02891 | 1 | 3.2 | 3.2 | 32.3 | 32.3 |
| 2.08425 | 1 | 3.2 | 3.2 | 35.5 | 35.5 |
| 2.10418 | 1 | 3.2 | 3.2 | 38.7 | 38.7 |
| 2.36376 | 1 | 3.2 | 3.2 | 41.9 | 41.9 |
| 2.5962 | 1 | 3.2 | 3.2 | 45.2 | 45.2 |
| 2.66358 | 1 | 3.2 | 3.2 | 48.4 | 48.4 |
| 2.70053 | 1 | 3.2 | 3.2 | 51.6 | 51.6 |
| 2.79113 | 1 | 3.2 | 3.2 | 54.8 | 54.8 |
| 2.81128 | 1 | 3.2 | 3.2 | 58.1 | 58.1 |
| 3.00314 | 1 | 3.2 | 3.2 | 61.3 | 61.3 |
| 3.12614 | 1 | 3.2 | 3.2 | 64.5 | 64.5 |
| 3.25675 | 1 | 3.2 | 3.2 | 67.7 | 67.7 |
| 3.49341 | 1 | 3.2 | 3.2 | 71.0 | 71.0 |
| 3.64749 | 1 | 3.2 | 3.2 | 74.2 | 74.2 |
| 3.80312 | 1 | 3.2 | 3.2 | 77.4 | 77.4 |
| 3.85648 | 1 | 3.2 | 3.2 | 80.6 | 80.6 |
| 3.96161 | 1 | 3.2 | 3.2 | 83.9 | 83.9 |
| 4.0793 | 1 | 3.2 | 3.2 | 87.1 | 87.1 |
| 4.20726 | 1 | 3.2 | 3.2 | 90.3 | 90.3 |
| 4.74385 | 1 | 3.2 | 3.2 | 93.5 | 93.5 |
| 5.94535 | 1 | 3.2 | 3.2 | 96.8 | 96.8 |
| 6.19218 | 1 | 3.2 | 3.2 | 100.0 | 100.0 |
| Total | 31 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 32 obs. of 5 variables:
## $ n : num 1 1 1 1 1 1 1 1 1 1 ...
## $ % : num 3.2 3.2 3.2 3.2 3.2 3.2 3.2 3.2 3.2 3.2 ...
## $ val% : num 3.2 3.2 3.2 3.2 3.2 3.2 3.2 3.2 3.2 3.2 ...
## $ %cum : num 3.2 6.5 9.7 12.9 16.1 19.4 22.6 25.8 29 32.3 ...
## $ val%cum: num 3.2 6.5 9.7 12.9 16.1 19.4 22.6 25.8 29 32.3 ...x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.44764 | 1 |
| 0.65744 | 1 |
| 0.8904 | 1 |
| 0.94245 | 1 |
| 1.57381 | 1 |
| 1.6829 | 1 |
| 1.70147 | 1 |
| 1.83863 | 1 |
| 1.87009 | 1 |
| 2.02891 | 1 |
| 2.08425 | 1 |
| 2.10418 | 1 |
| 2.36376 | 1 |
| 2.5962 | 1 |
| 2.66358 | 1 |
| 2.70053 | 1 |
| 2.79113 | 1 |
| 2.81128 | 1 |
| 3.00314 | 1 |
| 3.12614 | 1 |
| 3.25675 | 1 |
| 3.49341 | 1 |
| 3.64749 | 1 |
| 3.80312 | 1 |
| 3.85648 | 1 |
| 3.96161 | 1 |
| 4.0793 | 1 |
| 4.20726 | 1 |
| 4.74385 | 1 |
| 5.94535 | 1 |
| 6.19218 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.44764 2.44764 4.44764 6.44764distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.448,2.45] | 12 | 0.4 | 12 |
| (2.45,4.45] | 15 | 0.5 | 27 |
| (4.45,6.45] | 3 | 0.1 | 30 |
str(Freq_table)## 'data.frame': 3 obs. of 4 variables:
## $ distance: Factor w/ 3 levels "(0.448,2.45]",..: 1 2 3
## $ Freq : int 12 15 3
## $ Rel_Freq: num 0.4 0.5 0.1
## $ Cum_Freq: int 12 27 30df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.448,2.45] | 12 |
| (2.45,4.45] | 15 |
| (4.45,6.45] | 3 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_GT)## id date time continent_code country_name country_code
## nbr.val 3.100000e+01 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 1.650000e+02 NA NA NA NA NA
## max 7.435000e+03 NA NA NA NA NA
## range 7.270000e+03 NA NA NA NA NA
## sum 1.638690e+05 NA NA NA NA NA
## median 7.345000e+03 NA NA NA NA NA
## mean 5.286097e+03 NA NA NA NA NA
## SE.mean 5.051486e+02 NA NA NA NA NA
## CI.mean.0.95 1.031651e+03 NA NA NA NA NA
## var 7.910428e+06 NA NA NA NA NA
## std.dev 2.812548e+03 NA NA NA NA NA
## coef.var 5.320652e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 3.100000e+01 NA 31.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 2.849200e+04 NA 0.4476400 NA
## max NA 9.949380e+05 NA 6.1921800 NA
## range NA 9.664460e+05 NA 5.7445400 NA
## sum NA 1.556974e+07 NA 87.0647300 NA
## median NA 4.730800e+05 NA 2.7005300 NA
## mean NA 5.022497e+05 NA 2.8085397 NA
## SE.mean NA 7.918482e+04 NA 0.2511060 NA
## CI.mean.0.95 NA 1.617170e+05 NA 0.5128270 NA
## var NA 1.943773e+11 NA 1.9546816 NA
## std.dev NA 4.408824e+05 NA 1.3980993 NA
## coef.var NA 8.778152e-01 NA 0.4978029 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 3.100000e+01 3.100000e+01 NA NA NA
## nbr.null 0.000000e+00 0.000000e+00 NA NA NA
## nbr.na 0.000000e+00 0.000000e+00 NA NA NA
## min 1.442360e+01 -9.063190e+01 NA NA NA
## max 1.469690e+01 -9.041910e+01 NA NA NA
## range 2.733000e-01 2.128000e-01 NA NA NA
## sum 4.528442e+02 -2.805914e+03 NA NA NA
## median 1.462290e+01 -9.050650e+01 NA NA NA
## mean 1.460788e+01 -9.051336e+01 NA NA NA
## SE.mean 1.173315e-02 8.643431e-03 NA NA NA
## CI.mean.0.95 2.396228e-02 1.765224e-02 NA NA NA
## var 4.267668e-03 2.315976e-03 NA NA NA
## std.dev 6.532739e-02 4.812459e-02 NA NA NA
## coef.var 4.472066e-03 -5.316849e-04 NA NA NA
## landslide_size trigger storm_name injuries fatalities
## nbr.val NA NA NA 20.0000000 31.000000
## nbr.null NA NA NA 18.0000000 21.000000
## nbr.na NA NA NA 11.0000000 0.000000
## min NA NA NA 0.0000000 0.000000
## max NA NA NA 6.0000000 280.000000
## range NA NA NA 6.0000000 280.000000
## sum NA NA NA 9.0000000 337.000000
## median NA NA NA 0.0000000 0.000000
## mean NA NA NA 0.4500000 10.870968
## SE.mean NA NA NA 0.3282730 8.997938
## CI.mean.0.95 NA NA NA 0.6870833 18.376241
## var NA NA NA 2.1552632 2509.849462
## std.dev NA NA NA 1.4680815 50.098398
## coef.var NA NA NA 3.2624032 4.608458
## source_name source_link prop ypos
## nbr.val NA NA 31.0000000 31.0000000
## nbr.null NA NA 0.0000000 0.0000000
## nbr.na NA NA 0.0000000 0.0000000
## min NA NA 0.5141462 0.3775582
## max NA NA 7.1121567 98.8348267
## range NA NA 6.5980105 98.4572685
## sum NA NA 100.0000000 1491.4174144
## median NA NA 3.1017497 49.4240435
## mean NA NA 3.2258065 48.1102392
## SE.mean NA NA 0.2884130 5.3801852
## CI.mean.0.95 NA NA 0.5890180 10.9878040
## var NA NA 2.5786447 897.3381627
## std.dev NA NA 1.6058159 29.9556032
## coef.var NA NA 0.4978029 0.6226451boxplot(data, horizontal=TRUE, col='green')
Gráfico para Huehuetenango (Guatemala)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_GT <- subset(df, country_name == "Guatemala")
knitr::kable(head(df_GT)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 165 | 8/9/07 | NA | NA | Guatemala | GT | Guatemala | 47247 | San José Pinula | 4.74385 | NA | 14.5667 | -90.4500 | (14.566700000000001, -90.45) | Landslide | Mudslide | Medium | Rain | NA | NA | 5 | International Herald | http://www.iht.com/articles/ap/2007/08/09/america/LA-GEN-Guatemala-Deadly-Mudslide.php |
| 198 | 8/21/07 | NA | NA | Guatemala | GT | Alta Verapaz | 2006 | Lanquín | 13.39817 | NA | 15.6046 | -90.0853 | (15.6046, -90.085300000000004) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Dean | NA | NA | United Nations Development Programme - Relief Web | http://www.reliefweb.int/rw/RWB.NSF/db900SID/EDIS-76BSG6?OpenDocument |
| 199 | 8/21/07 | NA | NA | Guatemala | GT | Izabal | 18994 | Morales | 12.55184 | NA | 15.5163 | -88.9286 | (15.516299999999999, -88.928600000000003) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Dean | NA | NA | United Nations Development Programme - Relief Web | http://www.reliefweb.int/rw/RWB.NSF/db900SID/EDIS-76BSG6?OpenDocument |
| 277 | 9/22/07 | NA | NA | Guatemala | GT | Guatemala | 994938 | Guatemala City | 2.79113 | NA | 14.6229 | -90.5316 | (14.6229, -90.531599999999997) | Landslide | Mudslide | Medium | Rain | NA | NA | 3 | Fox News | http://www.foxnews.com/story/0,2933,297714,00.html |
| 563 | 6/1/08 | NA | NA | Guatemala | GT | Escuintla | 31329 | Palín | 3.10150 | NA | 14.4226 | -90.6755 | (14.422599999999999, -90.6755) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Storm Arthur | NA | 1 | NA | http://209.85.215.104/search?q=cache:QU_lPxNfk78J:www.plenglish.com/article.asp?ID=%7B1D4A74F7-CDCA-49D0-ABD4-D2E0FD9D2130%7D&language=EN+Colom+said+the+declaration+came+after+a+death+in+Palin+and+40+houses+partially&hl=en&ct=clnk&cd=1&gl=us&c |
| 591 | 6/18/08 | NA | NA | Guatemala | GT | Guatemala | 994938 | Guatemala City | 3.12614 | NA | 14.6510 | -90.5403 | (14.651, -90.540300000000002) | Landslide | Complex | Medium | Rain | NA | NA | 8 | NA | http://cnnwire.blogs.cnn.com/2008/06/20/8-dead-in-rough-weather-in-guatemala/ |
library(dplyr)
df_GT <- subset(df, state == "Huehuetenango")
knitr::kable(head(df_GT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 867 | 10/28/08 | NA | NA | Guatemala | GT | Huehuetenango | 1311 | San Sebastián Huehuetenango | 1.58358 | NA | 15.3760 | -91.5960 | (15.375999999999999, -91.596000000000004) | Landslide | Mudslide | Medium | Downpour | NA | NA | NA | NA | http://www.yourmileagemayvary.ca/mudslide-impeeds-our-progress-in-guatemala |
| 2352 | 8/28/10 | NA | NA | Guatemala | GT | Huehuetenango | 2121 | Malacatancito | 0.03280 | NA | 15.2164 | -91.5168 | (15.2164, -91.516800000000003) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | NA |
| 3981 | 9/20/11 | 15:00 | NA | Guatemala | GT | Huehuetenango | 14100 | Barillas | 0.45507 | NA | 15.8076 | -91.3148 | (15.807600000000001, -91.314800000000005) | Landslide | Landslide | Large | Rain | NA | NA | 15 | BNO News | http://wireupdate.com/news/three-children-found-dead-ten-others-missing-after-landslide-in-guatemala.html |
| 6040 | 5/30/14 | 18:00 | NA | Guatemala | GT | Huehuetenango | 3554 | San Pedro Necta | 0.91108 | Natural slope | 15.4918 | -91.7671 | (15.4918, -91.767099999999999) | Landslide | Mudslide | Small | Downpour | NA | 7 | 6 | Reuters UK | http://uk.reuters.com/article/2014/05/31/uk-guatemala-landslide-idUKKBN0EB0X320140531 |
| 6666 | 9/27/14 | NA | NA | Guatemala | GT | Huehuetenango | 1713 | Cuilco | 3.30989 | Below road | 15.3975 | -91.9955 | (15.397500000000001, -91.995500000000007) | Landslide | Landslide | Medium | Downpour | NA | 0 | 0 | La Noticia | http://lanoticiaenguatemala.com/tectitan-declarado-en-alerta-por-deslizamiento/ |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_GT, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_GT, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_GT, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_GT <- df_GT %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_GT$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_GT, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_GT$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 1.58358 |
| 0.91108 |
| 0.03280 |
| 3.30989 |
| 0.45507 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_GT$distance
names(distance) <- df_GT$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Cuilco 3.3098900 3.3098900 52.6012250 52.6012250
## San Sebastián Huehuetenango 1.5835800 4.8934700 25.1664701 77.7676951
## San Pedro Necta 0.9110800 5.8045500 14.4790081 92.2467032
## Barillas 0.4550700 6.2596200 7.2320347 99.4787379
## Malacatancito 0.0328000 6.2924200 0.5212621 100.0000000stem(df_GT$"distance")##
## The decimal point is at the |
##
## 0 | 059
## 1 | 6
## 2 |
## 3 | 3head(df_GT)## # A tibble: 5 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 867 10/28/08 <NA> <NA> Guatemala GT Hueh~ 1311
## 2 6040 5/30/14 18:00 <NA> Guatemala GT Hueh~ 3554
## 3 2352 8/28/10 <NA> <NA> Guatemala GT Hueh~ 2121
## 4 6666 9/27/14 <NA> <NA> Guatemala GT Hueh~ 1713
## 5 3981 9/20/11 15:00 <NA> Guatemala GT Hueh~ 14100
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_GT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 867 | 10/28/08 | NA | NA | Guatemala | GT | Huehuetenango | 1311 | San Sebastián Huehuetenango | 1.58358 | NA | 15.3760 | -91.5960 | (15.375999999999999, -91.596000000000004) | Landslide | Mudslide | Medium | Downpour | NA | NA | NA | NA | http://www.yourmileagemayvary.ca/mudslide-impeeds-our-progress-in-guatemala | 25.1664701 | 12.58324 |
| 6040 | 5/30/14 | 18:00 | NA | Guatemala | GT | Huehuetenango | 3554 | San Pedro Necta | 0.91108 | Natural slope | 15.4918 | -91.7671 | (15.4918, -91.767099999999999) | Landslide | Mudslide | Small | Downpour | NA | 7 | 6 | Reuters UK | http://uk.reuters.com/article/2014/05/31/uk-guatemala-landslide-idUKKBN0EB0X320140531 | 14.4790081 | 32.40597 |
| 2352 | 8/28/10 | NA | NA | Guatemala | GT | Huehuetenango | 2121 | Malacatancito | 0.03280 | NA | 15.2164 | -91.5168 | (15.2164, -91.516800000000003) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | NA | 0.5212621 | 39.90611 |
| 6666 | 9/27/14 | NA | NA | Guatemala | GT | Huehuetenango | 1713 | Cuilco | 3.30989 | Below road | 15.3975 | -91.9955 | (15.397500000000001, -91.995500000000007) | Landslide | Landslide | Medium | Downpour | NA | 0 | 0 | La Noticia | http://lanoticiaenguatemala.com/tectitan-declarado-en-alerta-por-deslizamiento/ | 52.6012250 | 66.46735 |
| 3981 | 9/20/11 | 15:00 | NA | Guatemala | GT | Huehuetenango | 14100 | Barillas | 0.45507 | NA | 15.8076 | -91.3148 | (15.807600000000001, -91.314800000000005) | Landslide | Landslide | Large | Rain | NA | NA | 15 | BNO News | http://wireupdate.com/news/three-children-found-dead-ten-others-missing-after-landslide-in-guatemala.html | 7.2320347 | 96.38398 |
stem(df_GT$"distance")##
## The decimal point is at the |
##
## 0 | 059
## 1 | 6
## 2 |
## 3 | 3stem(df_GT$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 0
## 0 | 59
## 1 |
## 1 | 6
## 2 |
## 2 |
## 3 | 3Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.0328 | 1 | 20 | 20 | 20 | 20 |
| 0.45507 | 1 | 20 | 20 | 40 | 40 |
| 0.91108 | 1 | 20 | 20 | 60 | 60 |
| 1.58358 | 1 | 20 | 20 | 80 | 80 |
| 3.30989 | 1 | 20 | 20 | 100 | 100 |
| Total | 5 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 6 obs. of 5 variables:
## $ n : num 1 1 1 1 1 5
## $ % : num 20 20 20 20 20 100
## $ val% : num 20 20 20 20 20 100
## $ %cum : num 20 40 60 80 100 100
## $ val%cum: num 20 40 60 80 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.0328 | 1 |
| 0.45507 | 1 |
| 0.91108 | 1 |
| 1.58358 | 1 |
| 3.30989 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.0328 2.0328 4.0328distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.0328,2.03] | 3 | 0.75 | 3 |
| (2.03,4.03] | 1 | 0.25 | 4 |
str(Freq_table)## 'data.frame': 2 obs. of 4 variables:
## $ distance: Factor w/ 2 levels "(0.0328,2.03]",..: 1 2
## $ Freq : int 3 1
## $ Rel_Freq: num 0.75 0.25
## $ Cum_Freq: int 3 4df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.0328,2.03] | 3 |
| (2.03,4.03] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_GT)## id date time continent_code country_name country_code
## nbr.val 5.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 8.670000e+02 NA NA NA NA NA
## max 6.666000e+03 NA NA NA NA NA
## range 5.799000e+03 NA NA NA NA NA
## sum 1.990600e+04 NA NA NA NA NA
## median 3.981000e+03 NA NA NA NA NA
## mean 3.981200e+03 NA NA NA NA NA
## SE.mean 1.090856e+03 NA NA NA NA NA
## CI.mean.0.95 3.028702e+03 NA NA NA NA NA
## var 5.949836e+06 NA NA NA NA NA
## std.dev 2.439229e+03 NA NA NA NA NA
## coef.var 6.126868e-01 NA NA NA NA NA
## state population city distance location_description latitude
## nbr.val NA 5.000000e+00 NA 5.0000000 NA 5.00000000
## nbr.null NA 0.000000e+00 NA 0.0000000 NA 0.00000000
## nbr.na NA 0.000000e+00 NA 0.0000000 NA 0.00000000
## min NA 1.311000e+03 NA 0.0328000 NA 15.21640000
## max NA 1.410000e+04 NA 3.3098900 NA 15.80760000
## range NA 1.278900e+04 NA 3.2770900 NA 0.59120000
## sum NA 2.279900e+04 NA 6.2924200 NA 77.28930000
## median NA 2.121000e+03 NA 0.9110800 NA 15.39750000
## mean NA 4.559800e+03 NA 1.2584840 NA 15.45786000
## SE.mean NA 2.414889e+03 NA 0.5736906 NA 0.09800952
## CI.mean.0.95 NA 6.704806e+03 NA 1.5928205 NA 0.27211805
## var NA 2.915844e+07 NA 1.6456047 NA 0.04802933
## std.dev NA 5.399856e+03 NA 1.2828113 NA 0.21915594
## coef.var NA 1.184231e+00 NA 1.0193306 NA 0.01417764
## longitude geolocation hazard_type landslide_type
## nbr.val 5.000000e+00 NA NA NA
## nbr.null 0.000000e+00 NA NA NA
## nbr.na 0.000000e+00 NA NA NA
## min -9.199550e+01 NA NA NA
## max -9.131480e+01 NA NA NA
## range 6.807000e-01 NA NA NA
## sum -4.581902e+02 NA NA NA
## median -9.159600e+01 NA NA NA
## mean -9.163804e+01 NA NA NA
## SE.mean 1.151922e-01 NA NA NA
## CI.mean.0.95 3.198247e-01 NA NA NA
## var 6.634618e-02 NA NA NA
## std.dev 2.575775e-01 NA NA NA
## coef.var -2.810814e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 2.000000 4.000000 NA
## nbr.null NA NA NA 1.000000 2.000000 NA
## nbr.na NA NA NA 3.000000 1.000000 NA
## min NA NA NA 0.000000 0.000000 NA
## max NA NA NA 7.000000 15.000000 NA
## range NA NA NA 7.000000 15.000000 NA
## sum NA NA NA 7.000000 21.000000 NA
## median NA NA NA 3.500000 3.000000 NA
## mean NA NA NA 3.500000 5.250000 NA
## SE.mean NA NA NA 3.500000 3.544362 NA
## CI.mean.0.95 NA NA NA 44.471717 11.279741 NA
## var NA NA NA 24.500000 50.250000 NA
## std.dev NA NA NA 4.949747 7.088723 NA
## coef.var NA NA NA 1.414214 1.350233 NA
## source_link prop ypos
## nbr.val NA 5.0000000 5.0000000
## nbr.null NA 0.0000000 0.0000000
## nbr.na NA 0.0000000 0.0000000
## min NA 0.5212621 12.5832351
## max NA 52.6012250 96.3839826
## range NA 52.0799629 83.8007476
## sum NA 100.0000000 247.7466539
## median NA 14.4790081 39.9061093
## mean NA 20.0000000 49.5493308
## SE.mean NA 9.1171701 14.5483379
## CI.mean.0.95 NA 25.3133222 40.3926615
## var NA 415.6139506 1058.2706780
## std.dev NA 20.3866120 32.5310725
## coef.var NA 1.0193306 0.6565391boxplot(data, horizontal=TRUE, col='green')
Gráfico para Quetzaltenang (Guatemala)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_GT <- subset(df, country_name == "Guatemala")
knitr::kable(head(df_GT)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 165 | 8/9/07 | NA | NA | Guatemala | GT | Guatemala | 47247 | San José Pinula | 4.74385 | NA | 14.5667 | -90.4500 | (14.566700000000001, -90.45) | Landslide | Mudslide | Medium | Rain | NA | NA | 5 | International Herald | http://www.iht.com/articles/ap/2007/08/09/america/LA-GEN-Guatemala-Deadly-Mudslide.php |
| 198 | 8/21/07 | NA | NA | Guatemala | GT | Alta Verapaz | 2006 | Lanquín | 13.39817 | NA | 15.6046 | -90.0853 | (15.6046, -90.085300000000004) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Dean | NA | NA | United Nations Development Programme - Relief Web | http://www.reliefweb.int/rw/RWB.NSF/db900SID/EDIS-76BSG6?OpenDocument |
| 199 | 8/21/07 | NA | NA | Guatemala | GT | Izabal | 18994 | Morales | 12.55184 | NA | 15.5163 | -88.9286 | (15.516299999999999, -88.928600000000003) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Dean | NA | NA | United Nations Development Programme - Relief Web | http://www.reliefweb.int/rw/RWB.NSF/db900SID/EDIS-76BSG6?OpenDocument |
| 277 | 9/22/07 | NA | NA | Guatemala | GT | Guatemala | 994938 | Guatemala City | 2.79113 | NA | 14.6229 | -90.5316 | (14.6229, -90.531599999999997) | Landslide | Mudslide | Medium | Rain | NA | NA | 3 | Fox News | http://www.foxnews.com/story/0,2933,297714,00.html |
| 563 | 6/1/08 | NA | NA | Guatemala | GT | Escuintla | 31329 | Palín | 3.10150 | NA | 14.4226 | -90.6755 | (14.422599999999999, -90.6755) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Storm Arthur | NA | 1 | NA | http://209.85.215.104/search?q=cache:QU_lPxNfk78J:www.plenglish.com/article.asp?ID=%7B1D4A74F7-CDCA-49D0-ABD4-D2E0FD9D2130%7D&language=EN+Colom+said+the+declaration+came+after+a+death+in+Palin+and+40+houses+partially&hl=en&ct=clnk&cd=1&gl=us&c |
| 591 | 6/18/08 | NA | NA | Guatemala | GT | Guatemala | 994938 | Guatemala City | 3.12614 | NA | 14.6510 | -90.5403 | (14.651, -90.540300000000002) | Landslide | Complex | Medium | Rain | NA | NA | 8 | NA | http://cnnwire.blogs.cnn.com/2008/06/20/8-dead-in-rough-weather-in-guatemala/ |
library(dplyr)
df_GT <- subset(df, state == "Quetzaltenango")
knitr::kable(head(df_GT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1904 | 5/26/10 | NA | NA | Guatemala | GT | Quetzaltenango | 11913 | Almolonga | 0.77254 | NA | 14.8123 | -91.4944 | (14.8123, -91.494399999999999) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Cyclone Agatha | NA | 4 | NA | http://www.mb.com.ph/articles/259475/50-families-lose-homes-la-union-landslide |
| 2385 | 9/4/10 | NA | NA | Guatemala | GT | Quetzaltenango | 19115 | Colomba | 0.92729 | NA | 14.7085 | -91.7314 | (14.708500000000001, -91.731399999999994) | Landslide | Landslide | Medium | Downpour | NA | NA | 4 | NA | http://www.upi.com/Top_News/World-News/2010/09/05/Rain-blamed-for-21-deaths-in-Guatemala/UPI-36581283666884/ |
| 7439 | 10/6/15 | NA | NA | Guatemala | GT | Quetzaltenango | 45654 | Coatepeque | 1.81216 | Above road | 14.7159 | -91.8708 | (14.7159, -91.870800000000003) | Landslide | Landslide | Small | Rain | NA | 0 | 0 | Canal Antigua | https://canalantigua.tv/derrumbe-en-coatepeque/ |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_GT, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_GT, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_GT, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_GT <- df_GT %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_GT$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_GT, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_GT$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 0.92729 |
| 1.81216 |
| 0.77254 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_GT$distance
names(distance) <- df_GT$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Coatepeque 1.81216 1.81216 51.59924 51.59924
## Colomba 0.92729 2.73945 26.40355 78.00278
## Almolonga 0.77254 3.51199 21.99722 100.00000stem(df_GT$"distance")##
## The decimal point is at the |
##
## 0 | 89
## 1 |
## 1 | 8head(df_GT)## # A tibble: 3 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 2385 9/4/10 <NA> <NA> Guatemala GT Quetz~ 19115
## 2 7439 10/6/15 <NA> <NA> Guatemala GT Quetz~ 45654
## 3 1904 5/26/10 <NA> <NA> Guatemala GT Quetz~ 11913
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_GT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2385 | 9/4/10 | NA | NA | Guatemala | GT | Quetzaltenango | 19115 | Colomba | 0.92729 | NA | 14.7085 | -91.7314 | (14.708500000000001, -91.731399999999994) | Landslide | Landslide | Medium | Downpour | NA | NA | 4 | NA | http://www.upi.com/Top_News/World-News/2010/09/05/Rain-blamed-for-21-deaths-in-Guatemala/UPI-36581283666884/ | 26.40355 | 13.20177 |
| 7439 | 10/6/15 | NA | NA | Guatemala | GT | Quetzaltenango | 45654 | Coatepeque | 1.81216 | Above road | 14.7159 | -91.8708 | (14.7159, -91.870800000000003) | Landslide | Landslide | Small | Rain | NA | 0 | 0 | Canal Antigua | https://canalantigua.tv/derrumbe-en-coatepeque/ | 51.59924 | 52.20317 |
| 1904 | 5/26/10 | NA | NA | Guatemala | GT | Quetzaltenango | 11913 | Almolonga | 0.77254 | NA | 14.8123 | -91.4944 | (14.8123, -91.494399999999999) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Cyclone Agatha | NA | 4 | NA | http://www.mb.com.ph/articles/259475/50-families-lose-homes-la-union-landslide | 21.99722 | 89.00139 |
stem(df_GT$"distance")##
## The decimal point is at the |
##
## 0 | 89
## 1 |
## 1 | 8stem(df_GT$"distance", scale = 2)##
## The decimal point is 1 digit(s) to the left of the |
##
## 6 | 7
## 8 | 3
## 10 |
## 12 |
## 14 |
## 16 |
## 18 | 1Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.77254 | 1 | 33.3 | 33.3 | 33.3 | 33.3 |
| 0.92729 | 1 | 33.3 | 33.3 | 66.7 | 66.7 |
| 1.81216 | 1 | 33.3 | 33.3 | 100.0 | 100.0 |
| Total | 3 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 4 obs. of 5 variables:
## $ n : num 1 1 1 3
## $ % : num 33.3 33.3 33.3 100
## $ val% : num 33.3 33.3 33.3 100
## $ %cum : num 33.3 66.7 100 100
## $ val%cum: num 33.3 66.7 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.77254 | 1 |
| 0.92729 | 1 |
| 1.81216 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.77254 1.77254 2.77254distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.773,1.77] | 1 | 0.5 | 1 |
| (1.77,2.77] | 1 | 0.5 | 2 |
str(Freq_table)## 'data.frame': 2 obs. of 4 variables:
## $ distance: Factor w/ 2 levels "(0.773,1.77]",..: 1 2
## $ Freq : int 1 1
## $ Rel_Freq: num 0.5 0.5
## $ Cum_Freq: int 1 2df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.773,1.77] | 1 |
| (1.77,2.77] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_GT)## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 3.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 1.904000e+03 NA NA NA NA NA
## max 7.439000e+03 NA NA NA NA NA
## range 5.535000e+03 NA NA NA NA NA
## sum 1.172800e+04 NA NA NA NA NA
## median 2.385000e+03 NA NA NA NA NA
## mean 3.909333e+03 NA NA NA NA NA
## SE.mean 1.770287e+03 NA NA NA NA NA
## CI.mean.0.95 7.616931e+03 NA NA NA NA NA
## var 9.401750e+06 NA NA NA NA NA
## std.dev 3.066227e+03 NA NA NA NA NA
## coef.var 7.843351e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 3.000000e+00 NA 3.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 1.191300e+04 NA 0.7725400 NA
## max NA 4.565400e+04 NA 1.8121600 NA
## range NA 3.374100e+04 NA 1.0396200 NA
## sum NA 7.668200e+04 NA 3.5119900 NA
## median NA 1.911500e+04 NA 0.9272900 NA
## mean NA 2.556067e+04 NA 1.1706633 NA
## SE.mean NA 1.025953e+04 NA 0.3238443 NA
## CI.mean.0.95 NA 4.414319e+04 NA 1.3933895 NA
## var NA 3.157737e+08 NA 0.3146254 NA
## std.dev NA 1.777002e+04 NA 0.5609148 NA
## coef.var NA 6.952097e-01 NA 0.4791427 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 3.000000000 3.000000e+00 NA NA NA
## nbr.null 0.000000000 0.000000e+00 NA NA NA
## nbr.na 0.000000000 0.000000e+00 NA NA NA
## min 14.708500000 -9.187080e+01 NA NA NA
## max 14.812300000 -9.149440e+01 NA NA NA
## range 0.103800000 3.764000e-01 NA NA NA
## sum 44.236700000 -2.750966e+02 NA NA NA
## median 14.715900000 -9.173140e+01 NA NA NA
## mean 14.745566667 -9.169887e+01 NA NA NA
## SE.mean 0.033434978 1.098682e-01 NA NA NA
## CI.mean.0.95 0.143859101 4.727246e-01 NA NA NA
## var 0.003353693 3.621305e-02 NA NA NA
## std.dev 0.057911081 1.902973e-01 NA NA NA
## coef.var 0.003927355 -2.075241e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 1 3.0000000 NA
## nbr.null NA NA NA 1 1.0000000 NA
## nbr.na NA NA NA 2 0.0000000 NA
## min NA NA NA 0 0.0000000 NA
## max NA NA NA 0 4.0000000 NA
## range NA NA NA 0 4.0000000 NA
## sum NA NA NA 0 8.0000000 NA
## median NA NA NA 0 4.0000000 NA
## mean NA NA NA 0 2.6666667 NA
## SE.mean NA NA NA NA 1.3333333 NA
## CI.mean.0.95 NA NA NA NaN 5.7368703 NA
## var NA NA NA NA 5.3333333 NA
## std.dev NA NA NA NA 2.3094011 NA
## coef.var NA NA NA NA 0.8660254 NA
## source_link prop ypos
## nbr.val NA 3.0000000 3.0000000
## nbr.null NA 0.0000000 0.0000000
## nbr.na NA 0.0000000 0.0000000
## min NA 21.9972153 13.2017745
## max NA 51.5992358 89.0013924
## range NA 29.6020205 75.7996179
## sum NA 100.0000000 154.4063337
## median NA 26.4035490 52.2031669
## mean NA 33.3333333 51.4687779
## SE.mean NA 9.2211051 21.8845456
## CI.mean.0.95 NA 39.6752130 94.1616000
## var NA 255.0863379 1436.8000131
## std.dev NA 15.9714225 37.9051449
## coef.var NA 0.4791427 0.7364687boxplot(data, horizontal=TRUE, col='green')
Gráfico para Quiché (Guatemala)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_GT <- subset(df, country_name == "Guatemala")
knitr::kable(head(df_GT)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 165 | 8/9/07 | NA | NA | Guatemala | GT | Guatemala | 47247 | San José Pinula | 4.74385 | NA | 14.5667 | -90.4500 | (14.566700000000001, -90.45) | Landslide | Mudslide | Medium | Rain | NA | NA | 5 | International Herald | http://www.iht.com/articles/ap/2007/08/09/america/LA-GEN-Guatemala-Deadly-Mudslide.php |
| 198 | 8/21/07 | NA | NA | Guatemala | GT | Alta Verapaz | 2006 | Lanquín | 13.39817 | NA | 15.6046 | -90.0853 | (15.6046, -90.085300000000004) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Dean | NA | NA | United Nations Development Programme - Relief Web | http://www.reliefweb.int/rw/RWB.NSF/db900SID/EDIS-76BSG6?OpenDocument |
| 199 | 8/21/07 | NA | NA | Guatemala | GT | Izabal | 18994 | Morales | 12.55184 | NA | 15.5163 | -88.9286 | (15.516299999999999, -88.928600000000003) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Dean | NA | NA | United Nations Development Programme - Relief Web | http://www.reliefweb.int/rw/RWB.NSF/db900SID/EDIS-76BSG6?OpenDocument |
| 277 | 9/22/07 | NA | NA | Guatemala | GT | Guatemala | 994938 | Guatemala City | 2.79113 | NA | 14.6229 | -90.5316 | (14.6229, -90.531599999999997) | Landslide | Mudslide | Medium | Rain | NA | NA | 3 | Fox News | http://www.foxnews.com/story/0,2933,297714,00.html |
| 563 | 6/1/08 | NA | NA | Guatemala | GT | Escuintla | 31329 | Palín | 3.10150 | NA | 14.4226 | -90.6755 | (14.422599999999999, -90.6755) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Storm Arthur | NA | 1 | NA | http://209.85.215.104/search?q=cache:QU_lPxNfk78J:www.plenglish.com/article.asp?ID=%7B1D4A74F7-CDCA-49D0-ABD4-D2E0FD9D2130%7D&language=EN+Colom+said+the+declaration+came+after+a+death+in+Palin+and+40+houses+partially&hl=en&ct=clnk&cd=1&gl=us&c |
| 591 | 6/18/08 | NA | NA | Guatemala | GT | Guatemala | 994938 | Guatemala City | 3.12614 | NA | 14.6510 | -90.5403 | (14.651, -90.540300000000002) | Landslide | Complex | Medium | Rain | NA | NA | 8 | NA | http://cnnwire.blogs.cnn.com/2008/06/20/8-dead-in-rough-weather-in-guatemala/ |
library(dplyr)
df_GT <- subset(df, state == "Quiché")
knitr::kable(head(df_GT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1924 | 5/30/10 | NA | NA | Guatemala | GT | Quiché | 11046 | San Juan Cotzal | 8.93658 | NA | 15.4446 | -90.9516 | (15.444599999999999, -90.951599999999999) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Cyclone Agatha | NA | 3 | NA | http://calamities.gaeatimes.com/2010/05/30/tropical-storm-agathas-torrential-rains-landslides-kill-44-in-central-america-27140/ |
| 2386 | 9/4/10 | NA | NA | Guatemala | GT | Quiché | 2090 | Chicamán | 21.83272 | NA | 15.5800 | -90.8500 | (15.58, -90.85) | Landslide | Landslide | Medium | Downpour | NA | NA | 1 | NA | http://www.upi.com/Top_News/World-News/2010/09/05/Rain-blamed-for-21-deaths-in-Guatemala/UPI-36581283666884/ |
| 2408 | 9/10/10 | NA | NA | Guatemala | GT | Quiché | 12088 | Sacapulas | 0.35171 | NA | 15.2892 | -91.0892 | (15.289199999999999, -91.089200000000005) | Landslide | Landslide | Medium | Downpour | NA | NA | 5 | NA | http://www.tmcnet.com/usubmit/2010/09/11/5001935.htm |
| 4361 | 5/15/12 | NA | NA | Guatemala | GT | Quiché | 11657 | Chajul | 7.39906 | NA | 15.5238 | -90.9778 | (15.5238, -90.977800000000002) | Landslide | Landslide | Medium | Downpour | NA | NA | 1 | NA | http://latino.foxnews.com/latino/news/2012/05/16/boy-dies-in-rains-in-guatemala/ |
| 6664 | 3/12/14 | Night | NA | Guatemala | GT | Quiché | 7850 | San Luis Ixcán | 22.56101 | Deforested slope | 15.7318 | -90.8924 | (15.7318, -90.892399999999995) | Landslide | Landslide | Medium | Downpour | NA | 0 | 0 | Hoy | http://www.hoy.com.ni/2014/03/13/deslizamiento-destruye-5-casas-en-poblado-indigena-guatemalteco/ |
| 6668 | 6/24/14 | NA | NA | Guatemala | GT | Quiché | 2693 | Chinique | 3.98185 | Unknown | 15.0771 | -91.0096 | (15.0771, -91.009600000000006) | Landslide | Landslide | Medium | Rain | NA | 0 | 2 | Noticias de Bomberos | http://noticiasdebomberosgua.blogspot.com/2014/06/muertos-por-deslizamiento-de-tierra-en.html |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_GT, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_GT, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_GT, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_GT <- df_GT %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_GT$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_GT, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_GT$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 22.56101 |
| 8.93658 |
| 0.35171 |
| 3.98185 |
| 2.27725 |
| 21.83272 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_GT$distance
names(distance) <- df_GT$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## San Luis Ixcán 22.5610100 22.5610100 33.5030438 33.5030438
## Chicamán 21.8327200 44.3937300 32.4215350 65.9245788
## San Juan Cotzal 8.9365800 53.3303100 13.2707991 79.1953779
## Chajul 7.3990600 60.7293700 10.9875857 90.1829636
## Chinique 3.9818500 64.7112200 5.9130374 96.0960009
## Chichicastenango 2.2772500 66.9884700 3.3817106 99.4777115
## Sacapulas 0.3517100 67.3401800 0.5222885 100.0000000stem(df_GT$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 024
## 0 | 79
## 1 |
## 1 |
## 2 | 23head(df_GT)## # A tibble: 6 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 6664 3/12/14 Night <NA> Guatemala GT Quiché 7850
## 2 1924 5/30/10 <NA> <NA> Guatemala GT Quiché 11046
## 3 2408 9/10/10 <NA> <NA> Guatemala GT Quiché 12088
## 4 6668 6/24/14 <NA> <NA> Guatemala GT Quiché 2693
## 5 7427 9/27/15 <NA> <NA> Guatemala GT Quiché 79759
## 6 2386 9/4/10 <NA> <NA> Guatemala GT Quiché 2090
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_GT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 6664 | 3/12/14 | Night | NA | Guatemala | GT | Quiché | 7850 | San Luis Ixcán | 22.56101 | Deforested slope | 15.7318 | -90.8924 | (15.7318, -90.892399999999995) | Landslide | Landslide | Medium | Downpour | NA | 0 | 0 | Hoy | http://www.hoy.com.ni/2014/03/13/deslizamiento-destruye-5-casas-en-poblado-indigena-guatemalteco/ | 33.5030438 | 16.75152 |
| 1924 | 5/30/10 | NA | NA | Guatemala | GT | Quiché | 11046 | San Juan Cotzal | 8.93658 | NA | 15.4446 | -90.9516 | (15.444599999999999, -90.951599999999999) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Cyclone Agatha | NA | 3 | NA | http://calamities.gaeatimes.com/2010/05/30/tropical-storm-agathas-torrential-rains-landslides-kill-44-in-central-america-27140/ | 13.2707991 | 40.13844 |
| 2408 | 9/10/10 | NA | NA | Guatemala | GT | Quiché | 12088 | Sacapulas | 0.35171 | NA | 15.2892 | -91.0892 | (15.289199999999999, -91.089200000000005) | Landslide | Landslide | Medium | Downpour | NA | NA | 5 | NA | http://www.tmcnet.com/usubmit/2010/09/11/5001935.htm | 0.5222885 | 47.03499 |
| 6668 | 6/24/14 | NA | NA | Guatemala | GT | Quiché | 2693 | Chinique | 3.98185 | Unknown | 15.0771 | -91.0096 | (15.0771, -91.009600000000006) | Landslide | Landslide | Medium | Rain | NA | 0 | 2 | Noticias de Bomberos | http://noticiasdebomberosgua.blogspot.com/2014/06/muertos-por-deslizamiento-de-tierra-en.html | 5.9130374 | 50.25265 |
| 7427 | 9/27/15 | NA | NA | Guatemala | GT | Quiché | 79759 | Chichicastenango | 2.27725 | Unknown | 14.9233 | -91.1352 | (14.923299999999999, -91.135199999999998) | Landslide | Landslide | Medium | Rain | NA | 1 | 2 | CONRED | http://www.redhum.org/documento_download/17080 | 3.3817106 | 54.90002 |
| 2386 | 9/4/10 | NA | NA | Guatemala | GT | Quiché | 2090 | Chicamán | 21.83272 | NA | 15.5800 | -90.8500 | (15.58, -90.85) | Landslide | Landslide | Medium | Downpour | NA | NA | 1 | NA | http://www.upi.com/Top_News/World-News/2010/09/05/Rain-blamed-for-21-deaths-in-Guatemala/UPI-36581283666884/ | 32.4215350 | 72.80165 |
stem(df_GT$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 024
## 0 | 79
## 1 |
## 1 |
## 2 | 23stem(df_GT$"distance", scale = 2)##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 024
## 0 | 79
## 1 |
## 1 |
## 2 | 23Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.35171 | 1 | 14.3 | 14.3 | 14.3 | 14.3 |
| 2.27725 | 1 | 14.3 | 14.3 | 28.6 | 28.6 |
| 3.98185 | 1 | 14.3 | 14.3 | 42.9 | 42.9 |
| 7.39906 | 1 | 14.3 | 14.3 | 57.1 | 57.1 |
| 8.93658 | 1 | 14.3 | 14.3 | 71.4 | 71.4 |
| 21.83272 | 1 | 14.3 | 14.3 | 85.7 | 85.7 |
| 22.56101 | 1 | 14.3 | 14.3 | 100.0 | 100.0 |
| Total | 7 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 8 obs. of 5 variables:
## $ n : num 1 1 1 1 1 1 1 7
## $ % : num 14.3 14.3 14.3 14.3 14.3 14.3 14.3 100
## $ val% : num 14.3 14.3 14.3 14.3 14.3 14.3 14.3 100
## $ %cum : num 14.3 28.6 42.9 57.1 71.4 85.7 100 100
## $ val%cum: num 14.3 28.6 42.9 57.1 71.4 85.7 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.35171 | 1 |
| 2.27725 | 1 |
| 3.98185 | 1 |
| 7.39906 | 1 |
| 8.93658 | 1 |
| 21.83272 | 1 |
| 22.56101 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.35171 8.35171 16.35171 24.35171distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.352,8.35] | 3 | 0.5000000 | 3 |
| (8.35,16.4] | 1 | 0.1666667 | 4 |
| (16.4,24.4] | 2 | 0.3333333 | 6 |
str(Freq_table)## 'data.frame': 3 obs. of 4 variables:
## $ distance: Factor w/ 3 levels "(0.352,8.35]",..: 1 2 3
## $ Freq : int 3 1 2
## $ Rel_Freq: num 0.5 0.167 0.333
## $ Cum_Freq: int 3 4 6df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.352,8.35] | 3 |
| (8.35,16.4] | 1 |
| (16.4,24.4] | 2 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_GT)## id date time continent_code country_name country_code
## nbr.val 7.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 1.924000e+03 NA NA NA NA NA
## max 7.427000e+03 NA NA NA NA NA
## range 5.503000e+03 NA NA NA NA NA
## sum 3.183800e+04 NA NA NA NA NA
## median 4.361000e+03 NA NA NA NA NA
## mean 4.548286e+03 NA NA NA NA NA
## SE.mean 8.922242e+02 NA NA NA NA NA
## CI.mean.0.95 2.183194e+03 NA NA NA NA NA
## var 5.572448e+06 NA NA NA NA NA
## std.dev 2.360603e+03 NA NA NA NA NA
## coef.var 5.190094e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 7.000000e+00 NA 7.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 2.090000e+03 NA 0.3517100 NA
## max NA 7.975900e+04 NA 22.5610100 NA
## range NA 7.766900e+04 NA 22.2093000 NA
## sum NA 1.271830e+05 NA 67.3401800 NA
## median NA 1.104600e+04 NA 7.3990600 NA
## mean NA 1.816900e+04 NA 9.6200257 NA
## SE.mean NA 1.038310e+04 NA 3.4282642 NA
## CI.mean.0.95 NA 2.540654e+04 NA 8.3886604 NA
## var NA 7.546621e+08 NA 82.2709699 NA
## std.dev NA 2.747111e+04 NA 9.0703346 NA
## coef.var NA 1.511977e+00 NA 0.9428597 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 7.00000000 7.000000e+00 NA NA NA
## nbr.null 0.00000000 0.000000e+00 NA NA NA
## nbr.na 0.00000000 0.000000e+00 NA NA NA
## min 14.92330000 -9.113520e+01 NA NA NA
## max 15.73180000 -9.085000e+01 NA NA NA
## range 0.80850000 2.852000e-01 NA NA NA
## sum 107.56980000 -6.369058e+02 NA NA NA
## median 15.44460000 -9.097780e+01 NA NA NA
## mean 15.36711429 -9.098654e+01 NA NA NA
## SE.mean 0.10867388 3.841296e-02 NA NA NA
## CI.mean.0.95 0.26591540 9.399313e-02 NA NA NA
## var 0.08267008 1.032889e-02 NA NA NA
## std.dev 0.28752405 1.016311e-01 NA NA NA
## coef.var 0.01871035 -1.116991e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 3.0000000 7.0000000 NA
## nbr.null NA NA NA 2.0000000 1.0000000 NA
## nbr.na NA NA NA 4.0000000 0.0000000 NA
## min NA NA NA 0.0000000 0.0000000 NA
## max NA NA NA 1.0000000 5.0000000 NA
## range NA NA NA 1.0000000 5.0000000 NA
## sum NA NA NA 1.0000000 14.0000000 NA
## median NA NA NA 0.0000000 2.0000000 NA
## mean NA NA NA 0.3333333 2.0000000 NA
## SE.mean NA NA NA 0.3333333 0.6172134 NA
## CI.mean.0.95 NA NA NA 1.4342176 1.5102668 NA
## var NA NA NA 0.3333333 2.6666667 NA
## std.dev NA NA NA 0.5773503 1.6329932 NA
## coef.var NA NA NA 1.7320508 0.8164966 NA
## source_link prop ypos
## nbr.val NA 7.0000000 7.0000000
## nbr.null NA 0.0000000 0.0000000
## nbr.na NA 0.0000000 0.0000000
## min NA 0.5222885 16.7515219
## max NA 33.5030438 94.5062071
## range NA 32.9807553 77.7546852
## sum NA 100.0000000 376.3854804
## median NA 10.9875857 50.2526501
## mean NA 14.2857143 53.7693543
## SE.mean NA 5.0909639 9.3054494
## CI.mean.0.95 NA 12.4571399 22.7696144
## var NA 181.4253926 606.1397184
## std.dev NA 13.4694244 24.6199049
## coef.var NA 0.9428597 0.4578799boxplot(data, horizontal=TRUE, col='green')
Gráfico para Sacatepéquez (Guatemala)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_GT <- subset(df, country_name == "Guatemala")
knitr::kable(head(df_GT)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 165 | 8/9/07 | NA | NA | Guatemala | GT | Guatemala | 47247 | San José Pinula | 4.74385 | NA | 14.5667 | -90.4500 | (14.566700000000001, -90.45) | Landslide | Mudslide | Medium | Rain | NA | NA | 5 | International Herald | http://www.iht.com/articles/ap/2007/08/09/america/LA-GEN-Guatemala-Deadly-Mudslide.php |
| 198 | 8/21/07 | NA | NA | Guatemala | GT | Alta Verapaz | 2006 | Lanquín | 13.39817 | NA | 15.6046 | -90.0853 | (15.6046, -90.085300000000004) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Dean | NA | NA | United Nations Development Programme - Relief Web | http://www.reliefweb.int/rw/RWB.NSF/db900SID/EDIS-76BSG6?OpenDocument |
| 199 | 8/21/07 | NA | NA | Guatemala | GT | Izabal | 18994 | Morales | 12.55184 | NA | 15.5163 | -88.9286 | (15.516299999999999, -88.928600000000003) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Dean | NA | NA | United Nations Development Programme - Relief Web | http://www.reliefweb.int/rw/RWB.NSF/db900SID/EDIS-76BSG6?OpenDocument |
| 277 | 9/22/07 | NA | NA | Guatemala | GT | Guatemala | 994938 | Guatemala City | 2.79113 | NA | 14.6229 | -90.5316 | (14.6229, -90.531599999999997) | Landslide | Mudslide | Medium | Rain | NA | NA | 3 | Fox News | http://www.foxnews.com/story/0,2933,297714,00.html |
| 563 | 6/1/08 | NA | NA | Guatemala | GT | Escuintla | 31329 | Palín | 3.10150 | NA | 14.4226 | -90.6755 | (14.422599999999999, -90.6755) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Storm Arthur | NA | 1 | NA | http://209.85.215.104/search?q=cache:QU_lPxNfk78J:www.plenglish.com/article.asp?ID=%7B1D4A74F7-CDCA-49D0-ABD4-D2E0FD9D2130%7D&language=EN+Colom+said+the+declaration+came+after+a+death+in+Palin+and+40+houses+partially&hl=en&ct=clnk&cd=1&gl=us&c |
| 591 | 6/18/08 | NA | NA | Guatemala | GT | Guatemala | 994938 | Guatemala City | 3.12614 | NA | 14.6510 | -90.5403 | (14.651, -90.540300000000002) | Landslide | Complex | Medium | Rain | NA | NA | 8 | NA | http://cnnwire.blogs.cnn.com/2008/06/20/8-dead-in-rough-weather-in-guatemala/ |
library(dplyr)
df_GT <- subset(df, state == "Sacatepéquez")
knitr::kable(head(df_GT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1917 | 5/29/10 | NA | NA | Guatemala | GT | Sacatepéquez | 15529 | Santa María De Jesús | 6.13527 | NA | 14.4651 | -90.7426 | (14.4651, -90.742599999999996) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Cyclone Agatha | NA | 0 | NA | http://www.boston.com/bigpicture/2010/06/a_rough_week_for_guatemala.html#photo17 |
| 2387 | 9/4/10 | NA | NA | Guatemala | GT | Sacatepéquez | 17918 | Jocotenango | 0.63089 | NA | 14.5832 | -90.7379 | (14.5832, -90.737899999999996) | Landslide | Landslide | Medium | Downpour | NA | NA | 1 | NA | http://www.upi.com/Top_News/World-News/2010/09/05/Rain-blamed-for-21-deaths-in-Guatemala/UPI-36581283666884/ |
| 7432 | 9/23/15 | NA | NA | Guatemala | GT | Sacatepéquez | 3214 | Santa Catarina Barahona | 1.45200 | Unknown | 14.5558 | -90.7998 | (14.5558, -90.799800000000005) | Landslide | Landslide | Medium | Continuous rain | NA | 0 | 0 | Prensa Libre | http://www.prensalibre.com/guatemala/comunitario/constante-lluvia-provoca-primeras-desastres-en-la-provincia |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_GT, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_GT, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_GT, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_GT <- df_GT %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_GT$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_GT, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_GT$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 6.13527 |
| 1.45200 |
| 0.63089 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_GT$distance
names(distance) <- df_GT$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Santa María De Jesús 6.135270 6.135270 74.655032 74.655032
## Santa Catarina Barahona 1.452000 7.587270 17.668188 92.323221
## Jocotenango 0.630890 8.218160 7.676779 100.000000stem(df_GT$"distance")##
## The decimal point is at the |
##
## 0 | 65
## 2 |
## 4 |
## 6 | 1head(df_GT)## # A tibble: 3 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 1917 5/29/10 <NA> <NA> Guatemala GT Sacat~ 15529
## 2 7432 9/23/15 <NA> <NA> Guatemala GT Sacat~ 3214
## 3 2387 9/4/10 <NA> <NA> Guatemala GT Sacat~ 17918
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_GT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1917 | 5/29/10 | NA | NA | Guatemala | GT | Sacatepéquez | 15529 | Santa María De Jesús | 6.13527 | NA | 14.4651 | -90.7426 | (14.4651, -90.742599999999996) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Cyclone Agatha | NA | 0 | NA | http://www.boston.com/bigpicture/2010/06/a_rough_week_for_guatemala.html#photo17 | 74.655032 | 37.32752 |
| 7432 | 9/23/15 | NA | NA | Guatemala | GT | Sacatepéquez | 3214 | Santa Catarina Barahona | 1.45200 | Unknown | 14.5558 | -90.7998 | (14.5558, -90.799800000000005) | Landslide | Landslide | Medium | Continuous rain | NA | 0 | 0 | Prensa Libre | http://www.prensalibre.com/guatemala/comunitario/constante-lluvia-provoca-primeras-desastres-en-la-provincia | 17.668188 | 83.48913 |
| 2387 | 9/4/10 | NA | NA | Guatemala | GT | Sacatepéquez | 17918 | Jocotenango | 0.63089 | NA | 14.5832 | -90.7379 | (14.5832, -90.737899999999996) | Landslide | Landslide | Medium | Downpour | NA | NA | 1 | NA | http://www.upi.com/Top_News/World-News/2010/09/05/Rain-blamed-for-21-deaths-in-Guatemala/UPI-36581283666884/ | 7.676779 | 96.16161 |
stem(df_GT$"distance")##
## The decimal point is at the |
##
## 0 | 65
## 2 |
## 4 |
## 6 | 1stem(df_GT$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 6
## 1 | 5
## 2 |
## 3 |
## 4 |
## 5 |
## 6 | 1Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.63089 | 1 | 33.3 | 33.3 | 33.3 | 33.3 |
| 1.452 | 1 | 33.3 | 33.3 | 66.7 | 66.7 |
| 6.13527 | 1 | 33.3 | 33.3 | 100.0 | 100.0 |
| Total | 3 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 4 obs. of 5 variables:
## $ n : num 1 1 1 3
## $ % : num 33.3 33.3 33.3 100
## $ val% : num 33.3 33.3 33.3 100
## $ %cum : num 33.3 66.7 100 100
## $ val%cum: num 33.3 66.7 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.63089 | 1 |
| 1.452 | 1 |
| 6.13527 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.63089 2.63089 4.63089 6.63089distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.631,2.63] | 1 | 0.5 | 1 |
| (2.63,4.63] | 0 | 0.0 | 1 |
| (4.63,6.63] | 1 | 0.5 | 2 |
str(Freq_table)## 'data.frame': 3 obs. of 4 variables:
## $ distance: Factor w/ 3 levels "(0.631,2.63]",..: 1 2 3
## $ Freq : int 1 0 1
## $ Rel_Freq: num 0.5 0 0.5
## $ Cum_Freq: int 1 1 2df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.631,2.63] | 1 |
| (2.63,4.63] | 0 |
| (4.63,6.63] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_GT)## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 3.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 1.917000e+03 NA NA NA NA NA
## max 7.432000e+03 NA NA NA NA NA
## range 5.515000e+03 NA NA NA NA NA
## sum 1.173600e+04 NA NA NA NA NA
## median 2.387000e+03 NA NA NA NA NA
## mean 3.912000e+03 NA NA NA NA NA
## SE.mean 1.765222e+03 NA NA NA NA NA
## CI.mean.0.95 7.595137e+03 NA NA NA NA NA
## var 9.348025e+06 NA NA NA NA NA
## std.dev 3.057454e+03 NA NA NA NA NA
## coef.var 7.815578e-01 NA NA NA NA NA
## state population city distance location_description latitude
## nbr.val NA 3.000000e+00 NA 3.000000 NA 3.000000000
## nbr.null NA 0.000000e+00 NA 0.000000 NA 0.000000000
## nbr.na NA 0.000000e+00 NA 0.000000 NA 0.000000000
## min NA 3.214000e+03 NA 0.630890 NA 14.465100000
## max NA 1.791800e+04 NA 6.135270 NA 14.583200000
## range NA 1.470400e+04 NA 5.504380 NA 0.118100000
## sum NA 3.666100e+04 NA 8.218160 NA 43.604100000
## median NA 1.552900e+04 NA 1.452000 NA 14.555800000
## mean NA 1.222033e+04 NA 2.739387 NA 14.534700000
## SE.mean NA 4.555669e+03 NA 1.714407 NA 0.035687580
## CI.mean.0.95 NA 1.960146e+04 NA 7.376498 NA 0.153551262
## var NA 6.226236e+07 NA 8.817573 NA 0.003820810
## std.dev NA 7.890650e+03 NA 2.969440 NA 0.061812701
## coef.var NA 6.456984e-01 NA 1.083980 NA 0.004252768
## longitude geolocation hazard_type landslide_type
## nbr.val 3.000000e+00 NA NA NA
## nbr.null 0.000000e+00 NA NA NA
## nbr.na 0.000000e+00 NA NA NA
## min -9.079980e+01 NA NA NA
## max -9.073790e+01 NA NA NA
## range 6.190000e-02 NA NA NA
## sum -2.722803e+02 NA NA NA
## median -9.074260e+01 NA NA NA
## mean -9.076010e+01 NA NA NA
## SE.mean 1.989631e-02 NA NA NA
## CI.mean.0.95 8.560693e-02 NA NA NA
## var 1.187590e-03 NA NA NA
## std.dev 3.446143e-02 NA NA NA
## coef.var -3.796980e-04 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 1 3.0000000 NA
## nbr.null NA NA NA 1 2.0000000 NA
## nbr.na NA NA NA 2 0.0000000 NA
## min NA NA NA 0 0.0000000 NA
## max NA NA NA 0 1.0000000 NA
## range NA NA NA 0 1.0000000 NA
## sum NA NA NA 0 1.0000000 NA
## median NA NA NA 0 0.0000000 NA
## mean NA NA NA 0 0.3333333 NA
## SE.mean NA NA NA NA 0.3333333 NA
## CI.mean.0.95 NA NA NA NaN 1.4342176 NA
## var NA NA NA NA 0.3333333 NA
## std.dev NA NA NA NA 0.5773503 NA
## coef.var NA NA NA NA 1.7320508 NA
## source_link prop ypos
## nbr.val NA 3.000000 3.0000000
## nbr.null NA 0.000000 0.0000000
## nbr.na NA 0.000000 0.0000000
## min NA 7.676779 37.3275161
## max NA 74.655032 96.1616104
## range NA 66.978253 58.8340942
## sum NA 100.000000 216.9782530
## median NA 17.668188 83.4891265
## mean NA 33.333333 72.3260843
## SE.mean NA 20.861201 17.8775725
## CI.mean.0.95 NA 89.758505 76.9209861
## var NA 1305.569167 958.8227945
## std.dev NA 36.132661 30.9648639
## coef.var NA 1.083980 0.4281286boxplot(data, horizontal=TRUE, col='green')
Gráfico para San Marcos (Guatemala)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_GT <- subset(df, country_name == "Guatemala")
knitr::kable(head(df_GT)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 165 | 8/9/07 | NA | NA | Guatemala | GT | Guatemala | 47247 | San José Pinula | 4.74385 | NA | 14.5667 | -90.4500 | (14.566700000000001, -90.45) | Landslide | Mudslide | Medium | Rain | NA | NA | 5 | International Herald | http://www.iht.com/articles/ap/2007/08/09/america/LA-GEN-Guatemala-Deadly-Mudslide.php |
| 198 | 8/21/07 | NA | NA | Guatemala | GT | Alta Verapaz | 2006 | Lanquín | 13.39817 | NA | 15.6046 | -90.0853 | (15.6046, -90.085300000000004) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Dean | NA | NA | United Nations Development Programme - Relief Web | http://www.reliefweb.int/rw/RWB.NSF/db900SID/EDIS-76BSG6?OpenDocument |
| 199 | 8/21/07 | NA | NA | Guatemala | GT | Izabal | 18994 | Morales | 12.55184 | NA | 15.5163 | -88.9286 | (15.516299999999999, -88.928600000000003) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Dean | NA | NA | United Nations Development Programme - Relief Web | http://www.reliefweb.int/rw/RWB.NSF/db900SID/EDIS-76BSG6?OpenDocument |
| 277 | 9/22/07 | NA | NA | Guatemala | GT | Guatemala | 994938 | Guatemala City | 2.79113 | NA | 14.6229 | -90.5316 | (14.6229, -90.531599999999997) | Landslide | Mudslide | Medium | Rain | NA | NA | 3 | Fox News | http://www.foxnews.com/story/0,2933,297714,00.html |
| 563 | 6/1/08 | NA | NA | Guatemala | GT | Escuintla | 31329 | Palín | 3.10150 | NA | 14.4226 | -90.6755 | (14.422599999999999, -90.6755) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Storm Arthur | NA | 1 | NA | http://209.85.215.104/search?q=cache:QU_lPxNfk78J:www.plenglish.com/article.asp?ID=%7B1D4A74F7-CDCA-49D0-ABD4-D2E0FD9D2130%7D&language=EN+Colom+said+the+declaration+came+after+a+death+in+Palin+and+40+houses+partially&hl=en&ct=clnk&cd=1&gl=us&c |
| 591 | 6/18/08 | NA | NA | Guatemala | GT | Guatemala | 994938 | Guatemala City | 3.12614 | NA | 14.6510 | -90.5403 | (14.651, -90.540300000000002) | Landslide | Complex | Medium | Rain | NA | NA | 8 | NA | http://cnnwire.blogs.cnn.com/2008/06/20/8-dead-in-rough-weather-in-guatemala/ |
library(dplyr)
df_GT <- subset(df, state == "San Marcos")
knitr::kable(head(df_GT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 5475 | 9/7/13 | 0:13:00 | NA | Guatemala | GT | San Marcos | 8164 | Pajapita | 0.96647 | NA | 14.7254 | -92.0335 | (14.7254, -92.033500000000004) | Landslide | Landslide | Large | Earthquake | NA | NA | 0 | www.chinapost.com.tw | http://www.chinapost.com.tw/international/americas/2013/09/09/388474/Power-outages.htm |
| 6669 | 9/27/14 | NA | NA | Guatemala | GT | San Marcos | 6438 | Tacaná | 0.75729 | Unknown | 15.2422 | -92.0738 | (15.2422, -92.073800000000006) | Landslide | Landslide | Medium | Rain | NA | 0 | 2 | Univision | http://www.kint.com/2014/09/28/lluvias-dejan-tres-muertos-y-cuatro-desaparecidos-en-guatemala/ |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_GT, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_GT, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_GT, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_GT <- df_GT %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_GT$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_GT, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_GT$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 0.75729 |
| 0.96647 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_GT$distance
names(distance) <- df_GT$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Pajapita 0.96647 0.96647 56.06755 56.06755
## Tacaná 0.75729 1.72376 43.93245 100.00000stem(df_GT$"distance")##
## The decimal point is 1 digit(s) to the left of the |
##
## 7 | 6
## 8 |
## 8 |
## 9 |
## 9 | 7head(df_GT)## # A tibble: 2 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 6669 9/27/14 <NA> <NA> Guatemala GT San ~ 6438
## 2 5475 9/7/13 0:13:00 <NA> Guatemala GT San ~ 8164
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_GT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 6669 | 9/27/14 | NA | NA | Guatemala | GT | San Marcos | 6438 | Tacaná | 0.75729 | Unknown | 15.2422 | -92.0738 | (15.2422, -92.073800000000006) | Landslide | Landslide | Medium | Rain | NA | 0 | 2 | Univision | http://www.kint.com/2014/09/28/lluvias-dejan-tres-muertos-y-cuatro-desaparecidos-en-guatemala/ | 43.93245 | 21.96623 |
| 5475 | 9/7/13 | 0:13:00 | NA | Guatemala | GT | San Marcos | 8164 | Pajapita | 0.96647 | NA | 14.7254 | -92.0335 | (14.7254, -92.033500000000004) | Landslide | Landslide | Large | Earthquake | NA | NA | 0 | www.chinapost.com.tw | http://www.chinapost.com.tw/international/americas/2013/09/09/388474/Power-outages.htm | 56.06755 | 71.96622 |
stem(df_GT$"distance")##
## The decimal point is 1 digit(s) to the left of the |
##
## 7 | 6
## 8 |
## 8 |
## 9 |
## 9 | 7stem(df_GT$"distance", scale = 2)##
## The decimal point is 1 digit(s) to the left of the |
##
## 7 | 6
## 8 |
## 8 |
## 9 |
## 9 | 7Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.75729 | 1 | 50 | 50 | 50 | 50 |
| 0.96647 | 1 | 50 | 50 | 100 | 100 |
| Total | 2 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 3 obs. of 5 variables:
## $ n : num 1 1 2
## $ % : num 50 50 100
## $ val% : num 50 50 100
## $ %cum : num 50 100 100
## $ val%cum: num 50 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.75729 | 1 |
| 0.96647 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.75729 1.75729distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.757,1.76] | 1 | 1 | 1 |
str(Freq_table)## 'data.frame': 1 obs. of 4 variables:
## $ distance: Factor w/ 1 level "(0.757,1.76]": 1
## $ Freq : int 1
## $ Rel_Freq: num 1
## $ Cum_Freq: int 1df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.757,1.76] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_GT)## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 2.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 5.475000e+03 NA NA NA NA NA
## max 6.669000e+03 NA NA NA NA NA
## range 1.194000e+03 NA NA NA NA NA
## sum 1.214400e+04 NA NA NA NA NA
## median 6.072000e+03 NA NA NA NA NA
## mean 6.072000e+03 NA NA NA NA NA
## SE.mean 5.970000e+02 NA NA NA NA NA
## CI.mean.0.95 7.585604e+03 NA NA NA NA NA
## var 7.128180e+05 NA NA NA NA NA
## std.dev 8.442855e+02 NA NA NA NA NA
## coef.var 1.390457e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 2.000000e+00 NA 2.00000000 NA
## nbr.null NA 0.000000e+00 NA 0.00000000 NA
## nbr.na NA 0.000000e+00 NA 0.00000000 NA
## min NA 6.438000e+03 NA 0.75729000 NA
## max NA 8.164000e+03 NA 0.96647000 NA
## range NA 1.726000e+03 NA 0.20918000 NA
## sum NA 1.460200e+04 NA 1.72376000 NA
## median NA 7.301000e+03 NA 0.86188000 NA
## mean NA 7.301000e+03 NA 0.86188000 NA
## SE.mean NA 8.630000e+02 NA 0.10459000 NA
## CI.mean.0.95 NA 1.096545e+04 NA 1.32894195 NA
## var NA 1.489538e+06 NA 0.02187814 NA
## std.dev NA 1.220466e+03 NA 0.14791260 NA
## coef.var NA 1.671643e-01 NA 0.17161623 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 2.00000000 2.000000e+00 NA NA NA
## nbr.null 0.00000000 0.000000e+00 NA NA NA
## nbr.na 0.00000000 0.000000e+00 NA NA NA
## min 14.72540000 -9.207380e+01 NA NA NA
## max 15.24220000 -9.203350e+01 NA NA NA
## range 0.51680000 4.030000e-02 NA NA NA
## sum 29.96760000 -1.841073e+02 NA NA NA
## median 14.98380000 -9.205365e+01 NA NA NA
## mean 14.98380000 -9.205365e+01 NA NA NA
## SE.mean 0.25840000 2.015000e-02 NA NA NA
## CI.mean.0.95 3.28328330 2.560300e-01 NA NA NA
## var 0.13354112 8.120450e-04 NA NA NA
## std.dev 0.36543278 2.849640e-02 NA NA NA
## coef.var 0.02438853 -3.095630e-04 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 1 2.000000 NA
## nbr.null NA NA NA 1 1.000000 NA
## nbr.na NA NA NA 1 0.000000 NA
## min NA NA NA 0 0.000000 NA
## max NA NA NA 0 2.000000 NA
## range NA NA NA 0 2.000000 NA
## sum NA NA NA 0 2.000000 NA
## median NA NA NA 0 1.000000 NA
## mean NA NA NA 0 1.000000 NA
## SE.mean NA NA NA NA 1.000000 NA
## CI.mean.0.95 NA NA NA NaN 12.706205 NA
## var NA NA NA NA 2.000000 NA
## std.dev NA NA NA NA 1.414214 NA
## coef.var NA NA NA NA 1.414214 NA
## source_link prop ypos
## nbr.val NA 2.0000000 2.0000000
## nbr.null NA 0.0000000 0.0000000
## nbr.na NA 0.0000000 0.0000000
## min NA 43.9324500 21.9662250
## max NA 56.0675500 71.9662250
## range NA 12.1351000 50.0000000
## sum NA 100.0000000 93.9324500
## median NA 50.0000000 46.9662250
## mean NA 50.0000000 46.9662250
## SE.mean NA 6.0675500 25.0000000
## CI.mean.0.95 NA 77.0955326 317.6551184
## var NA 73.6303262 1250.0000000
## std.dev NA 8.5808115 35.3553391
## coef.var NA 0.1716162 0.7527822boxplot(data, horizontal=TRUE, col='green')
Gráfico para Sololá (Guatemala)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_GT <- subset(df, country_name == "Guatemala")
knitr::kable(head(df_GT)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 165 | 8/9/07 | NA | NA | Guatemala | GT | Guatemala | 47247 | San José Pinula | 4.74385 | NA | 14.5667 | -90.4500 | (14.566700000000001, -90.45) | Landslide | Mudslide | Medium | Rain | NA | NA | 5 | International Herald | http://www.iht.com/articles/ap/2007/08/09/america/LA-GEN-Guatemala-Deadly-Mudslide.php |
| 198 | 8/21/07 | NA | NA | Guatemala | GT | Alta Verapaz | 2006 | Lanquín | 13.39817 | NA | 15.6046 | -90.0853 | (15.6046, -90.085300000000004) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Dean | NA | NA | United Nations Development Programme - Relief Web | http://www.reliefweb.int/rw/RWB.NSF/db900SID/EDIS-76BSG6?OpenDocument |
| 199 | 8/21/07 | NA | NA | Guatemala | GT | Izabal | 18994 | Morales | 12.55184 | NA | 15.5163 | -88.9286 | (15.516299999999999, -88.928600000000003) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Dean | NA | NA | United Nations Development Programme - Relief Web | http://www.reliefweb.int/rw/RWB.NSF/db900SID/EDIS-76BSG6?OpenDocument |
| 277 | 9/22/07 | NA | NA | Guatemala | GT | Guatemala | 994938 | Guatemala City | 2.79113 | NA | 14.6229 | -90.5316 | (14.6229, -90.531599999999997) | Landslide | Mudslide | Medium | Rain | NA | NA | 3 | Fox News | http://www.foxnews.com/story/0,2933,297714,00.html |
| 563 | 6/1/08 | NA | NA | Guatemala | GT | Escuintla | 31329 | Palín | 3.10150 | NA | 14.4226 | -90.6755 | (14.422599999999999, -90.6755) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Storm Arthur | NA | 1 | NA | http://209.85.215.104/search?q=cache:QU_lPxNfk78J:www.plenglish.com/article.asp?ID=%7B1D4A74F7-CDCA-49D0-ABD4-D2E0FD9D2130%7D&language=EN+Colom+said+the+declaration+came+after+a+death+in+Palin+and+40+houses+partially&hl=en&ct=clnk&cd=1&gl=us&c |
| 591 | 6/18/08 | NA | NA | Guatemala | GT | Guatemala | 994938 | Guatemala City | 3.12614 | NA | 14.6510 | -90.5403 | (14.651, -90.540300000000002) | Landslide | Complex | Medium | Rain | NA | NA | 8 | NA | http://cnnwire.blogs.cnn.com/2008/06/20/8-dead-in-rough-weather-in-guatemala/ |
library(dplyr)
df_GT <- subset(df, state == "Sololá")
knitr::kable(head(df_GT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1920 | 5/30/10 | NA | NA | Guatemala | GT | Sololá | 1422 | Santa Cruz La Laguna | 6.00513 | Urban area | 14.6918 | -91.1168 | (14.691800000000001, -91.116799999999998) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Cyclone Agatha | NA | 14 | Mayan Trip | http://mayantrip.com/lake-atitlan-guatemala-agatha-update-san-antonio-polopo |
| 1922 | 5/29/10 | Night | NA | Guatemala | GT | Sololá | 9681 | San Pedro La Laguna | 0.50611 | Natural slope | 14.6685 | -91.2697 | (14.6685, -91.2697) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Cyclone Agatha | NA | 1 | by Melissa Joy | http://melissajoy.wordpress.com/2010/06/01/mudslide/ |
| 2021 | 6/27/10 | NA | NA | Guatemala | GT | Sololá | 6186 | San Pablo La Laguna | 3.85753 | Unknown | 14.7801 | -91.2764 | (14.780099999999999, -91.276399999999995) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Alex | NA | 2 | Latin American Herald Tribune | http://www.laht.com/article.asp?ArticleId=359405&CategoryId=23558 |
| 2353 | 8/28/10 | NA | NA | Guatemala | GT | Sololá | 2605 | San Andrés Semetabaj | 0.00359 | NA | 14.7598 | -91.1287 | (14.7598, -91.128699999999995) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | NA |
| 2384 | 9/4/10 | NA | NA | Guatemala | GT | Sololá | 27690 | Nahualá | 3.04642 | NA | 14.8231 | -91.3227 | (14.8231, -91.322699999999998) | Landslide | Landslide | Large | Downpour | NA | NA | 25 | NA | http://www.upi.com/Top_News/World-News/2010/09/05/Rain-blamed-for-21-deaths-in-Guatemala/UPI-36581283666884/ |
| 6586 | 10/20/14 | NA | NA | Guatemala | GT | Sololá | 9986 | Zunil | 7.03115 | Natural slope | 14.7836 | -91.1836 | (14.7836, -91.183599999999998) | Landslide | Landslide | Small | Rain | NA | 0 | 6 | El Aragueno | http://elaragueno.com.ve/deslizamiento-en-guatemala-deja-tres-muertos-y-tres-desaparecidos/ |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_GT, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_GT, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_GT, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_GT <- df_GT %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_GT$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_GT, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_GT$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 7.03115 |
| 6.00513 |
| 0.50611 |
| 3.85753 |
| 3.18658 |
| 0.00359 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_GT$distance
names(distance) <- df_GT$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Zunil 7.03115000 7.03115000 28.05305349 28.05305349
## Santa Cruz La Laguna 6.00513000 13.03628000 23.95941391 52.01246740
## San Pablo La Laguna 3.85753000 16.89381000 15.39086713 67.40333454
## San Antonio Palopó 3.18658000 20.08039000 12.71389448 80.11722902
## Nahualá 3.04642000 23.12681000 12.15468070 92.27190972
## San Andrés Semetabaj 0.75685000 23.88366000 3.01969856 95.29160828
## San Andrés Semetabaj 0.67040000 24.55406000 2.67477825 97.96638653
## San Pedro La Laguna 0.50611000 25.06017000 2.01929000 99.98567653
## San Andrés Semetabaj 0.00359000 25.06376000 0.01432347 100.00000000stem(df_GT$"distance")##
## The decimal point is at the |
##
## 0 | 0578
## 2 | 029
## 4 |
## 6 | 00head(df_GT)## # A tibble: 6 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 6586 10/20/14 <NA> <NA> Guatemala GT Sololá 9986
## 2 1920 5/30/10 <NA> <NA> Guatemala GT Sololá 1422
## 3 1922 5/29/10 Night <NA> Guatemala GT Sololá 9681
## 4 2021 6/27/10 <NA> <NA> Guatemala GT Sololá 6186
## 5 7416 9/27/15 <NA> <NA> Guatemala GT Sololá 3588
## 6 2353 8/28/10 <NA> <NA> Guatemala GT Sololá 2605
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_GT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 6586 | 10/20/14 | NA | NA | Guatemala | GT | Sololá | 9986 | Zunil | 7.03115 | Natural slope | 14.7836 | -91.1836 | (14.7836, -91.183599999999998) | Landslide | Landslide | Small | Rain | NA | 0 | 6 | El Aragueno | http://elaragueno.com.ve/deslizamiento-en-guatemala-deja-tres-muertos-y-tres-desaparecidos/ | 28.0530535 | 14.02653 |
| 1920 | 5/30/10 | NA | NA | Guatemala | GT | Sololá | 1422 | Santa Cruz La Laguna | 6.00513 | Urban area | 14.6918 | -91.1168 | (14.691800000000001, -91.116799999999998) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Cyclone Agatha | NA | 14 | Mayan Trip | http://mayantrip.com/lake-atitlan-guatemala-agatha-update-san-antonio-polopo | 23.9594139 | 40.03276 |
| 1922 | 5/29/10 | Night | NA | Guatemala | GT | Sololá | 9681 | San Pedro La Laguna | 0.50611 | Natural slope | 14.6685 | -91.2697 | (14.6685, -91.2697) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Cyclone Agatha | NA | 1 | by Melissa Joy | http://melissajoy.wordpress.com/2010/06/01/mudslide/ | 2.0192900 | 53.02211 |
| 2021 | 6/27/10 | NA | NA | Guatemala | GT | Sololá | 6186 | San Pablo La Laguna | 3.85753 | Unknown | 14.7801 | -91.2764 | (14.780099999999999, -91.276399999999995) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Alex | NA | 2 | Latin American Herald Tribune | http://www.laht.com/article.asp?ArticleId=359405&CategoryId=23558 | 15.3908671 | 61.72719 |
| 7416 | 9/27/15 | NA | NA | Guatemala | GT | Sololá | 3588 | San Antonio Palopó | 3.18658 | Above road | 14.7038 | -91.0873 | (14.703799999999999, -91.087299999999999) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | CONRED | http://www.redhum.org/documento_detail/conred-boletin-informativo-no-4038-lluvias-del-domingo-generaron-22-incidentes-en-6-departamentos | 12.7138945 | 75.77957 |
| 2353 | 8/28/10 | NA | NA | Guatemala | GT | Sololá | 2605 | San Andrés Semetabaj | 0.00359 | NA | 14.7598 | -91.1287 | (14.7598, -91.128699999999995) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | NA | 0.0143235 | 82.14368 |
stem(df_GT$"distance")##
## The decimal point is at the |
##
## 0 | 0578
## 2 | 029
## 4 |
## 6 | 00stem(df_GT$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 0578
## 1 |
## 2 |
## 3 | 029
## 4 |
## 5 |
## 6 | 0
## 7 | 0Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.00359 | 1 | 11.1 | 11.1 | 11.1 | 11.1 |
| 0.50611 | 1 | 11.1 | 11.1 | 22.2 | 22.2 |
| 0.6704 | 1 | 11.1 | 11.1 | 33.3 | 33.3 |
| 0.75685 | 1 | 11.1 | 11.1 | 44.4 | 44.4 |
| 3.04642 | 1 | 11.1 | 11.1 | 55.6 | 55.6 |
| 3.18658 | 1 | 11.1 | 11.1 | 66.7 | 66.7 |
| 3.85753 | 1 | 11.1 | 11.1 | 77.8 | 77.8 |
| 6.00513 | 1 | 11.1 | 11.1 | 88.9 | 88.9 |
| 7.03115 | 1 | 11.1 | 11.1 | 100.0 | 100.0 |
| Total | 9 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 10 obs. of 5 variables:
## $ n : num 1 1 1 1 1 1 1 1 1 9
## $ % : num 11.1 11.1 11.1 11.1 11.1 11.1 11.1 11.1 11.1 100
## $ val% : num 11.1 11.1 11.1 11.1 11.1 11.1 11.1 11.1 11.1 100
## $ %cum : num 11.1 22.2 33.3 44.4 55.6 66.7 77.8 88.9 100 100
## $ val%cum: num 11.1 22.2 33.3 44.4 55.6 66.7 77.8 88.9 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.00359 | 1 |
| 0.50611 | 1 |
| 0.6704 | 1 |
| 0.75685 | 1 |
| 3.04642 | 1 |
| 3.18658 | 1 |
| 3.85753 | 1 |
| 6.00513 | 1 |
| 7.03115 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.00359 2.00359 4.00359 6.00359 8.00359distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.00359,2] | 3 | 0.375 | 3 |
| (2,4] | 3 | 0.375 | 6 |
| (4,6] | 0 | 0.000 | 6 |
| (6,8] | 2 | 0.250 | 8 |
str(Freq_table)## 'data.frame': 4 obs. of 4 variables:
## $ distance: Factor w/ 4 levels "(0.00359,2]",..: 1 2 3 4
## $ Freq : int 3 3 0 2
## $ Rel_Freq: num 0.375 0.375 0 0.25
## $ Cum_Freq: int 3 6 6 8df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.00359,2] | 3 |
| (2,4] | 3 |
| (4,6] | 0 |
| (6,8] | 2 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_GT)## id date time continent_code country_name country_code
## nbr.val 9.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 1.920000e+03 NA NA NA NA NA
## max 7.436000e+03 NA NA NA NA NA
## range 5.516000e+03 NA NA NA NA NA
## sum 3.945500e+04 NA NA NA NA NA
## median 2.384000e+03 NA NA NA NA NA
## mean 4.383889e+03 NA NA NA NA NA
## SE.mean 9.005946e+02 NA NA NA NA NA
## CI.mean.0.95 2.076775e+03 NA NA NA NA NA
## var 7.299636e+06 NA NA NA NA NA
## std.dev 2.701784e+03 NA NA NA NA NA
## coef.var 6.162984e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 9.000000e+00 NA 9.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 1.422000e+03 NA 0.0035900 NA
## max NA 2.769000e+04 NA 7.0311500 NA
## range NA 2.626800e+04 NA 7.0275600 NA
## sum NA 6.636800e+04 NA 25.0637600 NA
## median NA 3.588000e+03 NA 3.0464200 NA
## mean NA 7.374222e+03 NA 2.7848622 NA
## SE.mean NA 2.749460e+03 NA 0.8440434 NA
## CI.mean.0.95 NA 6.340266e+03 NA 1.9463675 NA
## var NA 6.803577e+07 NA 6.4116826 NA
## std.dev NA 8.248380e+03 NA 2.5321301 NA
## coef.var NA 1.118542e+00 NA 0.9092479 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 9.000000e+00 9.000000e+00 NA NA NA
## nbr.null 0.000000e+00 0.000000e+00 NA NA NA
## nbr.na 0.000000e+00 0.000000e+00 NA NA NA
## min 1.466850e+01 -9.132270e+01 NA NA NA
## max 1.482310e+01 -9.108730e+01 NA NA NA
## range 1.546000e-01 2.354000e-01 NA NA NA
## sum 1.327115e+02 -8.206534e+02 NA NA NA
## median 1.475680e+01 -9.113440e+01 NA NA NA
## mean 1.474572e+01 -9.118371e+01 NA NA NA
## SE.mean 1.648067e-02 2.814259e-02 NA NA NA
## CI.mean.0.95 3.800449e-02 6.489692e-02 NA NA NA
## var 2.444512e-03 7.128046e-03 NA NA NA
## std.dev 4.944201e-02 8.442776e-02 NA NA NA
## coef.var 3.352973e-03 -9.259083e-04 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 4 9.000000 NA
## nbr.null NA NA NA 4 4.000000 NA
## nbr.na NA NA NA 5 0.000000 NA
## min NA NA NA 0 0.000000 NA
## max NA NA NA 0 25.000000 NA
## range NA NA NA 0 25.000000 NA
## sum NA NA NA 0 48.000000 NA
## median NA NA NA 0 1.000000 NA
## mean NA NA NA 0 5.333333 NA
## SE.mean NA NA NA 0 2.901149 NA
## CI.mean.0.95 NA NA NA 0 6.690062 NA
## var NA NA NA 0 75.750000 NA
## std.dev NA NA NA 0 8.703448 NA
## coef.var NA NA NA NaN 1.631896 NA
## source_link prop ypos
## nbr.val NA 9.00000000 9.0000000
## nbr.null NA 0.00000000 0.0000000
## nbr.na NA 0.00000000 0.0000000
## min NA 0.01432347 14.0265267
## max NA 28.05305349 93.9226596
## range NA 28.03873002 79.8961329
## sum NA 100.00000000 590.4782044
## median NA 12.15468070 75.7795718
## mean NA 11.11111111 65.6086894
## SE.mean NA 3.36758473 8.6731921
## CI.mean.0.95 NA 7.76566431 20.0004168
## var NA 102.06564205 677.0183450
## std.dev NA 10.10275418 26.0195762
## coef.var NA 0.90924788 0.3965873boxplot(data, horizontal=TRUE, col='green')
Gráfico para Jamaica
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_JA <- subset(df, country_name == "Jamaica")
knitr::kable(head(df_JA))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 174 | 8/11/07 | NA | NA | Jamaica | JM | Portland | 14400 | Port Antonio | 7.79027 | NA | 18.1258 | -76.5082 | (18.125800000000002, -76.508200000000002) | Landslide | Landslide | Medium | Rain | NA | NA | NA | Jamaica Gleaner | http://www.jamaica-gleaner.com/gleaner/20070812/lead/lead2.html |
| 304 | 10/12/07 | NA | NA | Jamaica | JM | St. Elizabeth | 1371 | Maggotty | 4.57363 | NA | 18.1257 | -77.7405 | (18.125699999999998, -77.740499999999997) | Landslide | Complex | Medium | Rain | NA | NA | NA | RadioJamaica | http://www.radiojamaica.com/content/view/2039/26/ |
| 314 | 10/17/07 | NA | NA | Jamaica | JM | Saint Thomas | 2382 | Bath | 0.21825 | NA | 17.9500 | -76.3500 | (17.95, -76.349999999999994) | Landslide | Mudslide | Medium | Rain | NA | NA | NA | RadioJamaica | http://www.radiojamaica.com/content/view/2193/26/ |
| 339 | 10/31/07 | NA | NA | Jamaica | JM | Saint Thomas | 2634 | Easington | 6.51940 | NA | 17.9384 | -76.6479 | (17.938400000000001, -76.647900000000007) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Noel | NA | 1 | RadioJamaica | http://www.radiojamaica.com/content/view/2583/26/ |
| 340 | 10/31/07 | NA | NA | Jamaica | JM | Saint Catherine | 4085 | Riversdale | 5.46381 | NA | 18.2152 | -76.9659 | (18.215199999999999, -76.965900000000005) | Landslide | Complex | Medium | Rain | NA | NA | NA | RadioJamaica | http://www.radiojamaica.com/content/view/2933/26/ |
| 341 | 10/31/07 | NA | NA | Jamaica | JM | Saint Andrew | 1088 | Gordon Town | 0.96514 | NA | 18.0370 | -76.7088 | (18.036999999999999, -76.708799999999997) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Noel | NA | NA | Jamaica Observer | http://www.jamaicaobserver.com/news/html/20071101T010000-0500_128916_OBS_DEADLY_RAIN.asp |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_JA, aes(fill= state, y=distance, x=country_name)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_JA, aes(fill=state, y=distance, x=country_name)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_JA, aes(x=country_name, y=distance, fill=state)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_JA <- df_JA %>%
arrange(desc(state)) %>%
mutate(prop = distance / sum(df_JA$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_JA, aes(x=country_name, y=prop, fill=state)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_JA$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 4.57363 |
| 0.21825 |
| 6.51940 |
| 1.71217 |
| 4.53632 |
| 1.24727 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_JA$distance
names(distance) <- df_JA$state
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por estados"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Saint Andrew 10.8446700 10.8446700 7.3695199 7.3695199
## Saint Andrew 9.8305100 20.6751800 6.6803451 14.0498650
## Clarendon 9.5395300 30.2147100 6.4826090 20.5324740
## Saint Mary 8.7463500 38.9610600 5.9436018 26.4760758
## Portland 7.8126900 46.7737500 5.3091310 31.7852069
## Portland 7.7902700 54.5640200 5.2938955 37.0791023
## Portland 7.5231700 62.0871900 5.1123871 42.1914894
## Saint Catherine 6.7126900 68.7998800 4.5616236 46.7531130
## Saint Thomas 6.5194000 75.3192800 4.4302729 51.1833859
## Saint Andrew 5.9873100 81.3065900 4.0686900 55.2520758
## Saint Catherine 5.8653000 87.1718900 3.9857778 59.2378536
## Saint Catherine 5.4638100 92.6357000 3.7129444 62.9507980
## Portland 5.0235100 97.6592100 3.4137375 66.3645355
## Portland 4.6873200 102.3465300 3.1852788 69.5498143
## St. Elizabeth 4.5736300 106.9201600 3.1080205 72.6578348
## Saint Thomas 4.5363200 111.4564800 3.0826664 75.7405013
## Portland 4.4694200 115.9259000 3.0372044 78.7777057
## Portland 4.1345400 120.0604400 2.8096359 81.5873416
## Saint Ann 3.9653300 124.0257700 2.6946489 84.2819905
## Saint Mary 3.7758000 127.8015700 2.5658534 86.8478439
## Portland 3.6079900 131.4095600 2.4518177 89.2996616
## Portland 3.1793000 134.5888600 2.1605005 91.4601621
## Portland 2.7888500 137.3777100 1.8951693 93.3553313
## Saint Andrew 2.1387800 139.5164900 1.4534128 94.8087441
## Saint Thomas 1.7121700 141.2286600 1.1635090 95.9722531
## Saint Mary 1.2472700 142.4759300 0.8475851 96.8198382
## Saint Ann 1.0819600 143.5578900 0.7352483 97.5550865
## Saint Andrew 0.9651400 144.5230300 0.6558631 98.2109496
## Portland 0.7177300 145.2407600 0.4877350 98.6986846
## Portland 0.5959900 145.8367500 0.4050063 99.1036910
## Clarendon 0.5618600 146.3986100 0.3818132 99.4855042
## Saint Ann 0.5388600 146.9374700 0.3661835 99.8516877
## Saint Thomas 0.2182500 147.1557200 0.1483123 100.0000000stem(df_JA$"distance")##
## The decimal point is at the |
##
## 0 | 256670127
## 2 | 18268
## 4 | 015567059
## 6 | 057588
## 8 | 758
## 10 | 8head(df_JA)## # A tibble: 6 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 304 10/12/07 <NA> <NA> Jamaica JM St. ~ 1371
## 2 314 10/17/07 <NA> <NA> Jamaica JM Sain~ 2382
## 3 339 10/31/07 <NA> <NA> Jamaica JM Sain~ 2634
## 4 774 9/4/08 <NA> <NA> Jamaica JM Sain~ 2382
## 5 1760 4/18/10 <NA> <NA> Jamaica JM Sain~ 2634
## 6 2517 9/29/10 <NA> <NA> Jamaica JM Sain~ 2046
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_JA))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 304 | 10/12/07 | NA | NA | Jamaica | JM | St. Elizabeth | 1371 | Maggotty | 4.57363 | NA | 18.1257 | -77.7405 | (18.125699999999998, -77.740499999999997) | Landslide | Complex | Medium | Rain | NA | NA | NA | RadioJamaica | http://www.radiojamaica.com/content/view/2039/26/ | 3.1080205 | 1.554010 |
| 314 | 10/17/07 | NA | NA | Jamaica | JM | Saint Thomas | 2382 | Bath | 0.21825 | NA | 17.9500 | -76.3500 | (17.95, -76.349999999999994) | Landslide | Mudslide | Medium | Rain | NA | NA | NA | RadioJamaica | http://www.radiojamaica.com/content/view/2193/26/ | 0.1483123 | 3.182177 |
| 339 | 10/31/07 | NA | NA | Jamaica | JM | Saint Thomas | 2634 | Easington | 6.51940 | NA | 17.9384 | -76.6479 | (17.938400000000001, -76.647900000000007) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Noel | NA | 1 | RadioJamaica | http://www.radiojamaica.com/content/view/2583/26/ | 4.4302729 | 5.471469 |
| 774 | 9/4/08 | NA | NA | Jamaica | JM | Saint Thomas | 2382 | Bath | 1.71217 | NA | 17.9480 | -76.3330 | (17.948, -76.332999999999998) | Landslide | Complex | Medium | Tropical cyclone | Tropical Storm Gustav | NA | NA | NA | http://www.jamaica-gleaner.com/gleaner/20080905/lead/lead4.html | 1.1635090 | 8.268360 |
| 1760 | 4/18/10 | NA | NA | Jamaica | JM | Saint Thomas | 2634 | Easington | 4.53632 | NA | 17.9647 | -76.5835 | (17.964700000000001, -76.583500000000001) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.jamaica-gleaner.com/gleaner/20100420/lead/lead4.html | 3.0826664 | 10.391448 |
| 2517 | 9/29/10 | NA | NA | Jamaica | JM | Saint Mary | 2046 | Richmond | 1.24727 | NA | 18.2544 | -76.8865 | (18.2544, -76.886499999999998) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://go-jamaica.com/news/read_article.php?id=22964 | 0.8475851 | 12.356574 |
stem(df_JA$"distance")##
## The decimal point is at the |
##
## 0 | 256670127
## 2 | 18268
## 4 | 015567059
## 6 | 057588
## 8 | 758
## 10 | 8stem(df_JA$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 25667
## 1 | 0127
## 2 | 18
## 3 | 268
## 4 | 015567
## 5 | 059
## 6 | 057
## 7 | 588
## 8 | 7
## 9 | 58
## 10 | 8Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.21825 | 1 | 3 | 3 | 3.0 | 3.0 |
| 0.53886 | 1 | 3 | 3 | 6.1 | 6.1 |
| 0.56186 | 1 | 3 | 3 | 9.1 | 9.1 |
| 0.59599 | 1 | 3 | 3 | 12.1 | 12.1 |
| 0.71773 | 1 | 3 | 3 | 15.2 | 15.2 |
| 0.96514 | 1 | 3 | 3 | 18.2 | 18.2 |
| 1.08196 | 1 | 3 | 3 | 21.2 | 21.2 |
| 1.24727 | 1 | 3 | 3 | 24.2 | 24.2 |
| 1.71217 | 1 | 3 | 3 | 27.3 | 27.3 |
| 2.13878 | 1 | 3 | 3 | 30.3 | 30.3 |
| 2.78885 | 1 | 3 | 3 | 33.3 | 33.3 |
| 3.1793 | 1 | 3 | 3 | 36.4 | 36.4 |
| 3.60799 | 1 | 3 | 3 | 39.4 | 39.4 |
| 3.7758 | 1 | 3 | 3 | 42.4 | 42.4 |
| 3.96533 | 1 | 3 | 3 | 45.5 | 45.5 |
| 4.13454 | 1 | 3 | 3 | 48.5 | 48.5 |
| 4.46942 | 1 | 3 | 3 | 51.5 | 51.5 |
| 4.53632 | 1 | 3 | 3 | 54.5 | 54.5 |
| 4.57363 | 1 | 3 | 3 | 57.6 | 57.6 |
| 4.68732 | 1 | 3 | 3 | 60.6 | 60.6 |
| 5.02351 | 1 | 3 | 3 | 63.6 | 63.6 |
| 5.46381 | 1 | 3 | 3 | 66.7 | 66.7 |
| 5.8653 | 1 | 3 | 3 | 69.7 | 69.7 |
| 5.98731 | 1 | 3 | 3 | 72.7 | 72.7 |
| 6.5194 | 1 | 3 | 3 | 75.8 | 75.8 |
| 6.71269 | 1 | 3 | 3 | 78.8 | 78.8 |
| 7.52317 | 1 | 3 | 3 | 81.8 | 81.8 |
| 7.79027 | 1 | 3 | 3 | 84.8 | 84.8 |
| 7.81269 | 1 | 3 | 3 | 87.9 | 87.9 |
| 8.74635 | 1 | 3 | 3 | 90.9 | 90.9 |
| 9.53953 | 1 | 3 | 3 | 93.9 | 93.9 |
| 9.83051 | 1 | 3 | 3 | 97.0 | 97.0 |
| 10.84467 | 1 | 3 | 3 | 100.0 | 100.0 |
| Total | 33 | 100 | 100 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 34 obs. of 5 variables:
## $ n : num 1 1 1 1 1 1 1 1 1 1 ...
## $ % : num 3 3 3 3 3 3 3 3 3 3 ...
## $ val% : num 3 3 3 3 3 3 3 3 3 3 ...
## $ %cum : num 3 6.1 9.1 12.1 15.2 18.2 21.2 24.2 27.3 30.3 ...
## $ val%cum: num 3 6.1 9.1 12.1 15.2 18.2 21.2 24.2 27.3 30.3 ...x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.21825 | 1 |
| 0.53886 | 1 |
| 0.56186 | 1 |
| 0.59599 | 1 |
| 0.71773 | 1 |
| 0.96514 | 1 |
| 1.08196 | 1 |
| 1.24727 | 1 |
| 1.71217 | 1 |
| 2.13878 | 1 |
| 2.78885 | 1 |
| 3.1793 | 1 |
| 3.60799 | 1 |
| 3.7758 | 1 |
| 3.96533 | 1 |
| 4.13454 | 1 |
| 4.46942 | 1 |
| 4.53632 | 1 |
| 4.57363 | 1 |
| 4.68732 | 1 |
| 5.02351 | 1 |
| 5.46381 | 1 |
| 5.8653 | 1 |
| 5.98731 | 1 |
| 6.5194 | 1 |
| 6.71269 | 1 |
| 7.52317 | 1 |
| 7.79027 | 1 |
| 7.81269 | 1 |
| 8.74635 | 1 |
| 9.53953 | 1 |
| 9.83051 | 1 |
| 10.84467 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.21825 2.21825 4.21825 6.21825 8.21825 10.21825 12.21825distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.218,2.22] | 9 | 0.28125 | 9 |
| (2.22,4.22] | 6 | 0.18750 | 15 |
| (4.22,6.22] | 8 | 0.25000 | 23 |
| (6.22,8.22] | 5 | 0.15625 | 28 |
| (8.22,10.2] | 3 | 0.09375 | 31 |
| (10.2,12.2] | 1 | 0.03125 | 32 |
str(Freq_table)## 'data.frame': 6 obs. of 4 variables:
## $ distance: Factor w/ 6 levels "(0.218,2.22]",..: 1 2 3 4 5 6
## $ Freq : int 9 6 8 5 3 1
## $ Rel_Freq: num 0.2812 0.1875 0.25 0.1562 0.0938 ...
## $ Cum_Freq: int 9 15 23 28 31 32df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.218,2.22] | 9 |
| (2.22,4.22] | 6 |
| (4.22,6.22] | 8 |
| (6.22,8.22] | 5 |
| (8.22,10.2] | 3 |
| (10.2,12.2] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_JA)## id date time continent_code country_name country_code
## nbr.val 3.300000e+01 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 1.740000e+02 NA NA NA NA NA
## max 7.474000e+03 NA NA NA NA NA
## range 7.300000e+03 NA NA NA NA NA
## sum 8.120500e+04 NA NA NA NA NA
## median 2.233000e+03 NA NA NA NA NA
## mean 2.460758e+03 NA NA NA NA NA
## SE.mean 3.719434e+02 NA NA NA NA NA
## CI.mean.0.95 7.576240e+02 NA NA NA NA NA
## var 4.565283e+06 NA NA NA NA NA
## std.dev 2.136652e+03 NA NA NA NA NA
## coef.var 8.682905e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 3.300000e+01 NA 33.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 1.088000e+03 NA 0.2182500 NA
## max NA 4.475500e+04 NA 10.8446700 NA
## range NA 4.366700e+04 NA 10.6264200 NA
## sum NA 2.342270e+05 NA 147.1557200 NA
## median NA 2.757000e+03 NA 4.4694200 NA
## mean NA 7.097788e+03 NA 4.4592642 NA
## SE.mean NA 1.474547e+03 NA 0.5248336 NA
## CI.mean.0.95 NA 3.003553e+03 NA 1.0690510 NA
## var NA 7.175151e+07 NA 9.0898595 NA
## std.dev NA 8.470626e+03 NA 3.0149394 NA
## coef.var NA 1.193418e+00 NA 0.6761069 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 3.300000e+01 3.300000e+01 NA NA NA
## nbr.null 0.000000e+00 0.000000e+00 NA NA NA
## nbr.na 0.000000e+00 0.000000e+00 NA NA NA
## min 1.793840e+01 -7.774050e+01 NA NA NA
## max 1.843130e+01 -7.627810e+01 NA NA NA
## range 4.929000e-01 1.462400e+00 NA NA NA
## sum 5.982112e+02 -2.532567e+03 NA NA NA
## median 1.812570e+01 -7.668520e+01 NA NA NA
## mean 1.812761e+01 -7.674444e+01 NA NA NA
## SE.mean 2.204383e-02 6.043166e-02 NA NA NA
## CI.mean.0.95 4.490182e-02 1.230953e-01 NA NA NA
## var 1.603571e-02 1.205155e-01 NA NA NA
## std.dev 1.266322e-01 3.471534e-01 NA NA NA
## coef.var 6.985596e-03 -4.523499e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 4 23.0000000 NA
## nbr.null NA NA NA 4 20.0000000 NA
## nbr.na NA NA NA 29 10.0000000 NA
## min NA NA NA 0 0.0000000 NA
## max NA NA NA 0 7.0000000 NA
## range NA NA NA 0 7.0000000 NA
## sum NA NA NA 0 10.0000000 NA
## median NA NA NA 0 0.0000000 NA
## mean NA NA NA 0 0.4347826 NA
## SE.mean NA NA NA 0 0.3132520 NA
## CI.mean.0.95 NA NA NA 0 0.6496449 NA
## var NA NA NA 0 2.2569170 NA
## std.dev NA NA NA 0 1.5023039 NA
## coef.var NA NA NA NaN 3.4552990 NA
## source_link prop ypos
## nbr.val NA 33.0000000 33.0000000
## nbr.null NA 0.0000000 0.0000000
## nbr.na NA 0.0000000 0.0000000
## min NA 0.1483123 1.5540103
## max NA 7.3695199 99.8090934
## range NA 7.2212076 98.2550831
## sum NA 100.0000000 1613.0748027
## median NA 3.0372044 46.7168011
## mean NA 3.0303030 48.8810546
## SE.mean NA 0.3566518 5.3099807
## CI.mean.0.95 NA 0.7264760 10.8160768
## var NA 4.1976176 930.4645430
## std.dev NA 2.0488088 30.5035169
## coef.var NA 0.6761069 0.6240356boxplot(data, horizontal=TRUE, col='green')
Gráfico para Clarendon (Jamaica)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_JA <- subset(df, country_name == "Jamaica")
knitr::kable(head(df_JA)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 174 | 8/11/07 | NA | NA | Jamaica | JM | Portland | 14400 | Port Antonio | 7.79027 | NA | 18.1258 | -76.5082 | (18.125800000000002, -76.508200000000002) | Landslide | Landslide | Medium | Rain | NA | NA | NA | Jamaica Gleaner | http://www.jamaica-gleaner.com/gleaner/20070812/lead/lead2.html |
| 304 | 10/12/07 | NA | NA | Jamaica | JM | St. Elizabeth | 1371 | Maggotty | 4.57363 | NA | 18.1257 | -77.7405 | (18.125699999999998, -77.740499999999997) | Landslide | Complex | Medium | Rain | NA | NA | NA | RadioJamaica | http://www.radiojamaica.com/content/view/2039/26/ |
| 314 | 10/17/07 | NA | NA | Jamaica | JM | Saint Thomas | 2382 | Bath | 0.21825 | NA | 17.9500 | -76.3500 | (17.95, -76.349999999999994) | Landslide | Mudslide | Medium | Rain | NA | NA | NA | RadioJamaica | http://www.radiojamaica.com/content/view/2193/26/ |
| 339 | 10/31/07 | NA | NA | Jamaica | JM | Saint Thomas | 2634 | Easington | 6.51940 | NA | 17.9384 | -76.6479 | (17.938400000000001, -76.647900000000007) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Noel | NA | 1 | RadioJamaica | http://www.radiojamaica.com/content/view/2583/26/ |
| 340 | 10/31/07 | NA | NA | Jamaica | JM | Saint Catherine | 4085 | Riversdale | 5.46381 | NA | 18.2152 | -76.9659 | (18.215199999999999, -76.965900000000005) | Landslide | Complex | Medium | Rain | NA | NA | NA | RadioJamaica | http://www.radiojamaica.com/content/view/2933/26/ |
| 341 | 10/31/07 | NA | NA | Jamaica | JM | Saint Andrew | 1088 | Gordon Town | 0.96514 | NA | 18.0370 | -76.7088 | (18.036999999999999, -76.708799999999997) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Noel | NA | NA | Jamaica Observer | http://www.jamaicaobserver.com/news/html/20071101T010000-0500_128916_OBS_DEADLY_RAIN.asp |
library(dplyr)
df_JA <- subset(df, state == "Clarendon")
knitr::kable(head(df_JA))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1761 | 4/18/10 | NA | NA | Jamaica | JM | Clarendon | 4514 | Chapelton | 9.53953 | NA | 18.1437 | -77.3310 | (18.143699999999999, -77.331000000000003) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.jamaica-gleaner.com/gleaner/20100420/lead/lead4.html |
| 1762 | 4/18/10 | NA | NA | Jamaica | JM | Clarendon | 44755 | May Pen | 0.56186 | NA | 17.9693 | -77.2433 | (17.9693, -77.243300000000005) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.jamaica-gleaner.com/gleaner/20100420/lead/lead4.html |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_JA, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_JA, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_JA, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_JA <- df_JA %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_JA$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_JA, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_JA$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 0.56186 |
| 9.53953 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_JA$distance
names(distance) <- df_JA$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Chapelton 9.539530 9.539530 94.437795 94.437795
## May Pen 0.561860 10.101390 5.562205 100.000000stem(df_JA$"distance")##
## The decimal point is at the |
##
## 0 | 6
## 2 |
## 4 |
## 6 |
## 8 | 5head(df_JA)## # A tibble: 2 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 1762 4/18/10 <NA> <NA> Jamaica JM Clarendon 44755
## 2 1761 4/18/10 <NA> <NA> Jamaica JM Clarendon 4514
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_JA))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1762 | 4/18/10 | NA | NA | Jamaica | JM | Clarendon | 44755 | May Pen | 0.56186 | NA | 17.9693 | -77.2433 | (17.9693, -77.243300000000005) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.jamaica-gleaner.com/gleaner/20100420/lead/lead4.html | 5.562205 | 2.781102 |
| 1761 | 4/18/10 | NA | NA | Jamaica | JM | Clarendon | 4514 | Chapelton | 9.53953 | NA | 18.1437 | -77.3310 | (18.143699999999999, -77.331000000000003) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.jamaica-gleaner.com/gleaner/20100420/lead/lead4.html | 94.437795 | 52.781102 |
stem(df_JA$"distance")##
## The decimal point is at the |
##
## 0 | 6
## 2 |
## 4 |
## 6 |
## 8 | 5stem(df_JA$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 6
## 1 |
## 2 |
## 3 |
## 4 |
## 5 |
## 6 |
## 7 |
## 8 |
## 9 | 5Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.56186 | 1 | 50 | 50 | 50 | 50 |
| 9.53953 | 1 | 50 | 50 | 100 | 100 |
| Total | 2 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 3 obs. of 5 variables:
## $ n : num 1 1 2
## $ % : num 50 50 100
## $ val% : num 50 50 100
## $ %cum : num 50 100 100
## $ val%cum: num 50 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.56186 | 1 |
| 9.53953 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.56186 5.56186 10.56186distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.562,5.56] | 0 | 0 | 0 |
| (5.56,10.6] | 1 | 1 | 1 |
str(Freq_table)## 'data.frame': 2 obs. of 4 variables:
## $ distance: Factor w/ 2 levels "(0.562,5.56]",..: 1 2
## $ Freq : int 0 1
## $ Rel_Freq: num 0 1
## $ Cum_Freq: int 0 1df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.562,5.56] | 0 |
| (5.56,10.6] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_JA)## Warning in min(x): ningún argumento finito para min; retornando Inf## Warning in max(x): ningun argumento finito para max; retornando -Inf## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 2.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 1.761000e+03 NA NA NA NA NA
## max 1.762000e+03 NA NA NA NA NA
## range 1.000000e+00 NA NA NA NA NA
## sum 3.523000e+03 NA NA NA NA NA
## median 1.761500e+03 NA NA NA NA NA
## mean 1.761500e+03 NA NA NA NA NA
## SE.mean 5.000000e-01 NA NA NA NA NA
## CI.mean.0.95 6.353102e+00 NA NA NA NA NA
## var 5.000000e-01 NA NA NA NA NA
## std.dev 7.071068e-01 NA NA NA NA NA
## coef.var 4.014231e-04 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 2.000000e+00 NA 2.000000 NA
## nbr.null NA 0.000000e+00 NA 0.000000 NA
## nbr.na NA 0.000000e+00 NA 0.000000 NA
## min NA 4.514000e+03 NA 0.561860 NA
## max NA 4.475500e+04 NA 9.539530 NA
## range NA 4.024100e+04 NA 8.977670 NA
## sum NA 4.926900e+04 NA 10.101390 NA
## median NA 2.463450e+04 NA 5.050695 NA
## mean NA 2.463450e+04 NA 5.050695 NA
## SE.mean NA 2.012050e+04 NA 4.488835 NA
## CI.mean.0.95 NA 2.556552e+05 NA 57.036057 NA
## var NA 8.096690e+08 NA 40.299279 NA
## std.dev NA 2.845468e+04 NA 6.348171 NA
## coef.var NA 1.155075e+00 NA 1.256891 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 2.000000000 2.000000e+00 NA NA NA
## nbr.null 0.000000000 0.000000e+00 NA NA NA
## nbr.na 0.000000000 0.000000e+00 NA NA NA
## min 17.969300000 -7.733100e+01 NA NA NA
## max 18.143700000 -7.724330e+01 NA NA NA
## range 0.174400000 8.770000e-02 NA NA NA
## sum 36.113000000 -1.545743e+02 NA NA NA
## median 18.056500000 -7.728715e+01 NA NA NA
## mean 18.056500000 -7.728715e+01 NA NA NA
## SE.mean 0.087200000 4.385000e-02 NA NA NA
## CI.mean.0.95 1.107981053 5.571671e-01 NA NA NA
## var 0.015207680 3.845645e-03 NA NA NA
## std.dev 0.123319423 6.201326e-02 NA NA NA
## coef.var 0.006829642 -8.023748e-04 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 0 2 NA
## nbr.null NA NA NA 0 2 NA
## nbr.na NA NA NA 2 0 NA
## min NA NA NA Inf 0 NA
## max NA NA NA -Inf 0 NA
## range NA NA NA -Inf 0 NA
## sum NA NA NA 0 0 NA
## median NA NA NA NA 0 NA
## mean NA NA NA NaN 0 NA
## SE.mean NA NA NA NA 0 NA
## CI.mean.0.95 NA NA NA NaN 0 NA
## var NA NA NA NA 0 NA
## std.dev NA NA NA NA 0 NA
## coef.var NA NA NA NA NaN NA
## source_link prop ypos
## nbr.val NA 2.000000 2.000000
## nbr.null NA 0.000000 0.000000
## nbr.na NA 0.000000 0.000000
## min NA 5.562205 2.781102
## max NA 94.437795 52.781102
## range NA 88.875590 50.000000
## sum NA 100.000000 55.562205
## median NA 50.000000 27.781102
## mean NA 50.000000 27.781102
## SE.mean NA 44.437795 25.000000
## CI.mean.0.95 NA 564.635724 317.655118
## var NA 3949.435284 1250.000000
## std.dev NA 62.844533 35.355339
## coef.var NA 1.256891 1.272640boxplot(data, horizontal=TRUE, col='green')
Gráfico para Portland (Jamaica)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_JA <- subset(df, country_name == "Jamaica")
knitr::kable(head(df_JA)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 174 | 8/11/07 | NA | NA | Jamaica | JM | Portland | 14400 | Port Antonio | 7.79027 | NA | 18.1258 | -76.5082 | (18.125800000000002, -76.508200000000002) | Landslide | Landslide | Medium | Rain | NA | NA | NA | Jamaica Gleaner | http://www.jamaica-gleaner.com/gleaner/20070812/lead/lead2.html |
| 304 | 10/12/07 | NA | NA | Jamaica | JM | St. Elizabeth | 1371 | Maggotty | 4.57363 | NA | 18.1257 | -77.7405 | (18.125699999999998, -77.740499999999997) | Landslide | Complex | Medium | Rain | NA | NA | NA | RadioJamaica | http://www.radiojamaica.com/content/view/2039/26/ |
| 314 | 10/17/07 | NA | NA | Jamaica | JM | Saint Thomas | 2382 | Bath | 0.21825 | NA | 17.9500 | -76.3500 | (17.95, -76.349999999999994) | Landslide | Mudslide | Medium | Rain | NA | NA | NA | RadioJamaica | http://www.radiojamaica.com/content/view/2193/26/ |
| 339 | 10/31/07 | NA | NA | Jamaica | JM | Saint Thomas | 2634 | Easington | 6.51940 | NA | 17.9384 | -76.6479 | (17.938400000000001, -76.647900000000007) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Noel | NA | 1 | RadioJamaica | http://www.radiojamaica.com/content/view/2583/26/ |
| 340 | 10/31/07 | NA | NA | Jamaica | JM | Saint Catherine | 4085 | Riversdale | 5.46381 | NA | 18.2152 | -76.9659 | (18.215199999999999, -76.965900000000005) | Landslide | Complex | Medium | Rain | NA | NA | NA | RadioJamaica | http://www.radiojamaica.com/content/view/2933/26/ |
| 341 | 10/31/07 | NA | NA | Jamaica | JM | Saint Andrew | 1088 | Gordon Town | 0.96514 | NA | 18.0370 | -76.7088 | (18.036999999999999, -76.708799999999997) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Noel | NA | NA | Jamaica Observer | http://www.jamaicaobserver.com/news/html/20071101T010000-0500_128916_OBS_DEADLY_RAIN.asp |
library(dplyr)
df_JA <- subset(df, state == "Portland")
knitr::kable(head(df_JA))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 174 | 8/11/07 | NA | NA | Jamaica | JM | Portland | 14400 | Port Antonio | 7.79027 | NA | 18.1258 | -76.5082 | (18.125800000000002, -76.508200000000002) | Landslide | Landslide | Medium | Rain | NA | NA | NA | Jamaica Gleaner | http://www.jamaica-gleaner.com/gleaner/20070812/lead/lead2.html |
| 1391 | 1/10/10 | NA | NA | Jamaica | JM | Portland | 1119 | Moore Town | 5.02351 | NA | 18.1167 | -76.4500 | (18.116700000000002, -76.45) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://go-jamaica.com/news/read_article.php?id=15895 |
| 1763 | 4/18/10 | NA | NA | Jamaica | JM | Portland | 2757 | Buff Bay | 2.78885 | NA | 18.2106 | -76.6735 | (18.210599999999999, -76.673500000000004) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.jamaica-gleaner.com/gleaner/20100420/lead/lead4.html |
| 1764 | 4/18/10 | NA | NA | Jamaica | JM | Portland | 14400 | Port Antonio | 4.46942 | NA | 18.1865 | -76.5029 | (18.186499999999999, -76.502899999999997) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://allafrica.com/stories/201004200719.html |
| 2418 | 9/13/10 | Night | NA | Jamaica | JM | Portland | 1119 | Moore Town | 0.59599 | NA | 18.0723 | -76.4254 | (18.072299999999998, -76.425399999999996) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.jamaica-gleaner.com/gleaner/20100916/news/news4.html |
| 2511 | 9/28/10 | NA | NA | Jamaica | JM | Portland | 1119 | Moore Town | 7.81269 | NA | 18.0083 | -76.4394 | (18.008299999999998, -76.439400000000006) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.jamaicaobserver.com/news/More-floods-in-St-Thomas |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_JA, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_JA, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_JA, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_JA <- df_JA %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_JA$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_JA, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_JA$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 7.79027 |
| 4.46942 |
| 3.60799 |
| 4.68732 |
| 5.02351 |
| 0.59599 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_JA$distance
names(distance) <- df_JA$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Moore Town 7.812690 7.812690 14.929435 14.929435
## Port Antonio 7.790270 15.602960 14.886593 29.816028
## Buff Bay 7.523170 23.126130 14.376185 44.192213
## Moore Town 5.023510 28.149640 9.599532 53.791746
## Port Antonio 4.687320 32.836960 8.957099 62.748845
## Port Antonio 4.469420 37.306380 8.540710 71.289555
## Manchioneal 4.134540 41.440920 7.900780 79.190335
## Port Antonio 3.607990 45.048910 6.894585 86.084920
## Moore Town 3.179300 48.228210 6.075392 92.160312
## Buff Bay 2.788850 51.017060 5.329273 97.489585
## Manchioneal 0.717730 51.734790 1.371526 98.861110
## Moore Town 0.595990 52.330780 1.138890 100.000000stem(df_JA$"distance")##
## The decimal point is at the |
##
## 0 | 67
## 2 | 826
## 4 | 1570
## 6 | 588head(df_JA)## # A tibble: 6 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 174 8/11/07 <NA> <NA> Jamaica JM Portland 14400
## 2 1764 4/18/10 <NA> <NA> Jamaica JM Portland 14400
## 3 6345 9/8/14 0:15 <NA> Jamaica JM Portland 14400
## 4 7474 12/1/15 <NA> <NA> Jamaica JM Portland 14400
## 5 1391 1/10/10 <NA> <NA> Jamaica JM Portland 1119
## 6 2418 9/13/10 Night <NA> Jamaica JM Portland 1119
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_JA))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 174 | 8/11/07 | NA | NA | Jamaica | JM | Portland | 14400 | Port Antonio | 7.79027 | NA | 18.1258 | -76.5082 | (18.125800000000002, -76.508200000000002) | Landslide | Landslide | Medium | Rain | NA | NA | NA | Jamaica Gleaner | http://www.jamaica-gleaner.com/gleaner/20070812/lead/lead2.html | 14.886593 | 7.443296 |
| 1764 | 4/18/10 | NA | NA | Jamaica | JM | Portland | 14400 | Port Antonio | 4.46942 | NA | 18.1865 | -76.5029 | (18.186499999999999, -76.502899999999997) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://allafrica.com/stories/201004200719.html | 8.540710 | 19.156947 |
| 6345 | 9/8/14 | 0:15 | NA | Jamaica | JM | Portland | 14400 | Port Antonio | 3.60799 | Unknown | 18.1444 | -76.4587 | (18.144400000000001, -76.458699999999993) | Landslide | Mudslide | Small | Downpour | NA | 0 | 0 | Gleaner | http://jamaica-gleaner.com/gleaner/20140909/lead/lead23.html | 6.894585 | 26.874595 |
| 7474 | 12/1/15 | NA | NA | Jamaica | JM | Portland | 14400 | Port Antonio | 4.68732 | Above road | 18.1340 | -76.4551 | (18.134, -76.455100000000002) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | Restoration Village Farm | http://www.restorationvillagefarm.com/tag/port-antonio/ | 8.957099 | 34.800437 |
| 1391 | 1/10/10 | NA | NA | Jamaica | JM | Portland | 1119 | Moore Town | 5.02351 | NA | 18.1167 | -76.4500 | (18.116700000000002, -76.45) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://go-jamaica.com/news/read_article.php?id=15895 | 9.599532 | 44.078753 |
| 2418 | 9/13/10 | Night | NA | Jamaica | JM | Portland | 1119 | Moore Town | 0.59599 | NA | 18.0723 | -76.4254 | (18.072299999999998, -76.425399999999996) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.jamaica-gleaner.com/gleaner/20100916/news/news4.html | 1.138890 | 49.447964 |
stem(df_JA$"distance")##
## The decimal point is at the |
##
## 0 | 67
## 2 | 826
## 4 | 1570
## 6 | 588stem(df_JA$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 67
## 1 |
## 2 | 8
## 3 | 26
## 4 | 157
## 5 | 0
## 6 |
## 7 | 588Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.59599 | 1 | 8.3 | 8.3 | 8.3 | 8.3 |
| 0.71773 | 1 | 8.3 | 8.3 | 16.7 | 16.7 |
| 2.78885 | 1 | 8.3 | 8.3 | 25.0 | 25.0 |
| 3.1793 | 1 | 8.3 | 8.3 | 33.3 | 33.3 |
| 3.60799 | 1 | 8.3 | 8.3 | 41.7 | 41.7 |
| 4.13454 | 1 | 8.3 | 8.3 | 50.0 | 50.0 |
| 4.46942 | 1 | 8.3 | 8.3 | 58.3 | 58.3 |
| 4.68732 | 1 | 8.3 | 8.3 | 66.7 | 66.7 |
| 5.02351 | 1 | 8.3 | 8.3 | 75.0 | 75.0 |
| 7.52317 | 1 | 8.3 | 8.3 | 83.3 | 83.3 |
| 7.79027 | 1 | 8.3 | 8.3 | 91.7 | 91.7 |
| 7.81269 | 1 | 8.3 | 8.3 | 100.0 | 100.0 |
| Total | 12 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 13 obs. of 5 variables:
## $ n : num 1 1 1 1 1 1 1 1 1 1 ...
## $ % : num 8.3 8.3 8.3 8.3 8.3 8.3 8.3 8.3 8.3 8.3 ...
## $ val% : num 8.3 8.3 8.3 8.3 8.3 8.3 8.3 8.3 8.3 8.3 ...
## $ %cum : num 8.3 16.7 25 33.3 41.7 50 58.3 66.7 75 83.3 ...
## $ val%cum: num 8.3 16.7 25 33.3 41.7 50 58.3 66.7 75 83.3 ...x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.59599 | 1 |
| 0.71773 | 1 |
| 2.78885 | 1 |
| 3.1793 | 1 |
| 3.60799 | 1 |
| 4.13454 | 1 |
| 4.46942 | 1 |
| 4.68732 | 1 |
| 5.02351 | 1 |
| 7.52317 | 1 |
| 7.79027 | 1 |
| 7.81269 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.59599 2.59599 4.59599 6.59599 8.59599distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.596,2.6] | 1 | 0.0909091 | 1 |
| (2.6,4.6] | 5 | 0.4545455 | 6 |
| (4.6,6.6] | 2 | 0.1818182 | 8 |
| (6.6,8.6] | 3 | 0.2727273 | 11 |
str(Freq_table)## 'data.frame': 4 obs. of 4 variables:
## $ distance: Factor w/ 4 levels "(0.596,2.6]",..: 1 2 3 4
## $ Freq : int 1 5 2 3
## $ Rel_Freq: num 0.0909 0.4545 0.1818 0.2727
## $ Cum_Freq: int 1 6 8 11df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.596,2.6] | 1 |
| (2.6,4.6] | 5 |
| (4.6,6.6] | 2 |
| (6.6,8.6] | 3 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_JA)## id date time continent_code country_name country_code
## nbr.val 1.200000e+01 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 1.740000e+02 NA NA NA NA NA
## max 7.474000e+03 NA NA NA NA NA
## range 7.300000e+03 NA NA NA NA NA
## sum 3.885800e+04 NA NA NA NA NA
## median 2.623000e+03 NA NA NA NA NA
## mean 3.238167e+03 NA NA NA NA NA
## SE.mean 6.142102e+02 NA NA NA NA NA
## CI.mean.0.95 1.351868e+03 NA NA NA NA NA
## var 4.527050e+06 NA NA NA NA NA
## std.dev 2.127687e+03 NA NA NA NA NA
## coef.var 6.570652e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 1.200000e+01 NA 12.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 1.119000e+03 NA 0.5959900 NA
## max NA 1.440000e+04 NA 7.8126900 NA
## range NA 1.328100e+04 NA 7.2167000 NA
## sum NA 7.223200e+04 NA 52.3307800 NA
## median NA 2.539000e+03 NA 4.3019800 NA
## mean NA 6.019333e+03 NA 4.3608983 NA
## SE.mean NA 1.795694e+03 NA 0.7079935 NA
## CI.mean.0.95 NA 3.952296e+03 NA 1.5582832 NA
## var NA 3.869421e+07 NA 6.0150573 NA
## std.dev NA 6.220467e+03 NA 2.4525614 NA
## coef.var NA 1.033415e+00 NA 0.5623982 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 1.200000e+01 1.200000e+01 NA NA NA
## nbr.null 0.000000e+00 0.000000e+00 NA NA NA
## nbr.na 0.000000e+00 0.000000e+00 NA NA NA
## min 1.800830e+01 -7.668520e+01 NA NA NA
## max 1.821060e+01 -7.627810e+01 NA NA NA
## range 2.023000e-01 4.071000e-01 NA NA NA
## sum 2.173922e+02 -9.175819e+02 NA NA NA
## median 1.812125e+01 -7.645255e+01 NA NA NA
## mean 1.811602e+01 -7.646516e+01 NA NA NA
## SE.mean 1.703378e-02 3.541084e-02 NA NA NA
## CI.mean.0.95 3.749110e-02 7.793873e-02 NA NA NA
## var 3.481796e-03 1.504713e-02 NA NA NA
## std.dev 5.900675e-02 1.226667e-01 NA NA NA
## coef.var 3.257159e-03 -1.604217e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 2 9 NA
## nbr.null NA NA NA 2 9 NA
## nbr.na NA NA NA 10 3 NA
## min NA NA NA 0 0 NA
## max NA NA NA 0 0 NA
## range NA NA NA 0 0 NA
## sum NA NA NA 0 0 NA
## median NA NA NA 0 0 NA
## mean NA NA NA 0 0 NA
## SE.mean NA NA NA 0 0 NA
## CI.mean.0.95 NA NA NA 0 0 NA
## var NA NA NA 0 0 NA
## std.dev NA NA NA 0 0 NA
## coef.var NA NA NA NaN NaN NA
## source_link prop ypos
## nbr.val NA 12.0000000 12.0000000
## nbr.null NA 0.0000000 0.0000000
## nbr.na NA 0.0000000 0.0000000
## min NA 1.1388900 7.4432963
## max NA 14.9294354 92.8119073
## range NA 13.7905454 85.3686110
## sum NA 100.0000000 631.0918928
## median NA 8.2207450 53.4650449
## mean NA 8.3333333 52.5909911
## SE.mean NA 1.3529198 7.7590755
## CI.mean.0.95 NA 2.9777564 17.0776100
## var NA 21.9647038 722.4390327
## std.dev NA 4.6866517 26.8782260
## coef.var NA 0.5623982 0.5110804boxplot(data, horizontal=TRUE, col='green')
Gráfico para Saint Andrew (Jamaica)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_JA <- subset(df, country_name == "Jamaica")
knitr::kable(head(df_JA)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 174 | 8/11/07 | NA | NA | Jamaica | JM | Portland | 14400 | Port Antonio | 7.79027 | NA | 18.1258 | -76.5082 | (18.125800000000002, -76.508200000000002) | Landslide | Landslide | Medium | Rain | NA | NA | NA | Jamaica Gleaner | http://www.jamaica-gleaner.com/gleaner/20070812/lead/lead2.html |
| 304 | 10/12/07 | NA | NA | Jamaica | JM | St. Elizabeth | 1371 | Maggotty | 4.57363 | NA | 18.1257 | -77.7405 | (18.125699999999998, -77.740499999999997) | Landslide | Complex | Medium | Rain | NA | NA | NA | RadioJamaica | http://www.radiojamaica.com/content/view/2039/26/ |
| 314 | 10/17/07 | NA | NA | Jamaica | JM | Saint Thomas | 2382 | Bath | 0.21825 | NA | 17.9500 | -76.3500 | (17.95, -76.349999999999994) | Landslide | Mudslide | Medium | Rain | NA | NA | NA | RadioJamaica | http://www.radiojamaica.com/content/view/2193/26/ |
| 339 | 10/31/07 | NA | NA | Jamaica | JM | Saint Thomas | 2634 | Easington | 6.51940 | NA | 17.9384 | -76.6479 | (17.938400000000001, -76.647900000000007) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Noel | NA | 1 | RadioJamaica | http://www.radiojamaica.com/content/view/2583/26/ |
| 340 | 10/31/07 | NA | NA | Jamaica | JM | Saint Catherine | 4085 | Riversdale | 5.46381 | NA | 18.2152 | -76.9659 | (18.215199999999999, -76.965900000000005) | Landslide | Complex | Medium | Rain | NA | NA | NA | RadioJamaica | http://www.radiojamaica.com/content/view/2933/26/ |
| 341 | 10/31/07 | NA | NA | Jamaica | JM | Saint Andrew | 1088 | Gordon Town | 0.96514 | NA | 18.0370 | -76.7088 | (18.036999999999999, -76.708799999999997) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Noel | NA | NA | Jamaica Observer | http://www.jamaicaobserver.com/news/html/20071101T010000-0500_128916_OBS_DEADLY_RAIN.asp |
library(dplyr)
df_JA <- subset(df, state == "Saint Andrew")
knitr::kable(head(df_JA))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 341 | 10/31/07 | NA | NA | Jamaica | JM | Saint Andrew | 1088 | Gordon Town | 0.96514 | NA | 18.0370 | -76.7088 | (18.036999999999999, -76.708799999999997) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Noel | NA | NA | Jamaica Observer | http://www.jamaicaobserver.com/news/html/20071101T010000-0500_128916_OBS_DEADLY_RAIN.asp |
| 756 | 8/28/08 | NA | NA | Jamaica | JM | Saint Andrew | 1821 | Mavis Bank | 9.83051 | NA | 18.0388 | -76.5740 | (18.038799999999998, -76.573999999999998) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Gustav | NA | 7 | NA | http://www.reliefweb.int/rw/rwb.nsf/db900SID/EDIS-7HYLCK?OpenDocument |
| 2233 | 8/11/10 | NA | NA | Jamaica | JM | Saint Andrew | 8551 | Stony Hill | 5.98731 | NA | 18.1260 | -76.8110 | (18.126000000000001, -76.811000000000007) | Landslide | Complex | Medium | Downpour | NA | NA | 0 | NA | NA |
| 2518 | 9/29/10 | NA | NA | Jamaica | JM | Saint Andrew | 8551 | Stony Hill | 10.84467 | NA | 18.1686 | -76.8226 | (18.168600000000001, -76.822599999999994) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Nicole | NA | 0 | NA | http://www.jamaica-gleaner.com/gleaner/20100930/lead/lead7.html |
| 2523 | 9/30/10 | Early morning | NA | Jamaica | JM | Saint Andrew | 8551 | Stony Hill | 2.13878 | NA | 18.0622 | -76.7763 | (18.062200000000001, -76.776300000000006) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Storm Nicole | NA | 2 | NA | http://www.todayonline.com/BreakingNews/EDC101001-0000003/Officials--Death-toll-from-Tropical-Storm-Nicole-at-5,-expected-to-rise |
| 2547 | 10/5/10 | NA | NA | Dominica | DM | Saint Andrew | 1020 | Calibishie | 2.64873 | NA | 15.5918 | -61.3731 | (15.591799999999999, -61.373100000000001) | Landslide | Landslide | Medium | Rain | NA | NA | 0 | NA | http://dominicanewsonline.com/dno/news-photo-landslide-in-blenhim/ |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_JA, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_JA, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_JA, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_JA <- df_JA %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_JA$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_JA, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_JA$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 5.98731 |
| 10.84467 |
| 2.13878 |
| 9.83051 |
| 0.96514 |
| 2.64873 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_JA$distance
names(distance) <- df_JA$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Stony Hill 10.844670 10.844670 33.455570 33.455570
## Mavis Bank 9.830510 20.675180 30.326909 63.782479
## Stony Hill 5.987310 26.662490 18.470721 82.253200
## Calibishie 2.648730 29.311220 8.171274 90.424474
## Stony Hill 2.138780 31.450000 6.598090 97.022564
## Gordon Town 0.965140 32.415140 2.977436 100.000000stem(df_JA$"distance")##
## The decimal point is at the |
##
## 0 | 0
## 2 | 16
## 4 |
## 6 | 0
## 8 | 8
## 10 | 8head(df_JA)## # A tibble: 6 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 2233 8/11/10 <NA> <NA> Jamaica JM Sain~ 8551
## 2 2518 9/29/10 <NA> <NA> Jamaica JM Sain~ 8551
## 3 2523 9/30/10 Earl~ <NA> Jamaica JM Sain~ 8551
## 4 756 8/28/08 <NA> <NA> Jamaica JM Sain~ 1821
## 5 341 10/31/07 <NA> <NA> Jamaica JM Sain~ 1088
## 6 2547 10/5/10 <NA> <NA> Dominica DM Sain~ 1020
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_JA))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2233 | 8/11/10 | NA | NA | Jamaica | JM | Saint Andrew | 8551 | Stony Hill | 5.98731 | NA | 18.1260 | -76.8110 | (18.126000000000001, -76.811000000000007) | Landslide | Complex | Medium | Downpour | NA | NA | 0 | NA | NA | 18.470721 | 9.23536 |
| 2518 | 9/29/10 | NA | NA | Jamaica | JM | Saint Andrew | 8551 | Stony Hill | 10.84467 | NA | 18.1686 | -76.8226 | (18.168600000000001, -76.822599999999994) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Nicole | NA | 0 | NA | http://www.jamaica-gleaner.com/gleaner/20100930/lead/lead7.html | 33.455571 | 35.19851 |
| 2523 | 9/30/10 | Early morning | NA | Jamaica | JM | Saint Andrew | 8551 | Stony Hill | 2.13878 | NA | 18.0622 | -76.7763 | (18.062200000000001, -76.776300000000006) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Storm Nicole | NA | 2 | NA | http://www.todayonline.com/BreakingNews/EDC101001-0000003/Officials--Death-toll-from-Tropical-Storm-Nicole-at-5,-expected-to-rise | 6.598090 | 55.22534 |
| 756 | 8/28/08 | NA | NA | Jamaica | JM | Saint Andrew | 1821 | Mavis Bank | 9.83051 | NA | 18.0388 | -76.5740 | (18.038799999999998, -76.573999999999998) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Gustav | NA | 7 | NA | http://www.reliefweb.int/rw/rwb.nsf/db900SID/EDIS-7HYLCK?OpenDocument | 30.326909 | 73.68784 |
| 341 | 10/31/07 | NA | NA | Jamaica | JM | Saint Andrew | 1088 | Gordon Town | 0.96514 | NA | 18.0370 | -76.7088 | (18.036999999999999, -76.708799999999997) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Noel | NA | NA | Jamaica Observer | http://www.jamaicaobserver.com/news/html/20071101T010000-0500_128916_OBS_DEADLY_RAIN.asp | 2.977436 | 90.34001 |
| 2547 | 10/5/10 | NA | NA | Dominica | DM | Saint Andrew | 1020 | Calibishie | 2.64873 | NA | 15.5918 | -61.3731 | (15.591799999999999, -61.373100000000001) | Landslide | Landslide | Medium | Rain | NA | NA | 0 | NA | http://dominicanewsonline.com/dno/news-photo-landslide-in-blenhim/ | 8.171274 | 95.91436 |
stem(df_JA$"distance")##
## The decimal point is at the |
##
## 0 | 0
## 2 | 16
## 4 |
## 6 | 0
## 8 | 8
## 10 | 8stem(df_JA$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 |
## 1 | 0
## 2 | 16
## 3 |
## 4 |
## 5 |
## 6 | 0
## 7 |
## 8 |
## 9 | 8
## 10 | 8Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.96514 | 1 | 16.7 | 16.7 | 16.7 | 16.7 |
| 2.13878 | 1 | 16.7 | 16.7 | 33.3 | 33.3 |
| 2.64873 | 1 | 16.7 | 16.7 | 50.0 | 50.0 |
| 5.98731 | 1 | 16.7 | 16.7 | 66.7 | 66.7 |
| 9.83051 | 1 | 16.7 | 16.7 | 83.3 | 83.3 |
| 10.84467 | 1 | 16.7 | 16.7 | 100.0 | 100.0 |
| Total | 6 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 7 obs. of 5 variables:
## $ n : num 1 1 1 1 1 1 6
## $ % : num 16.7 16.7 16.7 16.7 16.7 16.7 100
## $ val% : num 16.7 16.7 16.7 16.7 16.7 16.7 100
## $ %cum : num 16.7 33.3 50 66.7 83.3 100 100
## $ val%cum: num 16.7 33.3 50 66.7 83.3 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.96514 | 1 |
| 2.13878 | 1 |
| 2.64873 | 1 |
| 5.98731 | 1 |
| 9.83051 | 1 |
| 10.84467 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.96514 4.96514 8.96514 12.96514distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.965,4.97] | 2 | 0.4 | 2 |
| (4.97,8.97] | 1 | 0.2 | 3 |
| (8.97,13] | 2 | 0.4 | 5 |
str(Freq_table)## 'data.frame': 3 obs. of 4 variables:
## $ distance: Factor w/ 3 levels "(0.965,4.97]",..: 1 2 3
## $ Freq : int 2 1 2
## $ Rel_Freq: num 0.4 0.2 0.4
## $ Cum_Freq: int 2 3 5df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.965,4.97] | 2 |
| (4.97,8.97] | 1 |
| (8.97,13] | 2 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_JA)## Warning in min(x): ningún argumento finito para min; retornando Inf## Warning in max(x): ningun argumento finito para max; retornando -Inf## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 6.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 3.410000e+02 NA NA NA NA NA
## max 2.547000e+03 NA NA NA NA NA
## range 2.206000e+03 NA NA NA NA NA
## sum 1.091800e+04 NA NA NA NA NA
## median 2.375500e+03 NA NA NA NA NA
## mean 1.819667e+03 NA NA NA NA NA
## SE.mean 4.082502e+02 NA NA NA NA NA
## CI.mean.0.95 1.049441e+03 NA NA NA NA NA
## var 1.000009e+06 NA NA NA NA NA
## std.dev 1.000005e+03 NA NA NA NA NA
## coef.var 5.495538e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 6.000000e+00 NA 6.000000 NA
## nbr.null NA 0.000000e+00 NA 0.000000 NA
## nbr.na NA 0.000000e+00 NA 0.000000 NA
## min NA 1.020000e+03 NA 0.965140 NA
## max NA 8.551000e+03 NA 10.844670 NA
## range NA 7.531000e+03 NA 9.879530 NA
## sum NA 2.958200e+04 NA 32.415140 NA
## median NA 5.186000e+03 NA 4.318020 NA
## mean NA 4.930333e+03 NA 5.402523 NA
## SE.mean NA 1.623267e+03 NA 1.707745 NA
## CI.mean.0.95 NA 4.172741e+03 NA 4.389898 NA
## var NA 1.580997e+07 NA 17.498354 NA
## std.dev NA 3.976176e+03 NA 4.183103 NA
## coef.var NA 8.064720e-01 NA 0.774287 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 6.00000000 6.00000000 NA NA NA
## nbr.null 0.00000000 0.00000000 NA NA NA
## nbr.na 0.00000000 0.00000000 NA NA NA
## min 15.59180000 -76.82260000 NA NA NA
## max 18.16860000 -61.37310000 NA NA NA
## range 2.57680000 15.44950000 NA NA NA
## sum 106.02440000 -445.06580000 NA NA NA
## median 18.05050000 -76.74255000 NA NA NA
## mean 17.67073333 -74.17763333 NA NA NA
## SE.mean 0.41633213 2.56117804 NA NA NA
## CI.mean.0.95 1.07021581 6.58371775 NA NA NA
## var 1.03999465 39.35779778 NA NA NA
## std.dev 1.01980128 6.27357934 NA NA NA
## coef.var 0.05771132 -0.08457508 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 0 5.000000 NA
## nbr.null NA NA NA 0 3.000000 NA
## nbr.na NA NA NA 6 1.000000 NA
## min NA NA NA Inf 0.000000 NA
## max NA NA NA -Inf 7.000000 NA
## range NA NA NA -Inf 7.000000 NA
## sum NA NA NA 0 9.000000 NA
## median NA NA NA NA 0.000000 NA
## mean NA NA NA NaN 1.800000 NA
## SE.mean NA NA NA NA 1.356466 NA
## CI.mean.0.95 NA NA NA NaN 3.766153 NA
## var NA NA NA NA 9.200000 NA
## std.dev NA NA NA NA 3.033150 NA
## coef.var NA NA NA NA 1.685083 NA
## source_link prop ypos
## nbr.val NA 6.000000 6.0000000
## nbr.null NA 0.000000 0.0000000
## nbr.na NA 0.000000 0.0000000
## min NA 2.977436 9.2353604
## max NA 33.455570 95.9143629
## range NA 30.478135 86.6790025
## sum NA 100.000000 359.6014085
## median NA 13.320998 64.4565857
## mean NA 16.666667 59.9335681
## SE.mean NA 5.268356 13.6780214
## CI.mean.0.95 NA 13.542739 35.1604732
## var NA 166.533419 1122.5296089
## std.dev NA 12.904783 33.5041730
## coef.var NA 0.774287 0.5590218boxplot(data, horizontal=TRUE, col='green')
Gráfico para Saint Ann (Jamaica)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_JA <- subset(df, country_name == "Jamaica")
knitr::kable(head(df_JA)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 174 | 8/11/07 | NA | NA | Jamaica | JM | Portland | 14400 | Port Antonio | 7.79027 | NA | 18.1258 | -76.5082 | (18.125800000000002, -76.508200000000002) | Landslide | Landslide | Medium | Rain | NA | NA | NA | Jamaica Gleaner | http://www.jamaica-gleaner.com/gleaner/20070812/lead/lead2.html |
| 304 | 10/12/07 | NA | NA | Jamaica | JM | St. Elizabeth | 1371 | Maggotty | 4.57363 | NA | 18.1257 | -77.7405 | (18.125699999999998, -77.740499999999997) | Landslide | Complex | Medium | Rain | NA | NA | NA | RadioJamaica | http://www.radiojamaica.com/content/view/2039/26/ |
| 314 | 10/17/07 | NA | NA | Jamaica | JM | Saint Thomas | 2382 | Bath | 0.21825 | NA | 17.9500 | -76.3500 | (17.95, -76.349999999999994) | Landslide | Mudslide | Medium | Rain | NA | NA | NA | RadioJamaica | http://www.radiojamaica.com/content/view/2193/26/ |
| 339 | 10/31/07 | NA | NA | Jamaica | JM | Saint Thomas | 2634 | Easington | 6.51940 | NA | 17.9384 | -76.6479 | (17.938400000000001, -76.647900000000007) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Noel | NA | 1 | RadioJamaica | http://www.radiojamaica.com/content/view/2583/26/ |
| 340 | 10/31/07 | NA | NA | Jamaica | JM | Saint Catherine | 4085 | Riversdale | 5.46381 | NA | 18.2152 | -76.9659 | (18.215199999999999, -76.965900000000005) | Landslide | Complex | Medium | Rain | NA | NA | NA | RadioJamaica | http://www.radiojamaica.com/content/view/2933/26/ |
| 341 | 10/31/07 | NA | NA | Jamaica | JM | Saint Andrew | 1088 | Gordon Town | 0.96514 | NA | 18.0370 | -76.7088 | (18.036999999999999, -76.708799999999997) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Noel | NA | NA | Jamaica Observer | http://www.jamaicaobserver.com/news/html/20071101T010000-0500_128916_OBS_DEADLY_RAIN.asp |
library(dplyr)
df_JA <- subset(df, state == "Saint Ann")
knitr::kable(head(df_JA))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 354 | 11/12/07 | NA | NA | Jamaica | JM | Saint Ann | 13671 | Saint Ann<U+043D><U+045E><U+0434>‰<U+0435><U+0434>‹<U+045E>s Bay | 3.96533 | NA | 18.4000 | -77.2000 | (18.399999999999999, -77.2) | Landslide | Landslide | Medium | Rain | NA | NA | NA | Jamaica Gleaner | http://www.jamaica-gleaner.com/gleaner/20071113/news/news1.html |
| 501 | 4/16/08 | NA | NA | Jamaica | JM | Saint Ann | 9450 | Ocho Rios | 0.53886 | NA | 18.4054 | -77.1007 | (18.4054, -77.100700000000003) | Landslide | Mudslide | Medium | Rain | NA | NA | NA | NA | http://www.nwa.gov.jm/content/newsread.aspx?newsId=268 |
| 7473 | 12/1/15 | NA | NA | Jamaica | JM | Saint Ann | 13671 | Saint Ann<U+043D><U+045E><U+0434>‰<U+0435><U+0434>‹<U+045E>s Bay | 1.08196 | Above road | 18.4313 | -77.1919 | (18.4313, -77.191900000000004) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | First Look | http://go-jamaica.com/pressrelease/item.php?id=5755 |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_JA, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_JA, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_JA, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_JA <- df_JA %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_JA$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_JA, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_JA$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 3.96533 |
| 1.08196 |
| 0.53886 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_JA$distance
names(distance) <- df_JA$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Saint Ann<U+043D><U+045E><U+0434>‰<U+0435><U+0434>‹<U+045E>s Bay 3.965330 3.965330 70.985025 70.985025
## Saint Ann<U+043D><U+045E><U+0434>‰<U+0435><U+0434>‹<U+045E>s Bay 1.081960 5.047290 19.368617 90.353642
## Ocho Rios 0.538860 5.586150 9.646358 100.000000stem(df_JA$"distance")##
## The decimal point is at the |
##
## 0 | 5
## 1 | 1
## 2 |
## 3 |
## 4 | 0head(df_JA)## # A tibble: 3 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 354 11/12/07 <NA> <NA> Jamaica JM Saint Ann 13671
## 2 7473 12/1/15 <NA> <NA> Jamaica JM Saint Ann 13671
## 3 501 4/16/08 <NA> <NA> Jamaica JM Saint Ann 9450
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_JA))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 354 | 11/12/07 | NA | NA | Jamaica | JM | Saint Ann | 13671 | Saint Ann<U+043D><U+045E><U+0434>‰<U+0435><U+0434>‹<U+045E>s Bay | 3.96533 | NA | 18.4000 | -77.2000 | (18.399999999999999, -77.2) | Landslide | Landslide | Medium | Rain | NA | NA | NA | Jamaica Gleaner | http://www.jamaica-gleaner.com/gleaner/20071113/news/news1.html | 70.985026 | 35.49251 |
| 7473 | 12/1/15 | NA | NA | Jamaica | JM | Saint Ann | 13671 | Saint Ann<U+043D><U+045E><U+0434>‰<U+0435><U+0434>‹<U+045E>s Bay | 1.08196 | Above road | 18.4313 | -77.1919 | (18.4313, -77.191900000000004) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | First Look | http://go-jamaica.com/pressrelease/item.php?id=5755 | 19.368617 | 80.66933 |
| 501 | 4/16/08 | NA | NA | Jamaica | JM | Saint Ann | 9450 | Ocho Rios | 0.53886 | NA | 18.4054 | -77.1007 | (18.4054, -77.100700000000003) | Landslide | Mudslide | Medium | Rain | NA | NA | NA | NA | http://www.nwa.gov.jm/content/newsread.aspx?newsId=268 | 9.646358 | 95.17682 |
stem(df_JA$"distance")##
## The decimal point is at the |
##
## 0 | 5
## 1 | 1
## 2 |
## 3 |
## 4 | 0stem(df_JA$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 5
## 1 | 1
## 1 |
## 2 |
## 2 |
## 3 |
## 3 |
## 4 | 0Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.53886 | 1 | 33.3 | 33.3 | 33.3 | 33.3 |
| 1.08196 | 1 | 33.3 | 33.3 | 66.7 | 66.7 |
| 3.96533 | 1 | 33.3 | 33.3 | 100.0 | 100.0 |
| Total | 3 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 4 obs. of 5 variables:
## $ n : num 1 1 1 3
## $ % : num 33.3 33.3 33.3 100
## $ val% : num 33.3 33.3 33.3 100
## $ %cum : num 33.3 66.7 100 100
## $ val%cum: num 33.3 66.7 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.53886 | 1 |
| 1.08196 | 1 |
| 3.96533 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.53886 2.53886 4.53886distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.539,2.54] | 1 | 0.5 | 1 |
| (2.54,4.54] | 1 | 0.5 | 2 |
str(Freq_table)## 'data.frame': 2 obs. of 4 variables:
## $ distance: Factor w/ 2 levels "(0.539,2.54]",..: 1 2
## $ Freq : int 1 1
## $ Rel_Freq: num 0.5 0.5
## $ Cum_Freq: int 1 2df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.539,2.54] | 1 |
| (2.54,4.54] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_JA)## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced
## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 3.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 3.540000e+02 NA NA NA NA NA
## max 7.473000e+03 NA NA NA NA NA
## range 7.119000e+03 NA NA NA NA NA
## sum 8.328000e+03 NA NA NA NA NA
## median 5.010000e+02 NA NA NA NA NA
## mean 2.776000e+03 NA NA NA NA NA
## SE.mean 2.348883e+03 NA NA NA NA NA
## CI.mean.0.95 1.010643e+04 NA NA NA NA NA
## var 1.655176e+07 NA NA NA NA NA
## std.dev 4.068385e+03 NA NA NA NA NA
## coef.var 1.465557e+00 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 3.000000e+00 NA 3.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 9.450000e+03 NA 0.5388600 NA
## max NA 1.367100e+04 NA 3.9653300 NA
## range NA 4.221000e+03 NA 3.4264700 NA
## sum NA 3.679200e+04 NA 5.5861500 NA
## median NA 1.367100e+04 NA 1.0819600 NA
## mean NA 1.226400e+04 NA 1.8620500 NA
## SE.mean NA 1.407000e+03 NA 1.0632622 NA
## CI.mean.0.95 NA 6.053832e+03 NA 4.5748480 NA
## var NA 5.938947e+06 NA 3.3915795 NA
## std.dev NA 2.436995e+03 NA 1.8416241 NA
## coef.var NA 1.987113e-01 NA 0.9890304 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 3.000000e+00 3.000000e+00 NA NA NA
## nbr.null 0.000000e+00 0.000000e+00 NA NA NA
## nbr.na 0.000000e+00 0.000000e+00 NA NA NA
## min 1.840000e+01 -7.720000e+01 NA NA NA
## max 1.843130e+01 -7.710070e+01 NA NA NA
## range 3.130000e-02 9.930000e-02 NA NA NA
## sum 5.523670e+01 -2.314926e+02 NA NA NA
## median 1.840540e+01 -7.719190e+01 NA NA NA
## mean 1.841223e+01 -7.716420e+01 NA NA NA
## SE.mean 9.659940e-03 3.183599e-02 NA NA NA
## CI.mean.0.95 4.156337e-02 1.369792e-01 NA NA NA
## var 2.799433e-04 3.040590e-03 NA NA NA
## std.dev 1.673151e-02 5.514155e-02 NA NA NA
## coef.var 9.087169e-04 -7.146001e-04 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 1 1 NA
## nbr.null NA NA NA 1 1 NA
## nbr.na NA NA NA 2 2 NA
## min NA NA NA 0 0 NA
## max NA NA NA 0 0 NA
## range NA NA NA 0 0 NA
## sum NA NA NA 0 0 NA
## median NA NA NA 0 0 NA
## mean NA NA NA 0 0 NA
## SE.mean NA NA NA NA NA NA
## CI.mean.0.95 NA NA NA NaN NaN NA
## var NA NA NA NA NA NA
## std.dev NA NA NA NA NA NA
## coef.var NA NA NA NA NA NA
## source_link prop ypos
## nbr.val NA 3.0000000 3.0000000
## nbr.null NA 0.0000000 0.0000000
## nbr.na NA 0.0000000 0.0000000
## min NA 9.6463575 35.4925127
## max NA 70.9850255 95.1768212
## range NA 61.3386680 59.6843085
## sum NA 100.0000000 211.3386680
## median NA 19.3686170 80.6693340
## mean NA 33.3333333 70.4462227
## SE.mean NA 19.0338998 17.9716274
## CI.mean.0.95 NA 81.8962609 77.3256717
## var NA 1086.8680228 968.9381746
## std.dev NA 32.9676815 31.1277718
## coef.var NA 0.9890304 0.4418657boxplot(data, horizontal=TRUE, col='green')
Gráfico para Saint Catherine (Jamaica)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_JA <- subset(df, country_name == "Jamaica")
knitr::kable(head(df_JA)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 174 | 8/11/07 | NA | NA | Jamaica | JM | Portland | 14400 | Port Antonio | 7.79027 | NA | 18.1258 | -76.5082 | (18.125800000000002, -76.508200000000002) | Landslide | Landslide | Medium | Rain | NA | NA | NA | Jamaica Gleaner | http://www.jamaica-gleaner.com/gleaner/20070812/lead/lead2.html |
| 304 | 10/12/07 | NA | NA | Jamaica | JM | St. Elizabeth | 1371 | Maggotty | 4.57363 | NA | 18.1257 | -77.7405 | (18.125699999999998, -77.740499999999997) | Landslide | Complex | Medium | Rain | NA | NA | NA | RadioJamaica | http://www.radiojamaica.com/content/view/2039/26/ |
| 314 | 10/17/07 | NA | NA | Jamaica | JM | Saint Thomas | 2382 | Bath | 0.21825 | NA | 17.9500 | -76.3500 | (17.95, -76.349999999999994) | Landslide | Mudslide | Medium | Rain | NA | NA | NA | RadioJamaica | http://www.radiojamaica.com/content/view/2193/26/ |
| 339 | 10/31/07 | NA | NA | Jamaica | JM | Saint Thomas | 2634 | Easington | 6.51940 | NA | 17.9384 | -76.6479 | (17.938400000000001, -76.647900000000007) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Noel | NA | 1 | RadioJamaica | http://www.radiojamaica.com/content/view/2583/26/ |
| 340 | 10/31/07 | NA | NA | Jamaica | JM | Saint Catherine | 4085 | Riversdale | 5.46381 | NA | 18.2152 | -76.9659 | (18.215199999999999, -76.965900000000005) | Landslide | Complex | Medium | Rain | NA | NA | NA | RadioJamaica | http://www.radiojamaica.com/content/view/2933/26/ |
| 341 | 10/31/07 | NA | NA | Jamaica | JM | Saint Andrew | 1088 | Gordon Town | 0.96514 | NA | 18.0370 | -76.7088 | (18.036999999999999, -76.708799999999997) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Noel | NA | NA | Jamaica Observer | http://www.jamaicaobserver.com/news/html/20071101T010000-0500_128916_OBS_DEADLY_RAIN.asp |
library(dplyr)
df_JA <- subset(df, state == "Saint Catherine")
knitr::kable(head(df_JA))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 340 | 10/31/07 | NA | NA | Jamaica | JM | Saint Catherine | 4085 | Riversdale | 5.46381 | NA | 18.2152 | -76.9659 | (18.215199999999999, -76.965900000000005) | Landslide | Complex | Medium | Rain | NA | NA | NA | RadioJamaica | http://www.radiojamaica.com/content/view/2933/26/ |
| 2519 | 9/29/10 | NA | NA | Jamaica | JM | Saint Catherine | 12873 | Bog Walk | 5.86530 | NA | 18.0677 | -77.0476 | (18.067699999999999, -77.047600000000003) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Nicole | NA | 0 | NA | http://www.reliefweb.int/rw/RWFiles2010.nsf/FilesByRWDocUnidFilename/KHII-89T7Y2-full_report.pdf/$File/full_report.pdf |
| 7472 | 12/1/15 | NA | NA | Jamaica | JM | Saint Catherine | 12873 | Bog Walk | 6.71269 | Above road | 18.0918 | -76.9429 | (18.091799999999999, -76.942899999999995) | Landslide | Landslide | Small | Rain | NA | 0 | 0 | Loop | http://www.loopjamaica.com/content/landslide-waugh-hill-main-road-blocks-thoroughfare |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_JA, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_JA, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_JA, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_JA <- df_JA %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_JA$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_JA, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_JA$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 5.46381 |
| 5.86530 |
| 6.71269 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_JA$distance
names(distance) <- df_JA$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Bog Walk 6.71269 6.71269 37.20632 37.20632
## Bog Walk 5.86530 12.57799 32.50951 69.71583
## Riversdale 5.46381 18.04180 30.28417 100.00000stem(df_JA$"distance")##
## The decimal point is at the |
##
## 5 |
## 5 | 59
## 6 |
## 6 | 7head(df_JA)## # A tibble: 3 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 340 10/31/07 <NA> <NA> Jamaica JM Sain~ 4085
## 2 2519 9/29/10 <NA> <NA> Jamaica JM Sain~ 12873
## 3 7472 12/1/15 <NA> <NA> Jamaica JM Sain~ 12873
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_JA))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 340 | 10/31/07 | NA | NA | Jamaica | JM | Saint Catherine | 4085 | Riversdale | 5.46381 | NA | 18.2152 | -76.9659 | (18.215199999999999, -76.965900000000005) | Landslide | Complex | Medium | Rain | NA | NA | NA | RadioJamaica | http://www.radiojamaica.com/content/view/2933/26/ | 30.28417 | 15.14209 |
| 2519 | 9/29/10 | NA | NA | Jamaica | JM | Saint Catherine | 12873 | Bog Walk | 5.86530 | NA | 18.0677 | -77.0476 | (18.067699999999999, -77.047600000000003) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Nicole | NA | 0 | NA | http://www.reliefweb.int/rw/RWFiles2010.nsf/FilesByRWDocUnidFilename/KHII-89T7Y2-full_report.pdf/$File/full_report.pdf | 32.50951 | 46.53893 |
| 7472 | 12/1/15 | NA | NA | Jamaica | JM | Saint Catherine | 12873 | Bog Walk | 6.71269 | Above road | 18.0918 | -76.9429 | (18.091799999999999, -76.942899999999995) | Landslide | Landslide | Small | Rain | NA | 0 | 0 | Loop | http://www.loopjamaica.com/content/landslide-waugh-hill-main-road-blocks-thoroughfare | 37.20632 | 81.39684 |
stem(df_JA$"distance")##
## The decimal point is at the |
##
## 5 |
## 5 | 59
## 6 |
## 6 | 7stem(df_JA$"distance", scale = 2)##
## The decimal point is 1 digit(s) to the left of the |
##
## 54 | 6
## 56 |
## 58 | 7
## 60 |
## 62 |
## 64 |
## 66 | 1Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 5.46381 | 1 | 33.3 | 33.3 | 33.3 | 33.3 |
| 5.8653 | 1 | 33.3 | 33.3 | 66.7 | 66.7 |
| 6.71269 | 1 | 33.3 | 33.3 | 100.0 | 100.0 |
| Total | 3 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 4 obs. of 5 variables:
## $ n : num 1 1 1 3
## $ % : num 33.3 33.3 33.3 100
## $ val% : num 33.3 33.3 33.3 100
## $ %cum : num 33.3 66.7 100 100
## $ val%cum: num 33.3 66.7 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 5.46381 | 1 |
| 5.8653 | 1 |
| 6.71269 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 5.46381 6.46381 7.46381distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (5.46,6.46] | 1 | 0.5 | 1 |
| (6.46,7.46] | 1 | 0.5 | 2 |
str(Freq_table)## 'data.frame': 2 obs. of 4 variables:
## $ distance: Factor w/ 2 levels "(5.46,6.46]",..: 1 2
## $ Freq : int 1 1
## $ Rel_Freq: num 0.5 0.5
## $ Cum_Freq: int 1 2df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (5.46,6.46] | 1 |
| (6.46,7.46] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_JA)## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 3.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 3.400000e+02 NA NA NA NA NA
## max 7.472000e+03 NA NA NA NA NA
## range 7.132000e+03 NA NA NA NA NA
## sum 1.033100e+04 NA NA NA NA NA
## median 2.519000e+03 NA NA NA NA NA
## mean 3.443667e+03 NA NA NA NA NA
## SE.mean 2.110104e+03 NA NA NA NA NA
## CI.mean.0.95 9.079043e+03 NA NA NA NA NA
## var 1.335761e+07 NA NA NA NA NA
## std.dev 3.654807e+03 NA NA NA NA NA
## coef.var 1.061313e+00 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 3.000000e+00 NA 3.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 4.085000e+03 NA 5.4638100 NA
## max NA 1.287300e+04 NA 6.7126900 NA
## range NA 8.788000e+03 NA 1.2488800 NA
## sum NA 2.983100e+04 NA 18.0418000 NA
## median NA 1.287300e+04 NA 5.8653000 NA
## mean NA 9.943667e+03 NA 6.0139333 NA
## SE.mean NA 2.929333e+03 NA 0.3681006 NA
## CI.mean.0.95 NA 1.260390e+04 NA 1.5838092 NA
## var NA 2.574298e+07 NA 0.4064942 NA
## std.dev NA 5.073754e+03 NA 0.6375690 NA
## coef.var NA 5.102498e-01 NA 0.1060153 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 3.000000000 3.000000e+00 NA NA NA
## nbr.null 0.000000000 0.000000e+00 NA NA NA
## nbr.na 0.000000000 0.000000e+00 NA NA NA
## min 18.067700000 -7.704760e+01 NA NA NA
## max 18.215200000 -7.694290e+01 NA NA NA
## range 0.147500000 1.047000e-01 NA NA NA
## sum 54.374700000 -2.309564e+02 NA NA NA
## median 18.091800000 -7.696590e+01 NA NA NA
## mean 18.124900000 -7.698547e+01 NA NA NA
## SE.mean 0.045682856 3.176824e-02 NA NA NA
## CI.mean.0.95 0.196557465 1.366877e-01 NA NA NA
## var 0.006260770 3.027663e-03 NA NA NA
## std.dev 0.079125028 5.502421e-02 NA NA NA
## coef.var 0.004365543 -7.147350e-04 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 1 2 NA
## nbr.null NA NA NA 1 2 NA
## nbr.na NA NA NA 2 1 NA
## min NA NA NA 0 0 NA
## max NA NA NA 0 0 NA
## range NA NA NA 0 0 NA
## sum NA NA NA 0 0 NA
## median NA NA NA 0 0 NA
## mean NA NA NA 0 0 NA
## SE.mean NA NA NA NA 0 NA
## CI.mean.0.95 NA NA NA NaN 0 NA
## var NA NA NA NA 0 NA
## std.dev NA NA NA NA 0 NA
## coef.var NA NA NA NA NaN NA
## source_link prop ypos
## nbr.val NA 3.0000000 3.0000000
## nbr.null NA 0.0000000 0.0000000
## nbr.na NA 0.0000000 0.0000000
## min NA 30.2841734 15.1420867
## max NA 37.2063209 81.3968396
## range NA 6.9221475 66.2547529
## sum NA 100.0000000 143.0778525
## median NA 32.5095057 46.5389263
## mean NA 33.3333333 47.6926175
## SE.mean NA 2.0402655 19.1347966
## CI.mean.0.95 NA 8.7785541 82.3303848
## var NA 12.4880503 1098.4213215
## std.dev NA 3.5338436 33.1424399
## coef.var NA 0.1060153 0.6949176boxplot(data, horizontal=TRUE, col='green')
Gráfico para Saint Thomas (Jamaica)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_JA <- subset(df, country_name == "Jamaica")
knitr::kable(head(df_JA)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 174 | 8/11/07 | NA | NA | Jamaica | JM | Portland | 14400 | Port Antonio | 7.79027 | NA | 18.1258 | -76.5082 | (18.125800000000002, -76.508200000000002) | Landslide | Landslide | Medium | Rain | NA | NA | NA | Jamaica Gleaner | http://www.jamaica-gleaner.com/gleaner/20070812/lead/lead2.html |
| 304 | 10/12/07 | NA | NA | Jamaica | JM | St. Elizabeth | 1371 | Maggotty | 4.57363 | NA | 18.1257 | -77.7405 | (18.125699999999998, -77.740499999999997) | Landslide | Complex | Medium | Rain | NA | NA | NA | RadioJamaica | http://www.radiojamaica.com/content/view/2039/26/ |
| 314 | 10/17/07 | NA | NA | Jamaica | JM | Saint Thomas | 2382 | Bath | 0.21825 | NA | 17.9500 | -76.3500 | (17.95, -76.349999999999994) | Landslide | Mudslide | Medium | Rain | NA | NA | NA | RadioJamaica | http://www.radiojamaica.com/content/view/2193/26/ |
| 339 | 10/31/07 | NA | NA | Jamaica | JM | Saint Thomas | 2634 | Easington | 6.51940 | NA | 17.9384 | -76.6479 | (17.938400000000001, -76.647900000000007) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Noel | NA | 1 | RadioJamaica | http://www.radiojamaica.com/content/view/2583/26/ |
| 340 | 10/31/07 | NA | NA | Jamaica | JM | Saint Catherine | 4085 | Riversdale | 5.46381 | NA | 18.2152 | -76.9659 | (18.215199999999999, -76.965900000000005) | Landslide | Complex | Medium | Rain | NA | NA | NA | RadioJamaica | http://www.radiojamaica.com/content/view/2933/26/ |
| 341 | 10/31/07 | NA | NA | Jamaica | JM | Saint Andrew | 1088 | Gordon Town | 0.96514 | NA | 18.0370 | -76.7088 | (18.036999999999999, -76.708799999999997) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Noel | NA | NA | Jamaica Observer | http://www.jamaicaobserver.com/news/html/20071101T010000-0500_128916_OBS_DEADLY_RAIN.asp |
library(dplyr)
df_JA <- subset(df, state == "Saint Thomas")
knitr::kable(head(df_JA))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 314 | 10/17/07 | NA | NA | Jamaica | JM | Saint Thomas | 2382 | Bath | 0.21825 | NA | 17.9500 | -76.3500 | (17.95, -76.349999999999994) | Landslide | Mudslide | Medium | Rain | NA | NA | NA | RadioJamaica | http://www.radiojamaica.com/content/view/2193/26/ |
| 339 | 10/31/07 | NA | NA | Jamaica | JM | Saint Thomas | 2634 | Easington | 6.51940 | NA | 17.9384 | -76.6479 | (17.938400000000001, -76.647900000000007) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Noel | NA | 1 | RadioJamaica | http://www.radiojamaica.com/content/view/2583/26/ |
| 774 | 9/4/08 | NA | NA | Jamaica | JM | Saint Thomas | 2382 | Bath | 1.71217 | NA | 17.9480 | -76.3330 | (17.948, -76.332999999999998) | Landslide | Complex | Medium | Tropical cyclone | Tropical Storm Gustav | NA | NA | NA | http://www.jamaica-gleaner.com/gleaner/20080905/lead/lead4.html |
| 1760 | 4/18/10 | NA | NA | Jamaica | JM | Saint Thomas | 2634 | Easington | 4.53632 | NA | 17.9647 | -76.5835 | (17.964700000000001, -76.583500000000001) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.jamaica-gleaner.com/gleaner/20100420/lead/lead4.html |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_JA, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_JA, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_JA, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_JA <- df_JA %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_JA$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_JA, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_JA$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 6.51940 |
| 4.53632 |
| 0.21825 |
| 1.71217 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_JA$distance
names(distance) <- df_JA$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Easington 6.519400 6.519400 50.202755 50.202755
## Easington 4.536320 11.055720 34.932012 85.134767
## Bath 1.712170 12.767890 13.184595 98.319362
## Bath 0.218250 12.986140 1.680638 100.000000stem(df_JA$"distance")##
## The decimal point is at the |
##
## 0 | 27
## 2 |
## 4 | 5
## 6 | 5head(df_JA)## # A tibble: 4 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 339 10/31/07 <NA> <NA> Jamaica JM Sain~ 2634
## 2 1760 4/18/10 <NA> <NA> Jamaica JM Sain~ 2634
## 3 314 10/17/07 <NA> <NA> Jamaica JM Sain~ 2382
## 4 774 9/4/08 <NA> <NA> Jamaica JM Sain~ 2382
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_JA))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 339 | 10/31/07 | NA | NA | Jamaica | JM | Saint Thomas | 2634 | Easington | 6.51940 | NA | 17.9384 | -76.6479 | (17.938400000000001, -76.647900000000007) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Noel | NA | 1 | RadioJamaica | http://www.radiojamaica.com/content/view/2583/26/ | 50.202755 | 25.10138 |
| 1760 | 4/18/10 | NA | NA | Jamaica | JM | Saint Thomas | 2634 | Easington | 4.53632 | NA | 17.9647 | -76.5835 | (17.964700000000001, -76.583500000000001) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.jamaica-gleaner.com/gleaner/20100420/lead/lead4.html | 34.932012 | 67.66876 |
| 314 | 10/17/07 | NA | NA | Jamaica | JM | Saint Thomas | 2382 | Bath | 0.21825 | NA | 17.9500 | -76.3500 | (17.95, -76.349999999999994) | Landslide | Mudslide | Medium | Rain | NA | NA | NA | RadioJamaica | http://www.radiojamaica.com/content/view/2193/26/ | 1.680638 | 85.97509 |
| 774 | 9/4/08 | NA | NA | Jamaica | JM | Saint Thomas | 2382 | Bath | 1.71217 | NA | 17.9480 | -76.3330 | (17.948, -76.332999999999998) | Landslide | Complex | Medium | Tropical cyclone | Tropical Storm Gustav | NA | NA | NA | http://www.jamaica-gleaner.com/gleaner/20080905/lead/lead4.html | 13.184595 | 93.40770 |
stem(df_JA$"distance")##
## The decimal point is at the |
##
## 0 | 27
## 2 |
## 4 | 5
## 6 | 5stem(df_JA$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 2
## 1 | 7
## 2 |
## 3 |
## 4 | 5
## 5 |
## 6 | 5Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.21825 | 1 | 25 | 25 | 25 | 25 |
| 1.71217 | 1 | 25 | 25 | 50 | 50 |
| 4.53632 | 1 | 25 | 25 | 75 | 75 |
| 6.5194 | 1 | 25 | 25 | 100 | 100 |
| Total | 4 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 5 obs. of 5 variables:
## $ n : num 1 1 1 1 4
## $ % : num 25 25 25 25 100
## $ val% : num 25 25 25 25 100
## $ %cum : num 25 50 75 100 100
## $ val%cum: num 25 50 75 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.21825 | 1 |
| 1.71217 | 1 |
| 4.53632 | 1 |
| 6.5194 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.21825 3.21825 6.21825 9.21825distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.218,3.22] | 1 | 0.3333333 | 1 |
| (3.22,6.22] | 1 | 0.3333333 | 2 |
| (6.22,9.22] | 1 | 0.3333333 | 3 |
str(Freq_table)## 'data.frame': 3 obs. of 4 variables:
## $ distance: Factor w/ 3 levels "(0.218,3.22]",..: 1 2 3
## $ Freq : int 1 1 1
## $ Rel_Freq: num 0.333 0.333 0.333
## $ Cum_Freq: int 1 2 3df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.218,3.22] | 1 |
| (3.22,6.22] | 1 |
| (6.22,9.22] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_JA)## Warning in min(x): ningún argumento finito para min; retornando Inf## Warning in max(x): ningun argumento finito para max; retornando -Inf## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 4.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 3.140000e+02 NA NA NA NA NA
## max 1.760000e+03 NA NA NA NA NA
## range 1.446000e+03 NA NA NA NA NA
## sum 3.187000e+03 NA NA NA NA NA
## median 5.565000e+02 NA NA NA NA NA
## mean 7.967500e+02 NA NA NA NA NA
## SE.mean 3.380028e+02 NA NA NA NA NA
## CI.mean.0.95 1.075676e+03 NA NA NA NA NA
## var 4.569836e+05 NA NA NA NA NA
## std.dev 6.760056e+02 NA NA NA NA NA
## coef.var 8.484539e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 4.000000e+00 NA 4.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 2.382000e+03 NA 0.2182500 NA
## max NA 2.634000e+03 NA 6.5194000 NA
## range NA 2.520000e+02 NA 6.3011500 NA
## sum NA 1.003200e+04 NA 12.9861400 NA
## median NA 2.508000e+03 NA 3.1242450 NA
## mean NA 2.508000e+03 NA 3.2465350 NA
## SE.mean NA 7.274613e+01 NA 1.4112635 NA
## CI.mean.0.95 NA 2.315107e+02 NA 4.4912704 NA
## var NA 2.116800e+04 NA 7.9666589 NA
## std.dev NA 1.454923e+02 NA 2.8225270 NA
## coef.var NA 5.801127e-02 NA 0.8693968 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 4.000000e+00 4.000000e+00 NA NA NA
## nbr.null 0.000000e+00 0.000000e+00 NA NA NA
## nbr.na 0.000000e+00 0.000000e+00 NA NA NA
## min 1.793840e+01 -7.664790e+01 NA NA NA
## max 1.796470e+01 -7.633300e+01 NA NA NA
## range 2.630000e-02 3.149000e-01 NA NA NA
## sum 7.180110e+01 -3.059144e+02 NA NA NA
## median 1.794900e+01 -7.646675e+01 NA NA NA
## mean 1.795028e+01 -7.647860e+01 NA NA NA
## SE.mean 5.434055e-03 8.031387e-02 NA NA NA
## CI.mean.0.95 1.729359e-02 2.555946e-01 NA NA NA
## var 1.181158e-04 2.580127e-02 NA NA NA
## std.dev 1.086811e-02 1.606277e-01 NA NA NA
## coef.var 6.054565e-04 -2.100297e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 0 2.0000000 NA
## nbr.null NA NA NA 0 1.0000000 NA
## nbr.na NA NA NA 4 2.0000000 NA
## min NA NA NA Inf 0.0000000 NA
## max NA NA NA -Inf 1.0000000 NA
## range NA NA NA -Inf 1.0000000 NA
## sum NA NA NA 0 1.0000000 NA
## median NA NA NA NA 0.5000000 NA
## mean NA NA NA NaN 0.5000000 NA
## SE.mean NA NA NA NA 0.5000000 NA
## CI.mean.0.95 NA NA NA NaN 6.3531024 NA
## var NA NA NA NA 0.5000000 NA
## std.dev NA NA NA NA 0.7071068 NA
## coef.var NA NA NA NA 1.4142136 NA
## source_link prop ypos
## nbr.val NA 4.0000000 4.0000000
## nbr.null NA 0.0000000 0.0000000
## nbr.na NA 0.0000000 0.0000000
## min NA 1.6806380 25.1013773
## max NA 50.2027546 93.4077024
## range NA 48.5221167 68.3063251
## sum NA 100.0000000 272.1529261
## median NA 24.0583037 76.8219232
## mean NA 25.0000000 68.0382315
## SE.mean NA 10.8674596 15.2999203
## CI.mean.0.95 NA 34.5851067 48.6911750
## var NA 472.4067134 936.3502494
## std.dev NA 21.7349192 30.5998407
## coef.var NA 0.8693968 0.4497448boxplot(data, horizontal=TRUE, col='green')
Gráfico para Saint Joseph (Barbados)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_BA <- subset(df, country_name == "Barbados")
knitr::kable(head(df_BA)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 857 | 10/22/08 | NA | NA | Barbados | BB | Saint Joseph | 1765 | Bathsheba | 2.87363 | NA | 13.229 | -59.54 | (13.228999999999999, -59.54) | Landslide | Mudslide | Medium | Downpour | NA | NA | NA | NA | http://www.nationnews.com/story/326456269849259.php |
library(dplyr)
df_BA <- subset(df, state == "Saint Joseph")
knitr::kable(head(df_BA))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 857 | 10/22/08 | NA | NA | Barbados | BB | Saint Joseph | 1765 | Bathsheba | 2.87363 | NA | 13.229 | -59.5400 | (13.228999999999999, -59.54) | Landslide | Mudslide | Medium | Downpour | NA | NA | NA | NA | http://www.nationnews.com/story/326456269849259.php |
| 5754 | 1/7/14 | Morning | NA | Dominica | DM | Saint Joseph | 2184 | Saint Joseph | 2.38605 | Above road | 15.421 | -61.4285 | (15.420999999999999, -61.4285) | Landslide | Landslide | Medium | unknown | NA | 0 | 0 | DaVibes The Caribbean News Portal | http://dominicavibes.dm/colihaut-men-escape-landslide/ |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_BA, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_BA, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_BA, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_BA <- df_BA %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_BA$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_BA, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_BA$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 2.38605 |
| 2.87363 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_BA$distance
names(distance) <- df_BA$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Bathsheba 2.87363 2.87363 54.63507 54.63507
## Saint Joseph 2.38605 5.25968 45.36493 100.00000stem(df_BA$"distance")##
## The decimal point is 1 digit(s) to the left of the |
##
## 23 | 9
## 24 |
## 25 |
## 26 |
## 27 |
## 28 | 7head(df_BA)## # A tibble: 2 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 5754 1/7/14 Morning <NA> Dominica DM Sain~ 2184
## 2 857 10/22/08 <NA> <NA> Barbados BB Sain~ 1765
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_BA))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 5754 | 1/7/14 | Morning | NA | Dominica | DM | Saint Joseph | 2184 | Saint Joseph | 2.38605 | Above road | 15.421 | -61.4285 | (15.420999999999999, -61.4285) | Landslide | Landslide | Medium | unknown | NA | 0 | 0 | DaVibes The Caribbean News Portal | http://dominicavibes.dm/colihaut-men-escape-landslide/ | 45.36493 | 22.68246 |
| 857 | 10/22/08 | NA | NA | Barbados | BB | Saint Joseph | 1765 | Bathsheba | 2.87363 | NA | 13.229 | -59.5400 | (13.228999999999999, -59.54) | Landslide | Mudslide | Medium | Downpour | NA | NA | NA | NA | http://www.nationnews.com/story/326456269849259.php | 54.63507 | 72.68246 |
stem(df_BA$"distance")##
## The decimal point is 1 digit(s) to the left of the |
##
## 23 | 9
## 24 |
## 25 |
## 26 |
## 27 |
## 28 | 7stem(df_BA$"distance", scale = 2)##
## The decimal point is 1 digit(s) to the left of the |
##
## 23 | 9
## 24 |
## 24 |
## 25 |
## 25 |
## 26 |
## 26 |
## 27 |
## 27 |
## 28 |
## 28 | 7Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 2.38605 | 1 | 50 | 50 | 50 | 50 |
| 2.87363 | 1 | 50 | 50 | 100 | 100 |
| Total | 2 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 3 obs. of 5 variables:
## $ n : num 1 1 2
## $ % : num 50 50 100
## $ val% : num 50 50 100
## $ %cum : num 50 100 100
## $ val%cum: num 50 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 2.38605 | 1 |
| 2.87363 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 2.38605 3.38605distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (2.39,3.39] | 1 | 1 | 1 |
str(Freq_table)## 'data.frame': 1 obs. of 4 variables:
## $ distance: Factor w/ 1 level "(2.39,3.39]": 1
## $ Freq : int 1
## $ Rel_Freq: num 1
## $ Cum_Freq: int 1df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (2.39,3.39] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_BA)## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced
## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 2.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 8.570000e+02 NA NA NA NA NA
## max 5.754000e+03 NA NA NA NA NA
## range 4.897000e+03 NA NA NA NA NA
## sum 6.611000e+03 NA NA NA NA NA
## median 3.305500e+03 NA NA NA NA NA
## mean 3.305500e+03 NA NA NA NA NA
## SE.mean 2.448500e+03 NA NA NA NA NA
## CI.mean.0.95 3.111114e+04 NA NA NA NA NA
## var 1.199030e+07 NA NA NA NA NA
## std.dev 3.462702e+03 NA NA NA NA NA
## coef.var 1.047558e+00 NA NA NA NA NA
## state population city distance location_description latitude
## nbr.val NA 2.000000 NA 2.0000000 NA 2.0000000
## nbr.null NA 0.000000 NA 0.0000000 NA 0.0000000
## nbr.na NA 0.000000 NA 0.0000000 NA 0.0000000
## min NA 1765.000000 NA 2.3860500 NA 13.2290000
## max NA 2184.000000 NA 2.8736300 NA 15.4210000
## range NA 419.000000 NA 0.4875800 NA 2.1920000
## sum NA 3949.000000 NA 5.2596800 NA 28.6500000
## median NA 1974.500000 NA 2.6298400 NA 14.3250000
## mean NA 1974.500000 NA 2.6298400 NA 14.3250000
## SE.mean NA 209.500000 NA 0.2437900 NA 1.0960000
## CI.mean.0.95 NA 2661.949892 NA 3.0976457 NA 13.9260004
## var NA 87780.500000 NA 0.1188671 NA 2.4024320
## std.dev NA 296.277741 NA 0.3447711 NA 1.5499781
## coef.var NA 0.150052 NA 0.1310997 NA 0.1082009
## longitude geolocation hazard_type landslide_type landslide_size
## nbr.val 2.000000 NA NA NA NA
## nbr.null 0.000000 NA NA NA NA
## nbr.na 0.000000 NA NA NA NA
## min -61.428500 NA NA NA NA
## max -59.540000 NA NA NA NA
## range 1.888500 NA NA NA NA
## sum -120.968500 NA NA NA NA
## median -60.484250 NA NA NA NA
## mean -60.484250 NA NA NA NA
## SE.mean 0.944250 NA NA NA NA
## CI.mean.0.95 11.997834 NA NA NA NA
## var 1.783216 NA NA NA NA
## std.dev 1.335371 NA NA NA NA
## coef.var -0.022078 NA NA NA NA
## trigger storm_name injuries fatalities source_name source_link
## nbr.val NA NA 1 1 NA NA
## nbr.null NA NA 1 1 NA NA
## nbr.na NA NA 1 1 NA NA
## min NA NA 0 0 NA NA
## max NA NA 0 0 NA NA
## range NA NA 0 0 NA NA
## sum NA NA 0 0 NA NA
## median NA NA 0 0 NA NA
## mean NA NA 0 0 NA NA
## SE.mean NA NA NA NA NA NA
## CI.mean.0.95 NA NA NaN NaN NA NA
## var NA NA NA NA NA NA
## std.dev NA NA NA NA NA NA
## coef.var NA NA NA NA NA NA
## prop ypos
## nbr.val 2.0000000 2.0000000
## nbr.null 0.0000000 0.0000000
## nbr.na 0.0000000 0.0000000
## min 45.3649271 22.6824636
## max 54.6350729 72.6824636
## range 9.2701457 50.0000000
## sum 100.0000000 95.3649271
## median 50.0000000 47.6824636
## mean 50.0000000 47.6824636
## SE.mean 4.6350729 25.0000000
## CI.mean.0.95 58.8941847 317.6551184
## var 42.9678008 1250.0000000
## std.dev 6.5549829 35.3553391
## coef.var 0.1310997 0.7414747boxplot(data, horizontal=TRUE, col='green')
Gráfico para Haiti
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_HT <- subset(df, country_name == "Haiti")
knitr::kable(head(df_HT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 297 | 10/8/07 | NA | NA | Haiti | HT | Artibonite | 7294 | Gros Morne | 8.70343 | NA | 19.6990 | -72.7540 | (19.699000000000002, -72.754000000000005) | Landslide | Landslide | Medium | Downpour | NA | NA | NA | NA | https://www-secure.ifrc.org/dmis/prepare/view_report.asp?ReportID=3285 |
| 303 | 10/12/07 | NA | NA | Haiti | HT | Ouest | 3951 | Cabaret | 0.51272 | NA | 18.7335 | -72.4133 | (18.733499999999999, -72.413300000000007) | Landslide | Complex | Large | Rain | NA | NA | 23 | Euronews.net | http://www.euronews.net/index.php?page=info&article=448067&lng=1 |
| 334 | 10/29/07 | NA | NA | Haiti | HT | Ouest | 1234742 | Port-au-Prince | 2.72168 | NA | 18.5146 | -72.3361 | (18.514600000000002, -72.336100000000002) | Landslide | Complex | Medium | Tropical cyclone | Tropical Storm Noel | NA | NA | ABC news | http://www.abcnews.go.com/International/wireStory?id=3807131 |
| 506 | 4/20/08 | NA | NA | Haiti | HT | Ouest | 1234742 | Port-au-Prince | 1.80063 | NA | 18.5283 | -72.3224 | (18.528300000000002, -72.322400000000002) | Landslide | Mudslide | Medium | Rain | NA | NA | 3 | NA | http://www.news.com.au/heraldsun/story/0,21985,23596379-5005961,00.html |
| 747 | 8/26/08 | NA | NA | Haiti | HT | Sud-Est | 137966 | Jacmel | 4.41574 | NA | 18.2640 | -72.5070 | (18.263999999999999, -72.507000000000005) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Gustav | NA | 25 | NA | http://ap.google.com/article/ALeqM5gVWjsPEiqe1tEu2mhBIRaxxGi8owD92RGO9O1 |
| 748 | 8/26/08 | NA | NA | Haiti | HT | Ouest | 1234742 | Port-au-Prince | 3.50201 | NA | 18.5090 | -72.3450 | (18.509, -72.344999999999999) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Gustav | NA | 3 | NA | http://www.reuters.com/article/worldNews/idUSN2541891320080827?pageNumber=1&virtualBrandChannel=0 |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_HT, aes(fill= state, y=distance, x=country_name)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_HT, aes(fill=state, y=distance, x=country_name)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_HT, aes(x=country_name, y=distance, fill=state)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_HT <- df_HT %>%
arrange(desc(state)) %>%
mutate(prop = distance / sum(df_HT$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_HT, aes(x=country_name, y=prop, fill=state)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_HT$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 4.41574 |
| 0.19079 |
| 0.51272 |
| 2.72168 |
| 1.80063 |
| 3.50201 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_HT$distance
names(distance) <- df_HT$state
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por estados"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Artibonite 17.29836000 17.29836000 20.57571552 20.57571552
## Ouest 12.13199000 29.43035000 14.43052260 35.00623813
## Artibonite 8.70343000 38.13378000 10.35238599 45.35862412
## Centre 7.86436000 45.99814000 9.35434539 54.71296951
## Ouest 7.67473000 53.67287000 9.12878800 63.84175751
## Nord 5.23459000 58.90746000 6.22633791 70.06809542
## Artibonite 4.72379000 63.63125000 5.61876150 75.68685693
## Sud-Est 4.41574000 68.04699000 5.25234820 80.93920513
## Ouest 3.50201000 71.54900000 4.16550248 85.10470761
## Ouest 2.72168000 74.27068000 3.23733079 88.34203840
## Ouest 2.63565000 76.90633000 3.13500150 91.47703990
## Ouest 1.80063000 78.70696000 2.14177822 93.61881812
## Nord 1.58489000 80.29185000 1.88516401 95.50398214
## Ouest 1.33931000 81.63116000 1.59305631 97.09703845
## Ouest 1.31659000 82.94775000 1.56603177 98.66307021
## Ouest 0.51272000 83.46047000 0.60986018 99.27293039
## Nord 0.27505000 83.73552000 0.32716110 99.60009149
## Sud-Est 0.19079000 83.92631000 0.22693716 99.82702866
## Ouest 0.11071000 84.03702000 0.13168517 99.95871383
## Nord 0.03471000 84.07173000 0.04128617 100.00000000stem(df_HT$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 0000111223344
## 0 | 55889
## 1 | 2
## 1 | 7head(df_HT)## # A tibble: 6 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 747 8/26/08 <NA> <NA> Haiti HT Sud-Est 137966
## 2 3563 6/2/11 <NA> <NA> Haiti HT Sud-Est 137966
## 3 303 10/12/07 <NA> <NA> Haiti HT Ouest 3951
## 4 334 10/29/07 <NA> <NA> Haiti HT Ouest 1234742
## 5 506 4/20/08 <NA> <NA> Haiti HT Ouest 1234742
## 6 748 8/26/08 <NA> <NA> Haiti HT Ouest 1234742
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_HT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 747 | 8/26/08 | NA | NA | Haiti | HT | Sud-Est | 137966 | Jacmel | 4.41574 | NA | 18.2640 | -72.5070 | (18.263999999999999, -72.507000000000005) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Gustav | NA | 25 | NA | http://ap.google.com/article/ALeqM5gVWjsPEiqe1tEu2mhBIRaxxGi8owD92RGO9O1 | 5.2523482 | 2.626174 |
| 3563 | 6/2/11 | NA | NA | Haiti | HT | Sud-Est | 137966 | Jacmel | 0.19079 | NA | 18.2348 | -72.5364 | (18.2348, -72.5364) | Landslide | Landslide | Small | Downpour | NA | NA | 0 | NA | http://www.haitilibre.com/en/news-3095-haiti-climate-the-situation-by-department.html | 0.2269372 | 5.365817 |
| 303 | 10/12/07 | NA | NA | Haiti | HT | Ouest | 3951 | Cabaret | 0.51272 | NA | 18.7335 | -72.4133 | (18.733499999999999, -72.413300000000007) | Landslide | Complex | Large | Rain | NA | NA | 23 | Euronews.net | http://www.euronews.net/index.php?page=info&article=448067&lng=1 | 0.6098602 | 5.784216 |
| 334 | 10/29/07 | NA | NA | Haiti | HT | Ouest | 1234742 | Port-au-Prince | 2.72168 | NA | 18.5146 | -72.3361 | (18.514600000000002, -72.336100000000002) | Landslide | Complex | Medium | Tropical cyclone | Tropical Storm Noel | NA | NA | ABC news | http://www.abcnews.go.com/International/wireStory?id=3807131 | 3.2373308 | 7.707811 |
| 506 | 4/20/08 | NA | NA | Haiti | HT | Ouest | 1234742 | Port-au-Prince | 1.80063 | NA | 18.5283 | -72.3224 | (18.528300000000002, -72.322400000000002) | Landslide | Mudslide | Medium | Rain | NA | NA | 3 | NA | http://www.news.com.au/heraldsun/story/0,21985,23596379-5005961,00.html | 2.1417782 | 10.397365 |
| 748 | 8/26/08 | NA | NA | Haiti | HT | Ouest | 1234742 | Port-au-Prince | 3.50201 | NA | 18.5090 | -72.3450 | (18.509, -72.344999999999999) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Gustav | NA | 3 | NA | http://www.reuters.com/article/worldNews/idUSN2541891320080827?pageNumber=1&virtualBrandChannel=0 | 4.1655025 | 13.551006 |
stem(df_HT$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 0000111223344
## 0 | 55889
## 1 | 2
## 1 | 7stem(df_HT$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 012353368
## 2 | 675
## 4 | 472
## 6 | 79
## 8 | 7
## 10 |
## 12 | 1
## 14 |
## 16 | 3Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.03471 | 1 | 5 | 5 | 5 | 5 |
| 0.11071 | 1 | 5 | 5 | 10 | 10 |
| 0.19079 | 1 | 5 | 5 | 15 | 15 |
| 0.27505 | 1 | 5 | 5 | 20 | 20 |
| 0.51272 | 1 | 5 | 5 | 25 | 25 |
| 1.31659 | 1 | 5 | 5 | 30 | 30 |
| 1.33931 | 1 | 5 | 5 | 35 | 35 |
| 1.58489 | 1 | 5 | 5 | 40 | 40 |
| 1.80063 | 1 | 5 | 5 | 45 | 45 |
| 2.63565 | 1 | 5 | 5 | 50 | 50 |
| 2.72168 | 1 | 5 | 5 | 55 | 55 |
| 3.50201 | 1 | 5 | 5 | 60 | 60 |
| 4.41574 | 1 | 5 | 5 | 65 | 65 |
| 4.72379 | 1 | 5 | 5 | 70 | 70 |
| 5.23459 | 1 | 5 | 5 | 75 | 75 |
| 7.67473 | 1 | 5 | 5 | 80 | 80 |
| 7.86436 | 1 | 5 | 5 | 85 | 85 |
| 8.70343 | 1 | 5 | 5 | 90 | 90 |
| 12.13199 | 1 | 5 | 5 | 95 | 95 |
| 17.29836 | 1 | 5 | 5 | 100 | 100 |
| Total | 20 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 21 obs. of 5 variables:
## $ n : num 1 1 1 1 1 1 1 1 1 1 ...
## $ % : num 5 5 5 5 5 5 5 5 5 5 ...
## $ val% : num 5 5 5 5 5 5 5 5 5 5 ...
## $ %cum : num 5 10 15 20 25 30 35 40 45 50 ...
## $ val%cum: num 5 10 15 20 25 30 35 40 45 50 ...x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.03471 | 1 |
| 0.11071 | 1 |
| 0.19079 | 1 |
| 0.27505 | 1 |
| 0.51272 | 1 |
| 1.31659 | 1 |
| 1.33931 | 1 |
| 1.58489 | 1 |
| 1.80063 | 1 |
| 2.63565 | 1 |
| 2.72168 | 1 |
| 3.50201 | 1 |
| 4.41574 | 1 |
| 4.72379 | 1 |
| 5.23459 | 1 |
| 7.67473 | 1 |
| 7.86436 | 1 |
| 8.70343 | 1 |
| 12.13199 | 1 |
| 17.29836 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.03471 4.03471 8.03471 12.03471 16.03471 20.03471distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.0347,4.03] | 11 | 0.5789474 | 11 |
| (4.03,8.03] | 5 | 0.2631579 | 16 |
| (8.03,12] | 1 | 0.0526316 | 17 |
| (12,16] | 1 | 0.0526316 | 18 |
| (16,20] | 1 | 0.0526316 | 19 |
str(Freq_table)## 'data.frame': 5 obs. of 4 variables:
## $ distance: Factor w/ 5 levels "(0.0347,4.03]",..: 1 2 3 4 5
## $ Freq : int 11 5 1 1 1
## $ Rel_Freq: num 0.5789 0.2632 0.0526 0.0526 0.0526
## $ Cum_Freq: int 11 16 17 18 19df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.0347,4.03] | 11 |
| (4.03,8.03] | 5 |
| (8.03,12] | 1 |
| (12,16] | 1 |
| (16,20] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_HT)## id date time continent_code country_name country_code
## nbr.val 2.000000e+01 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 2.970000e+02 NA NA NA NA NA
## max 6.722000e+03 NA NA NA NA NA
## range 6.425000e+03 NA NA NA NA NA
## sum 4.809400e+04 NA NA NA NA NA
## median 2.017000e+03 NA NA NA NA NA
## mean 2.404700e+03 NA NA NA NA NA
## SE.mean 4.506116e+02 NA NA NA NA NA
## CI.mean.0.95 9.431408e+02 NA NA NA NA NA
## var 4.061016e+06 NA NA NA NA NA
## std.dev 2.015196e+03 NA NA NA NA NA
## coef.var 8.380240e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 2.000000e+01 NA 20.000000 NA
## nbr.null NA 0.000000e+00 NA 0.000000 NA
## nbr.na NA 0.000000e+00 NA 0.000000 NA
## min NA 3.951000e+03 NA 0.034710 NA
## max NA 1.234742e+06 NA 17.298360 NA
## range NA 1.230791e+06 NA 17.263650 NA
## sum NA 6.625032e+06 NA 84.071730 NA
## median NA 1.363905e+05 NA 2.678665 NA
## mean NA 3.312516e+05 NA 4.203587 NA
## SE.mean NA 9.247531e+04 NA 1.019568 NA
## CI.mean.0.95 NA 1.935530e+05 NA 2.133979 NA
## var NA 1.710337e+11 NA 20.790360 NA
## std.dev NA 4.135622e+05 NA 4.559645 NA
## coef.var NA 1.248483e+00 NA 1.084703 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 20.00000000 2.000000e+01 NA NA NA
## nbr.null 0.00000000 0.000000e+00 NA NA NA
## nbr.na 0.00000000 0.000000e+00 NA NA NA
## min 18.23480000 -7.275400e+01 NA NA NA
## max 19.76980000 -7.197470e+01 NA NA NA
## range 1.53500000 7.793000e-01 NA NA NA
## sum 378.03620000 -1.448005e+03 NA NA NA
## median 18.53150000 -7.240515e+01 NA NA NA
## mean 18.90181000 -7.240024e+01 NA NA NA
## SE.mean 0.12729585 4.201268e-02 NA NA NA
## CI.mean.0.95 0.26643329 8.793354e-02 NA NA NA
## var 0.32408469 3.530130e-02 NA NA NA
## std.dev 0.56928437 1.878864e-01 NA NA NA
## coef.var 0.03011798 -2.595107e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities
## nbr.val NA NA NA 2.0000000 18.000000
## nbr.null NA NA NA 1.0000000 1.000000
## nbr.na NA NA NA 18.0000000 2.000000
## min NA NA NA 0.0000000 0.000000
## max NA NA NA 1.0000000 26.000000
## range NA NA NA 1.0000000 26.000000
## sum NA NA NA 1.0000000 128.000000
## median NA NA NA 0.5000000 3.000000
## mean NA NA NA 0.5000000 7.111111
## SE.mean NA NA NA 0.5000000 2.035452
## CI.mean.0.95 NA NA NA 6.3531024 4.294428
## var NA NA NA 0.5000000 74.575163
## std.dev NA NA NA 0.7071068 8.635691
## coef.var NA NA NA 1.4142136 1.214394
## source_name source_link prop ypos
## nbr.val NA NA 20.00000000 20.000000
## nbr.null NA NA 0.00000000 0.000000
## nbr.na NA NA 0.00000000 0.000000
## min NA NA 0.04128617 2.626174
## max NA NA 20.57571552 89.712142
## range NA NA 20.53442935 87.085968
## sum NA NA 100.00000000 741.305853
## median NA NA 3.18616615 43.143272
## mean NA NA 5.00000000 37.065293
## SE.mean NA NA 1.21273530 5.707890
## CI.mean.0.95 NA NA 2.53828416 11.946751
## var NA NA 29.41453837 651.600189
## std.dev NA NA 5.42351716 25.526461
## coef.var NA NA 1.08470343 0.688689boxplot(data, horizontal=TRUE, col='green')
Gráfico para Artibonite (Haiti)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_HT <- subset(df, country_name == "Haiti")
knitr::kable(head(df_HT)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 297 | 10/8/07 | NA | NA | Haiti | HT | Artibonite | 7294 | Gros Morne | 8.70343 | NA | 19.6990 | -72.7540 | (19.699000000000002, -72.754000000000005) | Landslide | Landslide | Medium | Downpour | NA | NA | NA | NA | https://www-secure.ifrc.org/dmis/prepare/view_report.asp?ReportID=3285 |
| 303 | 10/12/07 | NA | NA | Haiti | HT | Ouest | 3951 | Cabaret | 0.51272 | NA | 18.7335 | -72.4133 | (18.733499999999999, -72.413300000000007) | Landslide | Complex | Large | Rain | NA | NA | 23 | Euronews.net | http://www.euronews.net/index.php?page=info&article=448067&lng=1 |
| 334 | 10/29/07 | NA | NA | Haiti | HT | Ouest | 1234742 | Port-au-Prince | 2.72168 | NA | 18.5146 | -72.3361 | (18.514600000000002, -72.336100000000002) | Landslide | Complex | Medium | Tropical cyclone | Tropical Storm Noel | NA | NA | ABC news | http://www.abcnews.go.com/International/wireStory?id=3807131 |
| 506 | 4/20/08 | NA | NA | Haiti | HT | Ouest | 1234742 | Port-au-Prince | 1.80063 | NA | 18.5283 | -72.3224 | (18.528300000000002, -72.322400000000002) | Landslide | Mudslide | Medium | Rain | NA | NA | 3 | NA | http://www.news.com.au/heraldsun/story/0,21985,23596379-5005961,00.html |
| 747 | 8/26/08 | NA | NA | Haiti | HT | Sud-Est | 137966 | Jacmel | 4.41574 | NA | 18.2640 | -72.5070 | (18.263999999999999, -72.507000000000005) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Gustav | NA | 25 | NA | http://ap.google.com/article/ALeqM5gVWjsPEiqe1tEu2mhBIRaxxGi8owD92RGO9O1 |
| 748 | 8/26/08 | NA | NA | Haiti | HT | Ouest | 1234742 | Port-au-Prince | 3.50201 | NA | 18.5090 | -72.3450 | (18.509, -72.344999999999999) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Gustav | NA | 3 | NA | http://www.reuters.com/article/worldNews/idUSN2541891320080827?pageNumber=1&virtualBrandChannel=0 |
library(dplyr)
df_HT <- subset(df, state == "Artibonite")
knitr::kable(head(df_HT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 297 | 10/8/07 | NA | NA | Haiti | HT | Artibonite | 7294 | Gros Morne | 8.70343 | NA | 19.6990 | -72.7540 | (19.699000000000002, -72.754000000000005) | Landslide | Landslide | Medium | Downpour | NA | NA | NA | NA | https://www-secure.ifrc.org/dmis/prepare/view_report.asp?ReportID=3285 |
| 771 | 9/3/08 | NA | NA | Haiti | HT | Artibonite | 84961 | Gonaïves | 4.72379 | NA | 19.4300 | -72.6480 | (19.43, -72.647999999999996) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Hannah | NA | 26 | NA | http://www.miamiherald.com/news/americas/cuba/story/671682.html |
| 1140 | 9/7/09 | Early morning | NA | Haiti | HT | Artibonite | 66226 | Saint-Marc | 17.29836 | NA | 18.9523 | -72.7053 | (18.952300000000001, -72.705299999999994) | Landslide | Mudslide | Medium | Downpour | NA | NA | 1 | NA | http://www.google.com/hostednews/ap/article/ALeqM5hdjzxxFRHymhlrd1BpUjDSV3HK6AD9AIQ5OO0 |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_HT, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_HT, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_HT, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_HT <- df_HT %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_HT$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_HT, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_HT$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 17.29836 |
| 8.70343 |
| 4.72379 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_HT$distance
names(distance) <- df_HT$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Saint-Marc 17.29836 17.29836 56.29954 56.29954
## Gros Morne 8.70343 26.00179 28.32633 84.62587
## Gonaïves 4.72379 30.72558 15.37413 100.00000stem(df_HT$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 |
## 0 | 59
## 1 |
## 1 | 7head(df_HT)## # A tibble: 3 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 1140 9/7/09 Early~ <NA> Haiti HT Arti~ 66226
## 2 297 10/8/07 <NA> <NA> Haiti HT Arti~ 7294
## 3 771 9/3/08 <NA> <NA> Haiti HT Arti~ 84961
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_HT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1140 | 9/7/09 | Early morning | NA | Haiti | HT | Artibonite | 66226 | Saint-Marc | 17.29836 | NA | 18.9523 | -72.7053 | (18.952300000000001, -72.705299999999994) | Landslide | Mudslide | Medium | Downpour | NA | NA | 1 | NA | http://www.google.com/hostednews/ap/article/ALeqM5hdjzxxFRHymhlrd1BpUjDSV3HK6AD9AIQ5OO0 | 56.29954 | 28.14977 |
| 297 | 10/8/07 | NA | NA | Haiti | HT | Artibonite | 7294 | Gros Morne | 8.70343 | NA | 19.6990 | -72.7540 | (19.699000000000002, -72.754000000000005) | Landslide | Landslide | Medium | Downpour | NA | NA | NA | NA | https://www-secure.ifrc.org/dmis/prepare/view_report.asp?ReportID=3285 | 28.32633 | 70.46271 |
| 771 | 9/3/08 | NA | NA | Haiti | HT | Artibonite | 84961 | Gonaïves | 4.72379 | NA | 19.4300 | -72.6480 | (19.43, -72.647999999999996) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Hannah | NA | 26 | NA | http://www.miamiherald.com/news/americas/cuba/story/671682.html | 15.37413 | 92.31294 |
stem(df_HT$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 |
## 0 | 59
## 1 |
## 1 | 7stem(df_HT$"distance", scale = 2)##
## The decimal point is at the |
##
## 4 | 7
## 6 |
## 8 | 7
## 10 |
## 12 |
## 14 |
## 16 | 3Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 4.72379 | 1 | 33.3 | 33.3 | 33.3 | 33.3 |
| 8.70343 | 1 | 33.3 | 33.3 | 66.7 | 66.7 |
| 17.29836 | 1 | 33.3 | 33.3 | 100.0 | 100.0 |
| Total | 3 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 4 obs. of 5 variables:
## $ n : num 1 1 1 3
## $ % : num 33.3 33.3 33.3 100
## $ val% : num 33.3 33.3 33.3 100
## $ %cum : num 33.3 66.7 100 100
## $ val%cum: num 33.3 66.7 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 4.72379 | 1 |
| 8.70343 | 1 |
| 17.29836 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 4.72379 9.72379 14.72379 19.72379distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (4.72,9.72] | 1 | 0.5 | 1 |
| (9.72,14.7] | 0 | 0.0 | 1 |
| (14.7,19.7] | 1 | 0.5 | 2 |
str(Freq_table)## 'data.frame': 3 obs. of 4 variables:
## $ distance: Factor w/ 3 levels "(4.72,9.72]",..: 1 2 3
## $ Freq : int 1 0 1
## $ Rel_Freq: num 0.5 0 0.5
## $ Cum_Freq: int 1 1 2df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (4.72,9.72] | 1 |
| (9.72,14.7] | 0 |
| (14.7,19.7] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_HT)## Warning in min(x): ningún argumento finito para min; retornando Inf## Warning in max(x): ningun argumento finito para max; retornando -Inf## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 3.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 2.970000e+02 NA NA NA NA NA
## max 1.140000e+03 NA NA NA NA NA
## range 8.430000e+02 NA NA NA NA NA
## sum 2.208000e+03 NA NA NA NA NA
## median 7.710000e+02 NA NA NA NA NA
## mean 7.360000e+02 NA NA NA NA NA
## SE.mean 2.439816e+02 NA NA NA NA NA
## CI.mean.0.95 1.049768e+03 NA NA NA NA NA
## var 1.785810e+05 NA NA NA NA NA
## std.dev 4.225885e+02 NA NA NA NA NA
## coef.var 5.741691e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 3.000000e+00 NA 3.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 7.294000e+03 NA 4.7237900 NA
## max NA 8.496100e+04 NA 17.2983600 NA
## range NA 7.766700e+04 NA 12.5745700 NA
## sum NA 1.584810e+05 NA 30.7255800 NA
## median NA 6.622600e+04 NA 8.7034300 NA
## mean NA 5.282700e+04 NA 10.2418600 NA
## SE.mean NA 2.340008e+04 NA 3.7105717 NA
## CI.mean.0.95 NA 1.006824e+05 NA 15.9653016 NA
## var NA 1.642691e+09 NA 41.3050278 NA
## std.dev NA 4.053012e+04 NA 6.4268988 NA
## coef.var NA 7.672236e-01 NA 0.6275129 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 3.00000000 3.000000e+00 NA NA NA
## nbr.null 0.00000000 0.000000e+00 NA NA NA
## nbr.na 0.00000000 0.000000e+00 NA NA NA
## min 18.95230000 -7.275400e+01 NA NA NA
## max 19.69900000 -7.264800e+01 NA NA NA
## range 0.74670000 1.060000e-01 NA NA NA
## sum 58.08130000 -2.181073e+02 NA NA NA
## median 19.43000000 -7.270530e+01 NA NA NA
## mean 19.36043333 -7.270243e+01 NA NA NA
## SE.mean 0.21834213 3.063312e-02 NA NA NA
## CI.mean.0.95 0.93945038 1.318037e-01 NA NA NA
## var 0.14301986 2.815163e-03 NA NA NA
## std.dev 0.37817967 5.305811e-02 NA NA NA
## coef.var 0.01953364 -7.297983e-04 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 0 2.000000 NA
## nbr.null NA NA NA 0 0.000000 NA
## nbr.na NA NA NA 3 1.000000 NA
## min NA NA NA Inf 1.000000 NA
## max NA NA NA -Inf 26.000000 NA
## range NA NA NA -Inf 25.000000 NA
## sum NA NA NA 0 27.000000 NA
## median NA NA NA NA 13.500000 NA
## mean NA NA NA NaN 13.500000 NA
## SE.mean NA NA NA NA 12.500000 NA
## CI.mean.0.95 NA NA NA NaN 158.827559 NA
## var NA NA NA NA 312.500000 NA
## std.dev NA NA NA NA 17.677670 NA
## coef.var NA NA NA NA 1.309457 NA
## source_link prop ypos
## nbr.val NA 3.0000000 3.0000000
## nbr.null NA 0.0000000 0.0000000
## nbr.na NA 0.0000000 0.0000000
## min NA 15.3741280 28.1497697
## max NA 56.2995393 92.3129360
## range NA 40.9254113 64.1631663
## sum NA 100.0000000 190.9254113
## median NA 28.3263327 70.4627057
## mean NA 33.3333333 63.6418038
## SE.mean NA 12.0764905 18.8336711
## CI.mean.0.95 NA 51.9609446 81.0347465
## var NA 437.5248651 1064.1215052
## std.dev NA 20.9170950 32.6208753
## coef.var NA 0.6275129 0.5125699boxplot(data, horizontal=TRUE, col='green')
Gráfico para Nord (Haiti)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_HT <- subset(df, country_name == "Haiti")
knitr::kable(head(df_HT)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 297 | 10/8/07 | NA | NA | Haiti | HT | Artibonite | 7294 | Gros Morne | 8.70343 | NA | 19.6990 | -72.7540 | (19.699000000000002, -72.754000000000005) | Landslide | Landslide | Medium | Downpour | NA | NA | NA | NA | https://www-secure.ifrc.org/dmis/prepare/view_report.asp?ReportID=3285 |
| 303 | 10/12/07 | NA | NA | Haiti | HT | Ouest | 3951 | Cabaret | 0.51272 | NA | 18.7335 | -72.4133 | (18.733499999999999, -72.413300000000007) | Landslide | Complex | Large | Rain | NA | NA | 23 | Euronews.net | http://www.euronews.net/index.php?page=info&article=448067&lng=1 |
| 334 | 10/29/07 | NA | NA | Haiti | HT | Ouest | 1234742 | Port-au-Prince | 2.72168 | NA | 18.5146 | -72.3361 | (18.514600000000002, -72.336100000000002) | Landslide | Complex | Medium | Tropical cyclone | Tropical Storm Noel | NA | NA | ABC news | http://www.abcnews.go.com/International/wireStory?id=3807131 |
| 506 | 4/20/08 | NA | NA | Haiti | HT | Ouest | 1234742 | Port-au-Prince | 1.80063 | NA | 18.5283 | -72.3224 | (18.528300000000002, -72.322400000000002) | Landslide | Mudslide | Medium | Rain | NA | NA | 3 | NA | http://www.news.com.au/heraldsun/story/0,21985,23596379-5005961,00.html |
| 747 | 8/26/08 | NA | NA | Haiti | HT | Sud-Est | 137966 | Jacmel | 4.41574 | NA | 18.2640 | -72.5070 | (18.263999999999999, -72.507000000000005) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Gustav | NA | 25 | NA | http://ap.google.com/article/ALeqM5gVWjsPEiqe1tEu2mhBIRaxxGi8owD92RGO9O1 |
| 748 | 8/26/08 | NA | NA | Haiti | HT | Ouest | 1234742 | Port-au-Prince | 3.50201 | NA | 18.5090 | -72.3450 | (18.509, -72.344999999999999) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Gustav | NA | 3 | NA | http://www.reuters.com/article/worldNews/idUSN2541891320080827?pageNumber=1&virtualBrandChannel=0 |
library(dplyr)
df_HT <- subset(df, state == "Nord")
knitr::kable(head(df_HT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1506 | 2/15/10 | 12:00 | NA | Haiti | HT | Nord | 134815 | Cap-Haïtien | 0.27505 | Urban area | 19.7560 | -72.2060 | (19.756, -72.206000000000003) | Landslide | Mudslide | Medium | Downpour | NA | NA | 4 | Times Live | http://www.timeslive.co.za/world/article311411.ece |
| 4312 | 4/8/12 | NA | NA | Haiti | HT | Nord | 32645 | Limbé | 0.03471 | NA | 19.7041 | -72.4006 | (19.7041, -72.400599999999997) | Landslide | Landslide | Medium | Downpour | NA | NA | 2 | NA | http://www.usatoday.com/news/world/story/2012-04-10/Haiti-floods/54160810/1 |
| 6713 | 11/1/14 | NA | NA | Haiti | HT | Nord | 134815 | Okap | 5.23459 | Urban area | 19.7450 | -72.2152 | (19.745000000000001, -72.215199999999996) | Landslide | Landslide | Medium | Downpour | NA | 0 | 1 | reliefweb | http://reliefweb.int/report/haiti/undp-government-haiti-provide-immediate-support-flood-affected-victims |
| 6722 | 5/27/14 | NA | NA | Haiti | HT | Nord | 134815 | Okap | 1.58489 | Unknown | 19.7698 | -72.2085 | (19.7698, -72.208500000000001) | Landslide | Landslide | Small | Continuous rain | NA | 1 | 3 | Business Recorder | http://www.brecorder.com/world/north-america/15393-three-children-die-in-haiti-landslide.html |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_HT, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_HT, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_HT, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_HT <- df_HT %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_HT$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_HT, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_HT$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 5.23459 |
| 1.58489 |
| 0.03471 |
| 0.27505 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_HT$distance
names(distance) <- df_HT$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Okap 5.2345900 5.2345900 73.4242360 73.4242360
## Okap 1.5848900 6.8194800 22.2308409 95.6550768
## Cap-Haïtien 0.2750500 7.0945300 3.8580550 99.5131318
## Limbé 0.0347100 7.1292400 0.4868682 100.0000000stem(df_HT$"distance")##
## The decimal point is at the |
##
## 0 | 036
## 2 |
## 4 | 2head(df_HT)## # A tibble: 4 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 6713 11/1/14 <NA> <NA> Haiti HT Nord 134815
## 2 6722 5/27/14 <NA> <NA> Haiti HT Nord 134815
## 3 4312 4/8/12 <NA> <NA> Haiti HT Nord 32645
## 4 1506 2/15/10 12:00 <NA> Haiti HT Nord 134815
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_HT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 6713 | 11/1/14 | NA | NA | Haiti | HT | Nord | 134815 | Okap | 5.23459 | Urban area | 19.7450 | -72.2152 | (19.745000000000001, -72.215199999999996) | Landslide | Landslide | Medium | Downpour | NA | 0 | 1 | reliefweb | http://reliefweb.int/report/haiti/undp-government-haiti-provide-immediate-support-flood-affected-victims | 73.4242360 | 36.71212 |
| 6722 | 5/27/14 | NA | NA | Haiti | HT | Nord | 134815 | Okap | 1.58489 | Unknown | 19.7698 | -72.2085 | (19.7698, -72.208500000000001) | Landslide | Landslide | Small | Continuous rain | NA | 1 | 3 | Business Recorder | http://www.brecorder.com/world/north-america/15393-three-children-die-in-haiti-landslide.html | 22.2308409 | 84.53966 |
| 4312 | 4/8/12 | NA | NA | Haiti | HT | Nord | 32645 | Limbé | 0.03471 | NA | 19.7041 | -72.4006 | (19.7041, -72.400599999999997) | Landslide | Landslide | Medium | Downpour | NA | NA | 2 | NA | http://www.usatoday.com/news/world/story/2012-04-10/Haiti-floods/54160810/1 | 0.4868682 | 95.89851 |
| 1506 | 2/15/10 | 12:00 | NA | Haiti | HT | Nord | 134815 | Cap-Haïtien | 0.27505 | Urban area | 19.7560 | -72.2060 | (19.756, -72.206000000000003) | Landslide | Mudslide | Medium | Downpour | NA | NA | 4 | Times Live | http://www.timeslive.co.za/world/article311411.ece | 3.8580550 | 98.07097 |
stem(df_HT$"distance")##
## The decimal point is at the |
##
## 0 | 036
## 2 |
## 4 | 2stem(df_HT$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 03
## 1 | 6
## 2 |
## 3 |
## 4 |
## 5 | 2Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.03471 | 1 | 25 | 25 | 25 | 25 |
| 0.27505 | 1 | 25 | 25 | 50 | 50 |
| 1.58489 | 1 | 25 | 25 | 75 | 75 |
| 5.23459 | 1 | 25 | 25 | 100 | 100 |
| Total | 4 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 5 obs. of 5 variables:
## $ n : num 1 1 1 1 4
## $ % : num 25 25 25 25 100
## $ val% : num 25 25 25 25 100
## $ %cum : num 25 50 75 100 100
## $ val%cum: num 25 50 75 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.03471 | 1 |
| 0.27505 | 1 |
| 1.58489 | 1 |
| 5.23459 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.03471 2.03471 4.03471 6.03471distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.0347,2.03] | 2 | 0.6666667 | 2 |
| (2.03,4.03] | 0 | 0.0000000 | 2 |
| (4.03,6.03] | 1 | 0.3333333 | 3 |
str(Freq_table)## 'data.frame': 3 obs. of 4 variables:
## $ distance: Factor w/ 3 levels "(0.0347,2.03]",..: 1 2 3
## $ Freq : int 2 0 1
## $ Rel_Freq: num 0.667 0 0.333
## $ Cum_Freq: int 2 2 3df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.0347,2.03] | 2 |
| (2.03,4.03] | 0 |
| (4.03,6.03] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_HT)## id date time continent_code country_name country_code
## nbr.val 4.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 1.506000e+03 NA NA NA NA NA
## max 6.722000e+03 NA NA NA NA NA
## range 5.216000e+03 NA NA NA NA NA
## sum 1.925300e+04 NA NA NA NA NA
## median 5.512500e+03 NA NA NA NA NA
## mean 4.813250e+03 NA NA NA NA NA
## SE.mean 1.239675e+03 NA NA NA NA NA
## CI.mean.0.95 3.945199e+03 NA NA NA NA NA
## var 6.147177e+06 NA NA NA NA NA
## std.dev 2.479350e+03 NA NA NA NA NA
## coef.var 5.151094e-01 NA NA NA NA NA
## state population city distance location_description latitude
## nbr.val NA 4.000000e+00 NA 4.000000 NA 4.000000e+00
## nbr.null NA 0.000000e+00 NA 0.000000 NA 0.000000e+00
## nbr.na NA 0.000000e+00 NA 0.000000 NA 0.000000e+00
## min NA 3.264500e+04 NA 0.034710 NA 1.970410e+01
## max NA 1.348150e+05 NA 5.234590 NA 1.976980e+01
## range NA 1.021700e+05 NA 5.199880 NA 6.570000e-02
## sum NA 4.370900e+05 NA 7.129240 NA 7.897490e+01
## median NA 1.348150e+05 NA 0.929970 NA 1.975050e+01
## mean NA 1.092725e+05 NA 1.782310 NA 1.974373e+01
## SE.mean NA 2.554250e+04 NA 1.200109 NA 1.414905e-02
## CI.mean.0.95 NA 8.128763e+04 NA 3.819284 NA 4.502859e-02
## var NA 2.609677e+09 NA 5.761050 NA 8.007825e-04
## std.dev NA 5.108500e+04 NA 2.400219 NA 2.829810e-02
## coef.var NA 4.675010e-01 NA 1.346690 NA 1.433271e-03
## longitude geolocation hazard_type landslide_type
## nbr.val 4.000000e+00 NA NA NA
## nbr.null 0.000000e+00 NA NA NA
## nbr.na 0.000000e+00 NA NA NA
## min -7.240060e+01 NA NA NA
## max -7.220600e+01 NA NA NA
## range 1.946000e-01 NA NA NA
## sum -2.890303e+02 NA NA NA
## median -7.221185e+01 NA NA NA
## mean -7.225758e+01 NA NA NA
## SE.mean 4.771454e-02 NA NA NA
## CI.mean.0.95 1.518490e-01 NA NA NA
## var 9.106709e-03 NA NA NA
## std.dev 9.542908e-02 NA NA NA
## coef.var -1.320679e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 2.0000000 4.0000000 NA
## nbr.null NA NA NA 1.0000000 0.0000000 NA
## nbr.na NA NA NA 2.0000000 0.0000000 NA
## min NA NA NA 0.0000000 1.0000000 NA
## max NA NA NA 1.0000000 4.0000000 NA
## range NA NA NA 1.0000000 3.0000000 NA
## sum NA NA NA 1.0000000 10.0000000 NA
## median NA NA NA 0.5000000 2.5000000 NA
## mean NA NA NA 0.5000000 2.5000000 NA
## SE.mean NA NA NA 0.5000000 0.6454972 NA
## CI.mean.0.95 NA NA NA 6.3531024 2.0542603 NA
## var NA NA NA 0.5000000 1.6666667 NA
## std.dev NA NA NA 0.7071068 1.2909944 NA
## coef.var NA NA NA 1.4142136 0.5163978 NA
## source_link prop ypos
## nbr.val NA 4.0000000 4.000000
## nbr.null NA 0.0000000 0.000000
## nbr.na NA 0.0000000 0.000000
## min NA 0.4868682 36.712118
## max NA 73.4242360 98.070973
## range NA 72.9373678 61.358855
## sum NA 100.0000000 315.221258
## median NA 13.0444479 90.219084
## mean NA 25.0000000 78.805314
## SE.mean NA 16.8336230 14.341266
## CI.mean.0.95 NA 53.5721012 45.640308
## var NA 1133.4834473 822.687604
## std.dev NA 33.6672459 28.682531
## coef.var NA 1.3466898 0.363967boxplot(data, horizontal=TRUE, col='green')
Gráfico para Ouest (Haiti)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_HT <- subset(df, country_name == "Haiti")
knitr::kable(head(df_HT)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 297 | 10/8/07 | NA | NA | Haiti | HT | Artibonite | 7294 | Gros Morne | 8.70343 | NA | 19.6990 | -72.7540 | (19.699000000000002, -72.754000000000005) | Landslide | Landslide | Medium | Downpour | NA | NA | NA | NA | https://www-secure.ifrc.org/dmis/prepare/view_report.asp?ReportID=3285 |
| 303 | 10/12/07 | NA | NA | Haiti | HT | Ouest | 3951 | Cabaret | 0.51272 | NA | 18.7335 | -72.4133 | (18.733499999999999, -72.413300000000007) | Landslide | Complex | Large | Rain | NA | NA | 23 | Euronews.net | http://www.euronews.net/index.php?page=info&article=448067&lng=1 |
| 334 | 10/29/07 | NA | NA | Haiti | HT | Ouest | 1234742 | Port-au-Prince | 2.72168 | NA | 18.5146 | -72.3361 | (18.514600000000002, -72.336100000000002) | Landslide | Complex | Medium | Tropical cyclone | Tropical Storm Noel | NA | NA | ABC news | http://www.abcnews.go.com/International/wireStory?id=3807131 |
| 506 | 4/20/08 | NA | NA | Haiti | HT | Ouest | 1234742 | Port-au-Prince | 1.80063 | NA | 18.5283 | -72.3224 | (18.528300000000002, -72.322400000000002) | Landslide | Mudslide | Medium | Rain | NA | NA | 3 | NA | http://www.news.com.au/heraldsun/story/0,21985,23596379-5005961,00.html |
| 747 | 8/26/08 | NA | NA | Haiti | HT | Sud-Est | 137966 | Jacmel | 4.41574 | NA | 18.2640 | -72.5070 | (18.263999999999999, -72.507000000000005) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Gustav | NA | 25 | NA | http://ap.google.com/article/ALeqM5gVWjsPEiqe1tEu2mhBIRaxxGi8owD92RGO9O1 |
| 748 | 8/26/08 | NA | NA | Haiti | HT | Ouest | 1234742 | Port-au-Prince | 3.50201 | NA | 18.5090 | -72.3450 | (18.509, -72.344999999999999) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Gustav | NA | 3 | NA | http://www.reuters.com/article/worldNews/idUSN2541891320080827?pageNumber=1&virtualBrandChannel=0 |
library(dplyr)
df_HT <- subset(df, state == "Ouest")
knitr::kable(head(df_HT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 303 | 10/12/07 | NA | NA | Haiti | HT | Ouest | 3951 | Cabaret | 0.51272 | NA | 18.7335 | -72.4133 | (18.733499999999999, -72.413300000000007) | Landslide | Complex | Large | Rain | NA | NA | 23 | Euronews.net | http://www.euronews.net/index.php?page=info&article=448067&lng=1 |
| 334 | 10/29/07 | NA | NA | Haiti | HT | Ouest | 1234742 | Port-au-Prince | 2.72168 | NA | 18.5146 | -72.3361 | (18.514600000000002, -72.336100000000002) | Landslide | Complex | Medium | Tropical cyclone | Tropical Storm Noel | NA | NA | ABC news | http://www.abcnews.go.com/International/wireStory?id=3807131 |
| 506 | 4/20/08 | NA | NA | Haiti | HT | Ouest | 1234742 | Port-au-Prince | 1.80063 | NA | 18.5283 | -72.3224 | (18.528300000000002, -72.322400000000002) | Landslide | Mudslide | Medium | Rain | NA | NA | 3 | NA | http://www.news.com.au/heraldsun/story/0,21985,23596379-5005961,00.html |
| 748 | 8/26/08 | NA | NA | Haiti | HT | Ouest | 1234742 | Port-au-Prince | 3.50201 | NA | 18.5090 | -72.3450 | (18.509, -72.344999999999999) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Gustav | NA | 3 | NA | http://www.reuters.com/article/worldNews/idUSN2541891320080827?pageNumber=1&virtualBrandChannel=0 |
| 1266 | 10/20/09 | NA | NA | Haiti | HT | Ouest | 442156 | Carrefour | 1.31659 | NA | 18.5347 | -72.4097 | (18.534700000000001, -72.409700000000001) | Landslide | Landslide | Small | Downpour | NA | NA | 4 | NA | http://www.etaiwannews.com/etn/news_content.php?id=1088959&lang=eng_news |
| 2528 | 10/1/10 | NA | NA | Haiti | HT | Ouest | 442156 | Carrefour | 12.13199 | NA | 18.4468 | -72.4577 | (18.4468, -72.457700000000003) | Landslide | Mudslide | Medium | Downpour | NA | NA | 3 | NA | http://www.presstv.ir/detail/144854.html |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_HT, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_HT, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_HT, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_HT <- df_HT %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_HT$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_HT, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_HT$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 2.72168 |
| 1.80063 |
| 3.50201 |
| 0.11071 |
| 1.33931 |
| 7.67473 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_HT$distance
names(distance) <- df_HT$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Carrefour 12.1319900 12.1319900 35.9508766 35.9508766
## Léogâne 7.6747300 19.8067200 22.7426227 58.6934993
## Port-au-Prince 3.5020100 23.3087300 10.3775497 69.0710490
## Port-au-Prince 2.7216800 26.0304100 8.0651881 77.1362371
## Carrefour 2.6356500 28.6660600 7.8102544 84.9464915
## Port-au-Prince 1.8006300 30.4666900 5.3358292 90.2823207
## Pétionville 1.3393100 31.8060000 3.9687939 94.2511146
## Carrefour 1.3165900 33.1225900 3.9014675 98.1525821
## Cabaret 0.5127200 33.6353100 1.5193495 99.6719317
## Pétionville 0.1107100 33.7460200 0.3280683 100.0000000stem(df_HT$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 01112334
## 0 | 8
## 1 | 2head(df_HT)## # A tibble: 6 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 334 10/29/07 <NA> <NA> Haiti HT Ouest 1234742
## 2 506 4/20/08 <NA> <NA> Haiti HT Ouest 1234742
## 3 748 8/26/08 <NA> <NA> Haiti HT Ouest 1234742
## 4 3576 6/7/11 <NA> <NA> Haiti HT Ouest 283052
## 5 4289 3/30/12 Late night <NA> Haiti HT Ouest 283052
## 6 2604 10/17/10 <NA> <NA> Haiti HT Ouest 134190
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_HT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 334 | 10/29/07 | NA | NA | Haiti | HT | Ouest | 1234742 | Port-au-Prince | 2.72168 | NA | 18.5146 | -72.3361 | (18.514600000000002, -72.336100000000002) | Landslide | Complex | Medium | Tropical cyclone | Tropical Storm Noel | NA | NA | ABC news | http://www.abcnews.go.com/International/wireStory?id=3807131 | 8.0651881 | 4.032594 |
| 506 | 4/20/08 | NA | NA | Haiti | HT | Ouest | 1234742 | Port-au-Prince | 1.80063 | NA | 18.5283 | -72.3224 | (18.528300000000002, -72.322400000000002) | Landslide | Mudslide | Medium | Rain | NA | NA | 3 | NA | http://www.news.com.au/heraldsun/story/0,21985,23596379-5005961,00.html | 5.3358292 | 10.733103 |
| 748 | 8/26/08 | NA | NA | Haiti | HT | Ouest | 1234742 | Port-au-Prince | 3.50201 | NA | 18.5090 | -72.3450 | (18.509, -72.344999999999999) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Gustav | NA | 3 | NA | http://www.reuters.com/article/worldNews/idUSN2541891320080827?pageNumber=1&virtualBrandChannel=0 | 10.3775497 | 18.589792 |
| 3576 | 6/7/11 | NA | NA | Haiti | HT | Ouest | 283052 | Pétionville | 0.11071 | NA | 18.5135 | -72.2853 | (18.513500000000001, -72.285300000000007) | Landslide | Landslide | Large | Downpour | NA | NA | 13 | NA | http://www.bbc.co.uk/news/world-latin-america-13689711 | 0.3280683 | 23.942601 |
| 4289 | 3/30/12 | Late night | NA | Haiti | HT | Ouest | 283052 | Pétionville | 1.33931 | NA | 18.5044 | -72.2947 | (18.5044, -72.294700000000006) | Landslide | Landslide | Medium | Downpour | NA | NA | 6 | NA | http://www.haitilibre.com/en/news-5290-haiti-weather-first-drama-of-the-rain.html | 3.9687939 | 26.091032 |
| 2604 | 10/17/10 | NA | NA | Haiti | HT | Ouest | 134190 | Léogâne | 7.67473 | NA | 18.4674 | -72.5738 | (18.467400000000001, -72.573800000000006) | Landslide | Complex | Medium | Downpour | NA | NA | 8 | NA | http://edition.cnn.com/2010/WORLD/americas/10/19/haiti.flooding/ | 22.7426227 | 39.446741 |
stem(df_HT$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 01112334
## 0 | 8
## 1 | 2stem(df_HT$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 15338
## 2 | 675
## 4 |
## 6 | 7
## 8 |
## 10 |
## 12 | 1Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.11071 | 1 | 10 | 10 | 10 | 10 |
| 0.51272 | 1 | 10 | 10 | 20 | 20 |
| 1.31659 | 1 | 10 | 10 | 30 | 30 |
| 1.33931 | 1 | 10 | 10 | 40 | 40 |
| 1.80063 | 1 | 10 | 10 | 50 | 50 |
| 2.63565 | 1 | 10 | 10 | 60 | 60 |
| 2.72168 | 1 | 10 | 10 | 70 | 70 |
| 3.50201 | 1 | 10 | 10 | 80 | 80 |
| 7.67473 | 1 | 10 | 10 | 90 | 90 |
| 12.13199 | 1 | 10 | 10 | 100 | 100 |
| Total | 10 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 11 obs. of 5 variables:
## $ n : num 1 1 1 1 1 1 1 1 1 1 ...
## $ % : num 10 10 10 10 10 10 10 10 10 10 ...
## $ val% : num 10 10 10 10 10 10 10 10 10 10 ...
## $ %cum : num 10 20 30 40 50 60 70 80 90 100 ...
## $ val%cum: num 10 20 30 40 50 60 70 80 90 100 ...x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.11071 | 1 |
| 0.51272 | 1 |
| 1.31659 | 1 |
| 1.33931 | 1 |
| 1.80063 | 1 |
| 2.63565 | 1 |
| 2.72168 | 1 |
| 3.50201 | 1 |
| 7.67473 | 1 |
| 12.13199 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.11071 3.11071 6.11071 9.11071 12.11071 15.11071distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.111,3.11] | 6 | 0.6666667 | 6 |
| (3.11,6.11] | 1 | 0.1111111 | 7 |
| (6.11,9.11] | 1 | 0.1111111 | 8 |
| (9.11,12.1] | 0 | 0.0000000 | 8 |
| (12.1,15.1] | 1 | 0.1111111 | 9 |
str(Freq_table)## 'data.frame': 5 obs. of 4 variables:
## $ distance: Factor w/ 5 levels "(0.111,3.11]",..: 1 2 3 4 5
## $ Freq : int 6 1 1 0 1
## $ Rel_Freq: num 0.667 0.111 0.111 0 0.111
## $ Cum_Freq: int 6 7 8 8 9df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.111,3.11] | 6 |
| (3.11,6.11] | 1 |
| (6.11,9.11] | 1 |
| (9.11,12.1] | 0 |
| (12.1,15.1] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_HT)## Warning in min(x): ningún argumento finito para min; retornando Inf## Warning in max(x): ningun argumento finito para max; retornando -Inf## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 1.000000e+01 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 3.030000e+02 NA NA NA NA NA
## max 4.289000e+03 NA NA NA NA NA
## range 3.986000e+03 NA NA NA NA NA
## sum 1.875900e+04 NA NA NA NA NA
## median 1.897000e+03 NA NA NA NA NA
## mean 1.875900e+03 NA NA NA NA NA
## SE.mean 4.542708e+02 NA NA NA NA NA
## CI.mean.0.95 1.027632e+03 NA NA NA NA NA
## var 2.063619e+06 NA NA NA NA NA
## std.dev 1.436530e+03 NA NA NA NA NA
## coef.var 7.657819e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 1.000000e+01 NA 10.000000 NA
## nbr.null NA 0.000000e+00 NA 0.000000 NA
## nbr.na NA 0.000000e+00 NA 0.000000 NA
## min NA 3.951000e+03 NA 0.110710 NA
## max NA 1.234742e+06 NA 12.131990 NA
## range NA 1.230791e+06 NA 12.021280 NA
## sum NA 5.734939e+06 NA 33.746020 NA
## median NA 4.421560e+05 NA 2.218140 NA
## mean NA 5.734939e+05 NA 3.374602 NA
## SE.mean NA 1.509075e+05 NA 1.182606 NA
## CI.mean.0.95 NA 3.413764e+05 NA 2.675240 NA
## var NA 2.277307e+11 NA 13.985568 NA
## std.dev NA 4.772114e+05 NA 3.739728 NA
## coef.var NA 8.321123e-01 NA 1.108198 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 1.000000e+01 1.000000e+01 NA NA NA
## nbr.null 0.000000e+00 0.000000e+00 NA NA NA
## nbr.na 0.000000e+00 0.000000e+00 NA NA NA
## min 1.844680e+01 -7.257380e+01 NA NA NA
## max 1.873350e+01 -7.228530e+01 NA NA NA
## range 2.867000e-01 2.885000e-01 NA NA NA
## sum 1.852724e+02 -7.238491e+02 NA NA NA
## median 1.851405e+01 -7.237735e+01 NA NA NA
## mean 1.852724e+01 -7.238491e+01 NA NA NA
## SE.mean 2.447308e-02 2.769416e-02 NA NA NA
## CI.mean.0.95 5.536196e-02 6.264854e-02 NA NA NA
## var 5.989318e-03 7.669665e-03 NA NA NA
## std.dev 7.739069e-02 8.757663e-02 NA NA NA
## coef.var 4.177130e-03 -1.209874e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 0 9.0000000 NA
## nbr.null NA NA NA 0 0.0000000 NA
## nbr.na NA NA NA 10 1.0000000 NA
## min NA NA NA Inf 2.0000000 NA
## max NA NA NA -Inf 23.0000000 NA
## range NA NA NA -Inf 21.0000000 NA
## sum NA NA NA 0 65.0000000 NA
## median NA NA NA NA 4.0000000 NA
## mean NA NA NA NaN 7.2222222 NA
## SE.mean NA NA NA NA 2.2838672 NA
## CI.mean.0.95 NA NA NA NaN 5.2666072 NA
## var NA NA NA NA 46.9444444 NA
## std.dev NA NA NA NA 6.8516016 NA
## coef.var NA NA NA NA 0.9486833 NA
## source_link prop ypos
## nbr.val NA 10.0000000 10.0000000
## nbr.null NA 0.0000000 0.0000000
## nbr.na NA 0.0000000 0.0000000
## min NA 0.3280683 4.0325941
## max NA 35.9508766 99.2403252
## range NA 35.6228083 95.2077312
## sum NA 100.0000000 442.1154554
## median NA 6.5730418 32.7688865
## mean NA 10.0000000 44.2115455
## SE.mean NA 3.5044308 10.8539511
## CI.mean.0.95 NA 7.9275733 24.5533433
## var NA 122.8103537 1178.0825517
## std.dev NA 11.0819833 34.3232072
## coef.var NA 1.1081983 0.7763404boxplot(data, horizontal=TRUE, col='green')
Gráfico para Trinidad and Tobago
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_TT <- subset(df, country_name == "Trinidad and Tobago")
knitr::kable(head(df_TT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 224 | 9/1/07 | NA | NA | Trinidad and Tobago | TT | Tobago | 17000 | Scarborough | 9.11607 | NA | 11.2415 | -60.6742 | (11.2415, -60.674199999999999) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Felix | NA | NA | Trinadad Express | http://www.trinidadexpress.com/index.pl/article_news?id=161197580 |
| 357 | 11/17/07 | NA | NA | Trinidad and Tobago | TT | Eastern Tobago | 0 | Roxborough | 7.33295 | NA | 11.2965 | -60.6312 | (11.2965, -60.6312) | Landslide | Landslide | Medium | Rain | NA | NA | NA | Trinadad Express | http://www.trinidadexpress.com/index.pl/article_news?id=161237574 |
| 390 | 12/11/07 | NA | NA | Trinidad and Tobago | TT | Sangre Grande | 15968 | Sangre Grande | 29.28864 | NA | 10.8410 | -61.0550 | (10.840999999999999, -61.055) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Olga | NA | 3 | Trinidad and Tobago’s Newsday | http://www.newsday.co.tt/news/0,69681.html |
| 391 | 12/11/07 | NA | NA | Trinidad and Tobago | TT | Eastern Tobago | 0 | Roxborough | 8.62938 | NA | 11.3000 | -60.6440 | (11.3, -60.643999999999998) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Olga | NA | NA | Trinidad and Tobago’s Newsday | http://www.newsday.co.tt/news/0,69681.html |
| 392 | 12/11/07 | NA | NA | Trinidad and Tobago | TT | Eastern Tobago | 0 | Roxborough | 2.66802 | NA | 11.2670 | -60.5660 | (11.266999999999999, -60.566000000000003) | Landslide | Landslide | Small | Tropical cyclone | Tropical Storm Olga | NA | NA | Trinidad and Tobago’s Newsday | http://www.newsday.co.tt/news/0,69681.html |
| 780 | 9/7/08 | NA | NA | Trinidad and Tobago | TT | Diego Martin | 8140 | Petit Valley | 10.61854 | NA | 10.7603 | -61.4578 | (10.760300000000001, -61.457799999999999) | Landslide | Landslide | Medium | Downpour | NA | NA | NA | NA | http://www.newsday.co.tt/news/0,85847.html |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_TT, aes(fill= state, y=distance, x=country_name)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_TT, aes(fill=state, y=distance, x=country_name)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_TT, aes(x=country_name, y=distance, fill=state)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_TT <- df_TT %>%
arrange(desc(state)) %>%
mutate(prop = distance / sum(df_TT$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_TT, aes(x=country_name, y=prop, fill=state)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4## Warning in RColorBrewer::brewer.pal(n, pal): n too large, allowed maximum for palette Greens is 9
## Returning the palette you asked for with that many colors
Grafico de series temporales
library(forecast)
data<- ts(df_TT$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 2.64003 |
| 16.73194 |
| 13.75900 |
| 2.63186 |
| 9.11607 |
| 4.68038 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_TT$distance
names(distance) <- df_TT$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por estados"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Sangre Grande 33.51924000 33.51924000 6.44876727 6.44876727
## Sangre Grande 33.10893000 66.62817000 6.36982772 12.81859499
## Sangre Grande 33.10893000 99.73710000 6.36982772 19.18842271
## Sangre Grande 30.29383000 130.03093000 5.82823057 25.01665328
## Sangre Grande 29.28864000 159.31957000 5.63484205 30.65149533
## Sangre Grande 26.68822000 186.00779000 5.13454719 35.78604252
## Point Fortin 22.47289000 208.48068000 4.32355977 40.10960229
## Paradise 16.73194000 225.21262000 3.21905828 43.32866056
## Paradise 13.75900000 238.97162000 2.64709429 45.97575486
## Arima 13.34116000 252.31278000 2.56670605 48.54246090
## Petit Valley 11.75674000 264.06952000 2.26187945 50.80434035
## Petit Valley 10.61854000 274.68806000 2.04290113 52.84724148
## Marabella 9.42494000 284.11300000 1.81326440 54.66050588
## Scarborough 9.11607000 293.22907000 1.75384089 56.41434677
## Roxborough 8.62938000 301.85845000 1.66020659 58.07455336
## Tabaquite 8.55164000 310.41009000 1.64525019 59.71980356
## Roxborough 8.44112000 318.85121000 1.62398725 61.34379081
## Princes Town 8.41931000 327.27052000 1.61979122 62.96358203
## Roxborough 8.24676000 335.51728000 1.58659432 64.55017636
## Roxborough 7.87263000 343.38991000 1.51461545 66.06479180
## Roxborough 7.47816000 350.86807000 1.43872336 67.50351516
## Mucurapo 7.43310000 358.30117000 1.43005426 68.93356942
## Laventille 7.37181000 365.67298000 1.41826268 70.35183210
## Roxborough 7.33295000 373.00593000 1.41078640 71.76261850
## Mucurapo 7.24469000 380.25062000 1.39380606 73.15642455
## Petit Valley 6.95807000 387.20869000 1.33866323 74.49508778
## Tabaquite 6.91642000 394.12511000 1.33065019 75.82573797
## Scarborough 6.81393000 400.93904000 1.31093213 77.13667010
## Petit Valley 6.58396000 407.52300000 1.26668820 78.40335830
## Petit Valley 6.39375000 413.91675000 1.23009369 79.63345199
## Scarborough 6.35974000 420.27649000 1.22355051 80.85700250
## Petit Valley 5.91101000 426.18750000 1.13721933 81.99422184
## Petit Valley 5.73985000 431.92735000 1.10428986 83.09851169
## Roxborough 5.62092000 437.54827000 1.08140891 84.17992061
## Scarborough 4.68038000 442.22865000 0.90045840 85.08037901
## Petit Valley 4.66234000 446.89099000 0.89698769 85.97736670
## Petit Valley 4.64073000 451.53172000 0.89283014 86.87019684
## Petit Valley 4.50278000 456.03450000 0.86628994 87.73648678
## Petit Valley 4.33904000 460.37354000 0.83478799 88.57127477
## Peñal, 4.21321000 464.58675000 0.81057956 89.38185433
## Petit Valley 4.00979000 468.59654000 0.77144358 90.15329791
## Scarborough 3.88123000 472.47777000 0.74670992 90.90000783
## Siparia 3.75200000 476.22977000 0.72184736 91.62185518
## Scarborough 3.48176000 479.71153000 0.66985588 92.29171106
## Roxborough 3.36240000 483.07393000 0.64689220 92.93860327
## Petit Valley 3.33629000 486.41022000 0.64186890 93.58047217
## Scarborough 3.22335000 489.63357000 0.62014037 94.20061254
## Petit Valley 3.08955000 492.72312000 0.59439859 94.79501113
## Roxborough 2.66802000 495.39114000 0.51330042 95.30831155
## Paradise 2.64003000 498.03117000 0.50791543 95.81622697
## Tunapuna 2.63186000 500.66303000 0.50634360 96.32257057
## Peñal, 2.57071000 503.23374000 0.49457895 96.81714952
## Port-of-Spain 2.54016000 505.77390000 0.48870143 97.30585096
## Petit Valley 2.24772000 508.02162000 0.43243890 97.73828985
## Port-of-Spain 2.15046000 510.17208000 0.41372704 98.15201690
## Sangre Grande 2.00931000 512.18139000 0.38657119 98.53858809
## Petit Valley 1.84331000 514.02470000 0.35463445 98.89322254
## Petit Valley 1.83626000 515.86096000 0.35327810 99.24650064
## Port-of-Spain 1.07831000 516.93927000 0.20745608 99.45395672
## San Fernando 0.92162000 517.86089000 0.17731049 99.63126721
## Roxborough 0.91163000 518.77252000 0.17538851 99.80665573
## Tabaquite 0.61975000 519.39227000 0.11923372 99.92588944
## Laventille 0.38521000 519.77748000 0.07411056 100.00000000stem(df_TT$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 0111122222333333333344444
## 0 | 55556666677777777788889999
## 1 | 1234
## 1 | 7
## 2 | 2
## 2 | 79
## 3 | 0334head(df_TT)## # A tibble: 6 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 2667 10/31/10 Morning <NA> Trinidad an~ TT Tuna~ 15067
## 2 4108 12/25/11 <NA> <NA> Trinidad an~ TT Tuna~ 15067
## 3 4374 5/30/12 <NA> <NA> Trinidad an~ TT Tuna~ 15067
## 4 4919 6/14/13 Morning <NA> Trinidad an~ TT Tuna~ 17758
## 5 224 9/1/07 <NA> <NA> Trinidad an~ TT Toba~ 17000
## 6 2669 10/31/10 <NA> <NA> Trinidad an~ TT Toba~ 17000
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_TT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2667 | 10/31/10 | Morning | NA | Trinidad and Tobago | TT | Tunapuna/Piarco | 15067 | Paradise | 2.64003 | NA | 10.6660 | -61.3832 | (10.666, -61.383200000000002) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Tomas | NA | 0 | NA | http://stormcarib.com/reports/current/report.php?id=1288616789_49546 | 0.5079154 | 0.2539577 |
| 4108 | 12/25/11 | NA | NA | Trinidad and Tobago | TT | Tunapuna/Piarco | 15067 | Paradise | 16.73194 | NA | 10.7901 | -61.2984 | (10.790100000000001, -61.298400000000001) | Landslide | Landslide | Large | Downpour | NA | NA | 0 | NA | http://www.guardian.co.tt/news/thursday-december-29-2011/blanchisseuse-residents-cut-road-collapses | 3.2190583 | 2.1174446 |
| 4374 | 5/30/12 | NA | NA | Trinidad and Tobago | TT | Tunapuna/Piarco | 15067 | Paradise | 13.75900 | NA | 10.7692 | -61.4078 | (10.7692, -61.407800000000002) | Landslide | Landslide | Large | Downpour | NA | NA | NA | NA | http://www.guardian.co.tt/news/2012-05-31/landslides-choke-north-coast-road | 2.6470943 | 5.0505208 |
| 4919 | 6/14/13 | Morning | NA | Trinidad and Tobago | TT | Tunapuna/Piarco | 17758 | Tunapuna | 2.63186 | NA | 10.6501 | -61.4004 | (10.6501, -61.400399999999998) | Landslide | Landslide | Small | Downpour | NA | NA | 0 | www.newsday.co.tt | http://www.newsday.co.tt/news/0,179174.html | 0.5063436 | 6.6272398 |
| 224 | 9/1/07 | NA | NA | Trinidad and Tobago | TT | Tobago | 17000 | Scarborough | 9.11607 | NA | 11.2415 | -60.6742 | (11.2415, -60.674199999999999) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Felix | NA | NA | Trinadad Express | http://www.trinidadexpress.com/index.pl/article_news?id=161197580 | 1.7538409 | 7.7573320 |
| 2669 | 10/31/10 | NA | NA | Trinidad and Tobago | TT | Tobago | 17000 | Scarborough | 4.68038 | NA | 11.2246 | -60.7428 | (11.224600000000001, -60.742800000000003) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.trinidadexpress.com/news/Kamla_tours_affected_Tobago_areas_for_2nd_day-106494398.html | 0.9004584 | 9.0844817 |
stem(df_TT$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 0111122222333333333344444
## 0 | 55556666677777777788889999
## 1 | 1234
## 1 | 7
## 2 | 2
## 2 | 79
## 3 | 0334stem(df_TT$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 4699188
## 2 | 022566671234589
## 4 | 0235677679
## 6 | 446890234459
## 8 | 2446614
## 10 | 68
## 12 | 38
## 14 |
## 16 | 7
## 18 |
## 20 |
## 22 | 5
## 24 |
## 26 | 7
## 28 | 3
## 30 | 3
## 32 | 115Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 33.10893 | 2 | 3.2 | 3.2 | 3.2 | 3.2 |
| 0.38521 | 1 | 1.6 | 1.6 | 4.8 | 4.8 |
| 0.61975 | 1 | 1.6 | 1.6 | 6.3 | 6.3 |
| 0.91163 | 1 | 1.6 | 1.6 | 7.9 | 7.9 |
| 0.92162 | 1 | 1.6 | 1.6 | 9.5 | 9.5 |
| 1.07831 | 1 | 1.6 | 1.6 | 11.1 | 11.1 |
| 1.83626 | 1 | 1.6 | 1.6 | 12.7 | 12.7 |
| 1.84331 | 1 | 1.6 | 1.6 | 14.3 | 14.3 |
| 2.00931 | 1 | 1.6 | 1.6 | 15.9 | 15.9 |
| 2.15046 | 1 | 1.6 | 1.6 | 17.5 | 17.5 |
| 2.24772 | 1 | 1.6 | 1.6 | 19.0 | 19.0 |
| 2.54016 | 1 | 1.6 | 1.6 | 20.6 | 20.6 |
| 2.57071 | 1 | 1.6 | 1.6 | 22.2 | 22.2 |
| 2.63186 | 1 | 1.6 | 1.6 | 23.8 | 23.8 |
| 2.64003 | 1 | 1.6 | 1.6 | 25.4 | 25.4 |
| 2.66802 | 1 | 1.6 | 1.6 | 27.0 | 27.0 |
| 3.08955 | 1 | 1.6 | 1.6 | 28.6 | 28.6 |
| 3.22335 | 1 | 1.6 | 1.6 | 30.2 | 30.2 |
| 3.33629 | 1 | 1.6 | 1.6 | 31.7 | 31.7 |
| 3.3624 | 1 | 1.6 | 1.6 | 33.3 | 33.3 |
| 3.48176 | 1 | 1.6 | 1.6 | 34.9 | 34.9 |
| 3.752 | 1 | 1.6 | 1.6 | 36.5 | 36.5 |
| 3.88123 | 1 | 1.6 | 1.6 | 38.1 | 38.1 |
| 4.00979 | 1 | 1.6 | 1.6 | 39.7 | 39.7 |
| 4.21321 | 1 | 1.6 | 1.6 | 41.3 | 41.3 |
| 4.33904 | 1 | 1.6 | 1.6 | 42.9 | 42.9 |
| 4.50278 | 1 | 1.6 | 1.6 | 44.4 | 44.4 |
| 4.64073 | 1 | 1.6 | 1.6 | 46.0 | 46.0 |
| 4.66234 | 1 | 1.6 | 1.6 | 47.6 | 47.6 |
| 4.68038 | 1 | 1.6 | 1.6 | 49.2 | 49.2 |
| 5.62092 | 1 | 1.6 | 1.6 | 50.8 | 50.8 |
| 5.73985 | 1 | 1.6 | 1.6 | 52.4 | 52.4 |
| 5.91101 | 1 | 1.6 | 1.6 | 54.0 | 54.0 |
| 6.35974 | 1 | 1.6 | 1.6 | 55.6 | 55.6 |
| 6.39375 | 1 | 1.6 | 1.6 | 57.1 | 57.1 |
| 6.58396 | 1 | 1.6 | 1.6 | 58.7 | 58.7 |
| 6.81393 | 1 | 1.6 | 1.6 | 60.3 | 60.3 |
| 6.91642 | 1 | 1.6 | 1.6 | 61.9 | 61.9 |
| 6.95807 | 1 | 1.6 | 1.6 | 63.5 | 63.5 |
| 7.24469 | 1 | 1.6 | 1.6 | 65.1 | 65.1 |
| 7.33295 | 1 | 1.6 | 1.6 | 66.7 | 66.7 |
| 7.37181 | 1 | 1.6 | 1.6 | 68.3 | 68.3 |
| 7.4331 | 1 | 1.6 | 1.6 | 69.8 | 69.8 |
| 7.47816 | 1 | 1.6 | 1.6 | 71.4 | 71.4 |
| 7.87263 | 1 | 1.6 | 1.6 | 73.0 | 73.0 |
| 8.24676 | 1 | 1.6 | 1.6 | 74.6 | 74.6 |
| 8.41931 | 1 | 1.6 | 1.6 | 76.2 | 76.2 |
| 8.44112 | 1 | 1.6 | 1.6 | 77.8 | 77.8 |
| 8.55164 | 1 | 1.6 | 1.6 | 79.4 | 79.4 |
| 8.62938 | 1 | 1.6 | 1.6 | 81.0 | 81.0 |
| 9.11607 | 1 | 1.6 | 1.6 | 82.5 | 82.5 |
| 9.42494 | 1 | 1.6 | 1.6 | 84.1 | 84.1 |
| 10.61854 | 1 | 1.6 | 1.6 | 85.7 | 85.7 |
| 11.75674 | 1 | 1.6 | 1.6 | 87.3 | 87.3 |
| 13.34116 | 1 | 1.6 | 1.6 | 88.9 | 88.9 |
| 13.759 | 1 | 1.6 | 1.6 | 90.5 | 90.5 |
| 16.73194 | 1 | 1.6 | 1.6 | 92.1 | 92.1 |
| 22.47289 | 1 | 1.6 | 1.6 | 93.7 | 93.7 |
| 26.68822 | 1 | 1.6 | 1.6 | 95.2 | 95.2 |
| 29.28864 | 1 | 1.6 | 1.6 | 96.8 | 96.8 |
| 30.29383 | 1 | 1.6 | 1.6 | 98.4 | 98.4 |
| 33.51924 | 1 | 1.6 | 1.6 | 100.0 | 100.0 |
| Total | 63 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 63 obs. of 5 variables:
## $ n : num 2 1 1 1 1 1 1 1 1 1 ...
## $ % : num 3.2 1.6 1.6 1.6 1.6 1.6 1.6 1.6 1.6 1.6 ...
## $ val% : num 3.2 1.6 1.6 1.6 1.6 1.6 1.6 1.6 1.6 1.6 ...
## $ %cum : num 3.2 4.8 6.3 7.9 9.5 11.1 12.7 14.3 15.9 17.5 ...
## $ val%cum: num 3.2 4.8 6.3 7.9 9.5 11.1 12.7 14.3 15.9 17.5 ...x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 33.10893 | 2 |
| 0.38521 | 1 |
| 0.61975 | 1 |
| 0.91163 | 1 |
| 0.92162 | 1 |
| 1.07831 | 1 |
| 1.83626 | 1 |
| 1.84331 | 1 |
| 2.00931 | 1 |
| 2.15046 | 1 |
| 2.24772 | 1 |
| 2.54016 | 1 |
| 2.57071 | 1 |
| 2.63186 | 1 |
| 2.64003 | 1 |
| 2.66802 | 1 |
| 3.08955 | 1 |
| 3.22335 | 1 |
| 3.33629 | 1 |
| 3.3624 | 1 |
| 3.48176 | 1 |
| 3.752 | 1 |
| 3.88123 | 1 |
| 4.00979 | 1 |
| 4.21321 | 1 |
| 4.33904 | 1 |
| 4.50278 | 1 |
| 4.64073 | 1 |
| 4.66234 | 1 |
| 4.68038 | 1 |
| 5.62092 | 1 |
| 5.73985 | 1 |
| 5.91101 | 1 |
| 6.35974 | 1 |
| 6.39375 | 1 |
| 6.58396 | 1 |
| 6.81393 | 1 |
| 6.91642 | 1 |
| 6.95807 | 1 |
| 7.24469 | 1 |
| 7.33295 | 1 |
| 7.37181 | 1 |
| 7.4331 | 1 |
| 7.47816 | 1 |
| 7.87263 | 1 |
| 8.24676 | 1 |
| 8.41931 | 1 |
| 8.44112 | 1 |
| 8.55164 | 1 |
| 8.62938 | 1 |
| 9.11607 | 1 |
| 9.42494 | 1 |
| 10.61854 | 1 |
| 11.75674 | 1 |
| 13.34116 | 1 |
| 13.759 | 1 |
| 16.73194 | 1 |
| 22.47289 | 1 |
| 26.68822 | 1 |
| 29.28864 | 1 |
| 30.29383 | 1 |
| 33.51924 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.38521 5.38521 10.38521 15.38521 20.38521 25.38521 30.38521 35.38521distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.385,5.39] | 28 | 0.4516129 | 28 |
| (5.39,10.4] | 22 | 0.3548387 | 50 |
| (10.4,15.4] | 4 | 0.0645161 | 54 |
| (15.4,20.4] | 1 | 0.0161290 | 55 |
| (20.4,25.4] | 1 | 0.0161290 | 56 |
| (25.4,30.4] | 3 | 0.0483871 | 59 |
| (30.4,35.4] | 3 | 0.0483871 | 62 |
str(Freq_table)## 'data.frame': 7 obs. of 4 variables:
## $ distance: Factor w/ 7 levels "(0.385,5.39]",..: 1 2 3 4 5 6 7
## $ Freq : int 28 22 4 1 1 3 3
## $ Rel_Freq: num 0.4516 0.3548 0.0645 0.0161 0.0161 ...
## $ Cum_Freq: int 28 50 54 55 56 59 62df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.385,5.39] | 28 |
| (5.39,10.4] | 22 |
| (10.4,15.4] | 4 |
| (15.4,20.4] | 1 |
| (20.4,25.4] | 1 |
| (25.4,30.4] | 3 |
| (30.4,35.4] | 3 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_TT)## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 6.300000e+01 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 2.240000e+02 NA NA NA NA NA
## max 6.301000e+03 NA NA NA NA NA
## range 6.077000e+03 NA NA NA NA NA
## sum 1.939570e+05 NA NA NA NA NA
## median 2.759000e+03 NA NA NA NA NA
## mean 3.078683e+03 NA NA NA NA NA
## SE.mean 1.907885e+02 NA NA NA NA NA
## CI.mean.0.95 3.813809e+02 NA NA NA NA NA
## var 2.293217e+06 NA NA NA NA NA
## std.dev 1.514337e+03 NA NA NA NA NA
## coef.var 4.918783e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 6.300000e+01 NA 63.000000 NA
## nbr.null NA 1.000000e+01 NA 0.000000 NA
## nbr.na NA 0.000000e+00 NA 0.000000 NA
## min NA 0.000000e+00 NA 0.385210 NA
## max NA 1.572580e+05 NA 33.519240 NA
## range NA 1.572580e+05 NA 33.134030 NA
## sum NA 1.091655e+06 NA 519.777480 NA
## median NA 8.140000e+03 NA 5.911010 NA
## mean NA 1.732786e+04 NA 8.250436 NA
## SE.mean NA 3.563658e+03 NA 1.064793 NA
## CI.mean.0.95 NA 7.123651e+03 NA 2.128491 NA
## var NA 8.000786e+08 NA 71.428394 NA
## std.dev NA 2.828566e+04 NA 8.451532 NA
## coef.var NA 1.632381e+00 NA 1.024374 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 63.00000000 6.300000e+01 NA NA NA
## nbr.null 0.00000000 0.000000e+00 NA NA NA
## nbr.na 0.00000000 0.000000e+00 NA NA NA
## min 10.08760000 -6.186420e+01 NA NA NA
## max 11.31760000 -6.054170e+01 NA NA NA
## range 1.23000000 1.322500e+00 NA NA NA
## sum 679.61780000 -3.856206e+03 NA NA NA
## median 10.71420000 -6.139170e+01 NA NA NA
## mean 10.78758413 -6.120962e+01 NA NA NA
## SE.mean 0.04203106 4.867603e-02 NA NA NA
## CI.mean.0.95 0.08401889 9.730199e-02 NA NA NA
## var 0.11129642 1.492694e-01 NA NA NA
## std.dev 0.33361118 3.863540e-01 NA NA NA
## coef.var 0.03092548 -6.311982e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 1 44.00000000 NA
## nbr.null NA NA NA 1 40.00000000 NA
## nbr.na NA NA NA 62 19.00000000 NA
## min NA NA NA 0 0.00000000 NA
## max NA NA NA 0 3.00000000 NA
## range NA NA NA 0 3.00000000 NA
## sum NA NA NA 0 6.00000000 NA
## median NA NA NA 0 0.00000000 NA
## mean NA NA NA 0 0.13636364 NA
## SE.mean NA NA NA NA 0.07687686 NA
## CI.mean.0.95 NA NA NA NaN 0.15503697 NA
## var NA NA NA NA 0.26004228 NA
## std.dev NA NA NA NA 0.50994341 NA
## coef.var NA NA NA NA 3.73958502 NA
## source_link prop ypos
## nbr.val NA 63.00000000 63.0000000
## nbr.null NA 0.00000000 0.0000000
## nbr.na NA 0.00000000 0.0000000
## min NA 0.07411056 0.2539577
## max NA 6.44876727 99.8226828
## range NA 6.37465671 99.5687251
## sum NA 100.00000000 3733.7070298
## median NA 1.13721933 66.3125093
## mean NA 1.58730159 59.2651909
## SE.mean NA 0.20485554 3.8579049
## CI.mean.0.95 NA 0.40950038 7.7118419
## var NA 2.64384485 937.6560850
## std.dev NA 1.62599042 30.6211705
## coef.var NA 1.02437397 0.5166805boxplot(data, horizontal=TRUE, col='green')
Gráfico para City of Port of Spain (Trinidad and Tobago)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_TT <- subset(df, country_name == "Trinidad and Tobago")
knitr::kable(head(df_TT)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 224 | 9/1/07 | NA | NA | Trinidad and Tobago | TT | Tobago | 17000 | Scarborough | 9.11607 | NA | 11.2415 | -60.6742 | (11.2415, -60.674199999999999) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Felix | NA | NA | Trinadad Express | http://www.trinidadexpress.com/index.pl/article_news?id=161197580 |
| 357 | 11/17/07 | NA | NA | Trinidad and Tobago | TT | Eastern Tobago | 0 | Roxborough | 7.33295 | NA | 11.2965 | -60.6312 | (11.2965, -60.6312) | Landslide | Landslide | Medium | Rain | NA | NA | NA | Trinadad Express | http://www.trinidadexpress.com/index.pl/article_news?id=161237574 |
| 390 | 12/11/07 | NA | NA | Trinidad and Tobago | TT | Sangre Grande | 15968 | Sangre Grande | 29.28864 | NA | 10.8410 | -61.0550 | (10.840999999999999, -61.055) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Olga | NA | 3 | Trinidad and Tobago’s Newsday | http://www.newsday.co.tt/news/0,69681.html |
| 391 | 12/11/07 | NA | NA | Trinidad and Tobago | TT | Eastern Tobago | 0 | Roxborough | 8.62938 | NA | 11.3000 | -60.6440 | (11.3, -60.643999999999998) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Olga | NA | NA | Trinidad and Tobago’s Newsday | http://www.newsday.co.tt/news/0,69681.html |
| 392 | 12/11/07 | NA | NA | Trinidad and Tobago | TT | Eastern Tobago | 0 | Roxborough | 2.66802 | NA | 11.2670 | -60.5660 | (11.266999999999999, -60.566000000000003) | Landslide | Landslide | Small | Tropical cyclone | Tropical Storm Olga | NA | NA | Trinidad and Tobago’s Newsday | http://www.newsday.co.tt/news/0,69681.html |
| 780 | 9/7/08 | NA | NA | Trinidad and Tobago | TT | Diego Martin | 8140 | Petit Valley | 10.61854 | NA | 10.7603 | -61.4578 | (10.760300000000001, -61.457799999999999) | Landslide | Landslide | Medium | Downpour | NA | NA | NA | NA | http://www.newsday.co.tt/news/0,85847.html |
library(dplyr)
df_TT <- subset(df, state == "City of Port of Spain")
knitr::kable(head(df_TT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 891 | 11/16/08 | NA | NA | Trinidad and Tobago | TT | City of Port of Spain | 49031 | Port-of-Spain | 1.07831 | NA | 10.6760 | -61.5160 | (10.676, -61.515999999999998) | Landslide | Complex | Medium | Downpour | NA | NA | 1 | NA | http://www.newsday.co.tt/news/0,90097.html |
| 2157 | 7/29/10 | NA | NA | Trinidad and Tobago | TT | City of Port of Spain | 4342 | Mucurapo | 7.43310 | NA | 10.6871 | -61.6002 | (10.687099999999999, -61.600200000000001) | Landslide | Landslide | Small | Downpour | NA | NA | 0 | NA | http://www.i955fm.com/News.aspx?id=8920 |
| 2158 | 7/29/10 | NA | NA | Trinidad and Tobago | TT | City of Port of Spain | 49031 | Port-of-Spain | 2.15046 | NA | 10.6738 | -61.5006 | (10.6738, -61.500599999999999) | Landslide | Landslide | Small | Downpour | NA | NA | 0 | NA | http://www.i955fm.com/News.aspx?id=8920 |
| 2199 | 8/5/10 | 13:45:00 | NA | Trinidad and Tobago | TT | City of Port of Spain | 4342 | Mucurapo | 7.24469 | NA | 10.6857 | -61.5989 | (10.685700000000001, -61.5989) | Landslide | Landslide | Small | Downpour | NA | NA | 0 | NA | NA |
| 4558 | 9/16/12 | Early morning | NA | Trinidad and Tobago | TT | City of Port of Spain | 49031 | Port-of-Spain | 2.54016 | NA | 10.6771 | -61.4982 | (10.677099999999999, -61.498199999999997) | Landslide | Landslide | Medium | Downpour | NA | NA | NA | NA | http://92.f9.78ae.static.theplanet.com/news/2012-09-16/morvant-landslide-leaves-motorists-frustrated |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_TT, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_TT, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_TT, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_TT <- df_TT %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_TT$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_TT, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_TT$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 1.07831 |
| 2.15046 |
| 2.54016 |
| 7.43310 |
| 7.24469 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_TT$distance
names(distance) <- df_TT$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Mucurapo 7.433100 7.433100 36.353508 36.353508
## Mucurapo 7.244690 14.677790 35.432040 71.785548
## Port-of-Spain 2.540160 17.217950 12.423313 84.208861
## Port-of-Spain 2.150460 19.368410 10.517384 94.726245
## Port-of-Spain 1.078310 20.446720 5.273755 100.000000stem(df_TT$"distance")##
## The decimal point is at the |
##
## 0 | 1
## 2 | 25
## 4 |
## 6 | 24head(df_TT)## # A tibble: 5 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 891 11/16/08 <NA> <NA> Trinidad an~ TT City~ 49031
## 2 2158 7/29/10 <NA> <NA> Trinidad an~ TT City~ 49031
## 3 4558 9/16/12 Earl~ <NA> Trinidad an~ TT City~ 49031
## 4 2157 7/29/10 <NA> <NA> Trinidad an~ TT City~ 4342
## 5 2199 8/5/10 13:4~ <NA> Trinidad an~ TT City~ 4342
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_TT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 891 | 11/16/08 | NA | NA | Trinidad and Tobago | TT | City of Port of Spain | 49031 | Port-of-Spain | 1.07831 | NA | 10.6760 | -61.5160 | (10.676, -61.515999999999998) | Landslide | Complex | Medium | Downpour | NA | NA | 1 | NA | http://www.newsday.co.tt/news/0,90097.html | 5.273755 | 2.636878 |
| 2158 | 7/29/10 | NA | NA | Trinidad and Tobago | TT | City of Port of Spain | 49031 | Port-of-Spain | 2.15046 | NA | 10.6738 | -61.5006 | (10.6738, -61.500599999999999) | Landslide | Landslide | Small | Downpour | NA | NA | 0 | NA | http://www.i955fm.com/News.aspx?id=8920 | 10.517384 | 10.532447 |
| 4558 | 9/16/12 | Early morning | NA | Trinidad and Tobago | TT | City of Port of Spain | 49031 | Port-of-Spain | 2.54016 | NA | 10.6771 | -61.4982 | (10.677099999999999, -61.498199999999997) | Landslide | Landslide | Medium | Downpour | NA | NA | NA | NA | http://92.f9.78ae.static.theplanet.com/news/2012-09-16/morvant-landslide-leaves-motorists-frustrated | 12.423313 | 22.002796 |
| 2157 | 7/29/10 | NA | NA | Trinidad and Tobago | TT | City of Port of Spain | 4342 | Mucurapo | 7.43310 | NA | 10.6871 | -61.6002 | (10.687099999999999, -61.600200000000001) | Landslide | Landslide | Small | Downpour | NA | NA | 0 | NA | http://www.i955fm.com/News.aspx?id=8920 | 36.353508 | 46.391206 |
| 2199 | 8/5/10 | 13:45:00 | NA | Trinidad and Tobago | TT | City of Port of Spain | 4342 | Mucurapo | 7.24469 | NA | 10.6857 | -61.5989 | (10.685700000000001, -61.5989) | Landslide | Landslide | Small | Downpour | NA | NA | 0 | NA | NA | 35.432040 | 82.283980 |
stem(df_TT$"distance")##
## The decimal point is at the |
##
## 0 | 1
## 2 | 25
## 4 |
## 6 | 24stem(df_TT$"distance", scale = 2)##
## The decimal point is at the |
##
## 1 | 1
## 2 | 25
## 3 |
## 4 |
## 5 |
## 6 |
## 7 | 24Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 1.07831 | 1 | 20 | 20 | 20 | 20 |
| 2.15046 | 1 | 20 | 20 | 40 | 40 |
| 2.54016 | 1 | 20 | 20 | 60 | 60 |
| 7.24469 | 1 | 20 | 20 | 80 | 80 |
| 7.4331 | 1 | 20 | 20 | 100 | 100 |
| Total | 5 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 6 obs. of 5 variables:
## $ n : num 1 1 1 1 1 5
## $ % : num 20 20 20 20 20 100
## $ val% : num 20 20 20 20 20 100
## $ %cum : num 20 40 60 80 100 100
## $ val%cum: num 20 40 60 80 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 1.07831 | 1 |
| 2.15046 | 1 |
| 2.54016 | 1 |
| 7.24469 | 1 |
| 7.4331 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 1.07831 4.07831 7.07831 10.07831distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (1.08,4.08] | 2 | 0.5 | 2 |
| (4.08,7.08] | 0 | 0.0 | 2 |
| (7.08,10.1] | 2 | 0.5 | 4 |
str(Freq_table)## 'data.frame': 3 obs. of 4 variables:
## $ distance: Factor w/ 3 levels "(1.08,4.08]",..: 1 2 3
## $ Freq : int 2 0 2
## $ Rel_Freq: num 0.5 0 0.5
## $ Cum_Freq: int 2 2 4df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (1.08,4.08] | 2 |
| (4.08,7.08] | 0 |
| (7.08,10.1] | 2 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_TT)## Warning in min(x): ningún argumento finito para min; retornando Inf## Warning in max(x): ningun argumento finito para max; retornando -Inf## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 5.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 8.910000e+02 NA NA NA NA NA
## max 4.558000e+03 NA NA NA NA NA
## range 3.667000e+03 NA NA NA NA NA
## sum 1.196300e+04 NA NA NA NA NA
## median 2.158000e+03 NA NA NA NA NA
## mean 2.392600e+03 NA NA NA NA NA
## SE.mean 5.954740e+02 NA NA NA NA NA
## CI.mean.0.95 1.653301e+03 NA NA NA NA NA
## var 1.772946e+06 NA NA NA NA NA
## std.dev 1.331520e+03 NA NA NA NA NA
## coef.var 5.565160e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 5.000000e+00 NA 5.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 4.342000e+03 NA 1.0783100 NA
## max NA 4.903100e+04 NA 7.4331000 NA
## range NA 4.468900e+04 NA 6.3547900 NA
## sum NA 1.557770e+05 NA 20.4467200 NA
## median NA 4.903100e+04 NA 2.5401600 NA
## mean NA 3.115540e+04 NA 4.0893440 NA
## SE.mean NA 1.094652e+04 NA 1.3483783 NA
## CI.mean.0.95 NA 3.039242e+04 NA 3.7436983 NA
## var NA 5.991320e+08 NA 9.0906201 NA
## std.dev NA 2.447717e+04 NA 3.0150655 NA
## coef.var NA 7.856479e-01 NA 0.7372981 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 5.000000e+00 5.000000e+00 NA NA NA
## nbr.null 0.000000e+00 0.000000e+00 NA NA NA
## nbr.na 0.000000e+00 0.000000e+00 NA NA NA
## min 1.067380e+01 -6.160020e+01 NA NA NA
## max 1.068710e+01 -6.149820e+01 NA NA NA
## range 1.330000e-02 1.020000e-01 NA NA NA
## sum 5.339970e+01 -3.077139e+02 NA NA NA
## median 1.067710e+01 -6.151600e+01 NA NA NA
## mean 1.067994e+01 -6.154278e+01 NA NA NA
## SE.mean 2.699370e-03 2.337756e-02 NA NA NA
## CI.mean.0.95 7.494653e-03 6.490652e-02 NA NA NA
## var 3.643300e-05 2.732552e-03 NA NA NA
## std.dev 6.035975e-03 5.227382e-02 NA NA NA
## coef.var 5.651694e-04 -8.493899e-04 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 0 4.0000000 NA
## nbr.null NA NA NA 0 3.0000000 NA
## nbr.na NA NA NA 5 1.0000000 NA
## min NA NA NA Inf 0.0000000 NA
## max NA NA NA -Inf 1.0000000 NA
## range NA NA NA -Inf 1.0000000 NA
## sum NA NA NA 0 1.0000000 NA
## median NA NA NA NA 0.0000000 NA
## mean NA NA NA NaN 0.2500000 NA
## SE.mean NA NA NA NA 0.2500000 NA
## CI.mean.0.95 NA NA NA NaN 0.7956116 NA
## var NA NA NA NA 0.2500000 NA
## std.dev NA NA NA NA 0.5000000 NA
## coef.var NA NA NA NA 2.0000000 NA
## source_link prop ypos
## nbr.val NA 5.0000000 5.000000
## nbr.null NA 0.0000000 0.000000
## nbr.na NA 0.0000000 0.000000
## min NA 5.2737554 2.636878
## max NA 36.3535080 82.283980
## range NA 31.0797526 79.647102
## sum NA 100.0000000 163.847307
## median NA 12.4233129 22.002796
## mean NA 20.0000000 32.769461
## SE.mean NA 6.5945946 14.414607
## CI.mean.0.95 NA 18.3095299 40.021365
## var NA 217.4433905 1038.904493
## std.dev NA 14.7459618 32.232041
## coef.var NA 0.7372981 0.983600boxplot(data, horizontal=TRUE, col='green')
Gráfico para Tunapuna/Piarco (Trinidad and Tobago)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_TT <- subset(df, country_name == "Trinidad and Tobago")
knitr::kable(head(df_TT)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 224 | 9/1/07 | NA | NA | Trinidad and Tobago | TT | Tobago | 17000 | Scarborough | 9.11607 | NA | 11.2415 | -60.6742 | (11.2415, -60.674199999999999) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Felix | NA | NA | Trinadad Express | http://www.trinidadexpress.com/index.pl/article_news?id=161197580 |
| 357 | 11/17/07 | NA | NA | Trinidad and Tobago | TT | Eastern Tobago | 0 | Roxborough | 7.33295 | NA | 11.2965 | -60.6312 | (11.2965, -60.6312) | Landslide | Landslide | Medium | Rain | NA | NA | NA | Trinadad Express | http://www.trinidadexpress.com/index.pl/article_news?id=161237574 |
| 390 | 12/11/07 | NA | NA | Trinidad and Tobago | TT | Sangre Grande | 15968 | Sangre Grande | 29.28864 | NA | 10.8410 | -61.0550 | (10.840999999999999, -61.055) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Olga | NA | 3 | Trinidad and Tobago’s Newsday | http://www.newsday.co.tt/news/0,69681.html |
| 391 | 12/11/07 | NA | NA | Trinidad and Tobago | TT | Eastern Tobago | 0 | Roxborough | 8.62938 | NA | 11.3000 | -60.6440 | (11.3, -60.643999999999998) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Olga | NA | NA | Trinidad and Tobago’s Newsday | http://www.newsday.co.tt/news/0,69681.html |
| 392 | 12/11/07 | NA | NA | Trinidad and Tobago | TT | Eastern Tobago | 0 | Roxborough | 2.66802 | NA | 11.2670 | -60.5660 | (11.266999999999999, -60.566000000000003) | Landslide | Landslide | Small | Tropical cyclone | Tropical Storm Olga | NA | NA | Trinidad and Tobago’s Newsday | http://www.newsday.co.tt/news/0,69681.html |
| 780 | 9/7/08 | NA | NA | Trinidad and Tobago | TT | Diego Martin | 8140 | Petit Valley | 10.61854 | NA | 10.7603 | -61.4578 | (10.760300000000001, -61.457799999999999) | Landslide | Landslide | Medium | Downpour | NA | NA | NA | NA | http://www.newsday.co.tt/news/0,85847.html |
library(dplyr)
df_TT <- subset(df, state == "Tunapuna/Piarco")
knitr::kable(head(df_TT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2667 | 10/31/10 | Morning | NA | Trinidad and Tobago | TT | Tunapuna/Piarco | 15067 | Paradise | 2.64003 | NA | 10.6660 | -61.3832 | (10.666, -61.383200000000002) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Tomas | NA | 0 | NA | http://stormcarib.com/reports/current/report.php?id=1288616789_49546 |
| 4108 | 12/25/11 | NA | NA | Trinidad and Tobago | TT | Tunapuna/Piarco | 15067 | Paradise | 16.73194 | NA | 10.7901 | -61.2984 | (10.790100000000001, -61.298400000000001) | Landslide | Landslide | Large | Downpour | NA | NA | 0 | NA | http://www.guardian.co.tt/news/thursday-december-29-2011/blanchisseuse-residents-cut-road-collapses |
| 4374 | 5/30/12 | NA | NA | Trinidad and Tobago | TT | Tunapuna/Piarco | 15067 | Paradise | 13.75900 | NA | 10.7692 | -61.4078 | (10.7692, -61.407800000000002) | Landslide | Landslide | Large | Downpour | NA | NA | NA | NA | http://www.guardian.co.tt/news/2012-05-31/landslides-choke-north-coast-road |
| 4919 | 6/14/13 | Morning | NA | Trinidad and Tobago | TT | Tunapuna/Piarco | 17758 | Tunapuna | 2.63186 | NA | 10.6501 | -61.4004 | (10.6501, -61.400399999999998) | Landslide | Landslide | Small | Downpour | NA | NA | 0 | www.newsday.co.tt | http://www.newsday.co.tt/news/0,179174.html |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_TT, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_TT, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_TT, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_TT <- df_TT %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_TT$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_TT, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_TT$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 2.63186 |
| 2.64003 |
| 16.73194 |
| 13.75900 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_TT$distance
names(distance) <- df_TT$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Paradise 16.731940 16.731940 46.785839 46.785839
## Paradise 13.759000 30.490940 38.472906 85.258745
## Paradise 2.640030 33.130970 7.382050 92.640795
## Tunapuna 2.631860 35.762830 7.359205 100.000000stem(df_TT$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 33
## 0 |
## 1 | 4
## 1 | 7head(df_TT)## # A tibble: 4 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 4919 6/14/13 Morning <NA> Trinidad an~ TT Tuna~ 17758
## 2 2667 10/31/10 Morning <NA> Trinidad an~ TT Tuna~ 15067
## 3 4108 12/25/11 <NA> <NA> Trinidad an~ TT Tuna~ 15067
## 4 4374 5/30/12 <NA> <NA> Trinidad an~ TT Tuna~ 15067
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_TT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 4919 | 6/14/13 | Morning | NA | Trinidad and Tobago | TT | Tunapuna/Piarco | 17758 | Tunapuna | 2.63186 | NA | 10.6501 | -61.4004 | (10.6501, -61.400399999999998) | Landslide | Landslide | Small | Downpour | NA | NA | 0 | www.newsday.co.tt | http://www.newsday.co.tt/news/0,179174.html | 7.359205 | 3.679603 |
| 2667 | 10/31/10 | Morning | NA | Trinidad and Tobago | TT | Tunapuna/Piarco | 15067 | Paradise | 2.64003 | NA | 10.6660 | -61.3832 | (10.666, -61.383200000000002) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Tomas | NA | 0 | NA | http://stormcarib.com/reports/current/report.php?id=1288616789_49546 | 7.382050 | 11.050230 |
| 4108 | 12/25/11 | NA | NA | Trinidad and Tobago | TT | Tunapuna/Piarco | 15067 | Paradise | 16.73194 | NA | 10.7901 | -61.2984 | (10.790100000000001, -61.298400000000001) | Landslide | Landslide | Large | Downpour | NA | NA | 0 | NA | http://www.guardian.co.tt/news/thursday-december-29-2011/blanchisseuse-residents-cut-road-collapses | 46.785839 | 38.134175 |
| 4374 | 5/30/12 | NA | NA | Trinidad and Tobago | TT | Tunapuna/Piarco | 15067 | Paradise | 13.75900 | NA | 10.7692 | -61.4078 | (10.7692, -61.407800000000002) | Landslide | Landslide | Large | Downpour | NA | NA | NA | NA | http://www.guardian.co.tt/news/2012-05-31/landslides-choke-north-coast-road | 38.472906 | 80.763547 |
stem(df_TT$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 33
## 0 |
## 1 | 4
## 1 | 7stem(df_TT$"distance", scale = 2)##
## The decimal point is at the |
##
## 2 | 66
## 4 |
## 6 |
## 8 |
## 10 |
## 12 | 8
## 14 |
## 16 | 7Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 2.63186 | 1 | 25 | 25 | 25 | 25 |
| 2.64003 | 1 | 25 | 25 | 50 | 50 |
| 13.759 | 1 | 25 | 25 | 75 | 75 |
| 16.73194 | 1 | 25 | 25 | 100 | 100 |
| Total | 4 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 5 obs. of 5 variables:
## $ n : num 1 1 1 1 4
## $ % : num 25 25 25 25 100
## $ val% : num 25 25 25 25 100
## $ %cum : num 25 50 75 100 100
## $ val%cum: num 25 50 75 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 2.63186 | 1 |
| 2.64003 | 1 |
| 13.759 | 1 |
| 16.73194 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 2.63186 7.63186 12.63186 17.63186distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (2.63,7.63] | 1 | 0.3333333 | 1 |
| (7.63,12.6] | 0 | 0.0000000 | 1 |
| (12.6,17.6] | 2 | 0.6666667 | 3 |
str(Freq_table)## 'data.frame': 3 obs. of 4 variables:
## $ distance: Factor w/ 3 levels "(2.63,7.63]",..: 1 2 3
## $ Freq : int 1 0 2
## $ Rel_Freq: num 0.333 0 0.667
## $ Cum_Freq: int 1 1 3df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (2.63,7.63] | 1 |
| (7.63,12.6] | 0 |
| (12.6,17.6] | 2 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_TT)## Warning in min(x): ningún argumento finito para min; retornando Inf## Warning in max(x): ningun argumento finito para max; retornando -Inf## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 4.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 2.667000e+03 NA NA NA NA NA
## max 4.919000e+03 NA NA NA NA NA
## range 2.252000e+03 NA NA NA NA NA
## sum 1.606800e+04 NA NA NA NA NA
## median 4.241000e+03 NA NA NA NA NA
## mean 4.017000e+03 NA NA NA NA NA
## SE.mean 4.806102e+02 NA NA NA NA NA
## CI.mean.0.95 1.529516e+03 NA NA NA NA NA
## var 9.239447e+05 NA NA NA NA NA
## std.dev 9.612204e+02 NA NA NA NA NA
## coef.var 2.392881e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 4.000000e+00 NA 4.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 1.506700e+04 NA 2.6318600 NA
## max NA 1.775800e+04 NA 16.7319400 NA
## range NA 2.691000e+03 NA 14.1000800 NA
## sum NA 6.295900e+04 NA 35.7628300 NA
## median NA 1.506700e+04 NA 8.1995150 NA
## mean NA 1.573975e+04 NA 8.9407075 NA
## SE.mean NA 6.727500e+02 NA 3.6902952 NA
## CI.mean.0.95 NA 2.140991e+03 NA 11.7441662 NA
## var NA 1.810370e+06 NA 54.4731134 NA
## std.dev NA 1.345500e+03 NA 7.3805903 NA
## coef.var NA 8.548420e-02 NA 0.8255041 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 4.000000000 4.000000e+00 NA NA NA
## nbr.null 0.000000000 0.000000e+00 NA NA NA
## nbr.na 0.000000000 0.000000e+00 NA NA NA
## min 10.650100000 -6.140780e+01 NA NA NA
## max 10.790100000 -6.129840e+01 NA NA NA
## range 0.140000000 1.094000e-01 NA NA NA
## sum 42.875400000 -2.454898e+02 NA NA NA
## median 10.717600000 -6.139180e+01 NA NA NA
## mean 10.718850000 -6.137245e+01 NA NA NA
## SE.mean 0.035509823 2.521539e-02 NA NA NA
## CI.mean.0.95 0.113008104 8.024662e-02 NA NA NA
## var 0.005043790 2.543263e-03 NA NA NA
## std.dev 0.071019645 5.043078e-02 NA NA NA
## coef.var 0.006625678 -8.217169e-04 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 0 3 NA
## nbr.null NA NA NA 0 3 NA
## nbr.na NA NA NA 4 1 NA
## min NA NA NA Inf 0 NA
## max NA NA NA -Inf 0 NA
## range NA NA NA -Inf 0 NA
## sum NA NA NA 0 0 NA
## median NA NA NA NA 0 NA
## mean NA NA NA NaN 0 NA
## SE.mean NA NA NA NA 0 NA
## CI.mean.0.95 NA NA NA NaN 0 NA
## var NA NA NA NA 0 NA
## std.dev NA NA NA NA 0 NA
## coef.var NA NA NA NA NaN NA
## source_link prop ypos
## nbr.val NA 4.0000000 4.000000
## nbr.null NA 0.0000000 0.000000
## nbr.na NA 0.0000000 0.000000
## min NA 7.3592051 3.679603
## max NA 46.7858388 80.763547
## range NA 39.4266337 77.083944
## sum NA 100.0000000 133.627554
## median NA 22.9274781 24.592202
## mean NA 25.0000000 33.406889
## SE.mean NA 10.3188007 17.436867
## CI.mean.0.95 NA 32.8390292 55.491893
## var NA 425.9105928 1216.177346
## std.dev NA 20.6376014 34.873734
## coef.var NA 0.8255041 1.043908boxplot(data, horizontal=TRUE, col='green')
Gráfico para City of San Fernando (Trinidad and Tobago)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_TT <- subset(df, country_name == "Trinidad and Tobago")
knitr::kable(head(df_TT)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 224 | 9/1/07 | NA | NA | Trinidad and Tobago | TT | Tobago | 17000 | Scarborough | 9.11607 | NA | 11.2415 | -60.6742 | (11.2415, -60.674199999999999) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Felix | NA | NA | Trinadad Express | http://www.trinidadexpress.com/index.pl/article_news?id=161197580 |
| 357 | 11/17/07 | NA | NA | Trinidad and Tobago | TT | Eastern Tobago | 0 | Roxborough | 7.33295 | NA | 11.2965 | -60.6312 | (11.2965, -60.6312) | Landslide | Landslide | Medium | Rain | NA | NA | NA | Trinadad Express | http://www.trinidadexpress.com/index.pl/article_news?id=161237574 |
| 390 | 12/11/07 | NA | NA | Trinidad and Tobago | TT | Sangre Grande | 15968 | Sangre Grande | 29.28864 | NA | 10.8410 | -61.0550 | (10.840999999999999, -61.055) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Olga | NA | 3 | Trinidad and Tobago’s Newsday | http://www.newsday.co.tt/news/0,69681.html |
| 391 | 12/11/07 | NA | NA | Trinidad and Tobago | TT | Eastern Tobago | 0 | Roxborough | 8.62938 | NA | 11.3000 | -60.6440 | (11.3, -60.643999999999998) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Olga | NA | NA | Trinidad and Tobago’s Newsday | http://www.newsday.co.tt/news/0,69681.html |
| 392 | 12/11/07 | NA | NA | Trinidad and Tobago | TT | Eastern Tobago | 0 | Roxborough | 2.66802 | NA | 11.2670 | -60.5660 | (11.266999999999999, -60.566000000000003) | Landslide | Landslide | Small | Tropical cyclone | Tropical Storm Olga | NA | NA | Trinidad and Tobago’s Newsday | http://www.newsday.co.tt/news/0,69681.html |
| 780 | 9/7/08 | NA | NA | Trinidad and Tobago | TT | Diego Martin | 8140 | Petit Valley | 10.61854 | NA | 10.7603 | -61.4578 | (10.760300000000001, -61.457799999999999) | Landslide | Landslide | Medium | Downpour | NA | NA | NA | NA | http://www.newsday.co.tt/news/0,85847.html |
library(dplyr)
df_TT <- subset(df, state == "City of San Fernando")
knitr::kable(head(df_TT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1117 | 8/21/09 | NA | NA | Trinidad and Tobago | TT | City of San Fernando | 26700 | Marabella | 9.42494 | NA | 10.3717 | -61.3917 | (10.371700000000001, -61.3917) | Landslide | Landslide | Small | Downpour | NA | NA | 0 | NA | http://www.trinidadexpress.com/index.pl/article_news?id=161522186 |
| 2300 | 8/21/10 | Morning | NA | Trinidad and Tobago | TT | City of San Fernando | 55419 | San Fernando | 0.92162 | NA | 10.2753 | -61.4689 | (10.2753, -61.468899999999998) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | NA |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_TT, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_TT, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_TT, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_TT <- df_TT %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_TT$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_TT, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_TT$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 0.92162 |
| 9.42494 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_TT$distance
names(distance) <- df_TT$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Marabella 9.424940 9.424940 91.092498 91.092498
## San Fernando 0.921620 10.346560 8.907502 100.000000stem(df_TT$"distance")##
## The decimal point is at the |
##
## 0 | 9
## 2 |
## 4 |
## 6 |
## 8 | 4head(df_TT)## # A tibble: 2 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 2300 8/21/10 Morning <NA> Trinidad an~ TT City~ 55419
## 2 1117 8/21/09 <NA> <NA> Trinidad an~ TT City~ 26700
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_TT))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2300 | 8/21/10 | Morning | NA | Trinidad and Tobago | TT | City of San Fernando | 55419 | San Fernando | 0.92162 | NA | 10.2753 | -61.4689 | (10.2753, -61.468899999999998) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | NA | 8.907502 | 4.453751 |
| 1117 | 8/21/09 | NA | NA | Trinidad and Tobago | TT | City of San Fernando | 26700 | Marabella | 9.42494 | NA | 10.3717 | -61.3917 | (10.371700000000001, -61.3917) | Landslide | Landslide | Small | Downpour | NA | NA | 0 | NA | http://www.trinidadexpress.com/index.pl/article_news?id=161522186 | 91.092498 | 54.453751 |
stem(df_TT$"distance")##
## The decimal point is at the |
##
## 0 | 9
## 2 |
## 4 |
## 6 |
## 8 | 4stem(df_TT$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 9
## 1 |
## 2 |
## 3 |
## 4 |
## 5 |
## 6 |
## 7 |
## 8 |
## 9 | 4Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.92162 | 1 | 50 | 50 | 50 | 50 |
| 9.42494 | 1 | 50 | 50 | 100 | 100 |
| Total | 2 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 3 obs. of 5 variables:
## $ n : num 1 1 2
## $ % : num 50 50 100
## $ val% : num 50 50 100
## $ %cum : num 50 100 100
## $ val%cum: num 50 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.92162 | 1 |
| 9.42494 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.92162 5.92162 10.92162distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.922,5.92] | 0 | 0 | 0 |
| (5.92,10.9] | 1 | 1 | 1 |
str(Freq_table)## 'data.frame': 2 obs. of 4 variables:
## $ distance: Factor w/ 2 levels "(0.922,5.92]",..: 1 2
## $ Freq : int 0 1
## $ Rel_Freq: num 0 1
## $ Cum_Freq: int 0 1df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.922,5.92] | 0 |
| (5.92,10.9] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_TT)## Warning in min(x): ningún argumento finito para min; retornando Inf## Warning in max(x): ningun argumento finito para max; retornando -Inf## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 2.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 1.117000e+03 NA NA NA NA NA
## max 2.300000e+03 NA NA NA NA NA
## range 1.183000e+03 NA NA NA NA NA
## sum 3.417000e+03 NA NA NA NA NA
## median 1.708500e+03 NA NA NA NA NA
## mean 1.708500e+03 NA NA NA NA NA
## SE.mean 5.915000e+02 NA NA NA NA NA
## CI.mean.0.95 7.515720e+03 NA NA NA NA NA
## var 6.997445e+05 NA NA NA NA NA
## std.dev 8.365073e+02 NA NA NA NA NA
## coef.var 4.896151e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 2.000000e+00 NA 2.000000 NA
## nbr.null NA 0.000000e+00 NA 0.000000 NA
## nbr.na NA 0.000000e+00 NA 0.000000 NA
## min NA 2.670000e+04 NA 0.921620 NA
## max NA 5.541900e+04 NA 9.424940 NA
## range NA 2.871900e+04 NA 8.503320 NA
## sum NA 8.211900e+04 NA 10.346560 NA
## median NA 4.105950e+04 NA 5.173280 NA
## mean NA 4.105950e+04 NA 5.173280 NA
## SE.mean NA 1.435950e+04 NA 4.251660 NA
## CI.mean.0.95 NA 1.824547e+05 NA 54.022462 NA
## var NA 4.123905e+08 NA 36.153226 NA
## std.dev NA 2.030740e+04 NA 6.012755 NA
## coef.var NA 4.945847e-01 NA 1.162271 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 2.000000000 2.000000e+00 NA NA NA
## nbr.null 0.000000000 0.000000e+00 NA NA NA
## nbr.na 0.000000000 0.000000e+00 NA NA NA
## min 10.275300000 -6.146890e+01 NA NA NA
## max 10.371700000 -6.139170e+01 NA NA NA
## range 0.096400000 7.720000e-02 NA NA NA
## sum 20.647000000 -1.228606e+02 NA NA NA
## median 10.323500000 -6.143030e+01 NA NA NA
## mean 10.323500000 -6.143030e+01 NA NA NA
## SE.mean 0.048200000 3.860000e-02 NA NA NA
## CI.mean.0.95 0.612439068 4.904595e-01 NA NA NA
## var 0.004646480 2.979920e-03 NA NA NA
## std.dev 0.068165094 5.458864e-02 NA NA NA
## coef.var 0.006602905 -8.886273e-04 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 0 2 NA
## nbr.null NA NA NA 0 2 NA
## nbr.na NA NA NA 2 0 NA
## min NA NA NA Inf 0 NA
## max NA NA NA -Inf 0 NA
## range NA NA NA -Inf 0 NA
## sum NA NA NA 0 0 NA
## median NA NA NA NA 0 NA
## mean NA NA NA NaN 0 NA
## SE.mean NA NA NA NA 0 NA
## CI.mean.0.95 NA NA NA NaN 0 NA
## var NA NA NA NA 0 NA
## std.dev NA NA NA NA 0 NA
## coef.var NA NA NA NA NaN NA
## source_link prop ypos
## nbr.val NA 2.000000 2.000000
## nbr.null NA 0.000000 0.000000
## nbr.na NA 0.000000 0.000000
## min NA 8.907502 4.453751
## max NA 91.092498 54.453751
## range NA 82.184997 50.000000
## sum NA 100.000000 58.907502
## median NA 50.000000 29.453751
## mean NA 50.000000 29.453751
## SE.mean NA 41.092498 25.000000
## CI.mean.0.95 NA 522.129697 317.655118
## var NA 3377.186846 1250.000000
## std.dev NA 58.113569 35.355339
## coef.var NA 1.162271 1.200368boxplot(data, horizontal=TRUE, col='green')
Gráfico para Dominican Republic
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_DR <- subset(df, country_name == "Dominican Republic")
knitr::kable(head(df_DR))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 124 | 7/13/07 | Night | NA | Dominican Republic | DO | Distrito Nacional | 13456 | San Carlos | 1.70298 | NA | 18.4757 | -69.9140 | (18.4757, -69.914000000000001) | Landslide | Landslide | Small | Unknown | NA | NA | NA | Dominican Today | http://www.dominicantoday.com/app/article.aspx?id=24682 |
| 333 | 10/29/07 | NA | NA | Dominican Republic | DO | San Cristóbal | 66784 | Bajos de Haina | 1.72138 | NA | 18.4270 | -70.0440 | (18.427, -70.043999999999997) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Storm Noel | NA | 3 | United Nations Development Programme - Relief Web | http://news.scotsman.com/international.cfm?id=1730152007 |
| 343 | 11/1/07 | NA | NA | Dominican Republic | DO | La Vega | 3613 | Río Verde Abajo | 3.72637 | NA | 19.3050 | -70.6000 | (19.305, -70.599999999999994) | Landslide | Complex | Large | Tropical cyclone | Tropical Storm Noel | NA | 68 | United Nations Development Programme - Relief Web | http://www.reliefweb.int/rw/fullMaps_Am.nsf/luFullMap/CEB72F0756431A7CC125738D003E2EF4/$File/ifrc_TC_carib071108.pdf?OpenElement |
| 388 | 12/11/07 | NA | NA | Dominican Republic | DO | Santiago | 1200000 | Santiago de los Caballeros | 1.10868 | NA | 19.4550 | -70.7070 | (19.454999999999998, -70.706999999999994) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Olga | NA | 17 | news.gossip.info | http://clutchmagonline.com/newsgossipinfo/caribbean-storm-death-toll-rises/ |
| 724 | 8/17/08 | NA | NA | Dominican Republic | DO | Hato Mayor | 13977 | Sabana de La Mar | 0.75284 | NA | 19.0560 | -69.3822 | (19.056000000000001, -69.382199999999997) | Landslide | Complex | Medium | Tropical cyclone | Tropical Storm Fay | NA | NA | NA | http://www.dominicantoday.com/dr/economy/2008/8/18/29085/Storms-downpours-block-transit-on-newest-Dominican-highway |
| 746 | 8/26/08 | NA | NA | Dominican Republic | DO | Distrito Nacional | 10457 | La Agustina | 5.71058 | NA | 18.5500 | -69.9200 | (18.55, -69.92) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Gustav | NA | 8 | NA | http://www.reuters.com/article/worldNews/idUSN2541891320080827?pageNumber=1&virtualBrandChannel=0 |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_DR, aes(fill= state, y=distance, x=country_name)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_DR, aes(fill=state, y=distance, x=country_name)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_DR, aes(x=country_name, y=distance, fill=state)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_DR <- df_DR %>%
arrange(desc(state)) %>%
mutate(prop = distance / sum(df_DR$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_DR, aes(x=country_name, y=prop, fill=state)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_DR$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 3.98059 |
| 1.10868 |
| 4.86398 |
| 4.31327 |
| 2.72462 |
| 1.72138 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_DR$distance
names(distance) <- df_DR$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por estados"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## La Agustina 5.710580 5.710580 16.167021 16.167021
## Pedro García 4.863980 10.574560 13.770242 29.937264
## Tamboril 4.313270 14.887830 12.211146 42.148410
## Santo Domingo Este 3.980590 18.868420 11.269308 53.417718
## Río Verde Abajo 3.726370 22.594790 10.549595 63.967313
## San José de Las Matas 2.724620 25.319410 7.713576 71.680888
## Bajos de Haina 1.721380 27.040790 4.873338 76.554226
## San Carlos 1.702980 28.743770 4.821247 81.375473
## Luperón 1.548850 30.292620 4.384895 85.760367
## Puerto Plata 1.196360 31.488980 3.386973 89.147340
## Santiago de los Caballeros 1.108680 32.597660 3.138745 92.286085
## Altamira 0.885000 33.482660 2.505492 94.791577
## Sabana de La Mar 0.752840 34.235500 2.131339 96.922916
## Santo Domingo 0.557210 34.792710 1.577498 98.500413
## Constanza 0.529690 35.322400 1.499587 100.000000stem(df_DR$"distance")##
## The decimal point is at the |
##
## 0 | 568912577
## 2 | 77
## 4 | 0397head(df_DR)## # A tibble: 6 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 6706 8/3/14 <NA> <NA> Dominican R~ DO Sant~ 0
## 2 388 12/11/07 <NA> <NA> Dominican R~ DO Sant~ 1200000
## 3 984 2/12/09 <NA> <NA> Dominican R~ DO Sant~ 1457
## 4 1178 9/20/09 <NA> <NA> Dominican R~ DO Sant~ 23304
## 5 3569 6/3/11 <NA> <NA> Dominican R~ DO Sant~ 9853
## 6 333 10/29/07 <NA> <NA> Dominican R~ DO San ~ 66784
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_DR))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 6706 | 8/3/14 | NA | NA | Dominican Republic | DO | Santo Domingo | 0 | Santo Domingo Este | 3.98059 | Urban area | 18.5225 | -69.8693 | (18.522500000000001, -69.869299999999996) | Landslide | Landslide | Medium | Tropical cyclone | Bertha | 0 | 0 | Zona Oriental | http://www.delazonaoriental.net/2014/08/03/derrumbes-y-deslizamientos-de-tierra-afectan-varias-viviendas-en-la-barquita-tras-paso-tormenta-bertha/ | 11.269308 | 5.634654 |
| 388 | 12/11/07 | NA | NA | Dominican Republic | DO | Santiago | 1200000 | Santiago de los Caballeros | 1.10868 | NA | 19.4550 | -70.7070 | (19.454999999999998, -70.706999999999994) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Olga | NA | 17 | news.gossip.info | http://clutchmagonline.com/newsgossipinfo/caribbean-storm-death-toll-rises/ | 3.138745 | 12.838680 |
| 984 | 2/12/09 | NA | NA | Dominican Republic | DO | Santiago | 1457 | Pedro García | 4.86398 | NA | 19.5500 | -70.6390 | (19.55, -70.638999999999996) | Landslide | Mudslide | Medium | Downpour | NA | NA | 0 | NA | http://us.puerto-plata-live.com/puerto-plata/news/year-2009/february-2009.html | 13.770242 | 21.293174 |
| 1178 | 9/20/09 | NA | NA | Dominican Republic | DO | Santiago | 23304 | Tamboril | 4.31327 | NA | 19.5167 | -70.5866 | (19.5167, -70.586600000000004) | Landslide | Landslide | Small | Downpour | NA | NA | NA | NA | http://www.laht.com/article.asp?CategoryId=14092&ArticleId=327347 | 12.211146 | 34.283868 |
| 3569 | 6/3/11 | NA | NA | Dominican Republic | DO | Santiago | 9853 | San José de Las Matas | 2.72462 | NA | 19.3556 | -70.9189 | (19.355599999999999, -70.918899999999994) | Landslide | Landslide | Medium | Downpour | NA | NA | 1 | NA | http://english.peopledaily.com.cn/90001/90777/90852/7402423.html | 7.713576 | 44.246229 |
| 333 | 10/29/07 | NA | NA | Dominican Republic | DO | San Cristóbal | 66784 | Bajos de Haina | 1.72138 | NA | 18.4270 | -70.0440 | (18.427, -70.043999999999997) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Storm Noel | NA | 3 | United Nations Development Programme - Relief Web | http://news.scotsman.com/international.cfm?id=1730152007 | 4.873338 | 50.539686 |
stem(df_DR$"distance")##
## The decimal point is at the |
##
## 0 | 568912577
## 2 | 77
## 4 | 0397stem(df_DR$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 5689
## 1 | 12577
## 2 | 7
## 3 | 7
## 4 | 039
## 5 | 7Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.52969 | 1 | 6.7 | 6.7 | 6.7 | 6.7 |
| 0.55721 | 1 | 6.7 | 6.7 | 13.3 | 13.3 |
| 0.75284 | 1 | 6.7 | 6.7 | 20.0 | 20.0 |
| 0.885 | 1 | 6.7 | 6.7 | 26.7 | 26.7 |
| 1.10868 | 1 | 6.7 | 6.7 | 33.3 | 33.3 |
| 1.19636 | 1 | 6.7 | 6.7 | 40.0 | 40.0 |
| 1.54885 | 1 | 6.7 | 6.7 | 46.7 | 46.7 |
| 1.70298 | 1 | 6.7 | 6.7 | 53.3 | 53.3 |
| 1.72138 | 1 | 6.7 | 6.7 | 60.0 | 60.0 |
| 2.72462 | 1 | 6.7 | 6.7 | 66.7 | 66.7 |
| 3.72637 | 1 | 6.7 | 6.7 | 73.3 | 73.3 |
| 3.98059 | 1 | 6.7 | 6.7 | 80.0 | 80.0 |
| 4.31327 | 1 | 6.7 | 6.7 | 86.7 | 86.7 |
| 4.86398 | 1 | 6.7 | 6.7 | 93.3 | 93.3 |
| 5.71058 | 1 | 6.7 | 6.7 | 100.0 | 100.0 |
| Total | 15 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 16 obs. of 5 variables:
## $ n : num 1 1 1 1 1 1 1 1 1 1 ...
## $ % : num 6.7 6.7 6.7 6.7 6.7 6.7 6.7 6.7 6.7 6.7 ...
## $ val% : num 6.7 6.7 6.7 6.7 6.7 6.7 6.7 6.7 6.7 6.7 ...
## $ %cum : num 6.7 13.3 20 26.7 33.3 40 46.7 53.3 60 66.7 ...
## $ val%cum: num 6.7 13.3 20 26.7 33.3 40 46.7 53.3 60 66.7 ...x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.52969 | 1 |
| 0.55721 | 1 |
| 0.75284 | 1 |
| 0.885 | 1 |
| 1.10868 | 1 |
| 1.19636 | 1 |
| 1.54885 | 1 |
| 1.70298 | 1 |
| 1.72138 | 1 |
| 2.72462 | 1 |
| 3.72637 | 1 |
| 3.98059 | 1 |
| 4.31327 | 1 |
| 4.86398 | 1 |
| 5.71058 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.52969 2.52969 4.52969 6.52969distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.53,2.53] | 8 | 0.5714286 | 8 |
| (2.53,4.53] | 4 | 0.2857143 | 12 |
| (4.53,6.53] | 2 | 0.1428571 | 14 |
str(Freq_table)## 'data.frame': 3 obs. of 4 variables:
## $ distance: Factor w/ 3 levels "(0.53,2.53]",..: 1 2 3
## $ Freq : int 8 4 2
## $ Rel_Freq: num 0.571 0.286 0.143
## $ Cum_Freq: int 8 12 14df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.53,2.53] | 8 |
| (2.53,4.53] | 4 |
| (4.53,6.53] | 2 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_DR)## id date time continent_code country_name country_code
## nbr.val 1.500000e+01 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 1.240000e+02 NA NA NA NA NA
## max 6.707000e+03 NA NA NA NA NA
## range 6.583000e+03 NA NA NA NA NA
## sum 3.542100e+04 NA NA NA NA NA
## median 1.177000e+03 NA NA NA NA NA
## mean 2.361400e+03 NA NA NA NA NA
## SE.mean 6.027818e+02 NA NA NA NA NA
## CI.mean.0.95 1.292838e+03 NA NA NA NA NA
## var 5.450188e+06 NA NA NA NA NA
## std.dev 2.334564e+03 NA NA NA NA NA
## coef.var 9.886355e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 1.500000e+01 NA 15.0000000 NA
## nbr.null NA 1.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 0.000000e+00 NA 0.5296900 NA
## max NA 2.201941e+06 NA 5.7105800 NA
## range NA 2.201941e+06 NA 5.1808900 NA
## sum NA 3.729279e+06 NA 35.3224000 NA
## median NA 1.345600e+04 NA 1.7029800 NA
## mean NA 2.486186e+05 NA 2.3548267 NA
## SE.mean NA 1.601963e+05 NA 0.4456851 NA
## CI.mean.0.95 NA 3.435870e+05 NA 0.9558995 NA
## var NA 3.849430e+11 NA 2.9795286 NA
## std.dev NA 6.204378e+05 NA 1.7261311 NA
## coef.var NA 2.495540e+00 NA 0.7330183 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 15.00000000 1.500000e+01 NA NA NA
## nbr.null 0.00000000 0.000000e+00 NA NA NA
## nbr.na 0.00000000 0.000000e+00 NA NA NA
## min 18.42700000 -7.096300e+01 NA NA NA
## max 19.90530000 -6.938220e+01 NA NA NA
## range 1.47830000 1.580800e+00 NA NA NA
## sum 286.98100000 -1.055795e+03 NA NA NA
## median 19.30500000 -7.060000e+01 NA NA NA
## mean 19.13206667 -7.038631e+01 NA NA NA
## SE.mean 0.13659378 1.250746e-01 NA NA NA
## CI.mean.0.95 0.29296451 2.682583e-01 NA NA NA
## var 0.27986790 2.346547e-01 NA NA NA
## std.dev 0.52902542 4.844117e-01 NA NA NA
## coef.var 0.02765124 -6.882187e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 2 11.000000 NA
## nbr.null NA NA NA 2 4.000000 NA
## nbr.na NA NA NA 13 4.000000 NA
## min NA NA NA 0 0.000000 NA
## max NA NA NA 0 68.000000 NA
## range NA NA NA 0 68.000000 NA
## sum NA NA NA 0 100.000000 NA
## median NA NA NA 0 1.000000 NA
## mean NA NA NA 0 9.090909 NA
## SE.mean NA NA NA 0 6.092401 NA
## CI.mean.0.95 NA NA NA 0 13.574716 NA
## var NA NA NA 0 408.290909 NA
## std.dev NA NA NA 0 20.206210 NA
## coef.var NA NA NA NaN 2.222683 NA
## source_link prop ypos
## nbr.val NA 15.0000000 15.0000000
## nbr.null NA 0.0000000 0.0000000
## nbr.na NA 0.0000000 0.0000000
## min NA 1.4995867 5.6346539
## max NA 16.1670215 99.2112512
## range NA 14.6674348 93.5765973
## sum NA 100.0000000 830.1472720
## median NA 4.8212466 57.1753335
## mean NA 6.6666667 55.3431515
## SE.mean NA 1.2617635 7.1708290
## CI.mean.0.95 NA 2.7062135 15.3798986
## var NA 23.8807055 771.3118270
## std.dev NA 4.8867889 27.7725013
## coef.var NA 0.7330183 0.5018236boxplot(data, horizontal=TRUE, col='green')
Gráfico para Distrito Nacional (Dominican Republic)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_DR <- subset(df, country_name == "Dominican Republic")
knitr::kable(head(df_DR)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 124 | 7/13/07 | Night | NA | Dominican Republic | DO | Distrito Nacional | 13456 | San Carlos | 1.70298 | NA | 18.4757 | -69.9140 | (18.4757, -69.914000000000001) | Landslide | Landslide | Small | Unknown | NA | NA | NA | Dominican Today | http://www.dominicantoday.com/app/article.aspx?id=24682 |
| 333 | 10/29/07 | NA | NA | Dominican Republic | DO | San Cristóbal | 66784 | Bajos de Haina | 1.72138 | NA | 18.4270 | -70.0440 | (18.427, -70.043999999999997) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Storm Noel | NA | 3 | United Nations Development Programme - Relief Web | http://news.scotsman.com/international.cfm?id=1730152007 |
| 343 | 11/1/07 | NA | NA | Dominican Republic | DO | La Vega | 3613 | Río Verde Abajo | 3.72637 | NA | 19.3050 | -70.6000 | (19.305, -70.599999999999994) | Landslide | Complex | Large | Tropical cyclone | Tropical Storm Noel | NA | 68 | United Nations Development Programme - Relief Web | http://www.reliefweb.int/rw/fullMaps_Am.nsf/luFullMap/CEB72F0756431A7CC125738D003E2EF4/$File/ifrc_TC_carib071108.pdf?OpenElement |
| 388 | 12/11/07 | NA | NA | Dominican Republic | DO | Santiago | 1200000 | Santiago de los Caballeros | 1.10868 | NA | 19.4550 | -70.7070 | (19.454999999999998, -70.706999999999994) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Olga | NA | 17 | news.gossip.info | http://clutchmagonline.com/newsgossipinfo/caribbean-storm-death-toll-rises/ |
| 724 | 8/17/08 | NA | NA | Dominican Republic | DO | Hato Mayor | 13977 | Sabana de La Mar | 0.75284 | NA | 19.0560 | -69.3822 | (19.056000000000001, -69.382199999999997) | Landslide | Complex | Medium | Tropical cyclone | Tropical Storm Fay | NA | NA | NA | http://www.dominicantoday.com/dr/economy/2008/8/18/29085/Storms-downpours-block-transit-on-newest-Dominican-highway |
| 746 | 8/26/08 | NA | NA | Dominican Republic | DO | Distrito Nacional | 10457 | La Agustina | 5.71058 | NA | 18.5500 | -69.9200 | (18.55, -69.92) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Gustav | NA | 8 | NA | http://www.reuters.com/article/worldNews/idUSN2541891320080827?pageNumber=1&virtualBrandChannel=0 |
library(dplyr)
df_DR <- subset(df, state == "Distrito Nacional")
knitr::kable(head(df_DR))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 124 | 7/13/07 | Night | NA | Dominican Republic | DO | Distrito Nacional | 13456 | San Carlos | 1.70298 | NA | 18.4757 | -69.9140 | (18.4757, -69.914000000000001) | Landslide | Landslide | Small | Unknown | NA | NA | NA | Dominican Today | http://www.dominicantoday.com/app/article.aspx?id=24682 |
| 746 | 8/26/08 | NA | NA | Dominican Republic | DO | Distrito Nacional | 10457 | La Agustina | 5.71058 | NA | 18.5500 | -69.9200 | (18.55, -69.92) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Gustav | NA | 8 | NA | http://www.reuters.com/article/worldNews/idUSN2541891320080827?pageNumber=1&virtualBrandChannel=0 |
| 3736 | 7/6/11 | NA | NA | Dominican Republic | DO | Distrito Nacional | 2201941 | Santo Domingo | 0.55721 | NA | 18.5000 | -69.9833 | (18.5, -69.9833) | Landslide | Landslide | Medium | Downpour | NA | NA | 1 | NA | http://www.google.com/hostednews/ap/article/ALeqM5jKexw046ZtYaNWiMsOVfydb2LttA?docId=1ef9771813d64e66919fb5a9e3633a52 |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_DR, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_DR, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_DR, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_DR <- df_DR %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_DR$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_DR, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_DR$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 0.55721 |
| 1.70298 |
| 5.71058 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_DR$distance
names(distance) <- df_DR$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## La Agustina 5.710580 5.710580 71.644019 71.644019
## San Carlos 1.702980 7.413560 21.365314 93.009333
## Santo Domingo 0.557210 7.970770 6.990667 100.000000stem(df_DR$"distance")##
## The decimal point is at the |
##
## 0 | 67
## 2 |
## 4 | 7head(df_DR)## # A tibble: 3 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 3736 7/6/11 <NA> <NA> Dominican Re~ DO Dist~ 2201941
## 2 124 7/13/07 Night <NA> Dominican Re~ DO Dist~ 13456
## 3 746 8/26/08 <NA> <NA> Dominican Re~ DO Dist~ 10457
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_DR))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 3736 | 7/6/11 | NA | NA | Dominican Republic | DO | Distrito Nacional | 2201941 | Santo Domingo | 0.55721 | NA | 18.5000 | -69.9833 | (18.5, -69.9833) | Landslide | Landslide | Medium | Downpour | NA | NA | 1 | NA | http://www.google.com/hostednews/ap/article/ALeqM5jKexw046ZtYaNWiMsOVfydb2LttA?docId=1ef9771813d64e66919fb5a9e3633a52 | 6.990667 | 3.495334 |
| 124 | 7/13/07 | Night | NA | Dominican Republic | DO | Distrito Nacional | 13456 | San Carlos | 1.70298 | NA | 18.4757 | -69.9140 | (18.4757, -69.914000000000001) | Landslide | Landslide | Small | Unknown | NA | NA | NA | Dominican Today | http://www.dominicantoday.com/app/article.aspx?id=24682 | 21.365313 | 17.673324 |
| 746 | 8/26/08 | NA | NA | Dominican Republic | DO | Distrito Nacional | 10457 | La Agustina | 5.71058 | NA | 18.5500 | -69.9200 | (18.55, -69.92) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Gustav | NA | 8 | NA | http://www.reuters.com/article/worldNews/idUSN2541891320080827?pageNumber=1&virtualBrandChannel=0 | 71.644019 | 64.177990 |
stem(df_DR$"distance")##
## The decimal point is at the |
##
## 0 | 67
## 2 |
## 4 | 7stem(df_DR$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 6
## 1 | 7
## 2 |
## 3 |
## 4 |
## 5 | 7Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.55721 | 1 | 33.3 | 33.3 | 33.3 | 33.3 |
| 1.70298 | 1 | 33.3 | 33.3 | 66.7 | 66.7 |
| 5.71058 | 1 | 33.3 | 33.3 | 100.0 | 100.0 |
| Total | 3 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 4 obs. of 5 variables:
## $ n : num 1 1 1 3
## $ % : num 33.3 33.3 33.3 100
## $ val% : num 33.3 33.3 33.3 100
## $ %cum : num 33.3 66.7 100 100
## $ val%cum: num 33.3 66.7 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.55721 | 1 |
| 1.70298 | 1 |
| 5.71058 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.55721 2.55721 4.55721 6.55721distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.557,2.56] | 1 | 0.5 | 1 |
| (2.56,4.56] | 0 | 0.0 | 1 |
| (4.56,6.56] | 1 | 0.5 | 2 |
str(Freq_table)## 'data.frame': 3 obs. of 4 variables:
## $ distance: Factor w/ 3 levels "(0.557,2.56]",..: 1 2 3
## $ Freq : int 1 0 1
## $ Rel_Freq: num 0.5 0 0.5
## $ Cum_Freq: int 1 1 2df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.557,2.56] | 1 |
| (2.56,4.56] | 0 |
| (4.56,6.56] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_DR)## Warning in min(x): ningún argumento finito para min; retornando Inf## Warning in max(x): ningun argumento finito para max; retornando -Inf## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 3.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 1.240000e+02 NA NA NA NA NA
## max 3.736000e+03 NA NA NA NA NA
## range 3.612000e+03 NA NA NA NA NA
## sum 4.606000e+03 NA NA NA NA NA
## median 7.460000e+02 NA NA NA NA NA
## mean 1.535333e+03 NA NA NA NA NA
## SE.mean 1.114887e+03 NA NA NA NA NA
## CI.mean.0.95 4.796973e+03 NA NA NA NA NA
## var 3.728921e+06 NA NA NA NA NA
## std.dev 1.931042e+03 NA NA NA NA NA
## coef.var 1.257734e+00 NA NA NA NA NA
## state population city distance location_description latitude
## nbr.val NA 3.000000e+00 NA 3.000000 NA 3.000000000
## nbr.null NA 0.000000e+00 NA 0.000000 NA 0.000000000
## nbr.na NA 0.000000e+00 NA 0.000000 NA 0.000000000
## min NA 1.045700e+04 NA 0.557210 NA 18.475700000
## max NA 2.201941e+06 NA 5.710580 NA 18.550000000
## range NA 2.191484e+06 NA 5.153370 NA 0.074300000
## sum NA 2.225854e+06 NA 7.970770 NA 55.525700000
## median NA 1.345600e+04 NA 1.702980 NA 18.500000000
## mean NA 7.419513e+05 NA 2.656923 NA 18.508566667
## SE.mean NA 7.299953e+05 NA 1.562243 NA 0.021872078
## CI.mean.0.95 NA 3.140916e+06 NA 6.721790 NA 0.094107954
## var NA 1.598680e+12 NA 7.321812 NA 0.001435163
## std.dev NA 1.264389e+06 NA 2.705885 NA 0.037883550
## coef.var NA 1.704140e+00 NA 1.018428 NA 0.002046812
## longitude geolocation hazard_type landslide_type
## nbr.val 3.000000e+00 NA NA NA
## nbr.null 0.000000e+00 NA NA NA
## nbr.na 0.000000e+00 NA NA NA
## min -6.998330e+01 NA NA NA
## max -6.991400e+01 NA NA NA
## range 6.930000e-02 NA NA NA
## sum -2.098173e+02 NA NA NA
## median -6.992000e+01 NA NA NA
## mean -6.993910e+01 NA NA NA
## SE.mean 2.216777e-02 NA NA NA
## CI.mean.0.95 9.538021e-02 NA NA NA
## var 1.474230e-03 NA NA NA
## std.dev 3.839570e-02 NA NA NA
## coef.var -5.489877e-04 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 0 2.000000 NA
## nbr.null NA NA NA 0 0.000000 NA
## nbr.na NA NA NA 3 1.000000 NA
## min NA NA NA Inf 1.000000 NA
## max NA NA NA -Inf 8.000000 NA
## range NA NA NA -Inf 7.000000 NA
## sum NA NA NA 0 9.000000 NA
## median NA NA NA NA 4.500000 NA
## mean NA NA NA NaN 4.500000 NA
## SE.mean NA NA NA NA 3.500000 NA
## CI.mean.0.95 NA NA NA NaN 44.471717 NA
## var NA NA NA NA 24.500000 NA
## std.dev NA NA NA NA 4.949747 NA
## coef.var NA NA NA NA 1.099944 NA
## source_link prop ypos
## nbr.val NA 3.000000 3.000000
## nbr.null NA 0.000000 0.000000
## nbr.na NA 0.000000 0.000000
## min NA 6.990667 3.495334
## max NA 71.644019 64.177990
## range NA 64.653352 60.682657
## sum NA 100.000000 85.346648
## median NA 21.365314 17.673324
## mean NA 33.333333 28.448883
## SE.mean NA 19.599652 18.327399
## CI.mean.0.95 NA 84.330497 78.856435
## var NA 1152.439111 1007.680707
## std.dev NA 33.947594 31.743987
## coef.var NA 1.018428 1.115825boxplot(data, horizontal=TRUE, col='green')
Gráfico para La Vega (Dominican Republic)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_DR <- subset(df, country_name == "Dominican Republic")
knitr::kable(head(df_DR)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 124 | 7/13/07 | Night | NA | Dominican Republic | DO | Distrito Nacional | 13456 | San Carlos | 1.70298 | NA | 18.4757 | -69.9140 | (18.4757, -69.914000000000001) | Landslide | Landslide | Small | Unknown | NA | NA | NA | Dominican Today | http://www.dominicantoday.com/app/article.aspx?id=24682 |
| 333 | 10/29/07 | NA | NA | Dominican Republic | DO | San Cristóbal | 66784 | Bajos de Haina | 1.72138 | NA | 18.4270 | -70.0440 | (18.427, -70.043999999999997) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Storm Noel | NA | 3 | United Nations Development Programme - Relief Web | http://news.scotsman.com/international.cfm?id=1730152007 |
| 343 | 11/1/07 | NA | NA | Dominican Republic | DO | La Vega | 3613 | Río Verde Abajo | 3.72637 | NA | 19.3050 | -70.6000 | (19.305, -70.599999999999994) | Landslide | Complex | Large | Tropical cyclone | Tropical Storm Noel | NA | 68 | United Nations Development Programme - Relief Web | http://www.reliefweb.int/rw/fullMaps_Am.nsf/luFullMap/CEB72F0756431A7CC125738D003E2EF4/$File/ifrc_TC_carib071108.pdf?OpenElement |
| 388 | 12/11/07 | NA | NA | Dominican Republic | DO | Santiago | 1200000 | Santiago de los Caballeros | 1.10868 | NA | 19.4550 | -70.7070 | (19.454999999999998, -70.706999999999994) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Olga | NA | 17 | news.gossip.info | http://clutchmagonline.com/newsgossipinfo/caribbean-storm-death-toll-rises/ |
| 724 | 8/17/08 | NA | NA | Dominican Republic | DO | Hato Mayor | 13977 | Sabana de La Mar | 0.75284 | NA | 19.0560 | -69.3822 | (19.056000000000001, -69.382199999999997) | Landslide | Complex | Medium | Tropical cyclone | Tropical Storm Fay | NA | NA | NA | http://www.dominicantoday.com/dr/economy/2008/8/18/29085/Storms-downpours-block-transit-on-newest-Dominican-highway |
| 746 | 8/26/08 | NA | NA | Dominican Republic | DO | Distrito Nacional | 10457 | La Agustina | 5.71058 | NA | 18.5500 | -69.9200 | (18.55, -69.92) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Gustav | NA | 8 | NA | http://www.reuters.com/article/worldNews/idUSN2541891320080827?pageNumber=1&virtualBrandChannel=0 |
library(dplyr)
df_DR <- subset(df, state == "La Vega")
knitr::kable(head(df_DR))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 343 | 11/1/07 | NA | NA | Dominican Republic | DO | La Vega | 3613 | Río Verde Abajo | 3.72637 | NA | 19.3050 | -70.600 | (19.305, -70.599999999999994) | Landslide | Complex | Large | Tropical cyclone | Tropical Storm Noel | NA | 68 | United Nations Development Programme - Relief Web | http://www.reliefweb.int/rw/fullMaps_Am.nsf/luFullMap/CEB72F0756431A7CC125738D003E2EF4/$File/ifrc_TC_carib071108.pdf?OpenElement |
| 4051 | 11/18/11 | NA | NA | Dominican Republic | DO | La Vega | 29481 | Constanza | 0.52969 | NA | 18.9045 | -70.744 | (18.904499999999999, -70.744) | Landslide | Mudslide | Medium | Downpour | NA | NA | 0 | NA | http://www.dominicantoday.com/dr/local/2011/11/18/41684/Mudslides-halt-traffic-to-Constanza |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_DR, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_DR, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_DR, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_DR <- df_DR %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_DR$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_DR, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_DR$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 3.72637 |
| 0.52969 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_DR$distance
names(distance) <- df_DR$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Río Verde Abajo 3.72637 3.72637 87.55445 87.55445
## Constanza 0.52969 4.25606 12.44555 100.00000stem(df_DR$"distance")##
## The decimal point is at the |
##
## 0 | 5
## 1 |
## 2 |
## 3 | 7head(df_DR)## # A tibble: 2 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 343 11/1/07 <NA> <NA> Dominican R~ DO La V~ 3613
## 2 4051 11/18/11 <NA> <NA> Dominican R~ DO La V~ 29481
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_DR))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 343 | 11/1/07 | NA | NA | Dominican Republic | DO | La Vega | 3613 | Río Verde Abajo | 3.72637 | NA | 19.3050 | -70.600 | (19.305, -70.599999999999994) | Landslide | Complex | Large | Tropical cyclone | Tropical Storm Noel | NA | 68 | United Nations Development Programme - Relief Web | http://www.reliefweb.int/rw/fullMaps_Am.nsf/luFullMap/CEB72F0756431A7CC125738D003E2EF4/$File/ifrc_TC_carib071108.pdf?OpenElement | 87.55445 | 43.77723 |
| 4051 | 11/18/11 | NA | NA | Dominican Republic | DO | La Vega | 29481 | Constanza | 0.52969 | NA | 18.9045 | -70.744 | (18.904499999999999, -70.744) | Landslide | Mudslide | Medium | Downpour | NA | NA | 0 | NA | http://www.dominicantoday.com/dr/local/2011/11/18/41684/Mudslides-halt-traffic-to-Constanza | 12.44555 | 93.77723 |
stem(df_DR$"distance")##
## The decimal point is at the |
##
## 0 | 5
## 1 |
## 2 |
## 3 | 7stem(df_DR$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 5
## 1 |
## 1 |
## 2 |
## 2 |
## 3 |
## 3 | 7Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.52969 | 1 | 50 | 50 | 50 | 50 |
| 3.72637 | 1 | 50 | 50 | 100 | 100 |
| Total | 2 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 3 obs. of 5 variables:
## $ n : num 1 1 2
## $ % : num 50 50 100
## $ val% : num 50 50 100
## $ %cum : num 50 100 100
## $ val%cum: num 50 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.52969 | 1 |
| 3.72637 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.52969 2.52969 4.52969distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.53,2.53] | 0 | 0 | 0 |
| (2.53,4.53] | 1 | 1 | 1 |
str(Freq_table)## 'data.frame': 2 obs. of 4 variables:
## $ distance: Factor w/ 2 levels "(0.53,2.53]",..: 1 2
## $ Freq : int 0 1
## $ Rel_Freq: num 0 1
## $ Cum_Freq: int 0 1df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.53,2.53] | 0 |
| (2.53,4.53] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_DR)## Warning in min(x): ningún argumento finito para min; retornando Inf## Warning in max(x): ningun argumento finito para max; retornando -Inf## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 2.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 3.430000e+02 NA NA NA NA NA
## max 4.051000e+03 NA NA NA NA NA
## range 3.708000e+03 NA NA NA NA NA
## sum 4.394000e+03 NA NA NA NA NA
## median 2.197000e+03 NA NA NA NA NA
## mean 2.197000e+03 NA NA NA NA NA
## SE.mean 1.854000e+03 NA NA NA NA NA
## CI.mean.0.95 2.355730e+04 NA NA NA NA NA
## var 6.874632e+06 NA NA NA NA NA
## std.dev 2.621952e+03 NA NA NA NA NA
## coef.var 1.193424e+00 NA NA NA NA NA
## state population city distance location_description latitude
## nbr.val NA 2.000000e+00 NA 2.000000 NA 2.00000000
## nbr.null NA 0.000000e+00 NA 0.000000 NA 0.00000000
## nbr.na NA 0.000000e+00 NA 0.000000 NA 0.00000000
## min NA 3.613000e+03 NA 0.529690 NA 18.90450000
## max NA 2.948100e+04 NA 3.726370 NA 19.30500000
## range NA 2.586800e+04 NA 3.196680 NA 0.40050000
## sum NA 3.309400e+04 NA 4.256060 NA 38.20950000
## median NA 1.654700e+04 NA 2.128030 NA 19.10475000
## mean NA 1.654700e+04 NA 2.128030 NA 19.10475000
## SE.mean NA 1.293400e+04 NA 1.598340 NA 0.20025000
## CI.mean.0.95 NA 1.643421e+05 NA 20.308835 NA 2.54441750
## var NA 3.345767e+08 NA 5.109382 NA 0.08020013
## std.dev NA 1.829144e+04 NA 2.260394 NA 0.28319627
## coef.var NA 1.105423e+00 NA 1.062200 NA 0.01482334
## longitude geolocation hazard_type landslide_type
## nbr.val 2.000000e+00 NA NA NA
## nbr.null 0.000000e+00 NA NA NA
## nbr.na 0.000000e+00 NA NA NA
## min -7.074400e+01 NA NA NA
## max -7.060000e+01 NA NA NA
## range 1.440000e-01 NA NA NA
## sum -1.413440e+02 NA NA NA
## median -7.067200e+01 NA NA NA
## mean -7.067200e+01 NA NA NA
## SE.mean 7.200000e-02 NA NA NA
## CI.mean.0.95 9.148467e-01 NA NA NA
## var 1.036800e-02 NA NA NA
## std.dev 1.018234e-01 NA NA NA
## coef.var -1.440788e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 0 2.000000 NA
## nbr.null NA NA NA 0 1.000000 NA
## nbr.na NA NA NA 2 0.000000 NA
## min NA NA NA Inf 0.000000 NA
## max NA NA NA -Inf 68.000000 NA
## range NA NA NA -Inf 68.000000 NA
## sum NA NA NA 0 68.000000 NA
## median NA NA NA NA 34.000000 NA
## mean NA NA NA NaN 34.000000 NA
## SE.mean NA NA NA NA 34.000000 NA
## CI.mean.0.95 NA NA NA NaN 432.010961 NA
## var NA NA NA NA 2312.000000 NA
## std.dev NA NA NA NA 48.083261 NA
## coef.var NA NA NA NA 1.414214 NA
## source_link prop ypos
## nbr.val NA 2.00000 2.0000000
## nbr.null NA 0.00000 0.0000000
## nbr.na NA 0.00000 0.0000000
## min NA 12.44555 43.7772259
## max NA 87.55445 93.7772259
## range NA 75.10890 50.0000000
## sum NA 100.00000 137.5544518
## median NA 50.00000 68.7772259
## mean NA 50.00000 68.7772259
## SE.mean NA 37.55445 25.0000000
## CI.mean.0.95 NA 477.17455 317.6551184
## var NA 2820.67370 1250.0000000
## std.dev NA 53.11002 35.3553391
## coef.var NA 1.06220 0.5140559boxplot(data, horizontal=TRUE, col='green')
Gráfico para Puerto Plata (Dominican Republic)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_DR <- subset(df, country_name == "Dominican Republic")
knitr::kable(head(df_DR)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 124 | 7/13/07 | Night | NA | Dominican Republic | DO | Distrito Nacional | 13456 | San Carlos | 1.70298 | NA | 18.4757 | -69.9140 | (18.4757, -69.914000000000001) | Landslide | Landslide | Small | Unknown | NA | NA | NA | Dominican Today | http://www.dominicantoday.com/app/article.aspx?id=24682 |
| 333 | 10/29/07 | NA | NA | Dominican Republic | DO | San Cristóbal | 66784 | Bajos de Haina | 1.72138 | NA | 18.4270 | -70.0440 | (18.427, -70.043999999999997) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Storm Noel | NA | 3 | United Nations Development Programme - Relief Web | http://news.scotsman.com/international.cfm?id=1730152007 |
| 343 | 11/1/07 | NA | NA | Dominican Republic | DO | La Vega | 3613 | Río Verde Abajo | 3.72637 | NA | 19.3050 | -70.6000 | (19.305, -70.599999999999994) | Landslide | Complex | Large | Tropical cyclone | Tropical Storm Noel | NA | 68 | United Nations Development Programme - Relief Web | http://www.reliefweb.int/rw/fullMaps_Am.nsf/luFullMap/CEB72F0756431A7CC125738D003E2EF4/$File/ifrc_TC_carib071108.pdf?OpenElement |
| 388 | 12/11/07 | NA | NA | Dominican Republic | DO | Santiago | 1200000 | Santiago de los Caballeros | 1.10868 | NA | 19.4550 | -70.7070 | (19.454999999999998, -70.706999999999994) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Olga | NA | 17 | news.gossip.info | http://clutchmagonline.com/newsgossipinfo/caribbean-storm-death-toll-rises/ |
| 724 | 8/17/08 | NA | NA | Dominican Republic | DO | Hato Mayor | 13977 | Sabana de La Mar | 0.75284 | NA | 19.0560 | -69.3822 | (19.056000000000001, -69.382199999999997) | Landslide | Complex | Medium | Tropical cyclone | Tropical Storm Fay | NA | NA | NA | http://www.dominicantoday.com/dr/economy/2008/8/18/29085/Storms-downpours-block-transit-on-newest-Dominican-highway |
| 746 | 8/26/08 | NA | NA | Dominican Republic | DO | Distrito Nacional | 10457 | La Agustina | 5.71058 | NA | 18.5500 | -69.9200 | (18.55, -69.92) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Gustav | NA | 8 | NA | http://www.reuters.com/article/worldNews/idUSN2541891320080827?pageNumber=1&virtualBrandChannel=0 |
library(dplyr)
df_DR <- subset(df, state == "Puerto Plata")
knitr::kable(head(df_DR))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1177 | 9/20/09 | NA | NA | Dominican Republic | DO | Puerto Plata | 4563 | Altamira | 0.88500 | NA | 19.6750 | -70.8362 | (19.675000000000001, -70.836200000000005) | Landslide | Landslide | Medium | Downpour | NA | NA | 2 | NA | http://www.laht.com/article.asp?CategoryId=14092&ArticleId=327347 |
| 4655 | 12/5/12 | NA | NA | Dominican Republic | DO | Puerto Plata | 146000 | Puerto Plata | 1.19636 | NA | 19.7827 | -70.6871 | (19.782699999999998, -70.687100000000001) | Landslide | Landslide | Medium | Rain | NA | NA | NA | NA | http://www.dominicantoday.com/dr/local/2012/12/5/45992/Crews-clear-Santiago-Puerto-Plata-road-blocked-by-landslides |
| 6707 | 11/7/14 | NA | NA | Dominican Republic | DO | Puerto Plata | 4393 | Luperón | 1.54885 | Below road | 19.9053 | -70.9630 | (19.9053, -70.962999999999994) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | Hoy | http://hoy.com.do/carretera-luperon-presenta-hundimientos-y-deslizamientos-por-lluvias/ |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_DR, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_DR, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_DR, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_DR <- df_DR %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_DR$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_DR, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_DR$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 1.19636 |
| 1.54885 |
| 0.88500 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_DR$distance
names(distance) <- df_DR$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Luperón 1.54885 1.54885 42.66558 42.66558
## Puerto Plata 1.19636 2.74521 32.95567 75.62125
## Altamira 0.88500 3.63021 24.37875 100.00000stem(df_DR$"distance")##
## The decimal point is 1 digit(s) to the left of the |
##
## 8 | 9
## 10 |
## 12 | 0
## 14 | 5head(df_DR)## # A tibble: 3 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 4655 12/5/12 <NA> <NA> Dominican Re~ DO Puer~ 146000
## 2 6707 11/7/14 <NA> <NA> Dominican Re~ DO Puer~ 4393
## 3 1177 9/20/09 <NA> <NA> Dominican Re~ DO Puer~ 4563
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_DR))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 4655 | 12/5/12 | NA | NA | Dominican Republic | DO | Puerto Plata | 146000 | Puerto Plata | 1.19636 | NA | 19.7827 | -70.6871 | (19.782699999999998, -70.687100000000001) | Landslide | Landslide | Medium | Rain | NA | NA | NA | NA | http://www.dominicantoday.com/dr/local/2012/12/5/45992/Crews-clear-Santiago-Puerto-Plata-road-blocked-by-landslides | 32.95567 | 16.47783 |
| 6707 | 11/7/14 | NA | NA | Dominican Republic | DO | Puerto Plata | 4393 | Luperón | 1.54885 | Below road | 19.9053 | -70.9630 | (19.9053, -70.962999999999994) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | Hoy | http://hoy.com.do/carretera-luperon-presenta-hundimientos-y-deslizamientos-por-lluvias/ | 42.66558 | 54.28846 |
| 1177 | 9/20/09 | NA | NA | Dominican Republic | DO | Puerto Plata | 4563 | Altamira | 0.88500 | NA | 19.6750 | -70.8362 | (19.675000000000001, -70.836200000000005) | Landslide | Landslide | Medium | Downpour | NA | NA | 2 | NA | http://www.laht.com/article.asp?CategoryId=14092&ArticleId=327347 | 24.37875 | 87.81062 |
stem(df_DR$"distance")##
## The decimal point is 1 digit(s) to the left of the |
##
## 8 | 9
## 10 |
## 12 | 0
## 14 | 5stem(df_DR$"distance", scale = 2)##
## The decimal point is 1 digit(s) to the left of the |
##
## 8 | 9
## 9 |
## 10 |
## 11 |
## 12 | 0
## 13 |
## 14 |
## 15 | 5Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.885 | 1 | 33.3 | 33.3 | 33.3 | 33.3 |
| 1.19636 | 1 | 33.3 | 33.3 | 66.7 | 66.7 |
| 1.54885 | 1 | 33.3 | 33.3 | 100.0 | 100.0 |
| Total | 3 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 4 obs. of 5 variables:
## $ n : num 1 1 1 3
## $ % : num 33.3 33.3 33.3 100
## $ val% : num 33.3 33.3 33.3 100
## $ %cum : num 33.3 66.7 100 100
## $ val%cum: num 33.3 66.7 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.885 | 1 |
| 1.19636 | 1 |
| 1.54885 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.885 1.885distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.885,1.88] | 2 | 1 | 2 |
str(Freq_table)## 'data.frame': 1 obs. of 4 variables:
## $ distance: Factor w/ 1 level "(0.885,1.88]": 1
## $ Freq : int 2
## $ Rel_Freq: num 1
## $ Cum_Freq: int 2df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.885,1.88] | 2 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_DR)## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 3.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 1.177000e+03 NA NA NA NA NA
## max 6.707000e+03 NA NA NA NA NA
## range 5.530000e+03 NA NA NA NA NA
## sum 1.253900e+04 NA NA NA NA NA
## median 4.655000e+03 NA NA NA NA NA
## mean 4.179667e+03 NA NA NA NA NA
## SE.mean 1.613968e+03 NA NA NA NA NA
## CI.mean.0.95 6.944345e+03 NA NA NA NA NA
## var 7.814681e+06 NA NA NA NA NA
## std.dev 2.795475e+03 NA NA NA NA NA
## coef.var 6.688273e-01 NA NA NA NA NA
## state population city distance location_description latitude
## nbr.val NA 3.000000e+00 NA 3.0000000 NA 3.00000000
## nbr.null NA 0.000000e+00 NA 0.0000000 NA 0.00000000
## nbr.na NA 0.000000e+00 NA 0.0000000 NA 0.00000000
## min NA 4.393000e+03 NA 0.8850000 NA 19.67500000
## max NA 1.460000e+05 NA 1.5488500 NA 19.90530000
## range NA 1.416070e+05 NA 0.6638500 NA 0.23030000
## sum NA 1.549560e+05 NA 3.6302100 NA 59.36300000
## median NA 4.563000e+03 NA 1.1963600 NA 19.78270000
## mean NA 5.165200e+04 NA 1.2100700 NA 19.78766667
## SE.mean NA 4.717403e+04 NA 0.1917596 NA 0.06652825
## CI.mean.0.95 NA 2.029734e+05 NA 0.8250748 NA 0.28624795
## var NA 6.676166e+09 NA 0.1103152 NA 0.01327802
## std.dev NA 8.170781e+04 NA 0.3321373 NA 0.11523031
## coef.var NA 1.581891e+00 NA 0.2744777 NA 0.00582334
## longitude geolocation hazard_type landslide_type
## nbr.val 3.000000e+00 NA NA NA
## nbr.null 0.000000e+00 NA NA NA
## nbr.na 0.000000e+00 NA NA NA
## min -7.096300e+01 NA NA NA
## max -7.068710e+01 NA NA NA
## range 2.759000e-01 NA NA NA
## sum -2.124863e+02 NA NA NA
## median -7.083620e+01 NA NA NA
## mean -7.082877e+01 NA NA NA
## SE.mean 7.973214e-02 NA NA NA
## CI.mean.0.95 3.430597e-01 NA NA NA
## var 1.907164e-02 NA NA NA
## std.dev 1.381001e-01 NA NA NA
## coef.var -1.949774e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 1 2.000000 NA
## nbr.null NA NA NA 1 1.000000 NA
## nbr.na NA NA NA 2 1.000000 NA
## min NA NA NA 0 0.000000 NA
## max NA NA NA 0 2.000000 NA
## range NA NA NA 0 2.000000 NA
## sum NA NA NA 0 2.000000 NA
## median NA NA NA 0 1.000000 NA
## mean NA NA NA 0 1.000000 NA
## SE.mean NA NA NA NA 1.000000 NA
## CI.mean.0.95 NA NA NA NaN 12.706205 NA
## var NA NA NA NA 2.000000 NA
## std.dev NA NA NA NA 1.414214 NA
## coef.var NA NA NA NA 1.414214 NA
## source_link prop ypos
## nbr.val NA 3.0000000 3.0000000
## nbr.null NA 0.0000000 0.0000000
## nbr.na NA 0.0000000 0.0000000
## min NA 24.3787549 16.4778346
## max NA 42.6655758 87.8106225
## range NA 18.2868209 71.3327879
## sum NA 100.0000000 158.5769143
## median NA 32.9556692 54.2884571
## mean NA 33.3333333 52.8589714
## SE.mean NA 5.2823267 20.6044027
## CI.mean.0.95 NA 22.7280175 88.6535895
## var NA 83.7089270 1273.6242298
## std.dev NA 9.1492583 35.6878723
## coef.var NA 0.2744777 0.6751526boxplot(data, horizontal=TRUE, col='green')
Gráfico para Santiago (Dominican Republic)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_DR <- subset(df, country_name == "Dominican Republic")
knitr::kable(head(df_DR)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 124 | 7/13/07 | Night | NA | Dominican Republic | DO | Distrito Nacional | 13456 | San Carlos | 1.70298 | NA | 18.4757 | -69.9140 | (18.4757, -69.914000000000001) | Landslide | Landslide | Small | Unknown | NA | NA | NA | Dominican Today | http://www.dominicantoday.com/app/article.aspx?id=24682 |
| 333 | 10/29/07 | NA | NA | Dominican Republic | DO | San Cristóbal | 66784 | Bajos de Haina | 1.72138 | NA | 18.4270 | -70.0440 | (18.427, -70.043999999999997) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Storm Noel | NA | 3 | United Nations Development Programme - Relief Web | http://news.scotsman.com/international.cfm?id=1730152007 |
| 343 | 11/1/07 | NA | NA | Dominican Republic | DO | La Vega | 3613 | Río Verde Abajo | 3.72637 | NA | 19.3050 | -70.6000 | (19.305, -70.599999999999994) | Landslide | Complex | Large | Tropical cyclone | Tropical Storm Noel | NA | 68 | United Nations Development Programme - Relief Web | http://www.reliefweb.int/rw/fullMaps_Am.nsf/luFullMap/CEB72F0756431A7CC125738D003E2EF4/$File/ifrc_TC_carib071108.pdf?OpenElement |
| 388 | 12/11/07 | NA | NA | Dominican Republic | DO | Santiago | 1200000 | Santiago de los Caballeros | 1.10868 | NA | 19.4550 | -70.7070 | (19.454999999999998, -70.706999999999994) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Olga | NA | 17 | news.gossip.info | http://clutchmagonline.com/newsgossipinfo/caribbean-storm-death-toll-rises/ |
| 724 | 8/17/08 | NA | NA | Dominican Republic | DO | Hato Mayor | 13977 | Sabana de La Mar | 0.75284 | NA | 19.0560 | -69.3822 | (19.056000000000001, -69.382199999999997) | Landslide | Complex | Medium | Tropical cyclone | Tropical Storm Fay | NA | NA | NA | http://www.dominicantoday.com/dr/economy/2008/8/18/29085/Storms-downpours-block-transit-on-newest-Dominican-highway |
| 746 | 8/26/08 | NA | NA | Dominican Republic | DO | Distrito Nacional | 10457 | La Agustina | 5.71058 | NA | 18.5500 | -69.9200 | (18.55, -69.92) | Landslide | Mudslide | Medium | Tropical cyclone | Hurricane Gustav | NA | 8 | NA | http://www.reuters.com/article/worldNews/idUSN2541891320080827?pageNumber=1&virtualBrandChannel=0 |
library(dplyr)
df_DR <- subset(df, state == "Santiago")
knitr::kable(head(df_DR))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 388 | 12/11/07 | NA | NA | Dominican Republic | DO | Santiago | 1200000 | Santiago de los Caballeros | 1.10868 | NA | 19.4550 | -70.7070 | (19.454999999999998, -70.706999999999994) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Olga | NA | 17 | news.gossip.info | http://clutchmagonline.com/newsgossipinfo/caribbean-storm-death-toll-rises/ |
| 984 | 2/12/09 | NA | NA | Dominican Republic | DO | Santiago | 1457 | Pedro García | 4.86398 | NA | 19.5500 | -70.6390 | (19.55, -70.638999999999996) | Landslide | Mudslide | Medium | Downpour | NA | NA | 0 | NA | http://us.puerto-plata-live.com/puerto-plata/news/year-2009/february-2009.html |
| 1178 | 9/20/09 | NA | NA | Dominican Republic | DO | Santiago | 23304 | Tamboril | 4.31327 | NA | 19.5167 | -70.5866 | (19.5167, -70.586600000000004) | Landslide | Landslide | Small | Downpour | NA | NA | NA | NA | http://www.laht.com/article.asp?CategoryId=14092&ArticleId=327347 |
| 3569 | 6/3/11 | NA | NA | Dominican Republic | DO | Santiago | 9853 | San José de Las Matas | 2.72462 | NA | 19.3556 | -70.9189 | (19.355599999999999, -70.918899999999994) | Landslide | Landslide | Medium | Downpour | NA | NA | 1 | NA | http://english.peopledaily.com.cn/90001/90777/90852/7402423.html |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_DR, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_DR, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_DR, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_DR <- df_DR %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_DR$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_DR, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_DR$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 4.31327 |
| 1.10868 |
| 2.72462 |
| 4.86398 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_DR$distance
names(distance) <- df_DR$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Pedro García 4.863980 4.863980 37.384891 37.384891
## Tamboril 4.313270 9.177250 33.152096 70.536987
## San José de Las Matas 2.724620 11.901870 20.941620 91.478608
## Santiago de los Caballeros 1.108680 13.010550 8.521392 100.000000stem(df_DR$"distance")##
## The decimal point is at the |
##
## 1 | 1
## 2 | 7
## 3 |
## 4 | 39head(df_DR)## # A tibble: 4 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 1178 9/20/09 <NA> <NA> Dominican R~ DO Sant~ 23304
## 2 388 12/11/07 <NA> <NA> Dominican R~ DO Sant~ 1200000
## 3 3569 6/3/11 <NA> <NA> Dominican R~ DO Sant~ 9853
## 4 984 2/12/09 <NA> <NA> Dominican R~ DO Sant~ 1457
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_DR))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1178 | 9/20/09 | NA | NA | Dominican Republic | DO | Santiago | 23304 | Tamboril | 4.31327 | NA | 19.5167 | -70.5866 | (19.5167, -70.586600000000004) | Landslide | Landslide | Small | Downpour | NA | NA | NA | NA | http://www.laht.com/article.asp?CategoryId=14092&ArticleId=327347 | 33.152096 | 16.57605 |
| 388 | 12/11/07 | NA | NA | Dominican Republic | DO | Santiago | 1200000 | Santiago de los Caballeros | 1.10868 | NA | 19.4550 | -70.7070 | (19.454999999999998, -70.706999999999994) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Olga | NA | 17 | news.gossip.info | http://clutchmagonline.com/newsgossipinfo/caribbean-storm-death-toll-rises/ | 8.521392 | 37.41279 |
| 3569 | 6/3/11 | NA | NA | Dominican Republic | DO | Santiago | 9853 | San José de Las Matas | 2.72462 | NA | 19.3556 | -70.9189 | (19.355599999999999, -70.918899999999994) | Landslide | Landslide | Medium | Downpour | NA | NA | 1 | NA | http://english.peopledaily.com.cn/90001/90777/90852/7402423.html | 20.941620 | 52.14430 |
| 984 | 2/12/09 | NA | NA | Dominican Republic | DO | Santiago | 1457 | Pedro García | 4.86398 | NA | 19.5500 | -70.6390 | (19.55, -70.638999999999996) | Landslide | Mudslide | Medium | Downpour | NA | NA | 0 | NA | http://us.puerto-plata-live.com/puerto-plata/news/year-2009/february-2009.html | 37.384892 | 81.30755 |
stem(df_DR$"distance")##
## The decimal point is at the |
##
## 1 | 1
## 2 | 7
## 3 |
## 4 | 39stem(df_DR$"distance", scale = 2)##
## The decimal point is at the |
##
## 1 | 1
## 1 |
## 2 |
## 2 | 7
## 3 |
## 3 |
## 4 | 3
## 4 | 9Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 1.10868 | 1 | 25 | 25 | 25 | 25 |
| 2.72462 | 1 | 25 | 25 | 50 | 50 |
| 4.31327 | 1 | 25 | 25 | 75 | 75 |
| 4.86398 | 1 | 25 | 25 | 100 | 100 |
| Total | 4 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 5 obs. of 5 variables:
## $ n : num 1 1 1 1 4
## $ % : num 25 25 25 25 100
## $ val% : num 25 25 25 25 100
## $ %cum : num 25 50 75 100 100
## $ val%cum: num 25 50 75 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 1.10868 | 1 |
| 2.72462 | 1 |
| 4.31327 | 1 |
| 4.86398 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 1.10868 3.10868 5.10868distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (1.11,3.11] | 1 | 0.3333333 | 1 |
| (3.11,5.11] | 2 | 0.6666667 | 3 |
str(Freq_table)## 'data.frame': 2 obs. of 4 variables:
## $ distance: Factor w/ 2 levels "(1.11,3.11]",..: 1 2
## $ Freq : int 1 2
## $ Rel_Freq: num 0.333 0.667
## $ Cum_Freq: int 1 3df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (1.11,3.11] | 1 |
| (3.11,5.11] | 2 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_DR)## Warning in min(x): ningún argumento finito para min; retornando Inf## Warning in max(x): ningun argumento finito para max; retornando -Inf## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 4.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 3.880000e+02 NA NA NA NA NA
## max 3.569000e+03 NA NA NA NA NA
## range 3.181000e+03 NA NA NA NA NA
## sum 6.119000e+03 NA NA NA NA NA
## median 1.081000e+03 NA NA NA NA NA
## mean 1.529750e+03 NA NA NA NA NA
## SE.mean 7.002205e+02 NA NA NA NA NA
## CI.mean.0.95 2.228414e+03 NA NA NA NA NA
## var 1.961235e+06 NA NA NA NA NA
## std.dev 1.400441e+03 NA NA NA NA NA
## coef.var 9.154705e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 4.000000e+00 NA 4.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 1.457000e+03 NA 1.1086800 NA
## max NA 1.200000e+06 NA 4.8639800 NA
## range NA 1.198543e+06 NA 3.7553000 NA
## sum NA 1.234614e+06 NA 13.0105500 NA
## median NA 1.657850e+04 NA 3.5189450 NA
## mean NA 3.086535e+05 NA 3.2526375 NA
## SE.mean NA 2.971496e+05 NA 0.8464003 NA
## CI.mean.0.95 NA 9.456625e+05 NA 2.6936236 NA
## var NA 3.531914e+11 NA 2.8655741 NA
## std.dev NA 5.942991e+05 NA 1.6928007 NA
## coef.var NA 1.925457e+00 NA 0.5204394 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 4.000000000 4.000000e+00 NA NA NA
## nbr.null 0.000000000 0.000000e+00 NA NA NA
## nbr.na 0.000000000 0.000000e+00 NA NA NA
## min 19.355600000 -7.091890e+01 NA NA NA
## max 19.550000000 -7.058660e+01 NA NA NA
## range 0.194400000 3.323000e-01 NA NA NA
## sum 77.877300000 -2.828515e+02 NA NA NA
## median 19.485850000 -7.067300e+01 NA NA NA
## mean 19.469325000 -7.071287e+01 NA NA NA
## SE.mean 0.042711657 7.296329e-02 NA NA NA
## CI.mean.0.95 0.135927554 2.322018e-01 NA NA NA
## var 0.007297143 2.129457e-02 NA NA NA
## std.dev 0.085423314 1.459266e-01 NA NA NA
## coef.var 0.004387585 -2.063649e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 0 3.000000 NA
## nbr.null NA NA NA 0 1.000000 NA
## nbr.na NA NA NA 4 1.000000 NA
## min NA NA NA Inf 0.000000 NA
## max NA NA NA -Inf 17.000000 NA
## range NA NA NA -Inf 17.000000 NA
## sum NA NA NA 0 18.000000 NA
## median NA NA NA NA 1.000000 NA
## mean NA NA NA NaN 6.000000 NA
## SE.mean NA NA NA NA 5.507571 NA
## CI.mean.0.95 NA NA NA NaN 23.697163 NA
## var NA NA NA NA 91.000000 NA
## std.dev NA NA NA NA 9.539392 NA
## coef.var NA NA NA NA 1.589899 NA
## source_link prop ypos
## nbr.val NA 4.0000000 4.000000
## nbr.null NA 0.0000000 0.000000
## nbr.na NA 0.0000000 0.000000
## min NA 8.5213923 16.576048
## max NA 37.3848915 81.307554
## range NA 28.8634992 64.731506
## sum NA 100.0000000 187.440692
## median NA 27.0468581 44.778545
## mean NA 25.0000000 46.860173
## SE.mean NA 6.5054923 13.604305
## CI.mean.0.95 NA 20.7033799 43.294969
## var NA 169.2857203 740.308432
## std.dev NA 13.0109846 27.208610
## coef.var NA 0.5204394 0.580634boxplot(data, horizontal=TRUE, col='green')
Gráfico para Honduras
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_HD <- subset(df, country_name == "Honduras")
knitr::kable(head(df_HD))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 854 | 10/19/08 | NA | NA | Honduras | HN | Copán | 4752 | Corquín | 0.43391 | NA | 14.5637 | -88.8693 | (14.563700000000001, -88.869299999999996) | Landslide | Landslide | Large | Tropical cyclone | Tropical Depression 16 | NA | 23 | NA | http://www.chron.com/disp/story.mpl/ap/world/6068144.html |
| 855 | 10/20/08 | NA | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 2.99239 | NA | 14.1080 | -87.2137 | (14.108000000000001, -87.213700000000003) | Landslide | Mudslide | Large | Tropical cyclone | Tropical Depression 16 | NA | 29 | NA | http://in.ibtimes.com/articles/20081021/honduras-landslide-tegucigalpa-victim.htm |
| 2062 | 7/12/10 | 5:30:00 | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 0.98377 | NA | 14.0831 | -87.1978 | (14.0831, -87.197800000000001) | Landslide | Mudslide | Medium | Downpour | NA | NA | 1 | NA | http://mdn.mainichi.jp/mdnnews/news/20100713p2a00m0na013000c.html |
| 2093 | 7/18/10 | NA | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 1.24404 | NA | 14.0814 | -87.1953 | (14.0814, -87.195300000000003) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.insidecostarica.com/dailynews/2010/july/19/centralamerica10071903.htm |
| 2217 | 8/7/10 | Overnight | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 2.21442 | NA | 14.0783 | -87.2270 | (14.0783, -87.227000000000004) | Landslide | Mudslide | Medium | Downpour | NA | NA | 3 | NA | NA |
| 2358 | 8/29/10 | 4:30:00 | NA | Honduras | HN | Francisco Morazán | 2288 | Santa Lucía | 4.75791 | NA | 14.1015 | -87.1607 | (14.1015, -87.160700000000006) | Landslide | Rockfall | Medium | Downpour | NA | NA | 5 | NA | NA |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_HD, aes(fill= state, y=distance, x=country_name)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_HD, aes(fill=state, y=distance, x=country_name)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_HD, aes(x=country_name, y=distance, fill=state)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_HD <- df_HD %>%
arrange(desc(state)) %>%
mutate(prop = distance / sum(df_HD$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_HD, aes(x=country_name, y=prop, fill=state)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4## Warning in RColorBrewer::brewer.pal(n, pal): n too large, allowed maximum for palette Greens is 9
## Returning the palette you asked for with that many colors
Grafico de series temporales
library(forecast)
data<- ts(df_HD$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 0.31238 |
| 6.66574 |
| 2.91594 |
| 2.87349 |
| 2.00805 |
| 5.79867 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_HD$distance
names(distance) <- df_HD$state
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por estados"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Colón 36.3762900 36.3762900 21.8907391 21.8907391
## Comayagua 17.2861300 53.6624200 10.4025496 32.2932888
## Choluteca 11.6723700 65.3347900 7.0242679 39.3175567
## Comayagua 8.5258400 73.8606300 5.1307305 44.4482872
## Comayagua 7.2857500 81.1463800 4.3844618 48.8327489
## Yoro 6.6657400 87.8121200 4.0113485 52.8440974
## Copán 5.8972100 93.7093300 3.5488579 56.3929554
## Ocotepeque 5.7986700 99.5080000 3.4895580 59.8825133
## Francisco Morazán 4.7579100 104.2659100 2.8632432 62.7457566
## La Paz 4.6913300 108.9572400 2.8231763 65.5689329
## Comayagua 4.5336200 113.4908600 2.7282687 68.2972016
## Choluteca 3.6959600 117.1868200 2.2241767 70.5213783
## Francisco Morazán 3.6396200 120.8264400 2.1902721 72.7116504
## Francisco Morazán 3.5439900 124.3704300 2.1327233 74.8443736
## Cortés 3.5373700 127.9078000 2.1287395 76.9731131
## Francisco Morazán 3.2528100 131.1606100 1.9574953 78.9306084
## Francisco Morazán 3.1298600 134.2904700 1.8835057 80.8141140
## Francisco Morazán 2.9923900 137.2828600 1.8007782 82.6148922
## Santa Bárbara 2.9159400 140.1988000 1.7547716 84.3696639
## Francisco Morazán 2.9132600 143.1120600 1.7531588 86.1228227
## Santa Bárbara 2.8734900 145.9855500 1.7292258 87.8520485
## Francisco Morazán 2.2144200 148.1999700 1.3326068 89.1846553
## Francisco Morazán 2.0083000 150.2082700 1.2085667 90.3932220
## Ocotepeque 2.0080500 152.2163200 1.2084162 91.6016382
## El Paraíso 1.9005200 154.1168400 1.1437062 92.7453444
## Francisco Morazán 1.8589700 155.9758100 1.1187020 93.8640463
## Copán 1.3909500 157.3667600 0.8370541 94.7011005
## Francisco Morazán 1.3058300 158.6725900 0.7858301 95.4869306
## Francisco Morazán 1.2440400 159.9166300 0.7486458 96.2355763
## Francisco Morazán 1.2363900 161.1530200 0.7440421 96.9796184
## Francisco Morazán 0.9837700 162.1367900 0.5920189 97.5716373
## Cortés 0.9705700 163.1073600 0.5840754 98.1557127
## Francisco Morazán 0.9155200 164.0228800 0.5509470 98.7066598
## Copán 0.7441400 164.7670200 0.4478130 99.1544727
## Copán 0.4339100 165.2009300 0.2611209 99.4155937
## Choluteca 0.3698700 165.5708000 0.2225826 99.6381762
## Yoro 0.3123800 165.8831800 0.1879859 99.8261621
## Copán 0.2888700 166.1720500 0.1738379 100.0000000stem(df_HD$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 000011111111222223333334444
## 0 | 55566779
## 1 | 2
## 1 | 7
## 2 |
## 2 |
## 3 |
## 3 | 6head(df_HD)## # A tibble: 6 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 6202 5/20/14 <NA> <NA> Honduras HN Yoro 15774
## 2 7467 1/22/15 <NA> <NA> Honduras HN Yoro 2188
## 3 6691 10/14/14 Night <NA> Honduras HN Sant~ 1759
## 4 7464 9/28/15 Morning <NA> Honduras HN Sant~ 1811
## 5 6672 10/13/14 <NA> <NA> Honduras HN Ocot~ 2389
## 6 7462 9/25/15 <NA> <NA> Honduras HN Ocot~ 1416
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_HD))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 6202 | 5/20/14 | NA | NA | Honduras | HN | Yoro | 15774 | Yoro | 0.31238 | Unknown | 15.0666 | -87.3245 | (15.066599999999999, -87.3245) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | Prensa | http://www.laprensa.hn/lasultimas24/711060-98/deslizamientos-de-tierra-dejar%C3%ADa-incomunicadas-30-aldeas-en-yoro | 0.1879859 | 0.0939929 |
| 7467 | 1/22/15 | NA | NA | Honduras | HN | Yoro | 2188 | La Sarrosa | 6.66574 | Above road | 15.1754 | -87.8164 | (15.1754, -87.816400000000002) | Landslide | Rockfall | Small | Continuous rain | NA | 0 | 0 | La Prensa | http://www.laprensa.hn/honduras/787961-410/conductores-tienen-que-maniobrar-para-no-chocar-con-las-rocas-que-cubren | 4.0113485 | 2.1936601 |
| 6691 | 10/14/14 | Night | NA | Honduras | HN | Santa Bárbara | 1759 | Agualote | 2.91594 | Mine construction | 15.3090 | -88.5510 | (15.308999999999999, -88.551000000000002) | Landslide | Landslide | Medium | Rain | NA | 0 | 1 | Mundo | http://elmundo.com.sv/honduras-muere-un-minero-y-rescatan-a-otros-cinco-soterrados | 1.7547716 | 5.0767202 |
| 7464 | 9/28/15 | Morning | NA | Honduras | HN | Santa Bárbara | 1811 | Ilama | 2.87349 | Above road | 15.0909 | -88.2072 | (15.0909, -88.2072) | Landslide | Rockfall | Small | Rain | NA | 0 | 0 | Canal 6 | http://www.canal6.com.hn/destacado/derrumbes-incomunican-paso-entre-san-pedro-sula-y-santa-barbara.html | 1.7292258 | 6.8187189 |
| 6672 | 10/13/14 | NA | NA | Honduras | HN | Ocotepeque | 2389 | Sinuapa | 2.00805 | Below road | 14.4579 | -89.1666 | (14.4579, -89.166600000000003) | Landslide | Landslide | Medium | Downpour | NA | 0 | 0 | La Prensa | http://www.laprensa.hn/economia/757783-410/evac%C3%BAan-a-familias-por-deslizamientos-en-ocotepeque | 1.2084162 | 8.2875399 |
| 7462 | 9/25/15 | NA | NA | Honduras | HN | Ocotepeque | 1416 | La Labor | 5.79867 | Above road | 14.4810 | -89.0537 | (14.481, -89.053700000000006) | Landslide | Landslide | Small | Rain | NA | 0 | 0 | Tiempo | http://www.tiempo.hn/lluvias-comienzan-a-causar-deslizamientos-en-carreteras-del-occidente-de-honduras/ | 3.4895580 | 10.6365270 |
stem(df_HD$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 000011111111222223333334444
## 0 | 55566779
## 1 | 2
## 1 | 7
## 2 |
## 2 |
## 3 |
## 3 | 6stem(df_HD$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 33447900223499
## 2 | 0029990135567
## 4 | 57889
## 6 | 73
## 8 | 5
## 10 | 7
## 12 |
## 14 |
## 16 | 3
## 18 |
## 20 |
## 22 |
## 24 |
## 26 |
## 28 |
## 30 |
## 32 |
## 34 |
## 36 | 4Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.28887 | 1 | 2.6 | 2.6 | 2.6 | 2.6 |
| 0.31238 | 1 | 2.6 | 2.6 | 5.3 | 5.3 |
| 0.36987 | 1 | 2.6 | 2.6 | 7.9 | 7.9 |
| 0.43391 | 1 | 2.6 | 2.6 | 10.5 | 10.5 |
| 0.74414 | 1 | 2.6 | 2.6 | 13.2 | 13.2 |
| 0.91552 | 1 | 2.6 | 2.6 | 15.8 | 15.8 |
| 0.97057 | 1 | 2.6 | 2.6 | 18.4 | 18.4 |
| 0.98377 | 1 | 2.6 | 2.6 | 21.1 | 21.1 |
| 1.23639 | 1 | 2.6 | 2.6 | 23.7 | 23.7 |
| 1.24404 | 1 | 2.6 | 2.6 | 26.3 | 26.3 |
| 1.30583 | 1 | 2.6 | 2.6 | 28.9 | 28.9 |
| 1.39095 | 1 | 2.6 | 2.6 | 31.6 | 31.6 |
| 1.85897 | 1 | 2.6 | 2.6 | 34.2 | 34.2 |
| 1.90052 | 1 | 2.6 | 2.6 | 36.8 | 36.8 |
| 2.00805 | 1 | 2.6 | 2.6 | 39.5 | 39.5 |
| 2.0083 | 1 | 2.6 | 2.6 | 42.1 | 42.1 |
| 2.21442 | 1 | 2.6 | 2.6 | 44.7 | 44.7 |
| 2.87349 | 1 | 2.6 | 2.6 | 47.4 | 47.4 |
| 2.91326 | 1 | 2.6 | 2.6 | 50.0 | 50.0 |
| 2.91594 | 1 | 2.6 | 2.6 | 52.6 | 52.6 |
| 2.99239 | 1 | 2.6 | 2.6 | 55.3 | 55.3 |
| 3.12986 | 1 | 2.6 | 2.6 | 57.9 | 57.9 |
| 3.25281 | 1 | 2.6 | 2.6 | 60.5 | 60.5 |
| 3.53737 | 1 | 2.6 | 2.6 | 63.2 | 63.2 |
| 3.54399 | 1 | 2.6 | 2.6 | 65.8 | 65.8 |
| 3.63962 | 1 | 2.6 | 2.6 | 68.4 | 68.4 |
| 3.69596 | 1 | 2.6 | 2.6 | 71.1 | 71.1 |
| 4.53362 | 1 | 2.6 | 2.6 | 73.7 | 73.7 |
| 4.69133 | 1 | 2.6 | 2.6 | 76.3 | 76.3 |
| 4.75791 | 1 | 2.6 | 2.6 | 78.9 | 78.9 |
| 5.79867 | 1 | 2.6 | 2.6 | 81.6 | 81.6 |
| 5.89721 | 1 | 2.6 | 2.6 | 84.2 | 84.2 |
| 6.66574 | 1 | 2.6 | 2.6 | 86.8 | 86.8 |
| 7.28575 | 1 | 2.6 | 2.6 | 89.5 | 89.5 |
| 8.52584 | 1 | 2.6 | 2.6 | 92.1 | 92.1 |
| 11.67237 | 1 | 2.6 | 2.6 | 94.7 | 94.7 |
| 17.28613 | 1 | 2.6 | 2.6 | 97.4 | 97.4 |
| 36.37629 | 1 | 2.6 | 2.6 | 100.0 | 100.0 |
| Total | 38 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 39 obs. of 5 variables:
## $ n : num 1 1 1 1 1 1 1 1 1 1 ...
## $ % : num 2.6 2.6 2.6 2.6 2.6 2.6 2.6 2.6 2.6 2.6 ...
## $ val% : num 2.6 2.6 2.6 2.6 2.6 2.6 2.6 2.6 2.6 2.6 ...
## $ %cum : num 2.6 5.3 7.9 10.5 13.2 15.8 18.4 21.1 23.7 26.3 ...
## $ val%cum: num 2.6 5.3 7.9 10.5 13.2 15.8 18.4 21.1 23.7 26.3 ...x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.28887 | 1 |
| 0.31238 | 1 |
| 0.36987 | 1 |
| 0.43391 | 1 |
| 0.74414 | 1 |
| 0.91552 | 1 |
| 0.97057 | 1 |
| 0.98377 | 1 |
| 1.23639 | 1 |
| 1.24404 | 1 |
| 1.30583 | 1 |
| 1.39095 | 1 |
| 1.85897 | 1 |
| 1.90052 | 1 |
| 2.00805 | 1 |
| 2.0083 | 1 |
| 2.21442 | 1 |
| 2.87349 | 1 |
| 2.91326 | 1 |
| 2.91594 | 1 |
| 2.99239 | 1 |
| 3.12986 | 1 |
| 3.25281 | 1 |
| 3.53737 | 1 |
| 3.54399 | 1 |
| 3.63962 | 1 |
| 3.69596 | 1 |
| 4.53362 | 1 |
| 4.69133 | 1 |
| 4.75791 | 1 |
| 5.79867 | 1 |
| 5.89721 | 1 |
| 6.66574 | 1 |
| 7.28575 | 1 |
| 8.52584 | 1 |
| 11.67237 | 1 |
| 17.28613 | 1 |
| 36.37629 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.28887 6.28887 12.28887 18.28887 24.28887 30.28887 36.28887 42.28887distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.289,6.29] | 31 | 0.8378378 | 31 |
| (6.29,12.3] | 4 | 0.1081081 | 35 |
| (12.3,18.3] | 1 | 0.0270270 | 36 |
| (18.3,24.3] | 0 | 0.0000000 | 36 |
| (24.3,30.3] | 0 | 0.0000000 | 36 |
| (30.3,36.3] | 0 | 0.0000000 | 36 |
| (36.3,42.3] | 1 | 0.0270270 | 37 |
str(Freq_table)## 'data.frame': 7 obs. of 4 variables:
## $ distance: Factor w/ 7 levels "(0.289,6.29]",..: 1 2 3 4 5 6 7
## $ Freq : int 31 4 1 0 0 0 1
## $ Rel_Freq: num 0.838 0.108 0.027 0 0 ...
## $ Cum_Freq: int 31 35 36 36 36 36 37df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.289,6.29] | 31 |
| (6.29,12.3] | 4 |
| (12.3,18.3] | 1 |
| (18.3,24.3] | 0 |
| (24.3,30.3] | 0 |
| (30.3,36.3] | 0 |
| (36.3,42.3] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_HD)## id date time continent_code country_name country_code
## nbr.val 3.800000e+01 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 8.540000e+02 NA NA NA NA NA
## max 7.485000e+03 NA NA NA NA NA
## range 6.631000e+03 NA NA NA NA NA
## sum 2.290210e+05 NA NA NA NA NA
## median 7.448500e+03 NA NA NA NA NA
## mean 6.026868e+03 NA NA NA NA NA
## SE.mean 3.671138e+02 NA NA NA NA NA
## CI.mean.0.95 7.438432e+02 NA NA NA NA NA
## var 5.121356e+06 NA NA NA NA NA
## std.dev 2.263041e+03 NA NA NA NA NA
## coef.var 3.754921e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 3.800000e+01 NA 38.000000 NA
## nbr.null NA 0.000000e+00 NA 0.000000 NA
## nbr.na NA 0.000000e+00 NA 0.000000 NA
## min NA 1.043000e+03 NA 0.288870 NA
## max NA 8.508480e+05 NA 36.376290 NA
## range NA 8.498050e+05 NA 36.087420 NA
## sum NA 7.001138e+06 NA 166.172050 NA
## median NA 1.936000e+03 NA 2.914600 NA
## mean NA 1.842405e+05 NA 4.372949 NA
## SE.mean NA 5.663200e+04 NA 1.023393 NA
## CI.mean.0.95 NA 1.147473e+05 NA 2.073592 NA
## var NA 1.218729e+11 NA 39.798695 NA
## std.dev NA 3.491031e+05 NA 6.308621 NA
## coef.var NA 1.894823e+00 NA 1.442647 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 38.00000000 3.800000e+01 NA NA NA
## nbr.null 0.00000000 0.000000e+00 NA NA NA
## nbr.na 0.00000000 0.000000e+00 NA NA NA
## min 13.28610000 -8.916660e+01 NA NA NA
## max 15.52270000 -8.526500e+01 NA NA NA
## range 2.23660000 3.901600e+00 NA NA NA
## sum 546.00580000 -3.329927e+03 NA NA NA
## median 14.20695000 -8.728760e+01 NA NA NA
## mean 14.36857368 -8.762966e+01 NA NA NA
## SE.mean 0.08447952 1.301577e-01 NA NA NA
## CI.mean.0.95 0.17117178 2.637245e-01 NA NA NA
## var 0.27119802 6.437585e-01 NA NA NA
## std.dev 0.52076676 8.023457e-01 NA NA NA
## coef.var 0.03624346 -9.156096e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities
## nbr.val NA NA NA 29.0000000 38.0000000
## nbr.null NA NA NA 26.0000000 25.0000000
## nbr.na NA NA NA 9.0000000 0.0000000
## min NA NA NA 0.0000000 0.0000000
## max NA NA NA 3.0000000 29.0000000
## range NA NA NA 3.0000000 29.0000000
## sum NA NA NA 6.0000000 86.0000000
## median NA NA NA 0.0000000 0.0000000
## mean NA NA NA 0.2068966 2.2631579
## SE.mean NA NA NA 0.1253499 0.9774733
## CI.mean.0.95 NA NA NA 0.2567675 1.9805491
## var NA NA NA 0.4556650 36.3072546
## std.dev NA NA NA 0.6750296 6.0255502
## coef.var NA NA NA 3.2626433 2.6624524
## source_name source_link prop ypos
## nbr.val NA NA 38.0000000 3.800000e+01
## nbr.null NA NA 0.0000000 0.000000e+00
## nbr.na NA NA 0.0000000 0.000000e+00
## min NA NA 0.1738379 9.399294e-02
## max NA NA 21.8907391 9.988871e+01
## range NA NA 21.7169012 9.979472e+01
## sum NA NA 100.0000000 1.347990e+03
## median NA NA 1.7539652 3.219648e+01
## mean NA NA 2.6315789 3.547342e+01
## SE.mean NA NA 0.6158637 4.046533e+00
## CI.mean.0.95 NA NA 1.2478585 8.199055e+00
## var NA NA 14.4129500 6.222284e+02
## std.dev NA NA 3.7964391 2.494451e+01
## coef.var NA NA 1.4426469 7.031887e-01boxplot(data, horizontal=TRUE, col='green')
Gráfico para Choluteca (Honduras)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_HD <- subset(df, country_name == "Honduras")
knitr::kable(head(df_HD)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 854 | 10/19/08 | NA | NA | Honduras | HN | Copán | 4752 | Corquín | 0.43391 | NA | 14.5637 | -88.8693 | (14.563700000000001, -88.869299999999996) | Landslide | Landslide | Large | Tropical cyclone | Tropical Depression 16 | NA | 23 | NA | http://www.chron.com/disp/story.mpl/ap/world/6068144.html |
| 855 | 10/20/08 | NA | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 2.99239 | NA | 14.1080 | -87.2137 | (14.108000000000001, -87.213700000000003) | Landslide | Mudslide | Large | Tropical cyclone | Tropical Depression 16 | NA | 29 | NA | http://in.ibtimes.com/articles/20081021/honduras-landslide-tegucigalpa-victim.htm |
| 2062 | 7/12/10 | 5:30:00 | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 0.98377 | NA | 14.0831 | -87.1978 | (14.0831, -87.197800000000001) | Landslide | Mudslide | Medium | Downpour | NA | NA | 1 | NA | http://mdn.mainichi.jp/mdnnews/news/20100713p2a00m0na013000c.html |
| 2093 | 7/18/10 | NA | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 1.24404 | NA | 14.0814 | -87.1953 | (14.0814, -87.195300000000003) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.insidecostarica.com/dailynews/2010/july/19/centralamerica10071903.htm |
| 2217 | 8/7/10 | Overnight | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 2.21442 | NA | 14.0783 | -87.2270 | (14.0783, -87.227000000000004) | Landslide | Mudslide | Medium | Downpour | NA | NA | 3 | NA | NA |
| 2358 | 8/29/10 | 4:30:00 | NA | Honduras | HN | Francisco Morazán | 2288 | Santa Lucía | 4.75791 | NA | 14.1015 | -87.1607 | (14.1015, -87.160700000000006) | Landslide | Rockfall | Medium | Downpour | NA | NA | 5 | NA | NA |
library(dplyr)
df_HD <- subset(df, state == "Choluteca")
knitr::kable(head(df_HD))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 6123 | 7/2/14 | 16:30 | NA | Honduras | HN | Choluteca | 75872 | Ciudad Choluteca | 3.69596 | Mine construction | 13.2875 | -87.0325 | (13.2875, -87.032499999999999) | Landslide | Landslide | Small | Mining digging | NA | 3 | 8 | Sciency Thoughts | http://sciencythoughts.blogspot.com/2014/07/miners-trapped-by-honduran-landslide.html |
| 7448 | 6/11/15 | NA | NA | Honduras | HN | Choluteca | 1164 | Duyure | 11.67237 | Above road | 13.5807 | -86.9101 | (13.5807, -86.9101) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | El Heraldo | http://www.elheraldo.hn/regionales/848812-218/incomunicados-vecinos-del-municipio-de-morolica |
| 7449 | 12/15/15 | NA | NA | Honduras | HN | Choluteca | 1199 | Corpus | 0.36987 | Mine construction | 13.2861 | -87.0329 | (13.286099999999999, -87.032899999999998) | Landslide | Rockfall | Small | Rain | NA | 0 | 1 | La Prensa | http://www.laprensa.hn/sucesos/911394-410/minero-muere-soterrado-en-el-corpus-choluteca |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_HD, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_HD, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_HD, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_HD <- df_HD %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_HD$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_HD, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_HD$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 11.67237 |
| 0.36987 |
| 3.69596 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_HD$distance
names(distance) <- df_HD$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Duyure 11.672370 11.672370 74.165851 74.165851
## Ciudad Choluteca 3.695960 15.368330 23.484007 97.649858
## Corpus 0.369870 15.738200 2.350142 100.000000stem(df_HD$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 04
## 0 |
## 1 | 2head(df_HD)## # A tibble: 3 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 7448 6/11/15 <NA> <NA> Honduras HN Choluteca 1164
## 2 7449 12/15/15 <NA> <NA> Honduras HN Choluteca 1199
## 3 6123 7/2/14 16:30 <NA> Honduras HN Choluteca 75872
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_HD))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 7448 | 6/11/15 | NA | NA | Honduras | HN | Choluteca | 1164 | Duyure | 11.67237 | Above road | 13.5807 | -86.9101 | (13.5807, -86.9101) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | El Heraldo | http://www.elheraldo.hn/regionales/848812-218/incomunicados-vecinos-del-municipio-de-morolica | 74.165851 | 37.08293 |
| 7449 | 12/15/15 | NA | NA | Honduras | HN | Choluteca | 1199 | Corpus | 0.36987 | Mine construction | 13.2861 | -87.0329 | (13.286099999999999, -87.032899999999998) | Landslide | Rockfall | Small | Rain | NA | 0 | 1 | La Prensa | http://www.laprensa.hn/sucesos/911394-410/minero-muere-soterrado-en-el-corpus-choluteca | 2.350142 | 75.34092 |
| 6123 | 7/2/14 | 16:30 | NA | Honduras | HN | Choluteca | 75872 | Ciudad Choluteca | 3.69596 | Mine construction | 13.2875 | -87.0325 | (13.2875, -87.032499999999999) | Landslide | Landslide | Small | Mining digging | NA | 3 | 8 | Sciency Thoughts | http://sciencythoughts.blogspot.com/2014/07/miners-trapped-by-honduran-landslide.html | 23.484007 | 88.25800 |
stem(df_HD$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 04
## 0 |
## 1 | 2stem(df_HD$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 4
## 2 | 7
## 4 |
## 6 |
## 8 |
## 10 | 7Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.36987 | 1 | 33.3 | 33.3 | 33.3 | 33.3 |
| 3.69596 | 1 | 33.3 | 33.3 | 66.7 | 66.7 |
| 11.67237 | 1 | 33.3 | 33.3 | 100.0 | 100.0 |
| Total | 3 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 4 obs. of 5 variables:
## $ n : num 1 1 1 3
## $ % : num 33.3 33.3 33.3 100
## $ val% : num 33.3 33.3 33.3 100
## $ %cum : num 33.3 66.7 100 100
## $ val%cum: num 33.3 66.7 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.36987 | 1 |
| 3.69596 | 1 |
| 11.67237 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.36987 4.36987 8.36987 12.36987distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.37,4.37] | 1 | 0.5 | 1 |
| (4.37,8.37] | 0 | 0.0 | 1 |
| (8.37,12.4] | 1 | 0.5 | 2 |
str(Freq_table)## 'data.frame': 3 obs. of 4 variables:
## $ distance: Factor w/ 3 levels "(0.37,4.37]",..: 1 2 3
## $ Freq : int 1 0 1
## $ Rel_Freq: num 0.5 0 0.5
## $ Cum_Freq: int 1 1 2df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.37,4.37] | 1 |
| (4.37,8.37] | 0 |
| (8.37,12.4] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_HD)## id date time continent_code country_name country_code
## nbr.val 3.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 6.123000e+03 NA NA NA NA NA
## max 7.449000e+03 NA NA NA NA NA
## range 1.326000e+03 NA NA NA NA NA
## sum 2.102000e+04 NA NA NA NA NA
## median 7.448000e+03 NA NA NA NA NA
## mean 7.006667e+03 NA NA NA NA NA
## SE.mean 4.418334e+02 NA NA NA NA NA
## CI.mean.0.95 1.901056e+03 NA NA NA NA NA
## var 5.856503e+05 NA NA NA NA NA
## std.dev 7.652779e+02 NA NA NA NA NA
## coef.var 1.092214e-01 NA NA NA NA NA
## state population city distance location_description latitude
## nbr.val NA 3.000000e+00 NA 3.000000 NA 3.00000000
## nbr.null NA 0.000000e+00 NA 0.000000 NA 0.00000000
## nbr.na NA 0.000000e+00 NA 0.000000 NA 0.00000000
## min NA 1.164000e+03 NA 0.369870 NA 13.28610000
## max NA 7.587200e+04 NA 11.672370 NA 13.58070000
## range NA 7.470800e+04 NA 11.302500 NA 0.29460000
## sum NA 7.823500e+04 NA 15.738200 NA 40.15430000
## median NA 1.199000e+03 NA 3.695960 NA 13.28750000
## mean NA 2.607833e+04 NA 5.246067 NA 13.38476667
## SE.mean NA 2.489684e+04 NA 3.353543 NA 0.09796750
## CI.mean.0.95 NA 1.071224e+05 NA 14.429130 NA 0.42152013
## var NA 1.859557e+09 NA 33.738750 NA 0.02879289
## std.dev NA 4.312258e+04 NA 5.808507 NA 0.16968469
## coef.var NA 1.653579e+00 NA 1.107212 NA 0.01267745
## longitude geolocation hazard_type landslide_type
## nbr.val 3.000000e+00 NA NA NA
## nbr.null 0.000000e+00 NA NA NA
## nbr.na 0.000000e+00 NA NA NA
## min -8.703290e+01 NA NA NA
## max -8.691010e+01 NA NA NA
## range 1.228000e-01 NA NA NA
## sum -2.609755e+02 NA NA NA
## median -8.703250e+01 NA NA NA
## mean -8.699183e+01 NA NA NA
## SE.mean 4.086683e-02 NA NA NA
## CI.mean.0.95 1.758358e-01 NA NA NA
## var 5.010293e-03 NA NA NA
## std.dev 7.078343e-02 NA NA NA
## coef.var -8.136790e-04 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 3.000000 3.000000 NA
## nbr.null NA NA NA 2.000000 1.000000 NA
## nbr.na NA NA NA 0.000000 0.000000 NA
## min NA NA NA 0.000000 0.000000 NA
## max NA NA NA 3.000000 8.000000 NA
## range NA NA NA 3.000000 8.000000 NA
## sum NA NA NA 3.000000 9.000000 NA
## median NA NA NA 0.000000 1.000000 NA
## mean NA NA NA 1.000000 3.000000 NA
## SE.mean NA NA NA 1.000000 2.516611 NA
## CI.mean.0.95 NA NA NA 4.302653 10.828105 NA
## var NA NA NA 3.000000 19.000000 NA
## std.dev NA NA NA 1.732051 4.358899 NA
## coef.var NA NA NA 1.732051 1.452966 NA
## source_link prop ypos
## nbr.val NA 3.000000 3.0000000
## nbr.null NA 0.000000 0.0000000
## nbr.na NA 0.000000 0.0000000
## min NA 2.350142 37.0829256
## max NA 74.165851 88.2579965
## range NA 71.815710 51.1750708
## sum NA 100.000000 200.6818442
## median NA 23.484007 75.3409221
## mean NA 33.333333 66.8939481
## SE.mean NA 21.308300 15.3648462
## CI.mean.0.95 NA 91.682215 66.1095975
## var NA 1362.130955 708.2354967
## std.dev NA 36.907058 26.6126943
## coef.var NA 1.107212 0.3978341boxplot(data, horizontal=TRUE, col='green')
Gráfico para Colón (Honduras)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_HD <- subset(df, country_name == "Honduras")
knitr::kable(head(df_HD)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 854 | 10/19/08 | NA | NA | Honduras | HN | Copán | 4752 | Corquín | 0.43391 | NA | 14.5637 | -88.8693 | (14.563700000000001, -88.869299999999996) | Landslide | Landslide | Large | Tropical cyclone | Tropical Depression 16 | NA | 23 | NA | http://www.chron.com/disp/story.mpl/ap/world/6068144.html |
| 855 | 10/20/08 | NA | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 2.99239 | NA | 14.1080 | -87.2137 | (14.108000000000001, -87.213700000000003) | Landslide | Mudslide | Large | Tropical cyclone | Tropical Depression 16 | NA | 29 | NA | http://in.ibtimes.com/articles/20081021/honduras-landslide-tegucigalpa-victim.htm |
| 2062 | 7/12/10 | 5:30:00 | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 0.98377 | NA | 14.0831 | -87.1978 | (14.0831, -87.197800000000001) | Landslide | Mudslide | Medium | Downpour | NA | NA | 1 | NA | http://mdn.mainichi.jp/mdnnews/news/20100713p2a00m0na013000c.html |
| 2093 | 7/18/10 | NA | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 1.24404 | NA | 14.0814 | -87.1953 | (14.0814, -87.195300000000003) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.insidecostarica.com/dailynews/2010/july/19/centralamerica10071903.htm |
| 2217 | 8/7/10 | Overnight | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 2.21442 | NA | 14.0783 | -87.2270 | (14.0783, -87.227000000000004) | Landslide | Mudslide | Medium | Downpour | NA | NA | 3 | NA | NA |
| 2358 | 8/29/10 | 4:30:00 | NA | Honduras | HN | Francisco Morazán | 2288 | Santa Lucía | 4.75791 | NA | 14.1015 | -87.1607 | (14.1015, -87.160700000000006) | Landslide | Rockfall | Medium | Downpour | NA | NA | 5 | NA | NA |
library(dplyr)
df_HD <- subset(df, state == "Colón")
knitr::kable(head(df_HD))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2652 | 10/25/10 | NA | NA | Honduras | HN | Colón | 1441 | Cusuna | 36.37629 | NA | 15.5227 | -85.2650 | (15.5227, -85.265000000000001) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Richard | NA | 0 | NA | http://www.reliefweb.int/rw/RWFiles2010.nsf/FilesByRWDocUnidFilename/LSGZ-8ALBZE-full_report.pdf/$File/full_report.pdf |
| 2794 | 12/8/10 | NA | NA | Panama | PA | Colón | 1310 | El Giral | 1.80330 | NA | 9.2332 | -79.6961 | (9.2332000000000001, -79.696100000000001) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.portworld.com/news/i98731/Panama_Canal_disrupted_by_floods |
| 2795 | 12/9/10 | Morning | NA | Panama | PA | Colón | 1274 | Portobelo | 0.09491 | Deforested slope | 9.5493 | -79.6505 | (9.5493000000000006, -79.650499999999994) | Landslide | Mudslide | Medium | Downpour | NA | NA | 8 | Fox News Latino | http://latino.foxnews.com/latino/news/2010/12/09/heavy-rains-kill-panama-force-canal-close/ |
| 4632 | 11/25/12 | NA | NA | Panama | PA | Colón | 76643 | Colón | 0.16894 | NA | 9.3600 | -79.9001 | (9.36, -79.900099999999995) | Landslide | Landslide | Medium | Rain | NA | NA | 2 | NA | http://www.ndtv.com/article/world/two-dead-in-landslide-as-floods-hit-panama-297138 |
| 4879 | 5/28/13 | NA | NA | Panama | PA | Colón | 1274 | Portobelo | 2.67409 | NA | 9.5676 | -79.6667 | (9.5676000000000005, -79.666700000000006) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | www.newsroompanama.com | http://www.newsroompanama.com/panama/5804-rain-brings-floods-landslides-and-traffic-chaos-to-colon.html |
| 4880 | 5/28/13 | NA | NA | Panama | PA | Colón | 3302 | Margarita | 0.74760 | NA | 9.3381 | -79.8897 | (9.3381000000000007, -79.889700000000005) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | NA |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_HD, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_HD, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_HD, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_HD <- df_HD %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_HD$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_HD, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_HD$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 0.09491 |
| 2.67409 |
| 4.74914 |
| 0.18619 |
| 2.28589 |
| 0.74760 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_HD$distance
names(distance) <- df_HD$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Cusuna 36.3762900 36.3762900 71.7525220 71.7525220
## Nuevo San Juan 4.7491400 41.1254300 9.3677165 81.1202386
## Portobelo 2.6740900 43.7995200 5.2746638 86.3949024
## María Chiquita 2.2858900 46.0854100 4.5089363 90.9038387
## El Giral 1.8033000 47.8887100 3.5570236 94.4608623
## Margarita 0.7674000 48.6561100 1.5137026 95.9745649
## Margarita 0.7476000 49.4037100 1.4746470 97.4492119
## Cativá 0.6394800 50.0431900 1.2613794 98.7105913
## Colón 0.2036500 50.2468400 0.4017012 99.1122925
## Nueva Providencia 0.1861900 50.4330300 0.3672613 99.4795538
## Colón 0.1689400 50.6019700 0.3332355 99.8127893
## Portobelo 0.0949100 50.6968800 0.1872107 100.0000000stem(df_HD$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 00001112235
## 1 |
## 2 |
## 3 | 6head(df_HD)## # A tibble: 6 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 2795 12/9/10 Morning <NA> Panama PA Colón 1274
## 2 4879 5/28/13 <NA> <NA> Panama PA Colón 1274
## 3 6702 5/9/14 <NA> <NA> Panama PA Colón 1232
## 4 7450 9/7/15 <NA> <NA> Panama PA Colón 0
## 5 7451 7/2/15 <NA> <NA> Panama PA Colón 1146
## 6 4880 5/28/13 <NA> <NA> Panama PA Colón 3302
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_HD))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2795 | 12/9/10 | Morning | NA | Panama | PA | Colón | 1274 | Portobelo | 0.09491 | Deforested slope | 9.5493 | -79.6505 | (9.5493000000000006, -79.650499999999994) | Landslide | Mudslide | Medium | Downpour | NA | NA | 8 | Fox News Latino | http://latino.foxnews.com/latino/news/2010/12/09/heavy-rains-kill-panama-force-canal-close/ | 0.1872107 | 0.0936054 |
| 4879 | 5/28/13 | NA | NA | Panama | PA | Colón | 1274 | Portobelo | 2.67409 | NA | 9.5676 | -79.6667 | (9.5676000000000005, -79.666700000000006) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | www.newsroompanama.com | http://www.newsroompanama.com/panama/5804-rain-brings-floods-landslides-and-traffic-chaos-to-colon.html | 5.2746638 | 2.8245427 |
| 6702 | 5/9/14 | NA | NA | Panama | PA | Colón | 1232 | Nuevo San Juan | 4.74914 | Below road | 9.2924 | -79.7478 | (9.2924000000000007, -79.747799999999998) | Landslide | Landslide | Small | Downpour | NA | 0 | 0 | NEXtv | http://www.nexpanama.com/videos/deslizamiento-de-tierra-en-carretera-boyd-roosevelt-3800 | 9.3677165 | 10.1457328 |
| 7450 | 9/7/15 | NA | NA | Panama | PA | Colón | 0 | Nueva Providencia | 0.18619 | Unknown | 9.2619 | -79.8164 | (9.2619000000000007, -79.816400000000002) | Landslide | Landslide | Medium | Downpour | NA | 0 | 0 | Panamá América | http://www.panamaamerica.com.pa/provincias/un-colegio-y-20-casas-afectadas-por-las-lluvias-en-colon-991260 | 0.3672613 | 15.0132217 |
| 7451 | 7/2/15 | NA | NA | Panama | PA | Colón | 1146 | María Chiquita | 2.28589 | Mine construction | 9.4405 | -79.7754 | (9.4405000000000001, -79.775400000000005) | Landslide | Other | Medium | Construction | NA | 0 | 1 | El Siglo | http://elsiglo.com/panama/alud-tierra-obrero-colon-muere/23876592 | 4.5089363 | 17.4513205 |
| 4880 | 5/28/13 | NA | NA | Panama | PA | Colón | 3302 | Margarita | 0.74760 | NA | 9.3381 | -79.8897 | (9.3381000000000007, -79.889700000000005) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | NA | 1.4746470 | 20.4431121 |
stem(df_HD$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 00001112235
## 1 |
## 2 |
## 3 | 6stem(df_HD$"distance", scale = 2)##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 0000111223
## 0 | 5
## 1 |
## 1 |
## 2 |
## 2 |
## 3 |
## 3 | 6Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.09491 | 1 | 8.3 | 8.3 | 8.3 | 8.3 |
| 0.16894 | 1 | 8.3 | 8.3 | 16.7 | 16.7 |
| 0.18619 | 1 | 8.3 | 8.3 | 25.0 | 25.0 |
| 0.20365 | 1 | 8.3 | 8.3 | 33.3 | 33.3 |
| 0.63948 | 1 | 8.3 | 8.3 | 41.7 | 41.7 |
| 0.7476 | 1 | 8.3 | 8.3 | 50.0 | 50.0 |
| 0.7674 | 1 | 8.3 | 8.3 | 58.3 | 58.3 |
| 1.8033 | 1 | 8.3 | 8.3 | 66.7 | 66.7 |
| 2.28589 | 1 | 8.3 | 8.3 | 75.0 | 75.0 |
| 2.67409 | 1 | 8.3 | 8.3 | 83.3 | 83.3 |
| 4.74914 | 1 | 8.3 | 8.3 | 91.7 | 91.7 |
| 36.37629 | 1 | 8.3 | 8.3 | 100.0 | 100.0 |
| Total | 12 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 13 obs. of 5 variables:
## $ n : num 1 1 1 1 1 1 1 1 1 1 ...
## $ % : num 8.3 8.3 8.3 8.3 8.3 8.3 8.3 8.3 8.3 8.3 ...
## $ val% : num 8.3 8.3 8.3 8.3 8.3 8.3 8.3 8.3 8.3 8.3 ...
## $ %cum : num 8.3 16.7 25 33.3 41.7 50 58.3 66.7 75 83.3 ...
## $ val%cum: num 8.3 16.7 25 33.3 41.7 50 58.3 66.7 75 83.3 ...x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.09491 | 1 |
| 0.16894 | 1 |
| 0.18619 | 1 |
| 0.20365 | 1 |
| 0.63948 | 1 |
| 0.7476 | 1 |
| 0.7674 | 1 |
| 1.8033 | 1 |
| 2.28589 | 1 |
| 2.67409 | 1 |
| 4.74914 | 1 |
| 36.37629 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.09491 8.09491 16.09491 24.09491 32.09491 40.09491distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.0949,8.09] | 10 | 0.9090909 | 10 |
| (8.09,16.1] | 0 | 0.0000000 | 10 |
| (16.1,24.1] | 0 | 0.0000000 | 10 |
| (24.1,32.1] | 0 | 0.0000000 | 10 |
| (32.1,40.1] | 1 | 0.0909091 | 11 |
str(Freq_table)## 'data.frame': 5 obs. of 4 variables:
## $ distance: Factor w/ 5 levels "(0.0949,8.09]",..: 1 2 3 4 5
## $ Freq : int 10 0 0 0 1
## $ Rel_Freq: num 0.9091 0 0 0 0.0909
## $ Cum_Freq: int 10 10 10 10 11df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.0949,8.09] | 10 |
| (8.09,16.1] | 0 |
| (16.1,24.1] | 0 |
| (24.1,32.1] | 0 |
| (32.1,40.1] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_HD)## id date time continent_code country_name country_code
## nbr.val 1.200000e+01 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 2.652000e+03 NA NA NA NA NA
## max 7.452000e+03 NA NA NA NA NA
## range 4.800000e+03 NA NA NA NA NA
## sum 6.181400e+04 NA NA NA NA NA
## median 4.880500e+03 NA NA NA NA NA
## mean 5.151167e+03 NA NA NA NA NA
## SE.mean 5.231425e+02 NA NA NA NA NA
## CI.mean.0.95 1.151429e+03 NA NA NA NA NA
## var 3.284136e+06 NA NA NA NA NA
## std.dev 1.812219e+03 NA NA NA NA NA
## coef.var 3.518074e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 1.200000e+01 NA 12.000000 NA
## nbr.null NA 1.000000e+00 NA 0.000000 NA
## nbr.na NA 0.000000e+00 NA 0.000000 NA
## min NA 0.000000e+00 NA 0.094910 NA
## max NA 7.664300e+04 NA 36.376290 NA
## range NA 7.664300e+04 NA 36.281380 NA
## sum NA 1.971740e+05 NA 50.696880 NA
## median NA 1.375500e+03 NA 0.757500 NA
## mean NA 1.643117e+04 NA 4.224740 NA
## SE.mean NA 8.446243e+03 NA 2.950226 NA
## CI.mean.0.95 NA 1.859006e+04 NA 6.493404 NA
## var NA 8.560683e+08 NA 104.446004 NA
## std.dev NA 2.925864e+04 NA 10.219883 NA
## coef.var NA 1.780680e+00 NA 2.419056 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 12.0000000 12.00000000 NA NA NA
## nbr.null 0.0000000 0.00000000 NA NA NA
## nbr.na 0.0000000 0.00000000 NA NA NA
## min 9.2332000 -85.26500000 NA NA NA
## max 15.5227000 -79.65050000 NA NA NA
## range 6.2895000 5.61450000 NA NA NA
## sum 118.6112000 -963.01940000 NA NA NA
## median 9.3590500 -79.81925000 NA NA NA
## mean 9.8842667 -80.25161667 NA NA NA
## SE.mean 0.5134407 0.45651767 NA NA NA
## CI.mean.0.95 1.1300754 1.00478862 NA NA NA
## var 3.1634562 2.50090061 NA NA NA
## std.dev 1.7786107 1.58142360 NA NA NA
## coef.var 0.1799436 -0.01970582 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 4 12.0000000 NA
## nbr.null NA NA NA 4 8.0000000 NA
## nbr.na NA NA NA 8 0.0000000 NA
## min NA NA NA 0 0.0000000 NA
## max NA NA NA 0 8.0000000 NA
## range NA NA NA 0 8.0000000 NA
## sum NA NA NA 0 15.0000000 NA
## median NA NA NA 0 0.0000000 NA
## mean NA NA NA 0 1.2500000 NA
## SE.mean NA NA NA 0 0.7084447 NA
## CI.mean.0.95 NA NA NA 0 1.5592763 NA
## var NA NA NA 0 6.0227273 NA
## std.dev NA NA NA 0 2.4541245 NA
## coef.var NA NA NA NaN 1.9632996 NA
## source_link prop ypos
## nbr.val NA 12.0000000 1.200000e+01
## nbr.null NA 0.0000000 0.000000e+00
## nbr.na NA 0.0000000 0.000000e+00
## min NA 0.1872107 9.360537e-02
## max NA 71.7525220 9.936931e+01
## range NA 71.5653113 9.927570e+01
## sum NA 100.0000000 4.705863e+02
## median NA 1.4941748 2.119020e+01
## mean NA 8.3333333 3.921552e+01
## SE.mean NA 5.8193444 1.127004e+01
## CI.mean.0.95 NA 12.8082906 2.480520e+01
## var NA 406.3772270 1.524167e+03
## std.dev NA 20.1588002 3.904058e+01
## coef.var NA 2.4190560 9.955389e-01boxplot(data, horizontal=TRUE, col='green')
Gráfico para Comayagua (Honduras)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_HD <- subset(df, country_name == "Honduras")
knitr::kable(head(df_HD)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 854 | 10/19/08 | NA | NA | Honduras | HN | Copán | 4752 | Corquín | 0.43391 | NA | 14.5637 | -88.8693 | (14.563700000000001, -88.869299999999996) | Landslide | Landslide | Large | Tropical cyclone | Tropical Depression 16 | NA | 23 | NA | http://www.chron.com/disp/story.mpl/ap/world/6068144.html |
| 855 | 10/20/08 | NA | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 2.99239 | NA | 14.1080 | -87.2137 | (14.108000000000001, -87.213700000000003) | Landslide | Mudslide | Large | Tropical cyclone | Tropical Depression 16 | NA | 29 | NA | http://in.ibtimes.com/articles/20081021/honduras-landslide-tegucigalpa-victim.htm |
| 2062 | 7/12/10 | 5:30:00 | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 0.98377 | NA | 14.0831 | -87.1978 | (14.0831, -87.197800000000001) | Landslide | Mudslide | Medium | Downpour | NA | NA | 1 | NA | http://mdn.mainichi.jp/mdnnews/news/20100713p2a00m0na013000c.html |
| 2093 | 7/18/10 | NA | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 1.24404 | NA | 14.0814 | -87.1953 | (14.0814, -87.195300000000003) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.insidecostarica.com/dailynews/2010/july/19/centralamerica10071903.htm |
| 2217 | 8/7/10 | Overnight | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 2.21442 | NA | 14.0783 | -87.2270 | (14.0783, -87.227000000000004) | Landslide | Mudslide | Medium | Downpour | NA | NA | 3 | NA | NA |
| 2358 | 8/29/10 | 4:30:00 | NA | Honduras | HN | Francisco Morazán | 2288 | Santa Lucía | 4.75791 | NA | 14.1015 | -87.1607 | (14.1015, -87.160700000000006) | Landslide | Rockfall | Medium | Downpour | NA | NA | 5 | NA | NA |
library(dplyr)
df_HD <- subset(df, state == "Comayagua")
knitr::kable(head(df_HD))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2533 | 10/3/10 | 13:00 | NA | Honduras | HN | Comayagua | 1484 | El Rancho | 4.53362 | Unknown | 14.3898 | -87.7654 | (14.389799999999999, -87.7654) | Landslide | Mudslide | Medium | Rain | NA | NA | 0 | Honduras News | http://www.hondurasnews.com/2010/10/03/landslide-in-comayagua/ |
| 7454 | 10/16/15 | 18:00 | NA | Honduras | HN | Comayagua | 1389 | El Sauce | 7.28575 | Above road | 14.4837 | -87.7152 | (14.483700000000001, -87.715199999999996) | Landslide | Rockfall | Medium | Rain | NA | 0 | 0 | NTN24 | http://www.ntn24.com/video/lluvias-en-honduras-73259 |
| 7455 | 10/29/15 | NA | NA | Honduras | HN | Comayagua | 4673 | La Libertad | 17.28613 | Unknown | 14.9064 | -87.5930 | (14.9064, -87.593000000000004) | Landslide | Landslide | Medium | Continuous rain | NA | 0 | 1 | HRN | http://www.radiohrn.hn/l/noticias/menor-de-cinco-%C3%B1os-muere-en-vivienda-soterrada-por-las-lluvias-en-las-lajas-comayagua |
| 7456 | 10/16/15 | 23:00 | NA | Honduras | HN | Comayagua | 1470 | Concepción de Guasistagua | 8.52584 | Deforested slope | 14.5742 | -87.7286 | (14.574199999999999, -87.7286) | Landslide | Landslide | Medium | Rain | NA | 0 | 5 | La Prensa | http://www.laprensa.hn/honduras/891623-410/deslave-soterra-a-una-familia-en-comunidad-de-comayagua |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_HD, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_HD, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_HD, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_HD <- df_HD %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_HD$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_HD, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_HD$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 17.28613 |
| 7.28575 |
| 4.53362 |
| 8.52584 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_HD$distance
names(distance) <- df_HD$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## La Libertad 17.28613 17.28613 45.93546 45.93546
## Concepción de Guasistagua 8.52584 25.81197 22.65622 68.59168
## El Sauce 7.28575 33.09772 19.36086 87.95254
## El Rancho 4.53362 37.63134 12.04746 100.00000stem(df_HD$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 |
## 0 | 579
## 1 |
## 1 | 7head(df_HD)## # A tibble: 4 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 7455 10/29/15 <NA> <NA> Honduras HN Comayagua 4673
## 2 7454 10/16/15 18:00 <NA> Honduras HN Comayagua 1389
## 3 2533 10/3/10 13:00 <NA> Honduras HN Comayagua 1484
## 4 7456 10/16/15 23:00 <NA> Honduras HN Comayagua 1470
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_HD))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 7455 | 10/29/15 | NA | NA | Honduras | HN | Comayagua | 4673 | La Libertad | 17.28613 | Unknown | 14.9064 | -87.5930 | (14.9064, -87.593000000000004) | Landslide | Landslide | Medium | Continuous rain | NA | 0 | 1 | HRN | http://www.radiohrn.hn/l/noticias/menor-de-cinco-%C3%B1os-muere-en-vivienda-soterrada-por-las-lluvias-en-las-lajas-comayagua | 45.93546 | 22.96773 |
| 7454 | 10/16/15 | 18:00 | NA | Honduras | HN | Comayagua | 1389 | El Sauce | 7.28575 | Above road | 14.4837 | -87.7152 | (14.483700000000001, -87.715199999999996) | Landslide | Rockfall | Medium | Rain | NA | 0 | 0 | NTN24 | http://www.ntn24.com/video/lluvias-en-honduras-73259 | 19.36086 | 55.61589 |
| 2533 | 10/3/10 | 13:00 | NA | Honduras | HN | Comayagua | 1484 | El Rancho | 4.53362 | Unknown | 14.3898 | -87.7654 | (14.389799999999999, -87.7654) | Landslide | Mudslide | Medium | Rain | NA | NA | 0 | Honduras News | http://www.hondurasnews.com/2010/10/03/landslide-in-comayagua/ | 12.04746 | 71.32005 |
| 7456 | 10/16/15 | 23:00 | NA | Honduras | HN | Comayagua | 1470 | Concepción de Guasistagua | 8.52584 | Deforested slope | 14.5742 | -87.7286 | (14.574199999999999, -87.7286) | Landslide | Landslide | Medium | Rain | NA | 0 | 5 | La Prensa | http://www.laprensa.hn/honduras/891623-410/deslave-soterra-a-una-familia-en-comunidad-de-comayagua | 22.65622 | 88.67189 |
stem(df_HD$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 |
## 0 | 579
## 1 |
## 1 | 7stem(df_HD$"distance", scale = 2)##
## The decimal point is at the |
##
## 4 | 5
## 6 | 3
## 8 | 5
## 10 |
## 12 |
## 14 |
## 16 | 3Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 4.53362 | 1 | 25 | 25 | 25 | 25 |
| 7.28575 | 1 | 25 | 25 | 50 | 50 |
| 8.52584 | 1 | 25 | 25 | 75 | 75 |
| 17.28613 | 1 | 25 | 25 | 100 | 100 |
| Total | 4 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 5 obs. of 5 variables:
## $ n : num 1 1 1 1 4
## $ % : num 25 25 25 25 100
## $ val% : num 25 25 25 25 100
## $ %cum : num 25 50 75 100 100
## $ val%cum: num 25 50 75 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 4.53362 | 1 |
| 7.28575 | 1 |
| 8.52584 | 1 |
| 17.28613 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 4.53362 9.53362 14.53362 19.53362distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (4.53,9.53] | 2 | 0.6666667 | 2 |
| (9.53,14.5] | 0 | 0.0000000 | 2 |
| (14.5,19.5] | 1 | 0.3333333 | 3 |
str(Freq_table)## 'data.frame': 3 obs. of 4 variables:
## $ distance: Factor w/ 3 levels "(4.53,9.53]",..: 1 2 3
## $ Freq : int 2 0 1
## $ Rel_Freq: num 0.667 0 0.333
## $ Cum_Freq: int 2 2 3df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (4.53,9.53] | 2 |
| (9.53,14.5] | 0 |
| (14.5,19.5] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_HD)## id date time continent_code country_name country_code
## nbr.val 4.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 2.533000e+03 NA NA NA NA NA
## max 7.456000e+03 NA NA NA NA NA
## range 4.923000e+03 NA NA NA NA NA
## sum 2.489800e+04 NA NA NA NA NA
## median 7.454500e+03 NA NA NA NA NA
## mean 6.224500e+03 NA NA NA NA NA
## SE.mean 1.230500e+03 NA NA NA NA NA
## CI.mean.0.95 3.916000e+03 NA NA NA NA NA
## var 6.056522e+06 NA NA NA NA NA
## std.dev 2.461000e+03 NA NA NA NA NA
## coef.var 3.953731e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 4.000000e+00 NA 4.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 1.389000e+03 NA 4.5336200 NA
## max NA 4.673000e+03 NA 17.2861300 NA
## range NA 3.284000e+03 NA 12.7525100 NA
## sum NA 9.016000e+03 NA 37.6313400 NA
## median NA 1.477000e+03 NA 7.9057950 NA
## mean NA 2.254000e+03 NA 9.4078350 NA
## SE.mean NA 8.066051e+02 NA 2.7553987 NA
## CI.mean.0.95 NA 2.566978e+03 NA 8.7689084 NA
## var NA 2.602447e+06 NA 30.3688880 NA
## std.dev NA 1.613210e+03 NA 5.5107974 NA
## coef.var NA 7.157100e-01 NA 0.5857668 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 4.00000000 4.000000e+00 NA NA NA
## nbr.null 0.00000000 0.000000e+00 NA NA NA
## nbr.na 0.00000000 0.000000e+00 NA NA NA
## min 14.38980000 -8.776540e+01 NA NA NA
## max 14.90640000 -8.759300e+01 NA NA NA
## range 0.51660000 1.724000e-01 NA NA NA
## sum 58.35410000 -3.508022e+02 NA NA NA
## median 14.52895000 -8.772190e+01 NA NA NA
## mean 14.58852500 -8.770055e+01 NA NA NA
## SE.mean 0.11244615 3.738755e-02 NA NA NA
## CI.mean.0.95 0.35785382 1.189839e-01 NA NA NA
## var 0.05057654 5.591317e-03 NA NA NA
## std.dev 0.22489229 7.477511e-02 NA NA NA
## coef.var 0.01541570 -8.526185e-04 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 3 4.000000 NA
## nbr.null NA NA NA 3 2.000000 NA
## nbr.na NA NA NA 1 0.000000 NA
## min NA NA NA 0 0.000000 NA
## max NA NA NA 0 5.000000 NA
## range NA NA NA 0 5.000000 NA
## sum NA NA NA 0 6.000000 NA
## median NA NA NA 0 0.500000 NA
## mean NA NA NA 0 1.500000 NA
## SE.mean NA NA NA 0 1.190238 NA
## CI.mean.0.95 NA NA NA 0 3.787869 NA
## var NA NA NA 0 5.666667 NA
## std.dev NA NA NA 0 2.380476 NA
## coef.var NA NA NA NaN 1.586984 NA
## source_link prop ypos
## nbr.val NA 4.0000000 4.0000000
## nbr.null NA 0.0000000 0.0000000
## nbr.na NA 0.0000000 0.0000000
## min NA 12.0474583 22.9677312
## max NA 45.9354623 88.6718889
## range NA 33.8880040 65.7041578
## sum NA 100.0000000 238.5755596
## median NA 21.0085397 63.4679698
## mean NA 25.0000000 59.6438899
## SE.mean NA 7.3220850 13.9652032
## CI.mean.0.95 NA 23.3021423 44.4435093
## var NA 214.4517146 780.1076021
## std.dev NA 14.6441700 27.9304064
## coef.var NA 0.5857668 0.4682861boxplot(data, horizontal=TRUE, col='green')
Gráfico para Copán (Honduras)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_HD <- subset(df, country_name == "Honduras")
knitr::kable(head(df_HD)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 854 | 10/19/08 | NA | NA | Honduras | HN | Copán | 4752 | Corquín | 0.43391 | NA | 14.5637 | -88.8693 | (14.563700000000001, -88.869299999999996) | Landslide | Landslide | Large | Tropical cyclone | Tropical Depression 16 | NA | 23 | NA | http://www.chron.com/disp/story.mpl/ap/world/6068144.html |
| 855 | 10/20/08 | NA | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 2.99239 | NA | 14.1080 | -87.2137 | (14.108000000000001, -87.213700000000003) | Landslide | Mudslide | Large | Tropical cyclone | Tropical Depression 16 | NA | 29 | NA | http://in.ibtimes.com/articles/20081021/honduras-landslide-tegucigalpa-victim.htm |
| 2062 | 7/12/10 | 5:30:00 | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 0.98377 | NA | 14.0831 | -87.1978 | (14.0831, -87.197800000000001) | Landslide | Mudslide | Medium | Downpour | NA | NA | 1 | NA | http://mdn.mainichi.jp/mdnnews/news/20100713p2a00m0na013000c.html |
| 2093 | 7/18/10 | NA | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 1.24404 | NA | 14.0814 | -87.1953 | (14.0814, -87.195300000000003) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.insidecostarica.com/dailynews/2010/july/19/centralamerica10071903.htm |
| 2217 | 8/7/10 | Overnight | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 2.21442 | NA | 14.0783 | -87.2270 | (14.0783, -87.227000000000004) | Landslide | Mudslide | Medium | Downpour | NA | NA | 3 | NA | NA |
| 2358 | 8/29/10 | 4:30:00 | NA | Honduras | HN | Francisco Morazán | 2288 | Santa Lucía | 4.75791 | NA | 14.1015 | -87.1607 | (14.1015, -87.160700000000006) | Landslide | Rockfall | Medium | Downpour | NA | NA | 5 | NA | NA |
library(dplyr)
df_HD <- subset(df, state == "Copán")
knitr::kable(head(df_HD))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 854 | 10/19/08 | NA | NA | Honduras | HN | Copán | 4752 | Corquín | 0.43391 | NA | 14.5637 | -88.8693 | (14.563700000000001, -88.869299999999996) | Landslide | Landslide | Large | Tropical cyclone | Tropical Depression 16 | NA | 23 | NA | http://www.chron.com/disp/story.mpl/ap/world/6068144.html |
| 7457 | 9/6/15 | NA | NA | Honduras | HN | Copán | 27753 | Santa Rosa de Copán | 0.74414 | Urban area | 14.7698 | -88.7731 | (14.7698, -88.773099999999999) | Landslide | Landslide | Medium | Continuous rain | NA | 0 | 0 | La Prensa | http://www.laprensa.hn/honduras/877427-410/honduras-fuertes-lluvias-afectan-el-occidente |
| 7458 | 9/6/15 | NA | NA | Honduras | HN | Copán | 27753 | Santa Rosa de Copán | 0.28887 | Urban area | 14.7691 | -88.7800 | (14.7691, -88.78) | Landslide | Landslide | Medium | Continuous rain | NA | 0 | 0 | La Prensa | http://www.laprensa.hn/honduras/877427-410/honduras-fuertes-lluvias-afectan-el-occidente |
| 7459 | 11/21/15 | 22:30 | NA | Honduras | HN | Copán | 1340 | Ojos de Agua | 1.39095 | Below road | 14.6893 | -88.8098 | (14.689299999999999, -88.809799999999996) | Landslide | Landslide | Medium | Rain | NA | 0 | 1 | La Prensa | http://www.laprensa.hn/honduras/904048-410/beb%C3%A9-de-25-d%C3%ADas-de-nacida-muere-soterrada-en-cop%C3%A1n |
| 7461 | 9/24/15 | NA | NA | Honduras | HN | Copán | 1452 | Lucerna | 5.89721 | Above road | 14.6000 | -88.9144 | (14.6, -88.914400000000001) | Landslide | Landslide | Small | Rain | NA | 0 | 0 | El Heraldo | http://www.elheraldo.hn/pais/883672-214/ampl%C3%ADan-por-72-horas-alerta-verde-en-nueve-departamentos-de-honduras |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_HD, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_HD, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_HD, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_HD <- df_HD %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_HD$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_HD, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_HD$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 0.74414 |
| 0.28887 |
| 1.39095 |
| 5.89721 |
| 0.43391 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_HD$distance
names(distance) <- df_HD$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Lucerna 5.897210 5.897210 67.357580 67.357580
## Ojos de Agua 1.390950 7.288160 15.887348 83.244928
## Santa Rosa de Copán 0.744140 8.032300 8.499523 91.744450
## Corquín 0.433910 8.466210 4.956094 96.700544
## Santa Rosa de Copán 0.288870 8.755080 3.299456 100.000000stem(df_HD$"distance")##
## The decimal point is at the |
##
## 0 | 3474
## 2 |
## 4 | 9head(df_HD)## # A tibble: 5 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 7457 9/6/15 <NA> <NA> Honduras HN Copán 27753
## 2 7458 9/6/15 <NA> <NA> Honduras HN Copán 27753
## 3 7459 11/21/15 22:30 <NA> Honduras HN Copán 1340
## 4 7461 9/24/15 <NA> <NA> Honduras HN Copán 1452
## 5 854 10/19/08 <NA> <NA> Honduras HN Copán 4752
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_HD))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 7457 | 9/6/15 | NA | NA | Honduras | HN | Copán | 27753 | Santa Rosa de Copán | 0.74414 | Urban area | 14.7698 | -88.7731 | (14.7698, -88.773099999999999) | Landslide | Landslide | Medium | Continuous rain | NA | 0 | 0 | La Prensa | http://www.laprensa.hn/honduras/877427-410/honduras-fuertes-lluvias-afectan-el-occidente | 8.499523 | 4.249761 |
| 7458 | 9/6/15 | NA | NA | Honduras | HN | Copán | 27753 | Santa Rosa de Copán | 0.28887 | Urban area | 14.7691 | -88.7800 | (14.7691, -88.78) | Landslide | Landslide | Medium | Continuous rain | NA | 0 | 0 | La Prensa | http://www.laprensa.hn/honduras/877427-410/honduras-fuertes-lluvias-afectan-el-occidente | 3.299456 | 10.149251 |
| 7459 | 11/21/15 | 22:30 | NA | Honduras | HN | Copán | 1340 | Ojos de Agua | 1.39095 | Below road | 14.6893 | -88.8098 | (14.689299999999999, -88.809799999999996) | Landslide | Landslide | Medium | Rain | NA | 0 | 1 | La Prensa | http://www.laprensa.hn/honduras/904048-410/beb%C3%A9-de-25-d%C3%ADas-de-nacida-muere-soterrada-en-cop%C3%A1n | 15.887348 | 19.742652 |
| 7461 | 9/24/15 | NA | NA | Honduras | HN | Copán | 1452 | Lucerna | 5.89721 | Above road | 14.6000 | -88.9144 | (14.6, -88.914400000000001) | Landslide | Landslide | Small | Rain | NA | 0 | 0 | El Heraldo | http://www.elheraldo.hn/pais/883672-214/ampl%C3%ADan-por-72-horas-alerta-verde-en-nueve-departamentos-de-honduras | 67.357580 | 61.365116 |
| 854 | 10/19/08 | NA | NA | Honduras | HN | Copán | 4752 | Corquín | 0.43391 | NA | 14.5637 | -88.8693 | (14.563700000000001, -88.869299999999996) | Landslide | Landslide | Large | Tropical cyclone | Tropical Depression 16 | NA | 23 | NA | http://www.chron.com/disp/story.mpl/ap/world/6068144.html | 4.956094 | 97.521953 |
stem(df_HD$"distance")##
## The decimal point is at the |
##
## 0 | 3474
## 2 |
## 4 | 9stem(df_HD$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 347
## 1 | 4
## 2 |
## 3 |
## 4 |
## 5 | 9Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.28887 | 1 | 20 | 20 | 20 | 20 |
| 0.43391 | 1 | 20 | 20 | 40 | 40 |
| 0.74414 | 1 | 20 | 20 | 60 | 60 |
| 1.39095 | 1 | 20 | 20 | 80 | 80 |
| 5.89721 | 1 | 20 | 20 | 100 | 100 |
| Total | 5 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 6 obs. of 5 variables:
## $ n : num 1 1 1 1 1 5
## $ % : num 20 20 20 20 20 100
## $ val% : num 20 20 20 20 20 100
## $ %cum : num 20 40 60 80 100 100
## $ val%cum: num 20 40 60 80 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.28887 | 1 |
| 0.43391 | 1 |
| 0.74414 | 1 |
| 1.39095 | 1 |
| 5.89721 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.28887 2.28887 4.28887 6.28887distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.289,2.29] | 3 | 0.75 | 3 |
| (2.29,4.29] | 0 | 0.00 | 3 |
| (4.29,6.29] | 1 | 0.25 | 4 |
str(Freq_table)## 'data.frame': 3 obs. of 4 variables:
## $ distance: Factor w/ 3 levels "(0.289,2.29]",..: 1 2 3
## $ Freq : int 3 0 1
## $ Rel_Freq: num 0.75 0 0.25
## $ Cum_Freq: int 3 3 4df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.289,2.29] | 3 |
| (2.29,4.29] | 0 |
| (4.29,6.29] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_HD)## id date time continent_code country_name country_code
## nbr.val 5.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 8.540000e+02 NA NA NA NA NA
## max 7.461000e+03 NA NA NA NA NA
## range 6.607000e+03 NA NA NA NA NA
## sum 3.068900e+04 NA NA NA NA NA
## median 7.458000e+03 NA NA NA NA NA
## mean 6.137800e+03 NA NA NA NA NA
## SE.mean 1.320950e+03 NA NA NA NA NA
## CI.mean.0.95 3.667546e+03 NA NA NA NA NA
## var 8.724547e+06 NA NA NA NA NA
## std.dev 2.953734e+03 NA NA NA NA NA
## coef.var 4.812367e-01 NA NA NA NA NA
## state population city distance location_description latitude
## nbr.val NA 5.000000e+00 NA 5.000000 NA 5.000000000
## nbr.null NA 0.000000e+00 NA 0.000000 NA 0.000000000
## nbr.na NA 0.000000e+00 NA 0.000000 NA 0.000000000
## min NA 1.340000e+03 NA 0.288870 NA 14.563700000
## max NA 2.775300e+04 NA 5.897210 NA 14.769800000
## range NA 2.641300e+04 NA 5.608340 NA 0.206100000
## sum NA 6.305000e+04 NA 8.755080 NA 73.391900000
## median NA 4.752000e+03 NA 0.744140 NA 14.689300000
## mean NA 1.261000e+04 NA 1.751016 NA 14.678380000
## SE.mean NA 6.212419e+03 NA 1.053732 NA 0.042427531
## CI.mean.0.95 NA 1.724844e+04 NA 2.925628 NA 0.117797711
## var NA 1.929707e+08 NA 5.551753 NA 0.009000477
## std.dev NA 1.389139e+04 NA 2.356216 NA 0.094870844
## coef.var NA 1.101617e+00 NA 1.345628 NA 0.006463305
## longitude geolocation hazard_type landslide_type
## nbr.val 5.000000e+00 NA NA NA
## nbr.null 0.000000e+00 NA NA NA
## nbr.na 0.000000e+00 NA NA NA
## min -8.891440e+01 NA NA NA
## max -8.877310e+01 NA NA NA
## range 1.413000e-01 NA NA NA
## sum -4.441466e+02 NA NA NA
## median -8.880980e+01 NA NA NA
## mean -8.882932e+01 NA NA NA
## SE.mean 2.721322e-02 NA NA NA
## CI.mean.0.95 7.555601e-02 NA NA NA
## var 3.702797e-03 NA NA NA
## std.dev 6.085061e-02 NA NA NA
## coef.var -6.850285e-04 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 4 5.000000 NA
## nbr.null NA NA NA 4 3.000000 NA
## nbr.na NA NA NA 1 0.000000 NA
## min NA NA NA 0 0.000000 NA
## max NA NA NA 0 23.000000 NA
## range NA NA NA 0 23.000000 NA
## sum NA NA NA 0 24.000000 NA
## median NA NA NA 0 0.000000 NA
## mean NA NA NA 0 4.800000 NA
## SE.mean NA NA NA 0 4.554119 NA
## CI.mean.0.95 NA NA NA 0 12.644261 NA
## var NA NA NA 0 103.700000 NA
## std.dev NA NA NA 0 10.183320 NA
## coef.var NA NA NA NaN 2.121525 NA
## source_link prop ypos
## nbr.val NA 5.000000 5.000000
## nbr.null NA 0.000000 0.000000
## nbr.na NA 0.000000 0.000000
## min NA 3.299456 4.249761
## max NA 67.357580 97.521953
## range NA 64.058124 93.272192
## sum NA 100.000000 193.028733
## median NA 8.499523 19.742652
## mean NA 20.000000 38.605747
## SE.mean NA 12.035661 17.797515
## CI.mean.0.95 NA 33.416351 49.413822
## var NA 724.285634 1583.757624
## std.dev NA 26.912555 39.796452
## coef.var NA 1.345628 1.030843boxplot(data, horizontal=TRUE, col='green')
Gráfico para Cortés (Honduras)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_HD <- subset(df, country_name == "Honduras")
knitr::kable(head(df_HD)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 854 | 10/19/08 | NA | NA | Honduras | HN | Copán | 4752 | Corquín | 0.43391 | NA | 14.5637 | -88.8693 | (14.563700000000001, -88.869299999999996) | Landslide | Landslide | Large | Tropical cyclone | Tropical Depression 16 | NA | 23 | NA | http://www.chron.com/disp/story.mpl/ap/world/6068144.html |
| 855 | 10/20/08 | NA | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 2.99239 | NA | 14.1080 | -87.2137 | (14.108000000000001, -87.213700000000003) | Landslide | Mudslide | Large | Tropical cyclone | Tropical Depression 16 | NA | 29 | NA | http://in.ibtimes.com/articles/20081021/honduras-landslide-tegucigalpa-victim.htm |
| 2062 | 7/12/10 | 5:30:00 | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 0.98377 | NA | 14.0831 | -87.1978 | (14.0831, -87.197800000000001) | Landslide | Mudslide | Medium | Downpour | NA | NA | 1 | NA | http://mdn.mainichi.jp/mdnnews/news/20100713p2a00m0na013000c.html |
| 2093 | 7/18/10 | NA | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 1.24404 | NA | 14.0814 | -87.1953 | (14.0814, -87.195300000000003) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.insidecostarica.com/dailynews/2010/july/19/centralamerica10071903.htm |
| 2217 | 8/7/10 | Overnight | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 2.21442 | NA | 14.0783 | -87.2270 | (14.0783, -87.227000000000004) | Landslide | Mudslide | Medium | Downpour | NA | NA | 3 | NA | NA |
| 2358 | 8/29/10 | 4:30:00 | NA | Honduras | HN | Francisco Morazán | 2288 | Santa Lucía | 4.75791 | NA | 14.1015 | -87.1607 | (14.1015, -87.160700000000006) | Landslide | Rockfall | Medium | Downpour | NA | NA | 5 | NA | NA |
library(dplyr)
df_HD <- subset(df, state == "Cortés")
knitr::kable(head(df_HD))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 5415 | 8/29/13 | 0:05:00 | NA | Honduras | HN | Cortés | 1146 | Los Caminos | 3.53737 | NA | 14.9510 | -87.9338 | (14.951000000000001, -87.933800000000005) | Landslide | Landslide | Medium | Downpour | NA | 2 | 6 | www.reuters.com | http://www.reuters.com/article/2013/08/29/us-honduras-landslide-idUSBRE97S0SI20130829 |
| 6689 | 7/31/14 | Night | NA | Honduras | HN | Cortés | 1043 | Agua Azul Rancho | 0.97057 | Above road | 14.8955 | -87.9423 | (14.8955, -87.942300000000003) | Landslide | Landslide | Small | Unknown | NA | 0 | 0 | Tribuna | http://www.latribuna.hn/2014/08/01/deslizamiento-de-tierra-impide-parcialmente-trafico-vehicular-al-norte-de-honduras/ |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_HD, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_HD, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_HD, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_HD <- df_HD %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_HD$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_HD, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_HD$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 3.53737 |
| 0.97057 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_HD$distance
names(distance) <- df_HD$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Los Caminos 3.53737 3.53737 78.46977 78.46977
## Agua Azul Rancho 0.97057 4.50794 21.53023 100.00000stem(df_HD$"distance")##
## The decimal point is at the |
##
## 0 |
## 1 | 0
## 2 |
## 3 | 5head(df_HD)## # A tibble: 2 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 5415 8/29/13 0:05:00 <NA> Honduras HN Cortés 1146
## 2 6689 7/31/14 Night <NA> Honduras HN Cortés 1043
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_HD))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 5415 | 8/29/13 | 0:05:00 | NA | Honduras | HN | Cortés | 1146 | Los Caminos | 3.53737 | NA | 14.9510 | -87.9338 | (14.951000000000001, -87.933800000000005) | Landslide | Landslide | Medium | Downpour | NA | 2 | 6 | www.reuters.com | http://www.reuters.com/article/2013/08/29/us-honduras-landslide-idUSBRE97S0SI20130829 | 78.46977 | 39.23488 |
| 6689 | 7/31/14 | Night | NA | Honduras | HN | Cortés | 1043 | Agua Azul Rancho | 0.97057 | Above road | 14.8955 | -87.9423 | (14.8955, -87.942300000000003) | Landslide | Landslide | Small | Unknown | NA | 0 | 0 | Tribuna | http://www.latribuna.hn/2014/08/01/deslizamiento-de-tierra-impide-parcialmente-trafico-vehicular-al-norte-de-honduras/ | 21.53023 | 89.23488 |
stem(df_HD$"distance")##
## The decimal point is at the |
##
## 0 |
## 1 | 0
## 2 |
## 3 | 5stem(df_HD$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 |
## 1 | 0
## 1 |
## 2 |
## 2 |
## 3 |
## 3 | 5Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.97057 | 1 | 50 | 50 | 50 | 50 |
| 3.53737 | 1 | 50 | 50 | 100 | 100 |
| Total | 2 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 3 obs. of 5 variables:
## $ n : num 1 1 2
## $ % : num 50 50 100
## $ val% : num 50 50 100
## $ %cum : num 50 100 100
## $ val%cum: num 50 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.97057 | 1 |
| 3.53737 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.97057 2.97057 4.97057distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.971,2.97] | 0 | 0 | 0 |
| (2.97,4.97] | 1 | 1 | 1 |
str(Freq_table)## 'data.frame': 2 obs. of 4 variables:
## $ distance: Factor w/ 2 levels "(0.971,2.97]",..: 1 2
## $ Freq : int 0 1
## $ Rel_Freq: num 0 1
## $ Cum_Freq: int 0 1df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.971,2.97] | 0 |
| (2.97,4.97] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_HD)## id date time continent_code country_name country_code
## nbr.val 2.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 5.415000e+03 NA NA NA NA NA
## max 6.689000e+03 NA NA NA NA NA
## range 1.274000e+03 NA NA NA NA NA
## sum 1.210400e+04 NA NA NA NA NA
## median 6.052000e+03 NA NA NA NA NA
## mean 6.052000e+03 NA NA NA NA NA
## SE.mean 6.370000e+02 NA NA NA NA NA
## CI.mean.0.95 8.093852e+03 NA NA NA NA NA
## var 8.115380e+05 NA NA NA NA NA
## std.dev 9.008540e+02 NA NA NA NA NA
## coef.var 1.488523e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 2.000000e+00 NA 2.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 1.043000e+03 NA 0.9705700 NA
## max NA 1.146000e+03 NA 3.5373700 NA
## range NA 1.030000e+02 NA 2.5668000 NA
## sum NA 2.189000e+03 NA 4.5079400 NA
## median NA 1.094500e+03 NA 2.2539700 NA
## mean NA 1.094500e+03 NA 2.2539700 NA
## SE.mean NA 5.150000e+01 NA 1.2834000 NA
## CI.mean.0.95 NA 6.543695e+02 NA 16.3071432 NA
## var NA 5.304500e+03 NA 3.2942311 NA
## std.dev NA 7.283200e+01 NA 1.8150017 NA
## coef.var NA 6.654363e-02 NA 0.8052466 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 2.000000000 2.000000e+00 NA NA NA
## nbr.null 0.000000000 0.000000e+00 NA NA NA
## nbr.na 0.000000000 0.000000e+00 NA NA NA
## min 14.895500000 -8.794230e+01 NA NA NA
## max 14.951000000 -8.793380e+01 NA NA NA
## range 0.055500000 8.500000e-03 NA NA NA
## sum 29.846500000 -1.758761e+02 NA NA NA
## median 14.923250000 -8.793805e+01 NA NA NA
## mean 14.923250000 -8.793805e+01 NA NA NA
## SE.mean 0.027750000 4.250000e-03 NA NA NA
## CI.mean.0.95 0.352597181 5.400137e-02 NA NA NA
## var 0.001540125 3.612500e-05 NA NA NA
## std.dev 0.039244426 6.010408e-03 NA NA NA
## coef.var 0.002629751 -6.834820e-05 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 2.000000 2.000000 NA
## nbr.null NA NA NA 1.000000 1.000000 NA
## nbr.na NA NA NA 0.000000 0.000000 NA
## min NA NA NA 0.000000 0.000000 NA
## max NA NA NA 2.000000 6.000000 NA
## range NA NA NA 2.000000 6.000000 NA
## sum NA NA NA 2.000000 6.000000 NA
## median NA NA NA 1.000000 3.000000 NA
## mean NA NA NA 1.000000 3.000000 NA
## SE.mean NA NA NA 1.000000 3.000000 NA
## CI.mean.0.95 NA NA NA 12.706205 38.118614 NA
## var NA NA NA 2.000000 18.000000 NA
## std.dev NA NA NA 1.414214 4.242641 NA
## coef.var NA NA NA 1.414214 1.414214 NA
## source_link prop ypos
## nbr.val NA 2.0000000 2.0000000
## nbr.null NA 0.0000000 0.0000000
## nbr.na NA 0.0000000 0.0000000
## min NA 21.5302333 39.2348833
## max NA 78.4697667 89.2348833
## range NA 56.9395334 50.0000000
## sum NA 100.0000000 128.4697667
## median NA 50.0000000 64.2348833
## mean NA 50.0000000 64.2348833
## SE.mean NA 28.4697667 25.0000000
## CI.mean.0.95 NA 361.7426842 317.6551184
## var NA 1621.0552294 1250.0000000
## std.dev NA 40.2623302 35.3553391
## coef.var NA 0.8052466 0.5504071boxplot(data, horizontal=TRUE, col='green')
Gráfico para La Paz (Honduras)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_HD <- subset(df, country_name == "Honduras")
knitr::kable(head(df_HD)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 854 | 10/19/08 | NA | NA | Honduras | HN | Copán | 4752 | Corquín | 0.43391 | NA | 14.5637 | -88.8693 | (14.563700000000001, -88.869299999999996) | Landslide | Landslide | Large | Tropical cyclone | Tropical Depression 16 | NA | 23 | NA | http://www.chron.com/disp/story.mpl/ap/world/6068144.html |
| 855 | 10/20/08 | NA | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 2.99239 | NA | 14.1080 | -87.2137 | (14.108000000000001, -87.213700000000003) | Landslide | Mudslide | Large | Tropical cyclone | Tropical Depression 16 | NA | 29 | NA | http://in.ibtimes.com/articles/20081021/honduras-landslide-tegucigalpa-victim.htm |
| 2062 | 7/12/10 | 5:30:00 | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 0.98377 | NA | 14.0831 | -87.1978 | (14.0831, -87.197800000000001) | Landslide | Mudslide | Medium | Downpour | NA | NA | 1 | NA | http://mdn.mainichi.jp/mdnnews/news/20100713p2a00m0na013000c.html |
| 2093 | 7/18/10 | NA | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 1.24404 | NA | 14.0814 | -87.1953 | (14.0814, -87.195300000000003) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.insidecostarica.com/dailynews/2010/july/19/centralamerica10071903.htm |
| 2217 | 8/7/10 | Overnight | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 2.21442 | NA | 14.0783 | -87.2270 | (14.0783, -87.227000000000004) | Landslide | Mudslide | Medium | Downpour | NA | NA | 3 | NA | NA |
| 2358 | 8/29/10 | 4:30:00 | NA | Honduras | HN | Francisco Morazán | 2288 | Santa Lucía | 4.75791 | NA | 14.1015 | -87.1607 | (14.1015, -87.160700000000006) | Landslide | Rockfall | Medium | Downpour | NA | NA | 5 | NA | NA |
library(dplyr)
df_HD <- subset(df, state == "La Paz")
knitr::kable(head(df_HD))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 6683 | 10/15/14 | NA | NA | El Salvador | SV | La Paz | 2654 | San Pedro Masahuat | 0.31933 | Above river | 13.5461 | -89.0401 | (13.546099999999999, -89.040099999999995) | Landslide | Landslide | Medium | Continuous rain | NA | 0 | 0 | reliefweb | http://reliefweb.int/report/el-salvador/lluvias-causan-estragos-en-seis-departamentos |
| 7460 | 9/25/15 | NA | NA | Honduras | HN | La Paz | 1463 | San José | 4.69133 | Unknown | 14.2801 | -87.9369 | (14.280099999999999, -87.936899999999994) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | Tiempo | http://www.tiempo.hn/lluvias-comienzan-a-causar-deslizamientos-en-carreteras-del-occidente-de-honduras/ |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_HD, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_HD, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_HD, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_HD <- df_HD %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_HD$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_HD, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_HD$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 0.31933 |
| 4.69133 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_HD$distance
names(distance) <- df_HD$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## San José 4.691330 4.691330 93.626987 93.626987
## San Pedro Masahuat 0.319330 5.010660 6.373013 100.000000stem(df_HD$"distance")##
## The decimal point is at the |
##
## 0 | 3
## 1 |
## 2 |
## 3 |
## 4 | 7head(df_HD)## # A tibble: 2 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 6683 10/15/14 <NA> <NA> El Salvador SV La Paz 2654
## 2 7460 9/25/15 <NA> <NA> Honduras HN La Paz 1463
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_HD))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 6683 | 10/15/14 | NA | NA | El Salvador | SV | La Paz | 2654 | San Pedro Masahuat | 0.31933 | Above river | 13.5461 | -89.0401 | (13.546099999999999, -89.040099999999995) | Landslide | Landslide | Medium | Continuous rain | NA | 0 | 0 | reliefweb | http://reliefweb.int/report/el-salvador/lluvias-causan-estragos-en-seis-departamentos | 6.373013 | 3.186506 |
| 7460 | 9/25/15 | NA | NA | Honduras | HN | La Paz | 1463 | San José | 4.69133 | Unknown | 14.2801 | -87.9369 | (14.280099999999999, -87.936899999999994) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | Tiempo | http://www.tiempo.hn/lluvias-comienzan-a-causar-deslizamientos-en-carreteras-del-occidente-de-honduras/ | 93.626987 | 53.186506 |
stem(df_HD$"distance")##
## The decimal point is at the |
##
## 0 | 3
## 1 |
## 2 |
## 3 |
## 4 | 7stem(df_HD$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 3
## 0 |
## 1 |
## 1 |
## 2 |
## 2 |
## 3 |
## 3 |
## 4 |
## 4 | 7Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.31933 | 1 | 50 | 50 | 50 | 50 |
| 4.69133 | 1 | 50 | 50 | 100 | 100 |
| Total | 2 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 3 obs. of 5 variables:
## $ n : num 1 1 2
## $ % : num 50 50 100
## $ val% : num 50 50 100
## $ %cum : num 50 100 100
## $ val%cum: num 50 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.31933 | 1 |
| 4.69133 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.31933 3.31933 6.31933distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.319,3.32] | 0 | 0 | 0 |
| (3.32,6.32] | 1 | 1 | 1 |
str(Freq_table)## 'data.frame': 2 obs. of 4 variables:
## $ distance: Factor w/ 2 levels "(0.319,3.32]",..: 1 2
## $ Freq : int 0 1
## $ Rel_Freq: num 0 1
## $ Cum_Freq: int 0 1df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.319,3.32] | 0 |
| (3.32,6.32] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_HD)## id date time continent_code country_name country_code
## nbr.val 2.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 6.683000e+03 NA NA NA NA NA
## max 7.460000e+03 NA NA NA NA NA
## range 7.770000e+02 NA NA NA NA NA
## sum 1.414300e+04 NA NA NA NA NA
## median 7.071500e+03 NA NA NA NA NA
## mean 7.071500e+03 NA NA NA NA NA
## SE.mean 3.885000e+02 NA NA NA NA NA
## CI.mean.0.95 4.936361e+03 NA NA NA NA NA
## var 3.018645e+05 NA NA NA NA NA
## std.dev 5.494220e+02 NA NA NA NA NA
## coef.var 7.769525e-02 NA NA NA NA NA
## state population city distance location_description latitude
## nbr.val NA 2.000000e+00 NA 2.000000 NA 2.00000000
## nbr.null NA 0.000000e+00 NA 0.000000 NA 0.00000000
## nbr.na NA 0.000000e+00 NA 0.000000 NA 0.00000000
## min NA 1.463000e+03 NA 0.319330 NA 13.54610000
## max NA 2.654000e+03 NA 4.691330 NA 14.28010000
## range NA 1.191000e+03 NA 4.372000 NA 0.73400000
## sum NA 4.117000e+03 NA 5.010660 NA 27.82620000
## median NA 2.058500e+03 NA 2.505330 NA 13.91310000
## mean NA 2.058500e+03 NA 2.505330 NA 13.91310000
## SE.mean NA 5.955000e+02 NA 2.186000 NA 0.36700000
## CI.mean.0.95 NA 7.566545e+03 NA 27.775764 NA 4.66317714
## var NA 7.092405e+05 NA 9.557192 NA 0.26937800
## std.dev NA 8.421642e+02 NA 3.091471 NA 0.51901638
## coef.var NA 4.091155e-01 NA 1.233958 NA 0.03730415
## longitude geolocation hazard_type landslide_type
## nbr.val 2.000000e+00 NA NA NA
## nbr.null 0.000000e+00 NA NA NA
## nbr.na 0.000000e+00 NA NA NA
## min -8.904010e+01 NA NA NA
## max -8.793690e+01 NA NA NA
## range 1.103200e+00 NA NA NA
## sum -1.769770e+02 NA NA NA
## median -8.848850e+01 NA NA NA
## mean -8.848850e+01 NA NA NA
## SE.mean 5.516000e-01 NA NA NA
## CI.mean.0.95 7.008743e+00 NA NA NA
## var 6.085251e-01 NA NA NA
## std.dev 7.800802e-01 NA NA NA
## coef.var -8.815611e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 2 2 NA
## nbr.null NA NA NA 2 2 NA
## nbr.na NA NA NA 0 0 NA
## min NA NA NA 0 0 NA
## max NA NA NA 0 0 NA
## range NA NA NA 0 0 NA
## sum NA NA NA 0 0 NA
## median NA NA NA 0 0 NA
## mean NA NA NA 0 0 NA
## SE.mean NA NA NA 0 0 NA
## CI.mean.0.95 NA NA NA 0 0 NA
## var NA NA NA 0 0 NA
## std.dev NA NA NA 0 0 NA
## coef.var NA NA NA NaN NaN NA
## source_link prop ypos
## nbr.val NA 2.000000 2.000000
## nbr.null NA 0.000000 0.000000
## nbr.na NA 0.000000 0.000000
## min NA 6.373013 3.186506
## max NA 93.626987 53.186506
## range NA 87.253975 50.000000
## sum NA 100.000000 56.373013
## median NA 50.000000 28.186506
## mean NA 50.000000 28.186506
## SE.mean NA 43.626987 25.000000
## CI.mean.0.95 NA 554.333432 317.655118
## var NA 3806.628035 1250.000000
## std.dev NA 61.697877 35.355339
## coef.var NA 1.233958 1.254336boxplot(data, horizontal=TRUE, col='green')
Gráfico para Francisco Morazán (Honduras)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_HD <- subset(df, country_name == "Honduras")
knitr::kable(head(df_HD)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 854 | 10/19/08 | NA | NA | Honduras | HN | Copán | 4752 | Corquín | 0.43391 | NA | 14.5637 | -88.8693 | (14.563700000000001, -88.869299999999996) | Landslide | Landslide | Large | Tropical cyclone | Tropical Depression 16 | NA | 23 | NA | http://www.chron.com/disp/story.mpl/ap/world/6068144.html |
| 855 | 10/20/08 | NA | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 2.99239 | NA | 14.1080 | -87.2137 | (14.108000000000001, -87.213700000000003) | Landslide | Mudslide | Large | Tropical cyclone | Tropical Depression 16 | NA | 29 | NA | http://in.ibtimes.com/articles/20081021/honduras-landslide-tegucigalpa-victim.htm |
| 2062 | 7/12/10 | 5:30:00 | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 0.98377 | NA | 14.0831 | -87.1978 | (14.0831, -87.197800000000001) | Landslide | Mudslide | Medium | Downpour | NA | NA | 1 | NA | http://mdn.mainichi.jp/mdnnews/news/20100713p2a00m0na013000c.html |
| 2093 | 7/18/10 | NA | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 1.24404 | NA | 14.0814 | -87.1953 | (14.0814, -87.195300000000003) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.insidecostarica.com/dailynews/2010/july/19/centralamerica10071903.htm |
| 2217 | 8/7/10 | Overnight | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 2.21442 | NA | 14.0783 | -87.2270 | (14.0783, -87.227000000000004) | Landslide | Mudslide | Medium | Downpour | NA | NA | 3 | NA | NA |
| 2358 | 8/29/10 | 4:30:00 | NA | Honduras | HN | Francisco Morazán | 2288 | Santa Lucía | 4.75791 | NA | 14.1015 | -87.1607 | (14.1015, -87.160700000000006) | Landslide | Rockfall | Medium | Downpour | NA | NA | 5 | NA | NA |
library(dplyr)
df_HD <- subset(df, state == "Francisco Morazán")
knitr::kable(head(df_HD))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 855 | 10/20/08 | NA | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 2.99239 | NA | 14.1080 | -87.2137 | (14.108000000000001, -87.213700000000003) | Landslide | Mudslide | Large | Tropical cyclone | Tropical Depression 16 | NA | 29 | NA | http://in.ibtimes.com/articles/20081021/honduras-landslide-tegucigalpa-victim.htm |
| 2062 | 7/12/10 | 5:30:00 | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 0.98377 | NA | 14.0831 | -87.1978 | (14.0831, -87.197800000000001) | Landslide | Mudslide | Medium | Downpour | NA | NA | 1 | NA | http://mdn.mainichi.jp/mdnnews/news/20100713p2a00m0na013000c.html |
| 2093 | 7/18/10 | NA | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 1.24404 | NA | 14.0814 | -87.1953 | (14.0814, -87.195300000000003) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.insidecostarica.com/dailynews/2010/july/19/centralamerica10071903.htm |
| 2217 | 8/7/10 | Overnight | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 2.21442 | NA | 14.0783 | -87.2270 | (14.0783, -87.227000000000004) | Landslide | Mudslide | Medium | Downpour | NA | NA | 3 | NA | NA |
| 2358 | 8/29/10 | 4:30:00 | NA | Honduras | HN | Francisco Morazán | 2288 | Santa Lucía | 4.75791 | NA | 14.1015 | -87.1607 | (14.1015, -87.160700000000006) | Landslide | Rockfall | Medium | Downpour | NA | NA | 5 | NA | NA |
| 3988 | 9/26/11 | NA | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 1.23639 | NA | 14.0865 | -87.2172 | (14.086499999999999, -87.217200000000005) | Landslide | Landslide | Medium | Downpour | NA | NA | 2 | NA | http://english.peopledaily.com.cn/90777/90852/7610171.html |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_HD, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_HD, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_HD, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_HD <- df_HD %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_HD$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_HD, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_HD$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 1.30583 |
| 2.00830 |
| 2.99239 |
| 0.98377 |
| 1.24404 |
| 2.21442 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_HD$distance
names(distance) <- df_HD$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Santa Lucía 4.757910 4.757910 13.217489 13.217489
## Río Abajo 3.639620 8.397530 10.110876 23.328364
## El Guapinol 3.543990 11.941520 9.845215 33.173580
## Tegucigalpa 3.252810 15.194330 9.036316 42.209896
## El Tablón 3.129860 18.324190 8.694761 50.904657
## Tegucigalpa 2.992390 21.316580 8.312869 59.217525
## Tegucigalpa 2.913260 24.229840 8.093045 67.310571
## Tegucigalpa 2.214420 26.444260 6.151666 73.462236
## Villa Nueva 2.008300 28.452560 5.579064 79.041300
## El Lolo 1.858970 30.311530 5.164224 84.205524
## Yaguacire 1.305830 31.617360 3.627600 87.833124
## Tegucigalpa 1.244040 32.861400 3.455947 91.289071
## Tegucigalpa 1.236390 34.097790 3.434695 94.723766
## Tegucigalpa 0.983770 35.081560 2.732916 97.456683
## Tegucigalpa 0.915520 35.997080 2.543317 100.000000stem(df_HD$"distance")##
## The decimal point is at the |
##
## 0 | 9
## 1 | 02239
## 2 | 029
## 3 | 01356
## 4 | 8head(df_HD)## # A tibble: 6 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 7483 9/28/15 Morning <NA> Honduras HN Fran~ 1449
## 2 7463 6/13/15 Morning <NA> Honduras HN Fran~ 2295
## 3 855 10/20/08 <NA> <NA> Honduras HN Fran~ 850848
## 4 2062 7/12/10 5:30:00 <NA> Honduras HN Fran~ 850848
## 5 2093 7/18/10 <NA> <NA> Honduras HN Fran~ 850848
## 6 2217 8/7/10 Overnight <NA> Honduras HN Fran~ 850848
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_HD))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 7483 | 9/28/15 | Morning | NA | Honduras | HN | Francisco Morazán | 1449 | Yaguacire | 1.30583 | Urban area | 14.0211 | -87.2055 | (14.021100000000001, -87.205500000000001) | Landslide | Landslide | Medium | Downpour | NA | 0 | 0 | La Prensa | http://www.laprensa.hn/honduras/885141-410/dos-casas-a-punto-de-caer-por-derrumbe-en-tegucigalpa | 3.627600 | 1.813800 |
| 7463 | 6/13/15 | Morning | NA | Honduras | HN | Francisco Morazán | 2295 | Villa Nueva | 2.00830 | Above road | 14.0468 | -87.1528 | (14.046799999999999, -87.152799999999999) | Landslide | Rockfall | Medium | Rain | NA | 0 | 0 | La Tribuna | http://www.latribuna.hn/2015/06/13/lluvias-siguen-provocando-deslizamientos-en-el-oriente-de-tegucigalpa/ | 5.579064 | 6.417132 |
| 855 | 10/20/08 | NA | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 2.99239 | NA | 14.1080 | -87.2137 | (14.108000000000001, -87.213700000000003) | Landslide | Mudslide | Large | Tropical cyclone | Tropical Depression 16 | NA | 29 | NA | http://in.ibtimes.com/articles/20081021/honduras-landslide-tegucigalpa-victim.htm | 8.312869 | 13.363098 |
| 2062 | 7/12/10 | 5:30:00 | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 0.98377 | NA | 14.0831 | -87.1978 | (14.0831, -87.197800000000001) | Landslide | Mudslide | Medium | Downpour | NA | NA | 1 | NA | http://mdn.mainichi.jp/mdnnews/news/20100713p2a00m0na013000c.html | 2.732916 | 18.885990 |
| 2093 | 7/18/10 | NA | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 1.24404 | NA | 14.0814 | -87.1953 | (14.0814, -87.195300000000003) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.insidecostarica.com/dailynews/2010/july/19/centralamerica10071903.htm | 3.455947 | 21.980422 |
| 2217 | 8/7/10 | Overnight | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 2.21442 | NA | 14.0783 | -87.2270 | (14.0783, -87.227000000000004) | Landslide | Mudslide | Medium | Downpour | NA | NA | 3 | NA | NA | 6.151666 | 26.784228 |
stem(df_HD$"distance")##
## The decimal point is at the |
##
## 0 | 9
## 1 | 02239
## 2 | 029
## 3 | 01356
## 4 | 8stem(df_HD$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 9
## 1 | 0223
## 1 | 9
## 2 | 02
## 2 | 9
## 3 | 013
## 3 | 56
## 4 |
## 4 | 8Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.91552 | 1 | 6.7 | 6.7 | 6.7 | 6.7 |
| 0.98377 | 1 | 6.7 | 6.7 | 13.3 | 13.3 |
| 1.23639 | 1 | 6.7 | 6.7 | 20.0 | 20.0 |
| 1.24404 | 1 | 6.7 | 6.7 | 26.7 | 26.7 |
| 1.30583 | 1 | 6.7 | 6.7 | 33.3 | 33.3 |
| 1.85897 | 1 | 6.7 | 6.7 | 40.0 | 40.0 |
| 2.0083 | 1 | 6.7 | 6.7 | 46.7 | 46.7 |
| 2.21442 | 1 | 6.7 | 6.7 | 53.3 | 53.3 |
| 2.91326 | 1 | 6.7 | 6.7 | 60.0 | 60.0 |
| 2.99239 | 1 | 6.7 | 6.7 | 66.7 | 66.7 |
| 3.12986 | 1 | 6.7 | 6.7 | 73.3 | 73.3 |
| 3.25281 | 1 | 6.7 | 6.7 | 80.0 | 80.0 |
| 3.54399 | 1 | 6.7 | 6.7 | 86.7 | 86.7 |
| 3.63962 | 1 | 6.7 | 6.7 | 93.3 | 93.3 |
| 4.75791 | 1 | 6.7 | 6.7 | 100.0 | 100.0 |
| Total | 15 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 16 obs. of 5 variables:
## $ n : num 1 1 1 1 1 1 1 1 1 1 ...
## $ % : num 6.7 6.7 6.7 6.7 6.7 6.7 6.7 6.7 6.7 6.7 ...
## $ val% : num 6.7 6.7 6.7 6.7 6.7 6.7 6.7 6.7 6.7 6.7 ...
## $ %cum : num 6.7 13.3 20 26.7 33.3 40 46.7 53.3 60 66.7 ...
## $ val%cum: num 6.7 13.3 20 26.7 33.3 40 46.7 53.3 60 66.7 ...x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.91552 | 1 |
| 0.98377 | 1 |
| 1.23639 | 1 |
| 1.24404 | 1 |
| 1.30583 | 1 |
| 1.85897 | 1 |
| 2.0083 | 1 |
| 2.21442 | 1 |
| 2.91326 | 1 |
| 2.99239 | 1 |
| 3.12986 | 1 |
| 3.25281 | 1 |
| 3.54399 | 1 |
| 3.63962 | 1 |
| 4.75791 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.91552 1.91552 2.91552 3.91552 4.91552distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.916,1.92] | 5 | 0.3571429 | 5 |
| (1.92,2.92] | 3 | 0.2142857 | 8 |
| (2.92,3.92] | 5 | 0.3571429 | 13 |
| (3.92,4.92] | 1 | 0.0714286 | 14 |
str(Freq_table)## 'data.frame': 4 obs. of 4 variables:
## $ distance: Factor w/ 4 levels "(0.916,1.92]",..: 1 2 3 4
## $ Freq : int 5 3 5 1
## $ Rel_Freq: num 0.3571 0.2143 0.3571 0.0714
## $ Cum_Freq: int 5 8 13 14df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.916,1.92] | 5 |
| (1.92,2.92] | 3 |
| (2.92,3.92] | 5 |
| (3.92,4.92] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_HD)## id date time continent_code country_name country_code
## nbr.val 1.500000e+01 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 8.550000e+02 NA NA NA NA NA
## max 7.485000e+03 NA NA NA NA NA
## range 6.630000e+03 NA NA NA NA NA
## sum 8.079700e+04 NA NA NA NA NA
## median 7.447000e+03 NA NA NA NA NA
## mean 5.386467e+03 NA NA NA NA NA
## SE.mean 6.991591e+02 NA NA NA NA NA
## CI.mean.0.95 1.499547e+03 NA NA NA NA NA
## var 7.332353e+06 NA NA NA NA NA
## std.dev 2.707832e+03 NA NA NA NA NA
## coef.var 5.027102e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 1.500000e+01 NA 15.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 1.121000e+03 NA 0.9155200 NA
## max NA 8.508480e+05 NA 4.7579100 NA
## range NA 8.497270e+05 NA 3.8423900 NA
## sum NA 6.819247e+06 NA 35.9970800 NA
## median NA 8.508480e+05 NA 2.2144200 NA
## mean NA 4.546165e+05 NA 2.3998053 NA
## SE.mean NA 1.132090e+05 NA 0.2996574 NA
## CI.mean.0.95 NA 2.428092e+05 NA 0.6427013 NA
## var NA 1.922443e+11 NA 1.3469187 NA
## std.dev NA 4.384567e+05 NA 1.1605683 NA
## coef.var NA 9.644541e-01 NA 0.4836093 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 1.500000e+01 1.500000e+01 NA NA NA
## nbr.null 0.000000e+00 0.000000e+00 NA NA NA
## nbr.na 0.000000e+00 0.000000e+00 NA NA NA
## min 1.376450e+01 -8.743400e+01 NA NA NA
## max 1.413380e+01 -8.715280e+01 NA NA NA
## range 3.693000e-01 2.812000e-01 NA NA NA
## sum 2.109138e+02 -1.308243e+03 NA NA NA
## median 1.408140e+01 -8.720870e+01 NA NA NA
## mean 1.406092e+01 -8.721617e+01 NA NA NA
## SE.mean 2.234844e-02 1.715587e-02 NA NA NA
## CI.mean.0.95 4.793264e-02 3.679568e-02 NA NA NA
## var 7.491792e-03 4.414858e-03 NA NA NA
## std.dev 8.655514e-02 6.644440e-02 NA NA NA
## coef.var 6.155724e-03 -7.618358e-04 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 9.0000000 15.000000 NA
## nbr.null NA NA NA 8.0000000 10.000000 NA
## nbr.na NA NA NA 6.0000000 0.000000 NA
## min NA NA NA 0.0000000 0.000000 NA
## max NA NA NA 1.0000000 29.000000 NA
## range NA NA NA 1.0000000 29.000000 NA
## sum NA NA NA 1.0000000 40.000000 NA
## median NA NA NA 0.0000000 0.000000 NA
## mean NA NA NA 0.1111111 2.666667 NA
## SE.mean NA NA NA 0.1111111 1.918994 NA
## CI.mean.0.95 NA NA NA 0.2562227 4.115834 NA
## var NA NA NA 0.1111111 55.238095 NA
## std.dev NA NA NA 0.3333333 7.432234 NA
## coef.var NA NA NA 3.0000000 2.787088 NA
## source_link prop ypos
## nbr.val NA 15.0000000 15.0000000
## nbr.null NA 0.0000000 0.0000000
## nbr.na NA 0.0000000 0.0000000
## min NA 2.5433174 1.8137999
## max NA 13.2174888 95.0773924
## range NA 10.6741713 93.2635925
## sum NA 100.0000000 645.2684218
## median NA 6.1516656 37.8129143
## mean NA 6.6666667 43.0178948
## SE.mean NA 0.8324493 7.7398433
## CI.mean.0.95 NA 1.7854262 16.6003128
## var NA 10.3945777 898.5776101
## std.dev NA 3.2240623 29.9762841
## coef.var NA 0.4836093 0.6968329boxplot(data, horizontal=TRUE, col='green')
Gráfico para Ocotepeque (Honduras)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_HD <- subset(df, country_name == "Honduras")
knitr::kable(head(df_HD)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 854 | 10/19/08 | NA | NA | Honduras | HN | Copán | 4752 | Corquín | 0.43391 | NA | 14.5637 | -88.8693 | (14.563700000000001, -88.869299999999996) | Landslide | Landslide | Large | Tropical cyclone | Tropical Depression 16 | NA | 23 | NA | http://www.chron.com/disp/story.mpl/ap/world/6068144.html |
| 855 | 10/20/08 | NA | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 2.99239 | NA | 14.1080 | -87.2137 | (14.108000000000001, -87.213700000000003) | Landslide | Mudslide | Large | Tropical cyclone | Tropical Depression 16 | NA | 29 | NA | http://in.ibtimes.com/articles/20081021/honduras-landslide-tegucigalpa-victim.htm |
| 2062 | 7/12/10 | 5:30:00 | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 0.98377 | NA | 14.0831 | -87.1978 | (14.0831, -87.197800000000001) | Landslide | Mudslide | Medium | Downpour | NA | NA | 1 | NA | http://mdn.mainichi.jp/mdnnews/news/20100713p2a00m0na013000c.html |
| 2093 | 7/18/10 | NA | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 1.24404 | NA | 14.0814 | -87.1953 | (14.0814, -87.195300000000003) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.insidecostarica.com/dailynews/2010/july/19/centralamerica10071903.htm |
| 2217 | 8/7/10 | Overnight | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 2.21442 | NA | 14.0783 | -87.2270 | (14.0783, -87.227000000000004) | Landslide | Mudslide | Medium | Downpour | NA | NA | 3 | NA | NA |
| 2358 | 8/29/10 | 4:30:00 | NA | Honduras | HN | Francisco Morazán | 2288 | Santa Lucía | 4.75791 | NA | 14.1015 | -87.1607 | (14.1015, -87.160700000000006) | Landslide | Rockfall | Medium | Downpour | NA | NA | 5 | NA | NA |
library(dplyr)
df_HD <- subset(df, state == "Ocotepeque")
knitr::kable(head(df_HD))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 6672 | 10/13/14 | NA | NA | Honduras | HN | Ocotepeque | 2389 | Sinuapa | 2.00805 | Below road | 14.4579 | -89.1666 | (14.4579, -89.166600000000003) | Landslide | Landslide | Medium | Downpour | NA | 0 | 0 | La Prensa | http://www.laprensa.hn/economia/757783-410/evac%C3%BAan-a-familias-por-deslizamientos-en-ocotepeque |
| 7462 | 9/25/15 | NA | NA | Honduras | HN | Ocotepeque | 1416 | La Labor | 5.79867 | Above road | 14.4810 | -89.0537 | (14.481, -89.053700000000006) | Landslide | Landslide | Small | Rain | NA | 0 | 0 | Tiempo | http://www.tiempo.hn/lluvias-comienzan-a-causar-deslizamientos-en-carreteras-del-occidente-de-honduras/ |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_HD, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_HD, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_HD, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_HD <- df_HD %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_HD$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_HD, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_HD$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 2.00805 |
| 5.79867 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_HD$distance
names(distance) <- df_HD$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## La Labor 5.79867 5.79867 74.27793 74.27793
## Sinuapa 2.00805 7.80672 25.72207 100.00000stem(df_HD$"distance")##
## The decimal point is at the |
##
## 2 | 0
## 3 |
## 4 |
## 5 | 8head(df_HD)## # A tibble: 2 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 6672 10/13/14 <NA> <NA> Honduras HN Ocotepeque 2389
## 2 7462 9/25/15 <NA> <NA> Honduras HN Ocotepeque 1416
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_HD))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 6672 | 10/13/14 | NA | NA | Honduras | HN | Ocotepeque | 2389 | Sinuapa | 2.00805 | Below road | 14.4579 | -89.1666 | (14.4579, -89.166600000000003) | Landslide | Landslide | Medium | Downpour | NA | 0 | 0 | La Prensa | http://www.laprensa.hn/economia/757783-410/evac%C3%BAan-a-familias-por-deslizamientos-en-ocotepeque | 25.72207 | 12.86104 |
| 7462 | 9/25/15 | NA | NA | Honduras | HN | Ocotepeque | 1416 | La Labor | 5.79867 | Above road | 14.4810 | -89.0537 | (14.481, -89.053700000000006) | Landslide | Landslide | Small | Rain | NA | 0 | 0 | Tiempo | http://www.tiempo.hn/lluvias-comienzan-a-causar-deslizamientos-en-carreteras-del-occidente-de-honduras/ | 74.27793 | 62.86104 |
stem(df_HD$"distance")##
## The decimal point is at the |
##
## 2 | 0
## 3 |
## 4 |
## 5 | 8stem(df_HD$"distance", scale = 2)##
## The decimal point is at the |
##
## 2 | 0
## 2 |
## 3 |
## 3 |
## 4 |
## 4 |
## 5 |
## 5 | 8Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 2.00805 | 1 | 50 | 50 | 50 | 50 |
| 5.79867 | 1 | 50 | 50 | 100 | 100 |
| Total | 2 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 3 obs. of 5 variables:
## $ n : num 1 1 2
## $ % : num 50 50 100
## $ val% : num 50 50 100
## $ %cum : num 50 100 100
## $ val%cum: num 50 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 2.00805 | 1 |
| 5.79867 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 2.00805 4.00805 6.00805distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (2.01,4.01] | 0 | 0 | 0 |
| (4.01,6.01] | 1 | 1 | 1 |
str(Freq_table)## 'data.frame': 2 obs. of 4 variables:
## $ distance: Factor w/ 2 levels "(2.01,4.01]",..: 1 2
## $ Freq : int 0 1
## $ Rel_Freq: num 0 1
## $ Cum_Freq: int 0 1df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (2.01,4.01] | 0 |
| (4.01,6.01] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_HD)## id date time continent_code country_name country_code
## nbr.val 2.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 6.672000e+03 NA NA NA NA NA
## max 7.462000e+03 NA NA NA NA NA
## range 7.900000e+02 NA NA NA NA NA
## sum 1.413400e+04 NA NA NA NA NA
## median 7.067000e+03 NA NA NA NA NA
## mean 7.067000e+03 NA NA NA NA NA
## SE.mean 3.950000e+02 NA NA NA NA NA
## CI.mean.0.95 5.018951e+03 NA NA NA NA NA
## var 3.120500e+05 NA NA NA NA NA
## std.dev 5.586144e+02 NA NA NA NA NA
## coef.var 7.904547e-02 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 2.000000e+00 NA 2.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 1.416000e+03 NA 2.0080500 NA
## max NA 2.389000e+03 NA 5.7986700 NA
## range NA 9.730000e+02 NA 3.7906200 NA
## sum NA 3.805000e+03 NA 7.8067200 NA
## median NA 1.902500e+03 NA 3.9033600 NA
## mean NA 1.902500e+03 NA 3.9033600 NA
## SE.mean NA 4.865000e+02 NA 1.8953100 NA
## CI.mean.0.95 NA 6.181569e+03 NA 24.0821969 NA
## var NA 4.733645e+05 NA 7.1844000 NA
## std.dev NA 6.880149e+02 NA 2.6803731 NA
## coef.var NA 3.616373e-01 NA 0.6866836 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 2.000000000 2.000000e+00 NA NA NA
## nbr.null 0.000000000 0.000000e+00 NA NA NA
## nbr.na 0.000000000 0.000000e+00 NA NA NA
## min 14.457900000 -8.916660e+01 NA NA NA
## max 14.481000000 -8.905370e+01 NA NA NA
## range 0.023100000 1.129000e-01 NA NA NA
## sum 28.938900000 -1.782203e+02 NA NA NA
## median 14.469450000 -8.911015e+01 NA NA NA
## mean 14.469450000 -8.911015e+01 NA NA NA
## SE.mean 0.011550000 5.645000e-02 NA NA NA
## CI.mean.0.95 0.146756665 7.172653e-01 NA NA NA
## var 0.000266805 6.373205e-03 NA NA NA
## std.dev 0.016334167 7.983236e-02 NA NA NA
## coef.var 0.001128873 -8.958840e-04 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 2 2 NA
## nbr.null NA NA NA 2 2 NA
## nbr.na NA NA NA 0 0 NA
## min NA NA NA 0 0 NA
## max NA NA NA 0 0 NA
## range NA NA NA 0 0 NA
## sum NA NA NA 0 0 NA
## median NA NA NA 0 0 NA
## mean NA NA NA 0 0 NA
## SE.mean NA NA NA 0 0 NA
## CI.mean.0.95 NA NA NA 0 0 NA
## var NA NA NA 0 0 NA
## std.dev NA NA NA 0 0 NA
## coef.var NA NA NA NaN NaN NA
## source_link prop ypos
## nbr.val NA 2.0000000 2.0000000
## nbr.null NA 0.0000000 0.0000000
## nbr.na NA 0.0000000 0.0000000
## min NA 25.7220702 12.8610351
## max NA 74.2779298 62.8610351
## range NA 48.5558596 50.0000000
## sum NA 100.0000000 75.7220702
## median NA 50.0000000 37.8610351
## mean NA 50.0000000 37.8610351
## SE.mean NA 24.2779298 25.0000000
## CI.mean.0.95 NA 308.4803464 317.6551184
## var NA 1178.8357492 1250.0000000
## std.dev NA 34.3341776 35.3553391
## coef.var NA 0.6866836 0.9338186boxplot(data, horizontal=TRUE, col='green')
Gráfico para Santa Bárbara (Honduras)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_HD <- subset(df, country_name == "Honduras")
knitr::kable(head(df_HD)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 854 | 10/19/08 | NA | NA | Honduras | HN | Copán | 4752 | Corquín | 0.43391 | NA | 14.5637 | -88.8693 | (14.563700000000001, -88.869299999999996) | Landslide | Landslide | Large | Tropical cyclone | Tropical Depression 16 | NA | 23 | NA | http://www.chron.com/disp/story.mpl/ap/world/6068144.html |
| 855 | 10/20/08 | NA | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 2.99239 | NA | 14.1080 | -87.2137 | (14.108000000000001, -87.213700000000003) | Landslide | Mudslide | Large | Tropical cyclone | Tropical Depression 16 | NA | 29 | NA | http://in.ibtimes.com/articles/20081021/honduras-landslide-tegucigalpa-victim.htm |
| 2062 | 7/12/10 | 5:30:00 | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 0.98377 | NA | 14.0831 | -87.1978 | (14.0831, -87.197800000000001) | Landslide | Mudslide | Medium | Downpour | NA | NA | 1 | NA | http://mdn.mainichi.jp/mdnnews/news/20100713p2a00m0na013000c.html |
| 2093 | 7/18/10 | NA | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 1.24404 | NA | 14.0814 | -87.1953 | (14.0814, -87.195300000000003) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.insidecostarica.com/dailynews/2010/july/19/centralamerica10071903.htm |
| 2217 | 8/7/10 | Overnight | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 2.21442 | NA | 14.0783 | -87.2270 | (14.0783, -87.227000000000004) | Landslide | Mudslide | Medium | Downpour | NA | NA | 3 | NA | NA |
| 2358 | 8/29/10 | 4:30:00 | NA | Honduras | HN | Francisco Morazán | 2288 | Santa Lucía | 4.75791 | NA | 14.1015 | -87.1607 | (14.1015, -87.160700000000006) | Landslide | Rockfall | Medium | Downpour | NA | NA | 5 | NA | NA |
library(dplyr)
df_HD <- subset(df, state == "Santa Bárbara")
knitr::kable(head(df_HD))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 6691 | 10/14/14 | Night | NA | Honduras | HN | Santa Bárbara | 1759 | Agualote | 2.91594 | Mine construction | 15.3090 | -88.5510 | (15.308999999999999, -88.551000000000002) | Landslide | Landslide | Medium | Rain | NA | 0 | 1 | Mundo | http://elmundo.com.sv/honduras-muere-un-minero-y-rescatan-a-otros-cinco-soterrados |
| 7464 | 9/28/15 | Morning | NA | Honduras | HN | Santa Bárbara | 1811 | Ilama | 2.87349 | Above road | 15.0909 | -88.2072 | (15.0909, -88.2072) | Landslide | Rockfall | Small | Rain | NA | 0 | 0 | Canal 6 | http://www.canal6.com.hn/destacado/derrumbes-incomunican-paso-entre-san-pedro-sula-y-santa-barbara.html |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_HD, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_HD, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_HD, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_HD <- df_HD %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_HD$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_HD, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_HD$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 2.87349 |
| 2.91594 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_HD$distance
names(distance) <- df_HD$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Agualote 2.91594 2.91594 50.36662 50.36662
## Ilama 2.87349 5.78943 49.63338 100.00000stem(df_HD$"distance")##
## The decimal point is 2 digit(s) to the left of the |
##
## 287 | 3
## 288 |
## 289 |
## 290 |
## 291 | 6head(df_HD)## # A tibble: 2 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 7464 9/28/15 Morning <NA> Honduras HN Sant~ 1811
## 2 6691 10/14/14 Night <NA> Honduras HN Sant~ 1759
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_HD))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 7464 | 9/28/15 | Morning | NA | Honduras | HN | Santa Bárbara | 1811 | Ilama | 2.87349 | Above road | 15.0909 | -88.2072 | (15.0909, -88.2072) | Landslide | Rockfall | Small | Rain | NA | 0 | 0 | Canal 6 | http://www.canal6.com.hn/destacado/derrumbes-incomunican-paso-entre-san-pedro-sula-y-santa-barbara.html | 49.63338 | 24.81669 |
| 6691 | 10/14/14 | Night | NA | Honduras | HN | Santa Bárbara | 1759 | Agualote | 2.91594 | Mine construction | 15.3090 | -88.5510 | (15.308999999999999, -88.551000000000002) | Landslide | Landslide | Medium | Rain | NA | 0 | 1 | Mundo | http://elmundo.com.sv/honduras-muere-un-minero-y-rescatan-a-otros-cinco-soterrados | 50.36662 | 74.81669 |
stem(df_HD$"distance")##
## The decimal point is 2 digit(s) to the left of the |
##
## 287 | 3
## 288 |
## 289 |
## 290 |
## 291 | 6stem(df_HD$"distance", scale = 2)##
## The decimal point is 2 digit(s) to the left of the |
##
## 287 | 3
## 287 |
## 288 |
## 288 |
## 289 |
## 289 |
## 290 |
## 290 |
## 291 |
## 291 | 6Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 2.87349 | 1 | 50 | 50 | 50 | 50 |
| 2.91594 | 1 | 50 | 50 | 100 | 100 |
| Total | 2 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 3 obs. of 5 variables:
## $ n : num 1 1 2
## $ % : num 50 50 100
## $ val% : num 50 50 100
## $ %cum : num 50 100 100
## $ val%cum: num 50 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 2.87349 | 1 |
| 2.91594 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 2.87349 3.87349distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (2.87,3.87] | 1 | 1 | 1 |
str(Freq_table)## 'data.frame': 1 obs. of 4 variables:
## $ distance: Factor w/ 1 level "(2.87,3.87]": 1
## $ Freq : int 1
## $ Rel_Freq: num 1
## $ Cum_Freq: int 1df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (2.87,3.87] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_HD)## id date time continent_code country_name country_code
## nbr.val 2.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 6.691000e+03 NA NA NA NA NA
## max 7.464000e+03 NA NA NA NA NA
## range 7.730000e+02 NA NA NA NA NA
## sum 1.415500e+04 NA NA NA NA NA
## median 7.077500e+03 NA NA NA NA NA
## mean 7.077500e+03 NA NA NA NA NA
## SE.mean 3.865000e+02 NA NA NA NA NA
## CI.mean.0.95 4.910948e+03 NA NA NA NA NA
## var 2.987645e+05 NA NA NA NA NA
## std.dev 5.465935e+02 NA NA NA NA NA
## coef.var 7.722975e-02 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 2.000000e+00 NA 2.0000000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000000 NA
## min NA 1.759000e+03 NA 2.8734900000 NA
## max NA 1.811000e+03 NA 2.9159400000 NA
## range NA 5.200000e+01 NA 0.0424500000 NA
## sum NA 3.570000e+03 NA 5.7894300000 NA
## median NA 1.785000e+03 NA 2.8947150000 NA
## mean NA 1.785000e+03 NA 2.8947150000 NA
## SE.mean NA 2.600000e+01 NA 0.0212250000 NA
## CI.mean.0.95 NA 3.303613e+02 NA 0.2696891955 NA
## var NA 1.352000e+03 NA 0.0009010013 NA
## std.dev NA 3.676955e+01 NA 0.0300166829 NA
## coef.var NA 2.059919e-02 NA 0.0103694778 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 2.00000000 2.000000e+00 NA NA NA
## nbr.null 0.00000000 0.000000e+00 NA NA NA
## nbr.na 0.00000000 0.000000e+00 NA NA NA
## min 15.09090000 -8.855100e+01 NA NA NA
## max 15.30900000 -8.820720e+01 NA NA NA
## range 0.21810000 3.438000e-01 NA NA NA
## sum 30.39990000 -1.767582e+02 NA NA NA
## median 15.19995000 -8.837910e+01 NA NA NA
## mean 15.19995000 -8.837910e+01 NA NA NA
## SE.mean 0.10905000 1.719000e-01 NA NA NA
## CI.mean.0.95 1.38561163 2.184197e+00 NA NA NA
## var 0.02378380 5.909922e-02 NA NA NA
## std.dev 0.15421999 2.431033e-01 NA NA NA
## coef.var 0.01014609 -2.750688e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 2 2.0000000 NA
## nbr.null NA NA NA 2 1.0000000 NA
## nbr.na NA NA NA 0 0.0000000 NA
## min NA NA NA 0 0.0000000 NA
## max NA NA NA 0 1.0000000 NA
## range NA NA NA 0 1.0000000 NA
## sum NA NA NA 0 1.0000000 NA
## median NA NA NA 0 0.5000000 NA
## mean NA NA NA 0 0.5000000 NA
## SE.mean NA NA NA 0 0.5000000 NA
## CI.mean.0.95 NA NA NA 0 6.3531024 NA
## var NA NA NA 0 0.5000000 NA
## std.dev NA NA NA 0 0.7071068 NA
## coef.var NA NA NA NaN 1.4142136 NA
## source_link prop ypos
## nbr.val NA 2.00000000 2.0000000
## nbr.null NA 0.00000000 0.0000000
## nbr.na NA 0.00000000 0.0000000
## min NA 49.63338360 24.8166918
## max NA 50.36661640 74.8166918
## range NA 0.73323281 50.0000000
## sum NA 100.00000000 99.6333836
## median NA 50.00000000 49.8166918
## mean NA 50.00000000 49.8166918
## SE.mean NA 0.36661640 25.0000000
## CI.mean.0.95 NA 4.65830307 317.6551184
## var NA 0.26881517 1250.0000000
## std.dev NA 0.51847389 35.3553391
## coef.var NA 0.01036948 0.7097087boxplot(data, horizontal=TRUE, col='green')
Gráfico para Nicaragua
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_NC <- subset(df, country_name == "Honduras")
knitr::kable(head(df_NC))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 854 | 10/19/08 | NA | NA | Honduras | HN | Copán | 4752 | Corquín | 0.43391 | NA | 14.5637 | -88.8693 | (14.563700000000001, -88.869299999999996) | Landslide | Landslide | Large | Tropical cyclone | Tropical Depression 16 | NA | 23 | NA | http://www.chron.com/disp/story.mpl/ap/world/6068144.html |
| 855 | 10/20/08 | NA | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 2.99239 | NA | 14.1080 | -87.2137 | (14.108000000000001, -87.213700000000003) | Landslide | Mudslide | Large | Tropical cyclone | Tropical Depression 16 | NA | 29 | NA | http://in.ibtimes.com/articles/20081021/honduras-landslide-tegucigalpa-victim.htm |
| 2062 | 7/12/10 | 5:30:00 | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 0.98377 | NA | 14.0831 | -87.1978 | (14.0831, -87.197800000000001) | Landslide | Mudslide | Medium | Downpour | NA | NA | 1 | NA | http://mdn.mainichi.jp/mdnnews/news/20100713p2a00m0na013000c.html |
| 2093 | 7/18/10 | NA | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 1.24404 | NA | 14.0814 | -87.1953 | (14.0814, -87.195300000000003) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.insidecostarica.com/dailynews/2010/july/19/centralamerica10071903.htm |
| 2217 | 8/7/10 | Overnight | NA | Honduras | HN | Francisco Morazán | 850848 | Tegucigalpa | 2.21442 | NA | 14.0783 | -87.2270 | (14.0783, -87.227000000000004) | Landslide | Mudslide | Medium | Downpour | NA | NA | 3 | NA | NA |
| 2358 | 8/29/10 | 4:30:00 | NA | Honduras | HN | Francisco Morazán | 2288 | Santa Lucía | 4.75791 | NA | 14.1015 | -87.1607 | (14.1015, -87.160700000000006) | Landslide | Rockfall | Medium | Downpour | NA | NA | 5 | NA | NA |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_NC, aes(fill= state, y=distance, x=country_name)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_NC, aes(fill=state, y=distance, x=country_name)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_NC, aes(x=country_name, y=distance, fill=state)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_NC <- df_NC %>%
arrange(desc(state)) %>%
mutate(prop = distance / sum(df_NC$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_NC, aes(x=country_name, y=prop, fill=state)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4## Warning in RColorBrewer::brewer.pal(n, pal): n too large, allowed maximum for palette Greens is 9
## Returning the palette you asked for with that many colors
Grafico de series temporales
library(forecast)
data<- ts(df_NC$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 0.31238 |
| 6.66574 |
| 2.91594 |
| 2.87349 |
| 2.00805 |
| 5.79867 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_NC$distance
names(distance) <- df_NC$state
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por estados"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Colón 36.3762900 36.3762900 21.8907391 21.8907391
## Comayagua 17.2861300 53.6624200 10.4025496 32.2932888
## Choluteca 11.6723700 65.3347900 7.0242679 39.3175567
## Comayagua 8.5258400 73.8606300 5.1307305 44.4482872
## Comayagua 7.2857500 81.1463800 4.3844618 48.8327489
## Yoro 6.6657400 87.8121200 4.0113485 52.8440974
## Copán 5.8972100 93.7093300 3.5488579 56.3929554
## Ocotepeque 5.7986700 99.5080000 3.4895580 59.8825133
## Francisco Morazán 4.7579100 104.2659100 2.8632432 62.7457566
## La Paz 4.6913300 108.9572400 2.8231763 65.5689329
## Comayagua 4.5336200 113.4908600 2.7282687 68.2972016
## Choluteca 3.6959600 117.1868200 2.2241767 70.5213783
## Francisco Morazán 3.6396200 120.8264400 2.1902721 72.7116504
## Francisco Morazán 3.5439900 124.3704300 2.1327233 74.8443736
## Cortés 3.5373700 127.9078000 2.1287395 76.9731131
## Francisco Morazán 3.2528100 131.1606100 1.9574953 78.9306084
## Francisco Morazán 3.1298600 134.2904700 1.8835057 80.8141140
## Francisco Morazán 2.9923900 137.2828600 1.8007782 82.6148922
## Santa Bárbara 2.9159400 140.1988000 1.7547716 84.3696639
## Francisco Morazán 2.9132600 143.1120600 1.7531588 86.1228227
## Santa Bárbara 2.8734900 145.9855500 1.7292258 87.8520485
## Francisco Morazán 2.2144200 148.1999700 1.3326068 89.1846553
## Francisco Morazán 2.0083000 150.2082700 1.2085667 90.3932220
## Ocotepeque 2.0080500 152.2163200 1.2084162 91.6016382
## El Paraíso 1.9005200 154.1168400 1.1437062 92.7453444
## Francisco Morazán 1.8589700 155.9758100 1.1187020 93.8640463
## Copán 1.3909500 157.3667600 0.8370541 94.7011005
## Francisco Morazán 1.3058300 158.6725900 0.7858301 95.4869306
## Francisco Morazán 1.2440400 159.9166300 0.7486458 96.2355763
## Francisco Morazán 1.2363900 161.1530200 0.7440421 96.9796184
## Francisco Morazán 0.9837700 162.1367900 0.5920189 97.5716373
## Cortés 0.9705700 163.1073600 0.5840754 98.1557127
## Francisco Morazán 0.9155200 164.0228800 0.5509470 98.7066598
## Copán 0.7441400 164.7670200 0.4478130 99.1544727
## Copán 0.4339100 165.2009300 0.2611209 99.4155937
## Choluteca 0.3698700 165.5708000 0.2225826 99.6381762
## Yoro 0.3123800 165.8831800 0.1879859 99.8261621
## Copán 0.2888700 166.1720500 0.1738379 100.0000000stem(df_NC$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 000011111111222223333334444
## 0 | 55566779
## 1 | 2
## 1 | 7
## 2 |
## 2 |
## 3 |
## 3 | 6head(df_NC)## # A tibble: 6 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 6202 5/20/14 <NA> <NA> Honduras HN Yoro 15774
## 2 7467 1/22/15 <NA> <NA> Honduras HN Yoro 2188
## 3 6691 10/14/14 Night <NA> Honduras HN Sant~ 1759
## 4 7464 9/28/15 Morning <NA> Honduras HN Sant~ 1811
## 5 6672 10/13/14 <NA> <NA> Honduras HN Ocot~ 2389
## 6 7462 9/25/15 <NA> <NA> Honduras HN Ocot~ 1416
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_NC))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 6202 | 5/20/14 | NA | NA | Honduras | HN | Yoro | 15774 | Yoro | 0.31238 | Unknown | 15.0666 | -87.3245 | (15.066599999999999, -87.3245) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | Prensa | http://www.laprensa.hn/lasultimas24/711060-98/deslizamientos-de-tierra-dejar%C3%ADa-incomunicadas-30-aldeas-en-yoro | 0.1879859 | 0.0939929 |
| 7467 | 1/22/15 | NA | NA | Honduras | HN | Yoro | 2188 | La Sarrosa | 6.66574 | Above road | 15.1754 | -87.8164 | (15.1754, -87.816400000000002) | Landslide | Rockfall | Small | Continuous rain | NA | 0 | 0 | La Prensa | http://www.laprensa.hn/honduras/787961-410/conductores-tienen-que-maniobrar-para-no-chocar-con-las-rocas-que-cubren | 4.0113485 | 2.1936601 |
| 6691 | 10/14/14 | Night | NA | Honduras | HN | Santa Bárbara | 1759 | Agualote | 2.91594 | Mine construction | 15.3090 | -88.5510 | (15.308999999999999, -88.551000000000002) | Landslide | Landslide | Medium | Rain | NA | 0 | 1 | Mundo | http://elmundo.com.sv/honduras-muere-un-minero-y-rescatan-a-otros-cinco-soterrados | 1.7547716 | 5.0767202 |
| 7464 | 9/28/15 | Morning | NA | Honduras | HN | Santa Bárbara | 1811 | Ilama | 2.87349 | Above road | 15.0909 | -88.2072 | (15.0909, -88.2072) | Landslide | Rockfall | Small | Rain | NA | 0 | 0 | Canal 6 | http://www.canal6.com.hn/destacado/derrumbes-incomunican-paso-entre-san-pedro-sula-y-santa-barbara.html | 1.7292258 | 6.8187189 |
| 6672 | 10/13/14 | NA | NA | Honduras | HN | Ocotepeque | 2389 | Sinuapa | 2.00805 | Below road | 14.4579 | -89.1666 | (14.4579, -89.166600000000003) | Landslide | Landslide | Medium | Downpour | NA | 0 | 0 | La Prensa | http://www.laprensa.hn/economia/757783-410/evac%C3%BAan-a-familias-por-deslizamientos-en-ocotepeque | 1.2084162 | 8.2875399 |
| 7462 | 9/25/15 | NA | NA | Honduras | HN | Ocotepeque | 1416 | La Labor | 5.79867 | Above road | 14.4810 | -89.0537 | (14.481, -89.053700000000006) | Landslide | Landslide | Small | Rain | NA | 0 | 0 | Tiempo | http://www.tiempo.hn/lluvias-comienzan-a-causar-deslizamientos-en-carreteras-del-occidente-de-honduras/ | 3.4895580 | 10.6365270 |
stem(df_NC$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 000011111111222223333334444
## 0 | 55566779
## 1 | 2
## 1 | 7
## 2 |
## 2 |
## 3 |
## 3 | 6stem(df_NC$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 33447900223499
## 2 | 0029990135567
## 4 | 57889
## 6 | 73
## 8 | 5
## 10 | 7
## 12 |
## 14 |
## 16 | 3
## 18 |
## 20 |
## 22 |
## 24 |
## 26 |
## 28 |
## 30 |
## 32 |
## 34 |
## 36 | 4Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.28887 | 1 | 2.6 | 2.6 | 2.6 | 2.6 |
| 0.31238 | 1 | 2.6 | 2.6 | 5.3 | 5.3 |
| 0.36987 | 1 | 2.6 | 2.6 | 7.9 | 7.9 |
| 0.43391 | 1 | 2.6 | 2.6 | 10.5 | 10.5 |
| 0.74414 | 1 | 2.6 | 2.6 | 13.2 | 13.2 |
| 0.91552 | 1 | 2.6 | 2.6 | 15.8 | 15.8 |
| 0.97057 | 1 | 2.6 | 2.6 | 18.4 | 18.4 |
| 0.98377 | 1 | 2.6 | 2.6 | 21.1 | 21.1 |
| 1.23639 | 1 | 2.6 | 2.6 | 23.7 | 23.7 |
| 1.24404 | 1 | 2.6 | 2.6 | 26.3 | 26.3 |
| 1.30583 | 1 | 2.6 | 2.6 | 28.9 | 28.9 |
| 1.39095 | 1 | 2.6 | 2.6 | 31.6 | 31.6 |
| 1.85897 | 1 | 2.6 | 2.6 | 34.2 | 34.2 |
| 1.90052 | 1 | 2.6 | 2.6 | 36.8 | 36.8 |
| 2.00805 | 1 | 2.6 | 2.6 | 39.5 | 39.5 |
| 2.0083 | 1 | 2.6 | 2.6 | 42.1 | 42.1 |
| 2.21442 | 1 | 2.6 | 2.6 | 44.7 | 44.7 |
| 2.87349 | 1 | 2.6 | 2.6 | 47.4 | 47.4 |
| 2.91326 | 1 | 2.6 | 2.6 | 50.0 | 50.0 |
| 2.91594 | 1 | 2.6 | 2.6 | 52.6 | 52.6 |
| 2.99239 | 1 | 2.6 | 2.6 | 55.3 | 55.3 |
| 3.12986 | 1 | 2.6 | 2.6 | 57.9 | 57.9 |
| 3.25281 | 1 | 2.6 | 2.6 | 60.5 | 60.5 |
| 3.53737 | 1 | 2.6 | 2.6 | 63.2 | 63.2 |
| 3.54399 | 1 | 2.6 | 2.6 | 65.8 | 65.8 |
| 3.63962 | 1 | 2.6 | 2.6 | 68.4 | 68.4 |
| 3.69596 | 1 | 2.6 | 2.6 | 71.1 | 71.1 |
| 4.53362 | 1 | 2.6 | 2.6 | 73.7 | 73.7 |
| 4.69133 | 1 | 2.6 | 2.6 | 76.3 | 76.3 |
| 4.75791 | 1 | 2.6 | 2.6 | 78.9 | 78.9 |
| 5.79867 | 1 | 2.6 | 2.6 | 81.6 | 81.6 |
| 5.89721 | 1 | 2.6 | 2.6 | 84.2 | 84.2 |
| 6.66574 | 1 | 2.6 | 2.6 | 86.8 | 86.8 |
| 7.28575 | 1 | 2.6 | 2.6 | 89.5 | 89.5 |
| 8.52584 | 1 | 2.6 | 2.6 | 92.1 | 92.1 |
| 11.67237 | 1 | 2.6 | 2.6 | 94.7 | 94.7 |
| 17.28613 | 1 | 2.6 | 2.6 | 97.4 | 97.4 |
| 36.37629 | 1 | 2.6 | 2.6 | 100.0 | 100.0 |
| Total | 38 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 39 obs. of 5 variables:
## $ n : num 1 1 1 1 1 1 1 1 1 1 ...
## $ % : num 2.6 2.6 2.6 2.6 2.6 2.6 2.6 2.6 2.6 2.6 ...
## $ val% : num 2.6 2.6 2.6 2.6 2.6 2.6 2.6 2.6 2.6 2.6 ...
## $ %cum : num 2.6 5.3 7.9 10.5 13.2 15.8 18.4 21.1 23.7 26.3 ...
## $ val%cum: num 2.6 5.3 7.9 10.5 13.2 15.8 18.4 21.1 23.7 26.3 ...x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.28887 | 1 |
| 0.31238 | 1 |
| 0.36987 | 1 |
| 0.43391 | 1 |
| 0.74414 | 1 |
| 0.91552 | 1 |
| 0.97057 | 1 |
| 0.98377 | 1 |
| 1.23639 | 1 |
| 1.24404 | 1 |
| 1.30583 | 1 |
| 1.39095 | 1 |
| 1.85897 | 1 |
| 1.90052 | 1 |
| 2.00805 | 1 |
| 2.0083 | 1 |
| 2.21442 | 1 |
| 2.87349 | 1 |
| 2.91326 | 1 |
| 2.91594 | 1 |
| 2.99239 | 1 |
| 3.12986 | 1 |
| 3.25281 | 1 |
| 3.53737 | 1 |
| 3.54399 | 1 |
| 3.63962 | 1 |
| 3.69596 | 1 |
| 4.53362 | 1 |
| 4.69133 | 1 |
| 4.75791 | 1 |
| 5.79867 | 1 |
| 5.89721 | 1 |
| 6.66574 | 1 |
| 7.28575 | 1 |
| 8.52584 | 1 |
| 11.67237 | 1 |
| 17.28613 | 1 |
| 36.37629 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.28887 6.28887 12.28887 18.28887 24.28887 30.28887 36.28887 42.28887distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.289,6.29] | 31 | 0.8378378 | 31 |
| (6.29,12.3] | 4 | 0.1081081 | 35 |
| (12.3,18.3] | 1 | 0.0270270 | 36 |
| (18.3,24.3] | 0 | 0.0000000 | 36 |
| (24.3,30.3] | 0 | 0.0000000 | 36 |
| (30.3,36.3] | 0 | 0.0000000 | 36 |
| (36.3,42.3] | 1 | 0.0270270 | 37 |
str(Freq_table)## 'data.frame': 7 obs. of 4 variables:
## $ distance: Factor w/ 7 levels "(0.289,6.29]",..: 1 2 3 4 5 6 7
## $ Freq : int 31 4 1 0 0 0 1
## $ Rel_Freq: num 0.838 0.108 0.027 0 0 ...
## $ Cum_Freq: int 31 35 36 36 36 36 37df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.289,6.29] | 31 |
| (6.29,12.3] | 4 |
| (12.3,18.3] | 1 |
| (18.3,24.3] | 0 |
| (24.3,30.3] | 0 |
| (30.3,36.3] | 0 |
| (36.3,42.3] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_NC)## id date time continent_code country_name country_code
## nbr.val 3.800000e+01 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 8.540000e+02 NA NA NA NA NA
## max 7.485000e+03 NA NA NA NA NA
## range 6.631000e+03 NA NA NA NA NA
## sum 2.290210e+05 NA NA NA NA NA
## median 7.448500e+03 NA NA NA NA NA
## mean 6.026868e+03 NA NA NA NA NA
## SE.mean 3.671138e+02 NA NA NA NA NA
## CI.mean.0.95 7.438432e+02 NA NA NA NA NA
## var 5.121356e+06 NA NA NA NA NA
## std.dev 2.263041e+03 NA NA NA NA NA
## coef.var 3.754921e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 3.800000e+01 NA 38.000000 NA
## nbr.null NA 0.000000e+00 NA 0.000000 NA
## nbr.na NA 0.000000e+00 NA 0.000000 NA
## min NA 1.043000e+03 NA 0.288870 NA
## max NA 8.508480e+05 NA 36.376290 NA
## range NA 8.498050e+05 NA 36.087420 NA
## sum NA 7.001138e+06 NA 166.172050 NA
## median NA 1.936000e+03 NA 2.914600 NA
## mean NA 1.842405e+05 NA 4.372949 NA
## SE.mean NA 5.663200e+04 NA 1.023393 NA
## CI.mean.0.95 NA 1.147473e+05 NA 2.073592 NA
## var NA 1.218729e+11 NA 39.798695 NA
## std.dev NA 3.491031e+05 NA 6.308621 NA
## coef.var NA 1.894823e+00 NA 1.442647 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 38.00000000 3.800000e+01 NA NA NA
## nbr.null 0.00000000 0.000000e+00 NA NA NA
## nbr.na 0.00000000 0.000000e+00 NA NA NA
## min 13.28610000 -8.916660e+01 NA NA NA
## max 15.52270000 -8.526500e+01 NA NA NA
## range 2.23660000 3.901600e+00 NA NA NA
## sum 546.00580000 -3.329927e+03 NA NA NA
## median 14.20695000 -8.728760e+01 NA NA NA
## mean 14.36857368 -8.762966e+01 NA NA NA
## SE.mean 0.08447952 1.301577e-01 NA NA NA
## CI.mean.0.95 0.17117178 2.637245e-01 NA NA NA
## var 0.27119802 6.437585e-01 NA NA NA
## std.dev 0.52076676 8.023457e-01 NA NA NA
## coef.var 0.03624346 -9.156096e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities
## nbr.val NA NA NA 29.0000000 38.0000000
## nbr.null NA NA NA 26.0000000 25.0000000
## nbr.na NA NA NA 9.0000000 0.0000000
## min NA NA NA 0.0000000 0.0000000
## max NA NA NA 3.0000000 29.0000000
## range NA NA NA 3.0000000 29.0000000
## sum NA NA NA 6.0000000 86.0000000
## median NA NA NA 0.0000000 0.0000000
## mean NA NA NA 0.2068966 2.2631579
## SE.mean NA NA NA 0.1253499 0.9774733
## CI.mean.0.95 NA NA NA 0.2567675 1.9805491
## var NA NA NA 0.4556650 36.3072546
## std.dev NA NA NA 0.6750296 6.0255502
## coef.var NA NA NA 3.2626433 2.6624524
## source_name source_link prop ypos
## nbr.val NA NA 38.0000000 3.800000e+01
## nbr.null NA NA 0.0000000 0.000000e+00
## nbr.na NA NA 0.0000000 0.000000e+00
## min NA NA 0.1738379 9.399294e-02
## max NA NA 21.8907391 9.988871e+01
## range NA NA 21.7169012 9.979472e+01
## sum NA NA 100.0000000 1.347990e+03
## median NA NA 1.7539652 3.219648e+01
## mean NA NA 2.6315789 3.547342e+01
## SE.mean NA NA 0.6158637 4.046533e+00
## CI.mean.0.95 NA NA 1.2478585 8.199055e+00
## var NA NA 14.4129500 6.222284e+02
## std.dev NA NA 3.7964391 2.494451e+01
## coef.var NA NA 1.4426469 7.031887e-01boxplot(data, horizontal=TRUE, col='green')
Gráfico para Masaya (Nicaragua)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_NC <- subset(df, country_name == "Nicaragua")
knitr::kable(head(df_NC)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 229 | 9/4/07 | NA | NA | Nicaragua | NI | Atlántico Norte | 6315 | Bonanza | 54.90196 | NA | 13.6670 | -84.2435 | (13.667, -84.243499999999997) | Landslide | Complex | Medium | Tropical cyclone | Hurricane Felix | NA | NA | United Nations Development Programme - Relief Web | http://www.reliefweb.int/ |
| 826 | 10/3/08 | NA | NA | Nicaragua | NI | Masaya | 5182 | Tisma | 14.49301 | NA | 12.1200 | -85.8900 | (12.12, -85.89) | Landslide | Landslide | Medium | Downpour | NA | NA | 9 | CBC | http://www.cbc.ca/world/story/2008/10/04/nicaragua-flooding.html |
| 2289 | 8/20/10 | NA | NA | Nicaragua | NI | Managua | 16469 | El Crucero | 5.84054 | NA | 12.0420 | -86.2998 | (12.042, -86.299800000000005) | Landslide | Mudslide | Medium | Downpour | NA | NA | 3 | NA | NA |
| 2330 | 8/25/10 | NA | NA | Nicaragua | NI | Jinotega | 2367 | San José de Bocay | 1.36745 | NA | 13.5317 | -85.5325 | (13.531700000000001, -85.532499999999999) | Landslide | Landslide | Medium | Downpour | NA | NA | NA | NA | NA |
| 6089 | 6/23/14 | NA | NA | Nicaragua | NI | Chontales | 5827 | Santo Domingo | 31.14242 | Unknown | 12.3535 | -84.8095 | (12.3535, -84.8095) | Landslide | Landslide | Small | Continuous rain | NA | 0 | 0 | Wilfried Strauch | NA |
| 6090 | 6/23/14 | NA | NA | Nicaragua | NI | Chontales | 5827 | Santo Domingo | 31.24511 | Unknown | 12.3521 | -84.8080 | (12.3521, -84.808000000000007) | Landslide | Landslide | Medium | Continuous rain | NA | 0 | 0 | Wilfried Strauch | NA |
library(dplyr)
df_NC <- subset(df, state == "Masaya")
knitr::kable(head(df_NC))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 826 | 10/3/08 | NA | NA | Nicaragua | NI | Masaya | 5182 | Tisma | 14.49301 | NA | 12.1200 | -85.89 | (12.12, -85.89) | Landslide | Landslide | Medium | Downpour | NA | NA | 9 | CBC | http://www.cbc.ca/world/story/2008/10/04/nicaragua-flooding.html |
| 7481 | 5/13/15 | NA | NA | Nicaragua | NI | Masaya | 2111 | San Juan de Oriente | 1.56730 | Natural slope | 11.9013 | -86.06 | (11.901300000000001, -86.06) | Landslide | Debris flow | Large | Rain | NA | 0 | 0 | La Gente | http://www.radiolaprimerisima.com/noticias/183345/reportan-despales-en-la-reserva-rio-indio-maiz |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_NC, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_NC, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_NC, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_NC <- df_NC %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_NC$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_NC, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_NC$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 14.49301 |
| 1.56730 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_NC$distance
names(distance) <- df_NC$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Tisma 14.49301 14.49301 90.24116 90.24116
## San Juan de Oriente 1.56730 16.06031 9.75884 100.00000stem(df_NC$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 2
## 0 |
## 1 | 4head(df_NC)## # A tibble: 2 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 826 10/3/08 <NA> <NA> Nicaragua NI Masaya 5182
## 2 7481 5/13/15 <NA> <NA> Nicaragua NI Masaya 2111
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_NC))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 826 | 10/3/08 | NA | NA | Nicaragua | NI | Masaya | 5182 | Tisma | 14.49301 | NA | 12.1200 | -85.89 | (12.12, -85.89) | Landslide | Landslide | Medium | Downpour | NA | NA | 9 | CBC | http://www.cbc.ca/world/story/2008/10/04/nicaragua-flooding.html | 90.24116 | 45.12058 |
| 7481 | 5/13/15 | NA | NA | Nicaragua | NI | Masaya | 2111 | San Juan de Oriente | 1.56730 | Natural slope | 11.9013 | -86.06 | (11.901300000000001, -86.06) | Landslide | Debris flow | Large | Rain | NA | 0 | 0 | La Gente | http://www.radiolaprimerisima.com/noticias/183345/reportan-despales-en-la-reserva-rio-indio-maiz | 9.75884 | 95.12058 |
stem(df_NC$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 2
## 0 |
## 1 | 4stem(df_NC$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 6
## 2 |
## 4 |
## 6 |
## 8 |
## 10 |
## 12 |
## 14 | 5Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 1.5673 | 1 | 50 | 50 | 50 | 50 |
| 14.49301 | 1 | 50 | 50 | 100 | 100 |
| Total | 2 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 3 obs. of 5 variables:
## $ n : num 1 1 2
## $ % : num 50 50 100
## $ val% : num 50 50 100
## $ %cum : num 50 100 100
## $ val%cum: num 50 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 1.5673 | 1 |
| 14.49301 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 1.5673 8.5673 15.5673distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (1.57,8.57] | 0 | 0 | 0 |
| (8.57,15.6] | 1 | 1 | 1 |
str(Freq_table)## 'data.frame': 2 obs. of 4 variables:
## $ distance: Factor w/ 2 levels "(1.57,8.57]",..: 1 2
## $ Freq : int 0 1
## $ Rel_Freq: num 0 1
## $ Cum_Freq: int 0 1df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (1.57,8.57] | 0 |
| (8.57,15.6] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_NC)## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 2.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 8.260000e+02 NA NA NA NA NA
## max 7.481000e+03 NA NA NA NA NA
## range 6.655000e+03 NA NA NA NA NA
## sum 8.307000e+03 NA NA NA NA NA
## median 4.153500e+03 NA NA NA NA NA
## mean 4.153500e+03 NA NA NA NA NA
## SE.mean 3.327500e+03 NA NA NA NA NA
## CI.mean.0.95 4.227990e+04 NA NA NA NA NA
## var 2.214451e+07 NA NA NA NA NA
## std.dev 4.705796e+03 NA NA NA NA NA
## coef.var 1.132971e+00 NA NA NA NA NA
## state population city distance location_description latitude
## nbr.val NA 2.000000e+00 NA 2.000000 NA 2.00000000
## nbr.null NA 0.000000e+00 NA 0.000000 NA 0.00000000
## nbr.na NA 0.000000e+00 NA 0.000000 NA 0.00000000
## min NA 2.111000e+03 NA 1.567300 NA 11.90130000
## max NA 5.182000e+03 NA 14.493010 NA 12.12000000
## range NA 3.071000e+03 NA 12.925710 NA 0.21870000
## sum NA 7.293000e+03 NA 16.060310 NA 24.02130000
## median NA 3.646500e+03 NA 8.030155 NA 12.01065000
## mean NA 3.646500e+03 NA 8.030155 NA 12.01065000
## SE.mean NA 1.535500e+03 NA 6.462855 NA 0.10935000
## CI.mean.0.95 NA 1.951038e+04 NA 82.118359 NA 1.38942349
## var NA 4.715521e+06 NA 83.536990 NA 0.02391484
## std.dev NA 2.171525e+03 NA 9.139857 NA 0.15464425
## coef.var NA 5.955094e-01 NA 1.138192 NA 0.01287559
## longitude geolocation hazard_type landslide_type
## nbr.val 2.000000e+00 NA NA NA
## nbr.null 0.000000e+00 NA NA NA
## nbr.na 0.000000e+00 NA NA NA
## min -8.606000e+01 NA NA NA
## max -8.589000e+01 NA NA NA
## range 1.700000e-01 NA NA NA
## sum -1.719500e+02 NA NA NA
## median -8.597500e+01 NA NA NA
## mean -8.597500e+01 NA NA NA
## SE.mean 8.500000e-02 NA NA NA
## CI.mean.0.95 1.080027e+00 NA NA NA
## var 1.445000e-02 NA NA NA
## std.dev 1.202082e-01 NA NA NA
## coef.var -1.398176e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 1 2.000000 NA
## nbr.null NA NA NA 1 1.000000 NA
## nbr.na NA NA NA 1 0.000000 NA
## min NA NA NA 0 0.000000 NA
## max NA NA NA 0 9.000000 NA
## range NA NA NA 0 9.000000 NA
## sum NA NA NA 0 9.000000 NA
## median NA NA NA 0 4.500000 NA
## mean NA NA NA 0 4.500000 NA
## SE.mean NA NA NA NA 4.500000 NA
## CI.mean.0.95 NA NA NA NaN 57.177921 NA
## var NA NA NA NA 40.500000 NA
## std.dev NA NA NA NA 6.363961 NA
## coef.var NA NA NA NA 1.414214 NA
## source_link prop ypos
## nbr.val NA 2.000000 2.0000000
## nbr.null NA 0.000000 0.0000000
## nbr.na NA 0.000000 0.0000000
## min NA 9.758840 45.1205799
## max NA 90.241160 95.1205799
## range NA 80.482319 50.0000000
## sum NA 100.000000 140.2411597
## median NA 50.000000 70.1205799
## mean NA 50.000000 70.1205799
## SE.mean NA 40.241160 25.0000000
## CI.mean.0.95 NA 511.312414 317.6551184
## var NA 3238.701873 1250.0000000
## std.dev NA 56.909594 35.3553391
## coef.var NA 1.138192 0.5042077boxplot(data, horizontal=TRUE, col='green')
Gráfico para Managua (Nicaragua)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_NC <- subset(df, country_name == "Nicaragua")
knitr::kable(head(df_NC)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 229 | 9/4/07 | NA | NA | Nicaragua | NI | Atlántico Norte | 6315 | Bonanza | 54.90196 | NA | 13.6670 | -84.2435 | (13.667, -84.243499999999997) | Landslide | Complex | Medium | Tropical cyclone | Hurricane Felix | NA | NA | United Nations Development Programme - Relief Web | http://www.reliefweb.int/ |
| 826 | 10/3/08 | NA | NA | Nicaragua | NI | Masaya | 5182 | Tisma | 14.49301 | NA | 12.1200 | -85.8900 | (12.12, -85.89) | Landslide | Landslide | Medium | Downpour | NA | NA | 9 | CBC | http://www.cbc.ca/world/story/2008/10/04/nicaragua-flooding.html |
| 2289 | 8/20/10 | NA | NA | Nicaragua | NI | Managua | 16469 | El Crucero | 5.84054 | NA | 12.0420 | -86.2998 | (12.042, -86.299800000000005) | Landslide | Mudslide | Medium | Downpour | NA | NA | 3 | NA | NA |
| 2330 | 8/25/10 | NA | NA | Nicaragua | NI | Jinotega | 2367 | San José de Bocay | 1.36745 | NA | 13.5317 | -85.5325 | (13.531700000000001, -85.532499999999999) | Landslide | Landslide | Medium | Downpour | NA | NA | NA | NA | NA |
| 6089 | 6/23/14 | NA | NA | Nicaragua | NI | Chontales | 5827 | Santo Domingo | 31.14242 | Unknown | 12.3535 | -84.8095 | (12.3535, -84.8095) | Landslide | Landslide | Small | Continuous rain | NA | 0 | 0 | Wilfried Strauch | NA |
| 6090 | 6/23/14 | NA | NA | Nicaragua | NI | Chontales | 5827 | Santo Domingo | 31.24511 | Unknown | 12.3521 | -84.8080 | (12.3521, -84.808000000000007) | Landslide | Landslide | Medium | Continuous rain | NA | 0 | 0 | Wilfried Strauch | NA |
library(dplyr)
df_NC <- subset(df, state == "Managua")
knitr::kable(head(df_NC))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2289 | 8/20/10 | NA | NA | Nicaragua | NI | Managua | 16469 | El Crucero | 5.84054 | NA | 12.0420 | -86.2998 | (12.042, -86.299800000000005) | Landslide | Mudslide | Medium | Downpour | NA | NA | 3 | NA | NA |
| 6270 | 10/16/14 | Night | NA | Nicaragua | NI | Managua | 70013 | Ciudad Sandino | 5.59574 | Retaining wall | 12.1137 | -86.2409 | (12.1137, -86.240899999999996) | Landslide | Mudslide | Small | Downpour | NA | 0 | 9 | The Washington Post | http://www.washingtonpost.com/posttv/world/at-least-nine-killed-in-nicaragua-mudslide/2014/10/17/4c9559dc-5633-11e4-b86d-184ac281388d_video.html |
| 7477 | 6/12/15 | NA | NA | Nicaragua | NI | Managua | 1902 | Terrabona | 18.92056 | Above road | 12.5769 | -86.0418 | (12.5769, -86.041799999999995) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | La Prensa | http://www.laprensa.com.ni/2015/06/12/nacionales/1849021-managua-colapsa |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_NC, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_NC, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_NC, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_NC <- df_NC %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_NC$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_NC, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_NC$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 18.92056 |
| 5.84054 |
| 5.59574 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_NC$distance
names(distance) <- df_NC$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Terrabona 18.92056 18.92056 62.32717 62.32717
## El Crucero 5.84054 24.76110 19.23962 81.56679
## Ciudad Sandino 5.59574 30.35684 18.43321 100.00000stem(df_NC$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 66
## 1 |
## 1 | 9head(df_NC)## # A tibble: 3 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 7477 6/12/15 <NA> <NA> Nicaragua NI Managua 1902
## 2 2289 8/20/10 <NA> <NA> Nicaragua NI Managua 16469
## 3 6270 10/16/14 Night <NA> Nicaragua NI Managua 70013
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_NC))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 7477 | 6/12/15 | NA | NA | Nicaragua | NI | Managua | 1902 | Terrabona | 18.92056 | Above road | 12.5769 | -86.0418 | (12.5769, -86.041799999999995) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | La Prensa | http://www.laprensa.com.ni/2015/06/12/nacionales/1849021-managua-colapsa | 62.32717 | 31.16359 |
| 2289 | 8/20/10 | NA | NA | Nicaragua | NI | Managua | 16469 | El Crucero | 5.84054 | NA | 12.0420 | -86.2998 | (12.042, -86.299800000000005) | Landslide | Mudslide | Medium | Downpour | NA | NA | 3 | NA | NA | 19.23962 | 71.94698 |
| 6270 | 10/16/14 | Night | NA | Nicaragua | NI | Managua | 70013 | Ciudad Sandino | 5.59574 | Retaining wall | 12.1137 | -86.2409 | (12.1137, -86.240899999999996) | Landslide | Mudslide | Small | Downpour | NA | 0 | 9 | The Washington Post | http://www.washingtonpost.com/posttv/world/at-least-nine-killed-in-nicaragua-mudslide/2014/10/17/4c9559dc-5633-11e4-b86d-184ac281388d_video.html | 18.43321 | 90.78340 |
stem(df_NC$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 66
## 1 |
## 1 | 9stem(df_NC$"distance", scale = 2)##
## The decimal point is at the |
##
## 4 | 68
## 6 |
## 8 |
## 10 |
## 12 |
## 14 |
## 16 |
## 18 | 9Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 5.59574 | 1 | 33.3 | 33.3 | 33.3 | 33.3 |
| 5.84054 | 1 | 33.3 | 33.3 | 66.7 | 66.7 |
| 18.92056 | 1 | 33.3 | 33.3 | 100.0 | 100.0 |
| Total | 3 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 4 obs. of 5 variables:
## $ n : num 1 1 1 3
## $ % : num 33.3 33.3 33.3 100
## $ val% : num 33.3 33.3 33.3 100
## $ %cum : num 33.3 66.7 100 100
## $ val%cum: num 33.3 66.7 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 5.59574 | 1 |
| 5.84054 | 1 |
| 18.92056 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 5.59574 10.59574 15.59574 20.59574distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (5.6,10.6] | 1 | 0.5 | 1 |
| (10.6,15.6] | 0 | 0.0 | 1 |
| (15.6,20.6] | 1 | 0.5 | 2 |
str(Freq_table)## 'data.frame': 3 obs. of 4 variables:
## $ distance: Factor w/ 3 levels "(5.6,10.6]","(10.6,15.6]",..: 1 2 3
## $ Freq : int 1 0 1
## $ Rel_Freq: num 0.5 0 0.5
## $ Cum_Freq: int 1 1 2df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (5.6,10.6] | 1 |
| (10.6,15.6] | 0 |
| (15.6,20.6] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_NC)## id date time continent_code country_name country_code
## nbr.val 3.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 2.289000e+03 NA NA NA NA NA
## max 7.477000e+03 NA NA NA NA NA
## range 5.188000e+03 NA NA NA NA NA
## sum 1.603600e+04 NA NA NA NA NA
## median 6.270000e+03 NA NA NA NA NA
## mean 5.345333e+03 NA NA NA NA NA
## SE.mean 1.567386e+03 NA NA NA NA NA
## CI.mean.0.95 6.743916e+03 NA NA NA NA NA
## var 7.370092e+06 NA NA NA NA NA
## std.dev 2.714791e+03 NA NA NA NA NA
## coef.var 5.078807e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 3.000000e+00 NA 3.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 1.902000e+03 NA 5.5957400 NA
## max NA 7.001300e+04 NA 18.9205600 NA
## range NA 6.811100e+04 NA 13.3248200 NA
## sum NA 8.838400e+04 NA 30.3568400 NA
## median NA 1.646900e+04 NA 5.8405400 NA
## mean NA 2.946133e+04 NA 10.1189467 NA
## SE.mean NA 2.070731e+04 NA 4.4013740 NA
## CI.mean.0.95 NA 8.909635e+04 NA 18.9375839 NA
## var NA 1.286378e+09 NA 58.1162797 NA
## std.dev NA 3.586611e+04 NA 7.6234034 NA
## coef.var NA 1.217396e+00 NA 0.7533791 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 3.00000000 3.00000000 NA NA NA
## nbr.null 0.00000000 0.00000000 NA NA NA
## nbr.na 0.00000000 0.00000000 NA NA NA
## min 12.04200000 -86.29980000 NA NA NA
## max 12.57690000 -86.04180000 NA NA NA
## range 0.53490000 0.25800000 NA NA NA
## sum 36.73260000 -258.58250000 NA NA NA
## median 12.11370000 -86.24090000 NA NA NA
## mean 12.24420000 -86.19416667 NA NA NA
## SE.mean 0.16763272 0.07805768 NA NA NA
## CI.mean.0.95 0.72126540 0.33585508 NA NA NA
## var 0.08430219 0.01827900 NA NA NA
## std.dev 0.29034839 0.13519986 NA NA NA
## coef.var 0.02371314 -0.00156855 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 2 3.000000 NA
## nbr.null NA NA NA 2 1.000000 NA
## nbr.na NA NA NA 1 0.000000 NA
## min NA NA NA 0 0.000000 NA
## max NA NA NA 0 9.000000 NA
## range NA NA NA 0 9.000000 NA
## sum NA NA NA 0 12.000000 NA
## median NA NA NA 0 3.000000 NA
## mean NA NA NA 0 4.000000 NA
## SE.mean NA NA NA 0 2.645751 NA
## CI.mean.0.95 NA NA NA 0 11.383749 NA
## var NA NA NA 0 21.000000 NA
## std.dev NA NA NA 0 4.582576 NA
## coef.var NA NA NA NaN 1.145644 NA
## source_link prop ypos
## nbr.val NA 3.0000000 3.0000000
## nbr.null NA 0.0000000 0.0000000
## nbr.na NA 0.0000000 0.0000000
## min NA 18.4332098 31.1635862
## max NA 62.3271724 90.7833951
## range NA 43.8939626 59.6198089
## sum NA 100.0000000 193.8939626
## median NA 19.2396178 71.9469813
## mean NA 33.3333333 64.6313209
## SE.mean NA 14.4987885 17.5951657
## CI.mean.0.95 NA 62.3832518 75.7058878
## var NA 630.6446011 928.7695694
## std.dev NA 25.1126383 30.4757210
## coef.var NA 0.7533791 0.4715318boxplot(data, horizontal=TRUE, col='green')
Gráfico para Jinotega (Nicaragua)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_NC <- subset(df, country_name == "Nicaragua")
knitr::kable(head(df_NC)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 229 | 9/4/07 | NA | NA | Nicaragua | NI | Atlántico Norte | 6315 | Bonanza | 54.90196 | NA | 13.6670 | -84.2435 | (13.667, -84.243499999999997) | Landslide | Complex | Medium | Tropical cyclone | Hurricane Felix | NA | NA | United Nations Development Programme - Relief Web | http://www.reliefweb.int/ |
| 826 | 10/3/08 | NA | NA | Nicaragua | NI | Masaya | 5182 | Tisma | 14.49301 | NA | 12.1200 | -85.8900 | (12.12, -85.89) | Landslide | Landslide | Medium | Downpour | NA | NA | 9 | CBC | http://www.cbc.ca/world/story/2008/10/04/nicaragua-flooding.html |
| 2289 | 8/20/10 | NA | NA | Nicaragua | NI | Managua | 16469 | El Crucero | 5.84054 | NA | 12.0420 | -86.2998 | (12.042, -86.299800000000005) | Landslide | Mudslide | Medium | Downpour | NA | NA | 3 | NA | NA |
| 2330 | 8/25/10 | NA | NA | Nicaragua | NI | Jinotega | 2367 | San José de Bocay | 1.36745 | NA | 13.5317 | -85.5325 | (13.531700000000001, -85.532499999999999) | Landslide | Landslide | Medium | Downpour | NA | NA | NA | NA | NA |
| 6089 | 6/23/14 | NA | NA | Nicaragua | NI | Chontales | 5827 | Santo Domingo | 31.14242 | Unknown | 12.3535 | -84.8095 | (12.3535, -84.8095) | Landslide | Landslide | Small | Continuous rain | NA | 0 | 0 | Wilfried Strauch | NA |
| 6090 | 6/23/14 | NA | NA | Nicaragua | NI | Chontales | 5827 | Santo Domingo | 31.24511 | Unknown | 12.3521 | -84.8080 | (12.3521, -84.808000000000007) | Landslide | Landslide | Medium | Continuous rain | NA | 0 | 0 | Wilfried Strauch | NA |
library(dplyr)
df_NC <- subset(df, state == "Jinotega")
knitr::kable(head(df_NC))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2330 | 8/25/10 | NA | NA | Nicaragua | NI | Jinotega | 2367 | San José de Bocay | 1.36745 | NA | 13.5317 | -85.5325 | (13.531700000000001, -85.532499999999999) | Landslide | Landslide | Medium | Downpour | NA | NA | NA | NA | NA |
| 7470 | 10/8/15 | NA | NA | Nicaragua | NI | Jinotega | 6955 | Wiwilí | 25.81514 | Unknown | 13.8176 | -85.6880 | (13.817600000000001, -85.688000000000002) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | El Nuevo Diario | http://www.elnuevodiario.com.ni/nacionales/372954-evacuan-cinco-familias-deslizamiento-tierra-jinote/ |
| 7471 | 2/19/16 | NA | NA | Nicaragua | NI | Jinotega | 51073 | Jinotega | 2.44880 | Below road | 13.0805 | -85.9925 | (13.080500000000001, -85.992500000000007) | Landslide | Landslide | Small | Rain | NA | 0 | 0 | Hoy | http://www.hoy.com.ni/2015/09/26/r%C3%ADo-ahoga-a-tres-ni%C3%B1as/ |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_NC, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_NC, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_NC, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_NC <- df_NC %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_NC$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_NC, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_NC$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 25.81514 |
| 1.36745 |
| 2.44880 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_NC$distance
names(distance) <- df_NC$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Wiwilí 25.815140 25.815140 87.120921 87.120921
## Jinotega 2.448800 28.263940 8.264209 95.385130
## San José de Bocay 1.367450 29.631390 4.614870 100.000000stem(df_NC$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 12
## 0 |
## 1 |
## 1 |
## 2 |
## 2 | 6head(df_NC)## # A tibble: 3 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 7470 10/8/15 <NA> <NA> Nicaragua NI Jinotega 6955
## 2 2330 8/25/10 <NA> <NA> Nicaragua NI Jinotega 2367
## 3 7471 2/19/16 <NA> <NA> Nicaragua NI Jinotega 51073
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_NC))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 7470 | 10/8/15 | NA | NA | Nicaragua | NI | Jinotega | 6955 | Wiwilí | 25.81514 | Unknown | 13.8176 | -85.6880 | (13.817600000000001, -85.688000000000002) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | El Nuevo Diario | http://www.elnuevodiario.com.ni/nacionales/372954-evacuan-cinco-familias-deslizamiento-tierra-jinote/ | 87.120921 | 43.56046 |
| 2330 | 8/25/10 | NA | NA | Nicaragua | NI | Jinotega | 2367 | San José de Bocay | 1.36745 | NA | 13.5317 | -85.5325 | (13.531700000000001, -85.532499999999999) | Landslide | Landslide | Medium | Downpour | NA | NA | NA | NA | NA | 4.614870 | 89.42836 |
| 7471 | 2/19/16 | NA | NA | Nicaragua | NI | Jinotega | 51073 | Jinotega | 2.44880 | Below road | 13.0805 | -85.9925 | (13.080500000000001, -85.992500000000007) | Landslide | Landslide | Small | Rain | NA | 0 | 0 | Hoy | http://www.hoy.com.ni/2015/09/26/r%C3%ADo-ahoga-a-tres-ni%C3%B1as/ | 8.264209 | 95.86790 |
stem(df_NC$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 12
## 0 |
## 1 |
## 1 |
## 2 |
## 2 | 6stem(df_NC$"distance", scale = 2)##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 12
## 0 |
## 1 |
## 1 |
## 2 |
## 2 | 6Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 1.36745 | 1 | 33.3 | 33.3 | 33.3 | 33.3 |
| 2.4488 | 1 | 33.3 | 33.3 | 66.7 | 66.7 |
| 25.81514 | 1 | 33.3 | 33.3 | 100.0 | 100.0 |
| Total | 3 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 4 obs. of 5 variables:
## $ n : num 1 1 1 3
## $ % : num 33.3 33.3 33.3 100
## $ val% : num 33.3 33.3 33.3 100
## $ %cum : num 33.3 66.7 100 100
## $ val%cum: num 33.3 66.7 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 1.36745 | 1 |
| 2.4488 | 1 |
| 25.81514 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 1.36745 10.36745 19.36745 28.36745distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (1.37,10.4] | 1 | 0.5 | 1 |
| (10.4,19.4] | 0 | 0.0 | 1 |
| (19.4,28.4] | 1 | 0.5 | 2 |
str(Freq_table)## 'data.frame': 3 obs. of 4 variables:
## $ distance: Factor w/ 3 levels "(1.37,10.4]",..: 1 2 3
## $ Freq : int 1 0 1
## $ Rel_Freq: num 0.5 0 0.5
## $ Cum_Freq: int 1 1 2df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (1.37,10.4] | 1 |
| (10.4,19.4] | 0 |
| (19.4,28.4] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_NC)## id date time continent_code country_name country_code
## nbr.val 3.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 2.330000e+03 NA NA NA NA NA
## max 7.471000e+03 NA NA NA NA NA
## range 5.141000e+03 NA NA NA NA NA
## sum 1.727100e+04 NA NA NA NA NA
## median 7.470000e+03 NA NA NA NA NA
## mean 5.757000e+03 NA NA NA NA NA
## SE.mean 1.713500e+03 NA NA NA NA NA
## CI.mean.0.95 7.372596e+03 NA NA NA NA NA
## var 8.808247e+06 NA NA NA NA NA
## std.dev 2.967869e+03 NA NA NA NA NA
## coef.var 5.155236e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 3.000000e+00 NA 3.000000 NA
## nbr.null NA 0.000000e+00 NA 0.000000 NA
## nbr.na NA 0.000000e+00 NA 0.000000 NA
## min NA 2.367000e+03 NA 1.367450 NA
## max NA 5.107300e+04 NA 25.815140 NA
## range NA 4.870600e+04 NA 24.447690 NA
## sum NA 6.039500e+04 NA 29.631390 NA
## median NA 6.955000e+03 NA 2.448800 NA
## mean NA 2.013167e+04 NA 9.877130 NA
## SE.mean NA 1.552726e+04 NA 7.975117 NA
## CI.mean.0.95 NA 6.680839e+04 NA 34.314157 NA
## var NA 7.232870e+08 NA 190.807452 NA
## std.dev NA 2.689400e+04 NA 13.813307 NA
## coef.var NA 1.335905e+00 NA 1.398514 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 3.00000000 3.000000e+00 NA NA NA
## nbr.null 0.00000000 0.000000e+00 NA NA NA
## nbr.na 0.00000000 0.000000e+00 NA NA NA
## min 13.08050000 -8.599250e+01 NA NA NA
## max 13.81760000 -8.553250e+01 NA NA NA
## range 0.73710000 4.600000e-01 NA NA NA
## sum 40.42980000 -2.572130e+02 NA NA NA
## median 13.53170000 -8.568800e+01 NA NA NA
## mean 13.47660000 -8.573767e+01 NA NA NA
## SE.mean 0.21455855 1.350927e-01 NA NA NA
## CI.mean.0.95 0.92317092 5.812568e-01 NA NA NA
## var 0.13810611 5.475008e-02 NA NA NA
## std.dev 0.37162630 2.339874e-01 NA NA NA
## coef.var 0.02757567 -2.729108e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 2 2 NA
## nbr.null NA NA NA 2 2 NA
## nbr.na NA NA NA 1 1 NA
## min NA NA NA 0 0 NA
## max NA NA NA 0 0 NA
## range NA NA NA 0 0 NA
## sum NA NA NA 0 0 NA
## median NA NA NA 0 0 NA
## mean NA NA NA 0 0 NA
## SE.mean NA NA NA 0 0 NA
## CI.mean.0.95 NA NA NA 0 0 NA
## var NA NA NA 0 0 NA
## std.dev NA NA NA 0 0 NA
## coef.var NA NA NA NaN NaN NA
## source_link prop ypos
## nbr.val NA 3.000000 3.0000000
## nbr.null NA 0.000000 0.0000000
## nbr.na NA 0.000000 0.0000000
## min NA 4.614870 43.5604607
## max NA 87.120921 95.8678955
## range NA 82.506052 52.3074348
## sum NA 100.000000 228.8567124
## median NA 8.264209 89.4283562
## mean NA 33.333333 76.2855708
## SE.mean NA 26.914419 16.4678124
## CI.mean.0.95 NA 115.803400 70.8552781
## var NA 2173.157894 813.5665396
## std.dev NA 46.617142 28.5230878
## coef.var NA 1.398514 0.3738989boxplot(data, horizontal=TRUE, col='green')
Gráfico para Costa Rica
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_CR <- subset(df, country_name == "Costa Rica")
knitr::kable(head(df_CR))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 249 | 9/9/07 | NA | NA | Costa Rica | CR | Heredia | 21947 | Heredia | 0.26208 | NA | 10.0000 | -84.1167 | (10, -84.116699999999994) | Landslide | Landslide | Medium | Rain | NA | NA | NA | ticotimes.net | http://www.ticotimes.net/dailyarchive/2007_09/0911072.htm |
| 299 | 10/9/07 | NA | NA | Costa Rica | CR | San José | 3072 | San Ignacio | 4.57763 | NA | 9.7789 | -84.1250 | (9.7789000000000001, -84.125) | Landslide | Complex | Medium | Rain | NA | NA | 4 | ticotimes.net | http://www.ticotimes.net/dailyarchive/2007_10/1010071.htm |
| 301 | 10/11/07 | NA | NA | Costa Rica | CR | Alajuela | 7014 | Atenas | 3.08459 | NA | 9.9869 | -84.4070 | (9.9869000000000003, -84.406999999999996) | Landslide | Mudslide | Large | Rain | NA | NA | 14 | Agence France-Presse, afp.google.com | http://afp.google.com/article/ALeqM5hu6a8oyAM1ycq9nU_6Zyj_l7F0AA |
| 302 | 10/11/07 | NA | NA | Costa Rica | CR | San José | 26669 | NA | 9.56251 | NA | 10.0214 | -83.9451 | (10.0214, -83.945099999999996) | Landslide | Landslide | Large | Rain | NA | NA | 10 | International Herald | http://www.iht.com/articles/ap/2007/10/12/america/LA-GEN-Costa-Rica-Mudslide.php |
| 323 | 10/24/07 | NA | NA | Costa Rica | CR | Puntarenas | 6540 | Miramar | 3.82425 | Mine construction | 10.0715 | -84.7575 | (10.0715, -84.757499999999993) | Landslide | Mudslide | Medium | Downpour | NA | NA | NA | Reuters - AlertNet.org | http://www.reuters.com/article/companyNewsAndPR/idUSN2435152820071025 |
| 556 | 5/29/08 | NA | NA | Costa Rica | CR | Guanacaste | 4108 | Bagaces | 17.65521 | NA | 10.4024 | -85.3555 | (10.4024, -85.355500000000006) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Alma | NA | NA | NA | http://www.reliefweb.int/rw/RWB.NSF/db900SID/ASAZ-7FHCHL?OpenDocument |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_CR, aes(fill= state, y=distance, x=country_name)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_CR, aes(fill=state, y=distance, x=country_name)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_CR, aes(x=country_name, y=distance, fill=state)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_CR <- df_CR %>%
arrange(desc(state)) %>%
mutate(prop = distance / sum(df_CR$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_CR, aes(x=country_name, y=prop, fill=state)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_CR$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 4.57763 |
| 9.56251 |
| 1.85787 |
| 16.24937 |
| 12.85801 |
| 0.25254 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_CR$distance
names(distance) <- df_CR$state
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por estados"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## San José 22.32368000 22.32368000 3.45492296 3.45492296
## Heredia 21.95470000 44.27838000 3.39781780 6.85274076
## San José 21.67452000 65.95290000 3.35445576 10.20719651
## Puntarenas 20.06633000 86.01923000 3.10556433 13.31276084
## Heredia 19.54581000 105.56504000 3.02500608 16.33776693
## Heredia 19.51432000 125.07936000 3.02013254 19.35789946
## Cartago 19.28722000 144.36658000 2.98498542 22.34288488
## Puntarenas 18.00524000 162.37182000 2.78657986 25.12946474
## Guanacaste 17.65521000 180.02703000 2.73240749 27.86187223
## Limón 17.23264000 197.25967000 2.66700847 30.52888070
## San José 16.24937000 213.50904000 2.51483275 33.04371345
## San José 15.64997000 229.15901000 2.42206664 35.46578009
## Heredia 15.05161000 244.21062000 2.32946150 37.79524159
## Heredia 14.81614000 259.02676000 2.29301900 40.08826059
## Puntarenas 13.48919000 272.51595000 2.08765366 42.17591425
## San José 12.85801000 285.37396000 1.98996913 44.16588338
## Guanacaste 12.33807000 297.71203000 1.90950065 46.07538402
## Guanacaste 12.21952000 309.93155000 1.89115326 47.96653728
## Guanacaste 12.18115000 322.11270000 1.88521493 49.85175221
## Alajuela 11.96524000 334.07794000 1.85179963 51.70355185
## Puntarenas 11.74074000 345.81868000 1.81705490 53.52060675
## San José 11.31047000 357.12915000 1.75046419 55.27107094
## San José 10.73752000 367.86667000 1.66179162 56.93286257
## Alajuela 10.32968000 378.19635000 1.59867229 58.53153486
## Guanacaste 10.21631000 388.41266000 1.58112659 60.11266145
## Heredia 10.01310000 398.42576000 1.54967681 61.66233825
## San José 10.01198000 408.43774000 1.54950347 63.21184172
## Heredia 9.85736000 418.29510000 1.52557371 64.73741544
## Alajuela 9.84213000 428.13723000 1.52321664 66.26063208
## Cartago 9.63616000 437.77339000 1.49133971 67.75197179
## Alajuela 9.61692000 447.39031000 1.48836203 69.24033382
## San José 9.56251000 456.95282000 1.47994127 70.72027510
## San José 9.53611000 466.48893000 1.47585548 72.19613057
## Cartago 9.53493000 476.02386000 1.47567286 73.67180343
## Puntarenas 8.92048000 484.94434000 1.38057754 75.05238097
## San José 8.39161000 493.33595000 1.29872701 76.35110797
## San José 8.27042000 501.60637000 1.27997104 77.63107902
## San José 8.21372000 509.82009000 1.27119587 78.90227489
## Puntarenas 7.87044000 517.69053000 1.21806816 80.12034305
## Alajuela 6.92174000 524.61227000 1.07124267 81.19158572
## Alajuela 6.88715000 531.49942000 1.06588935 82.25747506
## Alajuela 6.80061000 538.30003000 1.05249599 83.30997105
## San José 6.49523000 544.79526000 1.00523387 84.31520492
## Alajuela 5.96634000 550.76160000 0.92338024 85.23858516
## Alajuela 5.95519000 556.71679000 0.92165461 86.16023978
## Alajuela 5.57523000 562.29202000 0.86285013 87.02308991
## Alajuela 5.43516000 567.72718000 0.84117220 87.86426211
## Limón 5.36500000 573.09218000 0.83031390 88.69457601
## Cartago 5.15142000 578.24360000 0.79725920 89.49183521
## Alajuela 5.12667000 583.37027000 0.79342877 90.28526397
## Puntarenas 4.93053000 588.30080000 0.76307317 91.04833715
## San José 4.89954000 593.20034000 0.75827701 91.80661415
## Alajuela 4.87432000 598.07466000 0.75437384 92.56098799
## San José 4.57763000 602.65229000 0.70845663 93.26944461
## Alajuela 4.24199000 606.89428000 0.65651132 93.92595593
## Puntarenas 3.82425000 610.71853000 0.59185982 94.51781575
## San José 3.71407000 614.43260000 0.57480782 95.09262357
## San José 3.67691000 618.10951000 0.56905675 95.66168032
## Alajuela 3.21979000 621.32930000 0.49831060 96.15999092
## Alajuela 3.08916000 624.41846000 0.47809366 96.63808457
## Alajuela 3.08459000 627.50305000 0.47738638 97.11547096
## Cartago 3.07297000 630.57602000 0.47558801 97.59105897
## Cartago 2.94804000 633.52406000 0.45625323 98.04731220
## San José 2.92605000 636.45011000 0.45284995 98.50016215
## Alajuela 2.08469000 638.53480000 0.32263692 98.82279907
## San José 1.85787000 640.39267000 0.28753314 99.11033220
## Alajuela 1.47396000 641.86663000 0.22811733 99.33844953
## San José 1.16705000 643.03368000 0.18061842 99.51906795
## San José 0.72957000 643.76325000 0.11291186 99.63197981
## Alajuela 0.70048000 644.46373000 0.10840974 99.74038955
## San José 0.55804000 645.02177000 0.08636503 99.82675458
## Puntarenas 0.35225000 645.37402000 0.05451595 99.88127053
## Heredia 0.26208000 645.63610000 0.04056080 99.92183132
## San José 0.25254000 645.88864000 0.03908434 99.96091566
## San José 0.25254000 646.14118000 0.03908434 100.00000000stem(df_CR$"distance")##
## The decimal point is at the |
##
## 0 | 3334677259
## 2 | 1991112778
## 4 | 2699912446
## 6 | 0058999
## 8 | 23495566689
## 10 | 0023737
## 12 | 022395
## 14 | 816
## 16 | 227
## 18 | 0355
## 20 | 17
## 22 | 03head(df_CR)## # A tibble: 6 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 299 10/9/07 <NA> <NA> Costa Rica CR San José 3072
## 2 302 10/11/07 <NA> <NA> Costa Rica CR San José 26669
## 3 776 9/6/08 <NA> <NA> Costa Rica CR San José 10028
## 4 838 10/12/08 <NA> <NA> Costa Rica CR San José 34877
## 5 839 10/12/08 <NA> <NA> Costa Rica CR San José 8292
## 6 2526 10/1/10 <NA> <NA> Costa Rica CR San José 2833
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_CR))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 299 | 10/9/07 | NA | NA | Costa Rica | CR | San José | 3072 | San Ignacio | 4.57763 | NA | 9.7789 | -84.1250 | (9.7789000000000001, -84.125) | Landslide | Complex | Medium | Rain | NA | NA | 4 | ticotimes.net | http://www.ticotimes.net/dailyarchive/2007_10/1010071.htm | 0.7084566 | 0.3542283 |
| 302 | 10/11/07 | NA | NA | Costa Rica | CR | San José | 26669 | NA | 9.56251 | NA | 10.0214 | -83.9451 | (10.0214, -83.945099999999996) | Landslide | Landslide | Large | Rain | NA | NA | 10 | International Herald | http://www.iht.com/articles/ap/2007/10/12/america/LA-GEN-Costa-Rica-Mudslide.php | 1.4799413 | 1.4484273 |
| 776 | 9/6/08 | NA | NA | Costa Rica | CR | San José | 10028 | Daniel Flores | 1.85787 | NA | 9.3500 | -83.6780 | (9.35, -83.677999999999997) | Landslide | Mudslide | Medium | Downpour | NA | NA | NA | NA | http://insidecostarica.com/dailynews/2008/september/07/nac02.htm | 0.2875331 | 2.3321645 |
| 838 | 10/12/08 | NA | NA | Costa Rica | CR | San José | 34877 | San Isidro | 16.24937 | NA | 9.5190 | -83.7060 | (9.5190000000000001, -83.706000000000003) | Landslide | Landslide | Medium | Downpour | NA | NA | NA | NA | http://www.ticotimes.net/dailyarchive/2008_10/1014081.htm | 2.5148327 | 3.7333474 |
| 839 | 10/12/08 | NA | NA | Costa Rica | CR | San José | 8292 | Santiago | 12.85801 | NA | 9.7640 | -84.3970 | (9.7639999999999993, -84.397000000000006) | Landslide | Landslide | Medium | Downpour | NA | NA | NA | NA | http://www.ticotimes.net/dailyarchive/2008_10/1014082.htm | 1.9899691 | 5.9857483 |
| 2526 | 10/1/10 | NA | NA | Costa Rica | CR | San José | 2833 | Salitral | 0.25254 | NA | 9.9108 | -84.1764 | (9.9108000000000001, -84.176400000000001) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.ticotimes.net/News/Mudslides-Force-63-Out-of-Santa-Ana-Homes_Friday-October-01-2010 | 0.0390843 | 7.0002751 |
stem(df_CR$"distance")##
## The decimal point is at the |
##
## 0 | 3334677259
## 2 | 1991112778
## 4 | 2699912446
## 6 | 0058999
## 8 | 23495566689
## 10 | 0023737
## 12 | 022395
## 14 | 816
## 16 | 227
## 18 | 0355
## 20 | 17
## 22 | 03stem(df_CR$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 3334677259
## 2 | 1991112778
## 4 | 2699912446
## 6 | 0058999
## 8 | 23495566689
## 10 | 0023737
## 12 | 022395
## 14 | 816
## 16 | 227
## 18 | 0355
## 20 | 17
## 22 | 03Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.25254 | 2 | 2.7 | 2.7 | 2.7 | 2.7 |
| 0.26208 | 1 | 1.3 | 1.3 | 4.0 | 4.0 |
| 0.35225 | 1 | 1.3 | 1.3 | 5.3 | 5.3 |
| 0.55804 | 1 | 1.3 | 1.3 | 6.7 | 6.7 |
| 0.70048 | 1 | 1.3 | 1.3 | 8.0 | 8.0 |
| 0.72957 | 1 | 1.3 | 1.3 | 9.3 | 9.3 |
| 1.16705 | 1 | 1.3 | 1.3 | 10.7 | 10.7 |
| 1.47396 | 1 | 1.3 | 1.3 | 12.0 | 12.0 |
| 1.85787 | 1 | 1.3 | 1.3 | 13.3 | 13.3 |
| 2.08469 | 1 | 1.3 | 1.3 | 14.7 | 14.7 |
| 2.92605 | 1 | 1.3 | 1.3 | 16.0 | 16.0 |
| 2.94804 | 1 | 1.3 | 1.3 | 17.3 | 17.3 |
| 3.07297 | 1 | 1.3 | 1.3 | 18.7 | 18.7 |
| 3.08459 | 1 | 1.3 | 1.3 | 20.0 | 20.0 |
| 3.08916 | 1 | 1.3 | 1.3 | 21.3 | 21.3 |
| 3.21979 | 1 | 1.3 | 1.3 | 22.7 | 22.7 |
| 3.67691 | 1 | 1.3 | 1.3 | 24.0 | 24.0 |
| 3.71407 | 1 | 1.3 | 1.3 | 25.3 | 25.3 |
| 3.82425 | 1 | 1.3 | 1.3 | 26.7 | 26.7 |
| 4.24199 | 1 | 1.3 | 1.3 | 28.0 | 28.0 |
| 4.57763 | 1 | 1.3 | 1.3 | 29.3 | 29.3 |
| 4.87432 | 1 | 1.3 | 1.3 | 30.7 | 30.7 |
| 4.89954 | 1 | 1.3 | 1.3 | 32.0 | 32.0 |
| 4.93053 | 1 | 1.3 | 1.3 | 33.3 | 33.3 |
| 5.12667 | 1 | 1.3 | 1.3 | 34.7 | 34.7 |
| 5.15142 | 1 | 1.3 | 1.3 | 36.0 | 36.0 |
| 5.365 | 1 | 1.3 | 1.3 | 37.3 | 37.3 |
| 5.43516 | 1 | 1.3 | 1.3 | 38.7 | 38.7 |
| 5.57523 | 1 | 1.3 | 1.3 | 40.0 | 40.0 |
| 5.95519 | 1 | 1.3 | 1.3 | 41.3 | 41.3 |
| 5.96634 | 1 | 1.3 | 1.3 | 42.7 | 42.7 |
| 6.49523 | 1 | 1.3 | 1.3 | 44.0 | 44.0 |
| 6.80061 | 1 | 1.3 | 1.3 | 45.3 | 45.3 |
| 6.88715 | 1 | 1.3 | 1.3 | 46.7 | 46.7 |
| 6.92174 | 1 | 1.3 | 1.3 | 48.0 | 48.0 |
| 7.87044 | 1 | 1.3 | 1.3 | 49.3 | 49.3 |
| 8.21372 | 1 | 1.3 | 1.3 | 50.7 | 50.7 |
| 8.27042 | 1 | 1.3 | 1.3 | 52.0 | 52.0 |
| 8.39161 | 1 | 1.3 | 1.3 | 53.3 | 53.3 |
| 8.92048 | 1 | 1.3 | 1.3 | 54.7 | 54.7 |
| 9.53493 | 1 | 1.3 | 1.3 | 56.0 | 56.0 |
| 9.53611 | 1 | 1.3 | 1.3 | 57.3 | 57.3 |
| 9.56251 | 1 | 1.3 | 1.3 | 58.7 | 58.7 |
| 9.61692 | 1 | 1.3 | 1.3 | 60.0 | 60.0 |
| 9.63616 | 1 | 1.3 | 1.3 | 61.3 | 61.3 |
| 9.84213 | 1 | 1.3 | 1.3 | 62.7 | 62.7 |
| 9.85736 | 1 | 1.3 | 1.3 | 64.0 | 64.0 |
| 10.01198 | 1 | 1.3 | 1.3 | 65.3 | 65.3 |
| 10.0131 | 1 | 1.3 | 1.3 | 66.7 | 66.7 |
| 10.21631 | 1 | 1.3 | 1.3 | 68.0 | 68.0 |
| 10.32968 | 1 | 1.3 | 1.3 | 69.3 | 69.3 |
| 10.73752 | 1 | 1.3 | 1.3 | 70.7 | 70.7 |
| 11.31047 | 1 | 1.3 | 1.3 | 72.0 | 72.0 |
| 11.74074 | 1 | 1.3 | 1.3 | 73.3 | 73.3 |
| 11.96524 | 1 | 1.3 | 1.3 | 74.7 | 74.7 |
| 12.18115 | 1 | 1.3 | 1.3 | 76.0 | 76.0 |
| 12.21952 | 1 | 1.3 | 1.3 | 77.3 | 77.3 |
| 12.33807 | 1 | 1.3 | 1.3 | 78.7 | 78.7 |
| 12.85801 | 1 | 1.3 | 1.3 | 80.0 | 80.0 |
| 13.48919 | 1 | 1.3 | 1.3 | 81.3 | 81.3 |
| 14.81614 | 1 | 1.3 | 1.3 | 82.7 | 82.7 |
| 15.05161 | 1 | 1.3 | 1.3 | 84.0 | 84.0 |
| 15.64997 | 1 | 1.3 | 1.3 | 85.3 | 85.3 |
| 16.24937 | 1 | 1.3 | 1.3 | 86.7 | 86.7 |
| 17.23264 | 1 | 1.3 | 1.3 | 88.0 | 88.0 |
| 17.65521 | 1 | 1.3 | 1.3 | 89.3 | 89.3 |
| 18.00524 | 1 | 1.3 | 1.3 | 90.7 | 90.7 |
| 19.28722 | 1 | 1.3 | 1.3 | 92.0 | 92.0 |
| 19.51432 | 1 | 1.3 | 1.3 | 93.3 | 93.3 |
| 19.54581 | 1 | 1.3 | 1.3 | 94.7 | 94.7 |
| 20.06633 | 1 | 1.3 | 1.3 | 96.0 | 96.0 |
| 21.67452 | 1 | 1.3 | 1.3 | 97.3 | 97.3 |
| 21.9547 | 1 | 1.3 | 1.3 | 98.7 | 98.7 |
| 22.32368 | 1 | 1.3 | 1.3 | 100.0 | 100.0 |
| Total | 75 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 75 obs. of 5 variables:
## $ n : num 2 1 1 1 1 1 1 1 1 1 ...
## $ % : num 2.7 1.3 1.3 1.3 1.3 1.3 1.3 1.3 1.3 1.3 ...
## $ val% : num 2.7 1.3 1.3 1.3 1.3 1.3 1.3 1.3 1.3 1.3 ...
## $ %cum : num 2.7 4 5.3 6.7 8 9.3 10.7 12 13.3 14.7 ...
## $ val%cum: num 2.7 4 5.3 6.7 8 9.3 10.7 12 13.3 14.7 ...x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.25254 | 2 |
| 0.26208 | 1 |
| 0.35225 | 1 |
| 0.55804 | 1 |
| 0.70048 | 1 |
| 0.72957 | 1 |
| 1.16705 | 1 |
| 1.47396 | 1 |
| 1.85787 | 1 |
| 2.08469 | 1 |
| 2.92605 | 1 |
| 2.94804 | 1 |
| 3.07297 | 1 |
| 3.08459 | 1 |
| 3.08916 | 1 |
| 3.21979 | 1 |
| 3.67691 | 1 |
| 3.71407 | 1 |
| 3.82425 | 1 |
| 4.24199 | 1 |
| 4.57763 | 1 |
| 4.87432 | 1 |
| 4.89954 | 1 |
| 4.93053 | 1 |
| 5.12667 | 1 |
| 5.15142 | 1 |
| 5.365 | 1 |
| 5.43516 | 1 |
| 5.57523 | 1 |
| 5.95519 | 1 |
| 5.96634 | 1 |
| 6.49523 | 1 |
| 6.80061 | 1 |
| 6.88715 | 1 |
| 6.92174 | 1 |
| 7.87044 | 1 |
| 8.21372 | 1 |
| 8.27042 | 1 |
| 8.39161 | 1 |
| 8.92048 | 1 |
| 9.53493 | 1 |
| 9.53611 | 1 |
| 9.56251 | 1 |
| 9.61692 | 1 |
| 9.63616 | 1 |
| 9.84213 | 1 |
| 9.85736 | 1 |
| 10.01198 | 1 |
| 10.0131 | 1 |
| 10.21631 | 1 |
| 10.32968 | 1 |
| 10.73752 | 1 |
| 11.31047 | 1 |
| 11.74074 | 1 |
| 11.96524 | 1 |
| 12.18115 | 1 |
| 12.21952 | 1 |
| 12.33807 | 1 |
| 12.85801 | 1 |
| 13.48919 | 1 |
| 14.81614 | 1 |
| 15.05161 | 1 |
| 15.64997 | 1 |
| 16.24937 | 1 |
| 17.23264 | 1 |
| 17.65521 | 1 |
| 18.00524 | 1 |
| 19.28722 | 1 |
| 19.51432 | 1 |
| 19.54581 | 1 |
| 20.06633 | 1 |
| 21.67452 | 1 |
| 21.9547 | 1 |
| 22.32368 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.25254 4.25254 8.25254 12.25254 16.25254 20.25254 24.25254distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.253,4.25] | 19 | 0.2602740 | 19 |
| (4.25,8.25] | 17 | 0.2328767 | 36 |
| (8.25,12.3] | 20 | 0.2739726 | 56 |
| (12.3,16.3] | 7 | 0.0958904 | 63 |
| (16.3,20.3] | 7 | 0.0958904 | 70 |
| (20.3,24.3] | 3 | 0.0410959 | 73 |
str(Freq_table)## 'data.frame': 6 obs. of 4 variables:
## $ distance: Factor w/ 6 levels "(0.253,4.25]",..: 1 2 3 4 5 6
## $ Freq : int 19 17 20 7 7 3
## $ Rel_Freq: num 0.2603 0.2329 0.274 0.0959 0.0959 ...
## $ Cum_Freq: int 19 36 56 63 70 73df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.253,4.25] | 19 |
| (4.25,8.25] | 17 |
| (8.25,12.3] | 20 |
| (12.3,16.3] | 7 |
| (16.3,20.3] | 7 |
| (20.3,24.3] | 3 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_CR)## id date time continent_code country_name country_code
## nbr.val 7.500000e+01 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 2.490000e+02 NA NA NA NA NA
## max 7.496000e+03 NA NA NA NA NA
## range 7.247000e+03 NA NA NA NA NA
## sum 3.121850e+05 NA NA NA NA NA
## median 3.762000e+03 NA NA NA NA NA
## mean 4.162467e+03 NA NA NA NA NA
## SE.mean 2.838021e+02 NA NA NA NA NA
## CI.mean.0.95 5.654880e+02 NA NA NA NA NA
## var 6.040771e+06 NA NA NA NA NA
## std.dev 2.457798e+03 NA NA NA NA NA
## coef.var 5.904667e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 7.500000e+01 NA 75.0000000 NA
## nbr.null NA 4.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 0.000000e+00 NA 0.2525400 NA
## max NA 3.350070e+05 NA 22.3236800 NA
## range NA 3.350070e+05 NA 22.0711400 NA
## sum NA 1.127522e+06 NA 646.1411800 NA
## median NA 6.784000e+03 NA 8.2137200 NA
## mean NA 1.503363e+04 NA 8.6152157 NA
## SE.mean NA 4.498709e+03 NA 0.6924979 NA
## CI.mean.0.95 NA 8.963873e+03 NA 1.3798322 NA
## var NA 1.517878e+09 NA 35.9665004 NA
## std.dev NA 3.895996e+04 NA 5.9972077 NA
## coef.var NA 2.591521e+00 NA 0.6961181 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 75.00000000 7.500000e+01 NA NA NA
## nbr.null 0.00000000 0.000000e+00 NA NA NA
## nbr.na 0.00000000 0.000000e+00 NA NA NA
## min 8.61170000 -8.535550e+01 NA NA NA
## max 10.89160000 -8.294180e+01 NA NA NA
## range 2.27990000 2.413700e+00 NA NA NA
## sum 740.80410000 -6.307925e+03 NA NA NA
## median 9.96430000 -8.408790e+01 NA NA NA
## mean 9.87738800 -8.410567e+01 NA NA NA
## SE.mean 0.05198610 5.429493e-02 NA NA NA
## CI.mean.0.95 0.10358456 1.081850e-01 NA NA NA
## var 0.20269158 2.210955e-01 NA NA NA
## std.dev 0.45021281 4.702079e-01 NA NA NA
## coef.var 0.04558015 -5.590680e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities
## nbr.val NA NA NA 27.0000000 60.0000000
## nbr.null NA NA NA 26.0000000 50.0000000
## nbr.na NA NA NA 48.0000000 15.0000000
## min NA NA NA 0.0000000 0.0000000
## max NA NA NA 3.0000000 23.0000000
## range NA NA NA 3.0000000 23.0000000
## sum NA NA NA 3.0000000 61.0000000
## median NA NA NA 0.0000000 0.0000000
## mean NA NA NA 0.1111111 1.0166667
## SE.mean NA NA NA 0.1111111 0.4750805
## CI.mean.0.95 NA NA NA 0.2283922 0.9506339
## var NA NA NA 0.3333333 13.5420904
## std.dev NA NA NA 0.5773503 3.6799579
## coef.var NA NA NA 5.1961524 3.6196308
## source_name source_link prop ypos
## nbr.val NA NA 75.00000000 75.0000000
## nbr.null NA NA 0.00000000 0.0000000
## nbr.na NA NA 0.00000000 0.0000000
## min NA NA 0.03908434 0.3542283
## max NA NA 3.45492296 99.8386815
## range NA NA 3.41583863 99.4844532
## sum NA NA 100.00000000 3898.8052162
## median NA NA 1.27119587 49.1708732
## mean NA NA 1.33333333 51.9840695
## SE.mean NA NA 0.10717439 3.7309554
## CI.mean.0.95 NA NA 0.21354964 7.4340909
## var NA NA 0.86147631 1044.0021043
## std.dev NA NA 0.92815748 32.3110214
## coef.var NA NA 0.69611811 0.6215562boxplot(data, horizontal=TRUE, col='green')
Gráfico para Heredia (Costa Rica)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_CR <- subset(df, country_name == "Costa Rica")
knitr::kable(head(df_CR)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 249 | 9/9/07 | NA | NA | Costa Rica | CR | Heredia | 21947 | Heredia | 0.26208 | NA | 10.0000 | -84.1167 | (10, -84.116699999999994) | Landslide | Landslide | Medium | Rain | NA | NA | NA | ticotimes.net | http://www.ticotimes.net/dailyarchive/2007_09/0911072.htm |
| 299 | 10/9/07 | NA | NA | Costa Rica | CR | San José | 3072 | San Ignacio | 4.57763 | NA | 9.7789 | -84.1250 | (9.7789000000000001, -84.125) | Landslide | Complex | Medium | Rain | NA | NA | 4 | ticotimes.net | http://www.ticotimes.net/dailyarchive/2007_10/1010071.htm |
| 301 | 10/11/07 | NA | NA | Costa Rica | CR | Alajuela | 7014 | Atenas | 3.08459 | NA | 9.9869 | -84.4070 | (9.9869000000000003, -84.406999999999996) | Landslide | Mudslide | Large | Rain | NA | NA | 14 | Agence France-Presse, afp.google.com | http://afp.google.com/article/ALeqM5hu6a8oyAM1ycq9nU_6Zyj_l7F0AA |
| 302 | 10/11/07 | NA | NA | Costa Rica | CR | San José | 26669 | NA | 9.56251 | NA | 10.0214 | -83.9451 | (10.0214, -83.945099999999996) | Landslide | Landslide | Large | Rain | NA | NA | 10 | International Herald | http://www.iht.com/articles/ap/2007/10/12/america/LA-GEN-Costa-Rica-Mudslide.php |
| 323 | 10/24/07 | NA | NA | Costa Rica | CR | Puntarenas | 6540 | Miramar | 3.82425 | Mine construction | 10.0715 | -84.7575 | (10.0715, -84.757499999999993) | Landslide | Mudslide | Medium | Downpour | NA | NA | NA | Reuters - AlertNet.org | http://www.reuters.com/article/companyNewsAndPR/idUSN2435152820071025 |
| 556 | 5/29/08 | NA | NA | Costa Rica | CR | Guanacaste | 4108 | Bagaces | 17.65521 | NA | 10.4024 | -85.3555 | (10.4024, -85.355500000000006) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Alma | NA | NA | NA | http://www.reliefweb.int/rw/RWB.NSF/db900SID/ASAZ-7FHCHL?OpenDocument |
library(dplyr)
df_CR <- subset(df, state == "Heredia")
knitr::kable(head(df_CR))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 249 | 9/9/07 | NA | NA | Costa Rica | CR | Heredia | 21947 | Heredia | 0.26208 | NA | 10.0000 | -84.1167 | (10, -84.116699999999994) | Landslide | Landslide | Medium | Rain | NA | NA | NA | ticotimes.net | http://www.ticotimes.net/dailyarchive/2007_09/0911072.htm |
| 1786 | 4/27/10 | Early morning | NA | Costa Rica | CR | Heredia | 1355 | Ángeles | 19.51432 | NA | 10.1452 | -83.9564 | (10.145200000000001, -83.956400000000002) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://en.trend.az/news/incident/1678592.html |
| 2598 | 10/15/10 | NA | NA | Costa Rica | CR | Heredia | 1355 | Ángeles | 14.81614 | NA | 10.1067 | -83.9753 | (10.1067, -83.975300000000004) | Landslide | Rockfall | Medium | Downpour | NA | NA | 2 | NA | http://www.ticotimes.net/News/Daily-News/Two-People-Die-in-Landslide-on-Limon-Highway_Saturday-October-16-2010 |
| 2742 | 11/21/10 | NA | NA | Costa Rica | CR | Heredia | 1355 | Ángeles | 19.54581 | NA | 10.1433 | -83.9529 | (10.1433, -83.9529) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://insidecostarica.com/dailynews/2010/november/22/costarica10112204.htm |
| 3472 | 5/8/11 | Night | NA | Costa Rica | CR | Heredia | 1355 | Ángeles | 15.05161 | NA | 10.1118 | -83.9793 | (10.111800000000001, -83.979299999999995) | Landslide | Landslide | Medium | Rain | NA | NA | 0 | NA | http://insidecostarica.com/dailynews/2011/may/10/costarica11051010.htm |
| 4358 | 5/13/12 | NA | NA | Costa Rica | CR | Heredia | 5745 | Santo Domingo | 21.95470 | NA | 10.1981 | -84.0074 | (10.1981, -84.007400000000004) | Landslide | Landslide | Medium | Downpour | NA | NA | NA | NA | http://www.insidecostarica.com/dailynews/2012/may/17/costarica12051708.htm |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_CR, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_CR, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_CR, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_CR <- df_CR %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_CR$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_CR, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_CR$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 21.95470 |
| 9.85736 |
| 0.26208 |
| 10.01310 |
| 19.51432 |
| 14.81614 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_CR$distance
names(distance) <- df_CR$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Santo Domingo 21.954700 21.954700 19.776315 19.776315
## Ángeles 19.545810 41.500510 17.606440 37.382755
## Ángeles 19.514320 61.014830 17.578074 54.960829
## Ángeles 15.051610 76.066440 13.558162 68.518991
## Ángeles 14.816140 90.882580 13.346056 81.865047
## Dulce Nombre de Jesus 10.013100 100.895680 9.019582 90.884629
## Santo Domingo 9.857360 110.753040 8.879295 99.763924
## Heredia 0.262080 111.015120 0.236076 100.000000stem(df_CR$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 0
## 0 |
## 1 | 00
## 1 | 55
## 2 | 002head(df_CR)## # A tibble: 6 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 4358 5/13/12 <NA> <NA> Costa Rica CR Here~ 5745
## 2 5541 9/16/13 <NA> <NA> Costa Rica CR Here~ 5745
## 3 249 9/9/07 <NA> <NA> Costa Rica CR Here~ 21947
## 4 6696 12/13/14 Night <NA> Costa Rica CR Here~ 0
## 5 1786 4/27/10 Earl~ <NA> Costa Rica CR Here~ 1355
## 6 2598 10/15/10 <NA> <NA> Costa Rica CR Here~ 1355
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_CR))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 4358 | 5/13/12 | NA | NA | Costa Rica | CR | Heredia | 5745 | Santo Domingo | 21.95470 | NA | 10.1981 | -84.0074 | (10.1981, -84.007400000000004) | Landslide | Landslide | Medium | Downpour | NA | NA | NA | NA | http://www.insidecostarica.com/dailynews/2012/may/17/costarica12051708.htm | 19.776315 | 9.888158 |
| 5541 | 9/16/13 | NA | NA | Costa Rica | CR | Heredia | 5745 | Santo Domingo | 9.85736 | NA | 10.1528 | -84.1489 | (10.152799999999999, -84.148899999999998) | Landslide | Landslide | Medium | Tropical cyclone | Manuel | NA | 0 | insidecostarica.com | http://insidecostarica.com/2013/09/17/torrential-rains-flooding-washed-out-bridges-and-landslides-wreak-havoc/ | 8.879295 | 24.215963 |
| 249 | 9/9/07 | NA | NA | Costa Rica | CR | Heredia | 21947 | Heredia | 0.26208 | NA | 10.0000 | -84.1167 | (10, -84.116699999999994) | Landslide | Landslide | Medium | Rain | NA | NA | NA | ticotimes.net | http://www.ticotimes.net/dailyarchive/2007_09/0911072.htm | 0.236076 | 28.773648 |
| 6696 | 12/13/14 | Night | NA | Costa Rica | CR | Heredia | 0 | Dulce Nombre de Jesus | 10.01310 | Unknown | 10.2054 | -83.9041 | (10.205399999999999, -83.9041) | Landslide | Landslide | Medium | Unknown | NA | 0 | 0 | Columbia | http://www.columbia.co.cr/index.php/nacionales/transporte/6953-la-ruta-32-se-mantiene-cerrada-desde-anoche-por-un-deslizamiento-en-el-sector-de-rio-sucio | 9.019582 | 33.401477 |
| 1786 | 4/27/10 | Early morning | NA | Costa Rica | CR | Heredia | 1355 | Ángeles | 19.51432 | NA | 10.1452 | -83.9564 | (10.145200000000001, -83.956400000000002) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://en.trend.az/news/incident/1678592.html | 17.578074 | 46.700305 |
| 2598 | 10/15/10 | NA | NA | Costa Rica | CR | Heredia | 1355 | Ángeles | 14.81614 | NA | 10.1067 | -83.9753 | (10.1067, -83.975300000000004) | Landslide | Rockfall | Medium | Downpour | NA | NA | 2 | NA | http://www.ticotimes.net/News/Daily-News/Two-People-Die-in-Landslide-on-Limon-Highway_Saturday-October-16-2010 | 13.346056 | 62.162370 |
stem(df_CR$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 0
## 0 |
## 1 | 00
## 1 | 55
## 2 | 002stem(df_CR$"distance", scale = 2)##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 0
## 0 |
## 1 | 00
## 1 | 55
## 2 | 002Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.26208 | 1 | 12.5 | 12.5 | 12.5 | 12.5 |
| 9.85736 | 1 | 12.5 | 12.5 | 25.0 | 25.0 |
| 10.0131 | 1 | 12.5 | 12.5 | 37.5 | 37.5 |
| 14.81614 | 1 | 12.5 | 12.5 | 50.0 | 50.0 |
| 15.05161 | 1 | 12.5 | 12.5 | 62.5 | 62.5 |
| 19.51432 | 1 | 12.5 | 12.5 | 75.0 | 75.0 |
| 19.54581 | 1 | 12.5 | 12.5 | 87.5 | 87.5 |
| 21.9547 | 1 | 12.5 | 12.5 | 100.0 | 100.0 |
| Total | 8 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 9 obs. of 5 variables:
## $ n : num 1 1 1 1 1 1 1 1 8
## $ % : num 12.5 12.5 12.5 12.5 12.5 12.5 12.5 12.5 100
## $ val% : num 12.5 12.5 12.5 12.5 12.5 12.5 12.5 12.5 100
## $ %cum : num 12.5 25 37.5 50 62.5 75 87.5 100 100
## $ val%cum: num 12.5 25 37.5 50 62.5 75 87.5 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.26208 | 1 |
| 9.85736 | 1 |
| 10.0131 | 1 |
| 14.81614 | 1 |
| 15.05161 | 1 |
| 19.51432 | 1 |
| 19.54581 | 1 |
| 21.9547 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.26208 6.26208 12.26208 18.26208 24.26208distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.262,6.26] | 0 | 0.0000000 | 0 |
| (6.26,12.3] | 2 | 0.2857143 | 2 |
| (12.3,18.3] | 2 | 0.2857143 | 4 |
| (18.3,24.3] | 3 | 0.4285714 | 7 |
str(Freq_table)## 'data.frame': 4 obs. of 4 variables:
## $ distance: Factor w/ 4 levels "(0.262,6.26]",..: 1 2 3 4
## $ Freq : int 0 2 2 3
## $ Rel_Freq: num 0 0.286 0.286 0.429
## $ Cum_Freq: int 0 2 4 7df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.262,6.26] | 0 |
| (6.26,12.3] | 2 |
| (12.3,18.3] | 2 |
| (18.3,24.3] | 3 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_CR)## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 8.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 2.490000e+02 NA NA NA NA NA
## max 6.696000e+03 NA NA NA NA NA
## range 6.447000e+03 NA NA NA NA NA
## sum 2.744200e+04 NA NA NA NA NA
## median 3.107000e+03 NA NA NA NA NA
## mean 3.430250e+03 NA NA NA NA NA
## SE.mean 7.315967e+02 NA NA NA NA NA
## CI.mean.0.95 1.729951e+03 NA NA NA NA NA
## var 4.281870e+06 NA NA NA NA NA
## std.dev 2.069268e+03 NA NA NA NA NA
## coef.var 6.032412e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 8.000000e+00 NA 8.0000000 NA
## nbr.null NA 1.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 0.000000e+00 NA 0.2620800 NA
## max NA 2.194700e+04 NA 21.9547000 NA
## range NA 2.194700e+04 NA 21.6926200 NA
## sum NA 3.885700e+04 NA 111.0151200 NA
## median NA 1.355000e+03 NA 14.9338750 NA
## mean NA 4.857125e+03 NA 13.8768900 NA
## SE.mean NA 2.557523e+03 NA 2.4924134 NA
## CI.mean.0.95 NA 6.047580e+03 NA 5.8936213 NA
## var NA 5.232738e+07 NA 49.6969984 NA
## std.dev NA 7.233767e+03 NA 7.0496098 NA
## coef.var NA 1.489310e+00 NA 0.5080108 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 8.000000000 8.000000e+00 NA NA NA
## nbr.null 0.000000000 0.000000e+00 NA NA NA
## nbr.na 0.000000000 0.000000e+00 NA NA NA
## min 10.000000000 -8.414890e+01 NA NA NA
## max 10.205400000 -8.390410e+01 NA NA NA
## range 0.205400000 2.448000e-01 NA NA NA
## sum 81.063300000 -6.720410e+02 NA NA NA
## median 10.144250000 -8.397730e+01 NA NA NA
## mean 10.132912500 -8.400512e+01 NA NA NA
## SE.mean 0.022739522 2.987758e-02 NA NA NA
## CI.mean.0.95 0.053770426 7.064924e-02 NA NA NA
## var 0.004136687 7.141356e-03 NA NA NA
## std.dev 0.064317081 8.450655e-02 NA NA NA
## coef.var 0.006347344 -1.005969e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 1 6.0000000 NA
## nbr.null NA NA NA 1 5.0000000 NA
## nbr.na NA NA NA 7 2.0000000 NA
## min NA NA NA 0 0.0000000 NA
## max NA NA NA 0 2.0000000 NA
## range NA NA NA 0 2.0000000 NA
## sum NA NA NA 0 2.0000000 NA
## median NA NA NA 0 0.0000000 NA
## mean NA NA NA 0 0.3333333 NA
## SE.mean NA NA NA NA 0.3333333 NA
## CI.mean.0.95 NA NA NA NaN 0.8568606 NA
## var NA NA NA NA 0.6666667 NA
## std.dev NA NA NA NA 0.8164966 NA
## coef.var NA NA NA NA 2.4494897 NA
## source_link prop ypos
## nbr.val NA 8.0000000 8.0000000
## nbr.null NA 0.0000000 0.0000000
## nbr.na NA 0.0000000 0.0000000
## min NA 0.2360760 9.8881576
## max NA 19.7763152 93.2209189
## range NA 19.5402392 83.3327613
## sum NA 100.0000000 376.0014582
## median NA 13.4521090 40.0508913
## mean NA 12.5000000 47.0001823
## SE.mean NA 2.2451117 10.1053438
## CI.mean.0.95 NA 5.3088456 23.8953410
## var NA 40.3242124 816.9437832
## std.dev NA 6.3501348 28.5822285
## coef.var NA 0.5080108 0.6081302boxplot(data, horizontal=TRUE, col='green')
Gráfico para San José (Costa Rica)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_CR <- subset(df, country_name == "Costa Rica")
knitr::kable(head(df_CR)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 249 | 9/9/07 | NA | NA | Costa Rica | CR | Heredia | 21947 | Heredia | 0.26208 | NA | 10.0000 | -84.1167 | (10, -84.116699999999994) | Landslide | Landslide | Medium | Rain | NA | NA | NA | ticotimes.net | http://www.ticotimes.net/dailyarchive/2007_09/0911072.htm |
| 299 | 10/9/07 | NA | NA | Costa Rica | CR | San José | 3072 | San Ignacio | 4.57763 | NA | 9.7789 | -84.1250 | (9.7789000000000001, -84.125) | Landslide | Complex | Medium | Rain | NA | NA | 4 | ticotimes.net | http://www.ticotimes.net/dailyarchive/2007_10/1010071.htm |
| 301 | 10/11/07 | NA | NA | Costa Rica | CR | Alajuela | 7014 | Atenas | 3.08459 | NA | 9.9869 | -84.4070 | (9.9869000000000003, -84.406999999999996) | Landslide | Mudslide | Large | Rain | NA | NA | 14 | Agence France-Presse, afp.google.com | http://afp.google.com/article/ALeqM5hu6a8oyAM1ycq9nU_6Zyj_l7F0AA |
| 302 | 10/11/07 | NA | NA | Costa Rica | CR | San José | 26669 | NA | 9.56251 | NA | 10.0214 | -83.9451 | (10.0214, -83.945099999999996) | Landslide | Landslide | Large | Rain | NA | NA | 10 | International Herald | http://www.iht.com/articles/ap/2007/10/12/america/LA-GEN-Costa-Rica-Mudslide.php |
| 323 | 10/24/07 | NA | NA | Costa Rica | CR | Puntarenas | 6540 | Miramar | 3.82425 | Mine construction | 10.0715 | -84.7575 | (10.0715, -84.757499999999993) | Landslide | Mudslide | Medium | Downpour | NA | NA | NA | Reuters - AlertNet.org | http://www.reuters.com/article/companyNewsAndPR/idUSN2435152820071025 |
| 556 | 5/29/08 | NA | NA | Costa Rica | CR | Guanacaste | 4108 | Bagaces | 17.65521 | NA | 10.4024 | -85.3555 | (10.4024, -85.355500000000006) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Alma | NA | NA | NA | http://www.reliefweb.int/rw/RWB.NSF/db900SID/ASAZ-7FHCHL?OpenDocument |
library(dplyr)
df_CR <- subset(df, state == "San José")
knitr::kable(head(df_CR))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 299 | 10/9/07 | NA | NA | Costa Rica | CR | San José | 3072 | San Ignacio | 4.57763 | NA | 9.7789 | -84.1250 | (9.7789000000000001, -84.125) | Landslide | Complex | Medium | Rain | NA | NA | 4 | ticotimes.net | http://www.ticotimes.net/dailyarchive/2007_10/1010071.htm |
| 302 | 10/11/07 | NA | NA | Costa Rica | CR | San José | 26669 | NA | 9.56251 | NA | 10.0214 | -83.9451 | (10.0214, -83.945099999999996) | Landslide | Landslide | Large | Rain | NA | NA | 10 | International Herald | http://www.iht.com/articles/ap/2007/10/12/america/LA-GEN-Costa-Rica-Mudslide.php |
| 776 | 9/6/08 | NA | NA | Costa Rica | CR | San José | 10028 | Daniel Flores | 1.85787 | NA | 9.3500 | -83.6780 | (9.35, -83.677999999999997) | Landslide | Mudslide | Medium | Downpour | NA | NA | NA | NA | http://insidecostarica.com/dailynews/2008/september/07/nac02.htm |
| 838 | 10/12/08 | NA | NA | Costa Rica | CR | San José | 34877 | San Isidro | 16.24937 | NA | 9.5190 | -83.7060 | (9.5190000000000001, -83.706000000000003) | Landslide | Landslide | Medium | Downpour | NA | NA | NA | NA | http://www.ticotimes.net/dailyarchive/2008_10/1014081.htm |
| 839 | 10/12/08 | NA | NA | Costa Rica | CR | San José | 8292 | Santiago | 12.85801 | NA | 9.7640 | -84.3970 | (9.7639999999999993, -84.397000000000006) | Landslide | Landslide | Medium | Downpour | NA | NA | NA | NA | http://www.ticotimes.net/dailyarchive/2008_10/1014082.htm |
| 2526 | 10/1/10 | NA | NA | Costa Rica | CR | San José | 2833 | Salitral | 0.25254 | NA | 9.9108 | -84.1764 | (9.9108000000000001, -84.176400000000001) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.ticotimes.net/News/Mudslides-Force-63-Out-of-Santa-Ana-Homes_Friday-October-01-2010 |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_CR, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_CR, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_CR, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_CR <- df_CR %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_CR$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_CR, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4## Warning in RColorBrewer::brewer.pal(n, pal): n too large, allowed maximum for palette Greens is 9
## Returning the palette you asked for with that many colors
Grafico de series temporales
library(forecast)
data<- ts(df_CR$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 6.49523 |
| 12.85801 |
| 8.27042 |
| 0.55804 |
| 0.72957 |
| 1.16705 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_CR$distance
names(distance) <- df_CR$state
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 200, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## San José 22.3236800 22.3236800 11.3956252 11.3956252
## San José 21.6745200 43.9982000 11.0642469 22.4598721
## San José 16.2493700 60.2475700 8.2948569 30.7547290
## San José 15.6499700 75.8975400 7.9888797 38.7436087
## San José 12.8580100 88.7555500 6.5636608 45.3072695
## San José 11.3104700 100.0660200 5.7736842 51.0809536
## San José 10.7375200 110.8035400 5.4812089 56.5621626
## San José 10.0119800 120.8155200 5.1108407 61.6730032
## San José 9.5625100 130.3780300 4.8813986 66.5544018
## San José 9.5361100 139.9141400 4.8679221 71.4223240
## San José 8.3916100 148.3057500 4.2836863 75.7060103
## San José 8.2704200 156.5761700 4.2218222 79.9278325
## San José 8.2137200 164.7898900 4.1928784 84.1207108
## San José 6.4952300 171.2851200 3.3156364 87.4363473
## San José 4.8995400 176.1846600 2.5010805 89.9374278
## San José 4.5776300 180.7622900 2.3367543 92.2741821
## San José 3.7140700 184.4763600 1.8959307 94.1701128
## San José 3.6769100 188.1532700 1.8769615 96.0470743
## San José 2.9260500 191.0793200 1.4936681 97.5407425
## San José 1.8578700 192.9371900 0.9483916 98.4891341
## San José 1.1670500 194.1042400 0.5957470 99.0848810
## San José 0.7295700 194.8338100 0.3724254 99.4573065
## San José 0.5580400 195.3918500 0.2848641 99.7421705
## San José 0.2525400 195.6443900 0.1289147 99.8710853
## San José 0.2525400 195.8969300 0.1289147 100.0000000stem(df_CR$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 001112344
## 0 | 556888
## 1 | 000113
## 1 | 66
## 2 | 22head(df_CR)## # A tibble: 6 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 2686 11/4/10 <NA> <NA> Costa Rica CR San José 22433
## 2 839 10/12/08 <NA> <NA> Costa Rica CR San José 8292
## 3 7496 11/11/15 <NA> <NA> Costa Rica CR San José 8292
## 4 2681 11/4/10 <NA> <NA> Costa Rica CR San José 4255
## 5 7444 10/29/15 <NA> <NA> Costa Rica CR San José 26047
## 6 7494 9/25/15 <NA> <NA> Costa Rica CR San José 335007
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_CR))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2686 | 11/4/10 | NA | NA | Costa Rica | CR | San José | 22433 | Tejar | 6.49523 | NA | 9.7112 | -84.2812 | (9.7111999999999998, -84.281199999999998) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Tomas | NA | 0 | NA | http://fortunatimes.com/2010/11/06/no-passage-to-the-south-and-central-pacific/ | 3.3156364 | 1.657818 |
| 839 | 10/12/08 | NA | NA | Costa Rica | CR | San José | 8292 | Santiago | 12.85801 | NA | 9.7640 | -84.3970 | (9.7639999999999993, -84.397000000000006) | Landslide | Landslide | Medium | Downpour | NA | NA | NA | NA | http://www.ticotimes.net/dailyarchive/2008_10/1014082.htm | 6.5636608 | 6.597467 |
| 7496 | 11/11/15 | NA | NA | Costa Rica | CR | San José | 8292 | Santiago | 8.27042 | Above road | 9.8747 | -84.3841 | (9.8747000000000007, -84.384100000000004) | Landslide | Landslide | Small | Rain | NA | 0 | 0 | La Nacion | http://www.nacion.com/sucesos/Camino-Puriscal-Turrubares-cerrado-derrumbe_0_1523647757.html | 4.2218222 | 11.990208 |
| 2681 | 11/4/10 | NA | NA | Costa Rica | CR | San José | 4255 | San Marcos | 0.55804 | NA | 9.6563 | -84.0236 | (9.6562999999999999, -84.023600000000002) | Landslide | Mudslide | Medium | Tropical cyclone | Tropical Storm Tomas | NA | 3 | NA | http://articles.cnn.com/2010-11-05/world/costa.rica.fatal.mudslides_1_mud-slides-drinking-or-cooking-safe-water-supplies?_s=PM:WORLD | 0.2848641 | 14.243551 |
| 7444 | 10/29/15 | NA | NA | Costa Rica | CR | San José | 26047 | San Juan | 0.72957 | Above road | 9.9574 | -84.0879 | (9.9573999999999998, -84.087900000000005) | Landslide | Landslide | Medium | Rain | NA | 0 | 0 | La Nacion | http://www.nacion.com/nacional/transportes/Deslizamiento-Tibas-afecta-servicio-Heredia_0_1521048003.html | 0.3724254 | 14.572196 |
| 7494 | 9/25/15 | NA | NA | Costa Rica | CR | San José | 335007 | San José | 1.16705 | Urban area | 9.9402 | -84.0771 | (9.9402000000000008, -84.077100000000002) | Landslide | Landslide | Small | Rain | NA | 0 | 0 | Repretel | http://www.repretel.com/actualidad/rally-amarralo-3337 | 0.5957470 | 15.056282 |
stem(df_CR$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 001112344
## 0 | 556888
## 1 | 000113
## 1 | 66
## 2 | 22stem(df_CR$"distance", scale = 2)##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 001112344
## 0 | 556888
## 1 | 000113
## 1 | 66
## 2 | 22Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.25254 | 2 | 8 | 8 | 8 | 8 |
| 0.55804 | 1 | 4 | 4 | 12 | 12 |
| 0.72957 | 1 | 4 | 4 | 16 | 16 |
| 1.16705 | 1 | 4 | 4 | 20 | 20 |
| 1.85787 | 1 | 4 | 4 | 24 | 24 |
| 2.92605 | 1 | 4 | 4 | 28 | 28 |
| 3.67691 | 1 | 4 | 4 | 32 | 32 |
| 3.71407 | 1 | 4 | 4 | 36 | 36 |
| 4.57763 | 1 | 4 | 4 | 40 | 40 |
| 4.89954 | 1 | 4 | 4 | 44 | 44 |
| 6.49523 | 1 | 4 | 4 | 48 | 48 |
| 8.21372 | 1 | 4 | 4 | 52 | 52 |
| 8.27042 | 1 | 4 | 4 | 56 | 56 |
| 8.39161 | 1 | 4 | 4 | 60 | 60 |
| 9.53611 | 1 | 4 | 4 | 64 | 64 |
| 9.56251 | 1 | 4 | 4 | 68 | 68 |
| 10.01198 | 1 | 4 | 4 | 72 | 72 |
| 10.73752 | 1 | 4 | 4 | 76 | 76 |
| 11.31047 | 1 | 4 | 4 | 80 | 80 |
| 12.85801 | 1 | 4 | 4 | 84 | 84 |
| 15.64997 | 1 | 4 | 4 | 88 | 88 |
| 16.24937 | 1 | 4 | 4 | 92 | 92 |
| 21.67452 | 1 | 4 | 4 | 96 | 96 |
| 22.32368 | 1 | 4 | 4 | 100 | 100 |
| Total | 25 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 25 obs. of 5 variables:
## $ n : num 2 1 1 1 1 1 1 1 1 1 ...
## $ % : num 8 4 4 4 4 4 4 4 4 4 ...
## $ val% : num 8 4 4 4 4 4 4 4 4 4 ...
## $ %cum : num 8 12 16 20 24 28 32 36 40 44 ...
## $ val%cum: num 8 12 16 20 24 28 32 36 40 44 ...x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.25254 | 2 |
| 0.55804 | 1 |
| 0.72957 | 1 |
| 1.16705 | 1 |
| 1.85787 | 1 |
| 2.92605 | 1 |
| 3.67691 | 1 |
| 3.71407 | 1 |
| 4.57763 | 1 |
| 4.89954 | 1 |
| 6.49523 | 1 |
| 8.21372 | 1 |
| 8.27042 | 1 |
| 8.39161 | 1 |
| 9.53611 | 1 |
| 9.56251 | 1 |
| 10.01198 | 1 |
| 10.73752 | 1 |
| 11.31047 | 1 |
| 12.85801 | 1 |
| 15.64997 | 1 |
| 16.24937 | 1 |
| 21.67452 | 1 |
| 22.32368 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.25254 5.25254 10.25254 15.25254 20.25254 25.25254distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.253,5.25] | 9 | 0.3913043 | 9 |
| (5.25,10.3] | 7 | 0.3043478 | 16 |
| (10.3,15.3] | 3 | 0.1304348 | 19 |
| (15.3,20.3] | 2 | 0.0869565 | 21 |
| (20.3,25.3] | 2 | 0.0869565 | 23 |
str(Freq_table)## 'data.frame': 5 obs. of 4 variables:
## $ distance: Factor w/ 5 levels "(0.253,5.25]",..: 1 2 3 4 5
## $ Freq : int 9 7 3 2 2
## $ Rel_Freq: num 0.391 0.304 0.13 0.087 0.087
## $ Cum_Freq: int 9 16 19 21 23df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.253,5.25] | 9 |
| (5.25,10.3] | 7 |
| (10.3,15.3] | 3 |
| (15.3,20.3] | 2 |
| (20.3,25.3] | 2 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_CR)## id date time continent_code country_name country_code
## nbr.val 2.500000e+01 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 2.990000e+02 NA NA NA NA NA
## max 7.496000e+03 NA NA NA NA NA
## range 7.197000e+03 NA NA NA NA NA
## sum 1.039670e+05 NA NA NA NA NA
## median 2.692000e+03 NA NA NA NA NA
## mean 4.158680e+03 NA NA NA NA NA
## SE.mean 5.330458e+02 NA NA NA NA NA
## CI.mean.0.95 1.100153e+03 NA NA NA NA NA
## var 7.103446e+06 NA NA NA NA NA
## std.dev 2.665229e+03 NA NA NA NA NA
## coef.var 6.408834e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 2.500000e+01 NA 25.000000 NA
## nbr.null NA 3.000000e+00 NA 0.000000 NA
## nbr.na NA 0.000000e+00 NA 0.000000 NA
## min NA 0.000000e+00 NA 0.252540 NA
## max NA 3.350070e+05 NA 22.323680 NA
## range NA 3.350070e+05 NA 22.071140 NA
## sum NA 6.934110e+05 NA 195.896930 NA
## median NA 1.002800e+04 NA 8.213720 NA
## mean NA 2.773644e+04 NA 7.835877 NA
## SE.mean NA 1.308803e+04 NA 1.270388 NA
## CI.mean.0.95 NA 2.701236e+04 NA 2.621953 NA
## var NA 4.282410e+09 NA 40.347169 NA
## std.dev NA 6.544013e+04 NA 6.351942 NA
## coef.var NA 2.359356e+00 NA 0.810623 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 25.00000000 2.500000e+01 NA NA NA
## nbr.null 0.00000000 0.000000e+00 NA NA NA
## nbr.na 0.00000000 0.000000e+00 NA NA NA
## min 9.19220000 -8.439700e+01 NA NA NA
## max 10.14950000 -8.355650e+01 NA NA NA
## range 0.95730000 8.405000e-01 NA NA NA
## sum 242.83950000 -2.098785e+03 NA NA NA
## median 9.77890000 -8.396730e+01 NA NA NA
## mean 9.71358000 -8.395140e+01 NA NA NA
## SE.mean 0.06054644 4.905849e-02 NA NA NA
## CI.mean.0.95 0.12496171 1.012517e-01 NA NA NA
## var 0.09164678 6.016838e-02 NA NA NA
## std.dev 0.30273219 2.452924e-01 NA NA NA
## coef.var 0.03116587 -2.921839e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 10 21.000000 NA
## nbr.null NA NA NA 10 17.000000 NA
## nbr.na NA NA NA 15 4.000000 NA
## min NA NA NA 0 0.000000 NA
## max NA NA NA 0 23.000000 NA
## range NA NA NA 0 23.000000 NA
## sum NA NA NA 0 40.000000 NA
## median NA NA NA 0 0.000000 NA
## mean NA NA NA 0 1.904762 NA
## SE.mean NA NA NA 0 1.172918 NA
## CI.mean.0.95 NA NA NA 0 2.446664 NA
## var NA NA NA 0 28.890476 NA
## std.dev NA NA NA 0 5.374986 NA
## coef.var NA NA NA NaN 2.821868 NA
## source_link prop ypos
## nbr.val NA 25.0000000 25.0000000
## nbr.null NA 0.0000000 0.0000000
## nbr.na NA 0.0000000 0.0000000
## min NA 0.1289147 1.6578182
## max NA 11.3956252 97.5593007
## range NA 11.2667105 95.9014825
## sum NA 100.0000000 1339.6995323
## median NA 4.1928784 66.5210348
## mean NA 4.0000000 53.5879813
## SE.mean NA 0.6484984 6.3076988
## CI.mean.0.95 NA 1.3384349 13.0184506
## var NA 10.5137540 994.6766161
## std.dev NA 3.2424919 31.5384942
## coef.var NA 0.8106230 0.5885367boxplot(data, horizontal=TRUE, col='green')
Gráfico para Alajuela (Costa Rica)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_CR <- subset(df, country_name == "Costa Rica")
knitr::kable(head(df_CR)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 249 | 9/9/07 | NA | NA | Costa Rica | CR | Heredia | 21947 | Heredia | 0.26208 | NA | 10.0000 | -84.1167 | (10, -84.116699999999994) | Landslide | Landslide | Medium | Rain | NA | NA | NA | ticotimes.net | http://www.ticotimes.net/dailyarchive/2007_09/0911072.htm |
| 299 | 10/9/07 | NA | NA | Costa Rica | CR | San José | 3072 | San Ignacio | 4.57763 | NA | 9.7789 | -84.1250 | (9.7789000000000001, -84.125) | Landslide | Complex | Medium | Rain | NA | NA | 4 | ticotimes.net | http://www.ticotimes.net/dailyarchive/2007_10/1010071.htm |
| 301 | 10/11/07 | NA | NA | Costa Rica | CR | Alajuela | 7014 | Atenas | 3.08459 | NA | 9.9869 | -84.4070 | (9.9869000000000003, -84.406999999999996) | Landslide | Mudslide | Large | Rain | NA | NA | 14 | Agence France-Presse, afp.google.com | http://afp.google.com/article/ALeqM5hu6a8oyAM1ycq9nU_6Zyj_l7F0AA |
| 302 | 10/11/07 | NA | NA | Costa Rica | CR | San José | 26669 | NA | 9.56251 | NA | 10.0214 | -83.9451 | (10.0214, -83.945099999999996) | Landslide | Landslide | Large | Rain | NA | NA | 10 | International Herald | http://www.iht.com/articles/ap/2007/10/12/america/LA-GEN-Costa-Rica-Mudslide.php |
| 323 | 10/24/07 | NA | NA | Costa Rica | CR | Puntarenas | 6540 | Miramar | 3.82425 | Mine construction | 10.0715 | -84.7575 | (10.0715, -84.757499999999993) | Landslide | Mudslide | Medium | Downpour | NA | NA | NA | Reuters - AlertNet.org | http://www.reuters.com/article/companyNewsAndPR/idUSN2435152820071025 |
| 556 | 5/29/08 | NA | NA | Costa Rica | CR | Guanacaste | 4108 | Bagaces | 17.65521 | NA | 10.4024 | -85.3555 | (10.4024, -85.355500000000006) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Alma | NA | NA | NA | http://www.reliefweb.int/rw/RWB.NSF/db900SID/ASAZ-7FHCHL?OpenDocument |
library(dplyr)
df_CR <- subset(df, state == "Alajuela")
knitr::kable(head(df_CR))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 301 | 10/11/07 | NA | NA | Costa Rica | CR | Alajuela | 7014 | Atenas | 3.08459 | NA | 9.9869 | -84.4070 | (9.9869000000000003, -84.406999999999996) | Landslide | Mudslide | Large | Rain | NA | NA | 14 | Agence France-Presse, afp.google.com | http://afp.google.com/article/ALeqM5hu6a8oyAM1ycq9nU_6Zyj_l7F0AA |
| 1749 | 4/14/10 | NA | NA | Costa Rica | CR | Alajuela | 14448 | Desamparados | 6.88715 | Above road | 9.9323 | -84.4453 | (9.9322999999999997, -84.445300000000003) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.insidecostarica.com/dailynews/2010/april/16/costarica10041602.htm |
| 1886 | 5/22/10 | 18:00:00 | NA | Costa Rica | CR | Alajuela | 14448 | Desamparados | 6.92174 | Above road | 9.9290 | -84.4428 | (9.9290000000000003, -84.442800000000005) | Landslide | Landslide | Medium | Downpour | NA | 3 | 0 | Costa Rica News | http://thecostaricanews.com/rains-cause-landslides-and-road-accidents-on-caldera/3255 |
| 2174 | 7/30/10 | 9:30:00 | NA | Costa Rica | CR | Alajuela | 14448 | Desamparados | 4.24199 | Above road | 9.9271 | -84.4568 | (9.9270999999999994, -84.456800000000001) | Landslide | Landslide | Medium | Rain | NA | NA | 0 | La Fortuna | https://lafortunatimes.wordpress.com/2010/07/30/landslide-caused-closure-of-san-jose-caldera-for-most-of-the-day-friday/ |
| 2516 | 9/29/10 | NA | NA | Costa Rica | CR | Alajuela | 3624 | San Rafael | 1.47396 | NA | 10.0757 | -84.4793 | (10.075699999999999, -84.479299999999995) | Landslide | Mudslide | Medium | Downpour | NA | NA | 0 | NA | http://www.ticotimes.net/News/Daily-News/Inter-American-Highway-Reopens-Caldera-Highway-Under-Repair_Monday-October-04-2010 |
| 2682 | 11/4/10 | NA | NA | Costa Rica | CR | Alajuela | 3624 | San Rafael | 9.61692 | NA | 10.0421 | -84.5577 | (10.0421, -84.557699999999997) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Tomas | NA | 0 | NA | http://fortunatimes.com/2010/11/06/no-passage-to-the-south-and-central-pacific/ |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_CR, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_CR, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_CR, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_CR <- df_CR %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_CR$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_CR, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4## Warning in RColorBrewer::brewer.pal(n, pal): n too large, allowed maximum for palette Greens is 9
## Returning the palette you asked for with that many colors
Grafico de series temporales
library(forecast)
data<- ts(df_CR$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 0.70048 |
| 3.21979 |
| 5.43516 |
| 1.47396 |
| 9.61692 |
| 4.87432 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_CR$distance
names(distance) <- df_CR$state
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Alajuela 11.9652400 11.9652400 10.5708367 10.5708367
## Alajuela 10.3296800 22.2949200 9.1258813 19.6967180
## Alajuela 9.8421300 32.1370500 8.6951494 28.3918674
## Alajuela 9.6169200 41.7539700 8.4961849 36.8880523
## Alajuela 6.9217400 48.6757100 6.1150953 43.0031476
## Alajuela 6.8871500 55.5628600 6.0845364 49.0876840
## Alajuela 6.8006100 62.3634700 6.0080816 55.0957655
## Alajuela 5.9663400 68.3298100 5.2710356 60.3668011
## Alajuela 5.9551900 74.2850000 5.2611850 65.6279861
## Alajuela 5.5752300 79.8602300 4.9255047 70.5534908
## Alajuela 5.4351600 85.2953900 4.8017582 75.3552490
## Alajuela 5.1266700 90.4220600 4.5292189 79.8844679
## Alajuela 4.8743200 95.2963800 4.3062772 84.1907451
## Alajuela 4.2419900 99.5383700 3.7476376 87.9383828
## Alajuela 3.2197900 102.7581600 2.8445626 90.7829454
## Alajuela 3.0891600 105.8473200 2.7291559 93.5121013
## Alajuela 3.0845900 108.9319100 2.7251185 96.2372198
## Alajuela 2.0846900 111.0166000 1.8417447 98.0789646
## Alajuela 1.4739600 112.4905600 1.3021879 99.3811524
## Alajuela 0.7004800 113.1910400 0.6188476 100.0000000stem(df_CR$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 1123334
## 0 | 555666777
## 1 | 0002head(df_CR)## # A tibble: 6 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 3762 7/12/11 <NA> <NA> Costa Rica CR Alajuela 4185
## 2 7486 10/27/15 <NA> <NA> Costa Rica CR Alajuela 5745
## 3 2703 11/5/10 <NA> <NA> Costa Rica CR Alajuela 2107
## 4 2516 9/29/10 <NA> <NA> Costa Rica CR Alajuela 3624
## 5 2682 11/4/10 <NA> <NA> Costa Rica CR Alajuela 3624
## 6 5408 8/27/13 <NA> <NA> Costa Rica CR Alajuela 1015
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_CR))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 3762 | 7/12/11 | NA | NA | Costa Rica | CR | Alajuela | 4185 | Upala | 0.70048 | NA | 10.8916 | -85.0141 | (10.8916, -85.014099999999999) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.ticotimes.net/Current-Edition/News-Briefs/Upala-on-yellow-alert-after-earthquake-heavy-rains_Wednesday-July-13-2011 | 0.6188476 | 0.3094238 |
| 7486 | 10/27/15 | NA | NA | Costa Rica | CR | Alajuela | 5745 | Santo Domingo | 3.21979 | Above road | 10.0600 | -84.1841 | (10.06, -84.184100000000001) | Landslide | Mudslide | Small | Rain | NA | 0 | 0 | La Prensa Libre | http://www.laprensalibre.cr/Noticias/detalle/45060/430/deslizamiento-deja-bus-atrapado-en-alajuela | 2.8445626 | 2.0411289 |
| 2703 | 11/5/10 | NA | NA | Costa Rica | CR | Alajuela | 2107 | Santiago | 5.43516 | NA | 9.9990 | -84.4876 | (9.9990000000000006, -84.4876) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Tomas | NA | 0 | NA | http://fortunatimes.com/2010/11/06/no-passage-to-the-south-and-central-pacific/ | 4.8017582 | 5.8642893 |
| 2516 | 9/29/10 | NA | NA | Costa Rica | CR | Alajuela | 3624 | San Rafael | 1.47396 | NA | 10.0757 | -84.4793 | (10.075699999999999, -84.479299999999995) | Landslide | Mudslide | Medium | Downpour | NA | NA | 0 | NA | http://www.ticotimes.net/News/Daily-News/Inter-American-Highway-Reopens-Caldera-Highway-Under-Repair_Monday-October-04-2010 | 1.3021879 | 8.9162623 |
| 2682 | 11/4/10 | NA | NA | Costa Rica | CR | Alajuela | 3624 | San Rafael | 9.61692 | NA | 10.0421 | -84.5577 | (10.0421, -84.557699999999997) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Tomas | NA | 0 | NA | http://fortunatimes.com/2010/11/06/no-passage-to-the-south-and-central-pacific/ | 8.4961849 | 13.8154486 |
| 5408 | 8/27/13 | NA | NA | Costa Rica | CR | Alajuela | 1015 | Sabanilla | 4.87432 | NA | 10.1181 | -84.2146 | (10.1181, -84.214600000000004) | Landslide | Landslide | Medium | Downpour | NA | NA | NA | insidecostarica.com | http://insidecostarica.com/2013/08/28/flooding-and-landslides-after-heavy-downpours-across-the-country/ | 4.3062772 | 20.2166797 |
stem(df_CR$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 1123334
## 0 | 555666777
## 1 | 0002stem(df_CR$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 75
## 2 | 1112
## 4 | 29146
## 6 | 00899
## 8 | 68
## 10 | 3
## 12 | 0Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.70048 | 1 | 5 | 5 | 5 | 5 |
| 1.47396 | 1 | 5 | 5 | 10 | 10 |
| 2.08469 | 1 | 5 | 5 | 15 | 15 |
| 3.08459 | 1 | 5 | 5 | 20 | 20 |
| 3.08916 | 1 | 5 | 5 | 25 | 25 |
| 3.21979 | 1 | 5 | 5 | 30 | 30 |
| 4.24199 | 1 | 5 | 5 | 35 | 35 |
| 4.87432 | 1 | 5 | 5 | 40 | 40 |
| 5.12667 | 1 | 5 | 5 | 45 | 45 |
| 5.43516 | 1 | 5 | 5 | 50 | 50 |
| 5.57523 | 1 | 5 | 5 | 55 | 55 |
| 5.95519 | 1 | 5 | 5 | 60 | 60 |
| 5.96634 | 1 | 5 | 5 | 65 | 65 |
| 6.80061 | 1 | 5 | 5 | 70 | 70 |
| 6.88715 | 1 | 5 | 5 | 75 | 75 |
| 6.92174 | 1 | 5 | 5 | 80 | 80 |
| 9.61692 | 1 | 5 | 5 | 85 | 85 |
| 9.84213 | 1 | 5 | 5 | 90 | 90 |
| 10.32968 | 1 | 5 | 5 | 95 | 95 |
| 11.96524 | 1 | 5 | 5 | 100 | 100 |
| Total | 20 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 21 obs. of 5 variables:
## $ n : num 1 1 1 1 1 1 1 1 1 1 ...
## $ % : num 5 5 5 5 5 5 5 5 5 5 ...
## $ val% : num 5 5 5 5 5 5 5 5 5 5 ...
## $ %cum : num 5 10 15 20 25 30 35 40 45 50 ...
## $ val%cum: num 5 10 15 20 25 30 35 40 45 50 ...x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.70048 | 1 |
| 1.47396 | 1 |
| 2.08469 | 1 |
| 3.08459 | 1 |
| 3.08916 | 1 |
| 3.21979 | 1 |
| 4.24199 | 1 |
| 4.87432 | 1 |
| 5.12667 | 1 |
| 5.43516 | 1 |
| 5.57523 | 1 |
| 5.95519 | 1 |
| 5.96634 | 1 |
| 6.80061 | 1 |
| 6.88715 | 1 |
| 6.92174 | 1 |
| 9.61692 | 1 |
| 9.84213 | 1 |
| 10.32968 | 1 |
| 11.96524 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.70048 3.70048 6.70048 9.70048 12.70048distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.7,3.7] | 5 | 0.2631579 | 5 |
| (3.7,6.7] | 7 | 0.3684211 | 12 |
| (6.7,9.7] | 4 | 0.2105263 | 16 |
| (9.7,12.7] | 3 | 0.1578947 | 19 |
str(Freq_table)## 'data.frame': 4 obs. of 4 variables:
## $ distance: Factor w/ 4 levels "(0.7,3.7]","(3.7,6.7]",..: 1 2 3 4
## $ Freq : int 5 7 4 3
## $ Rel_Freq: num 0.263 0.368 0.211 0.158
## $ Cum_Freq: int 5 12 16 19df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.7,3.7] | 5 |
| (3.7,6.7] | 7 |
| (6.7,9.7] | 4 |
| (9.7,12.7] | 3 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_CR)## id date time continent_code country_name country_code
## nbr.val 2.000000e+01 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 3.010000e+02 NA NA NA NA NA
## max 7.488000e+03 NA NA NA NA NA
## range 7.187000e+03 NA NA NA NA NA
## sum 9.718800e+04 NA NA NA NA NA
## median 5.878000e+03 NA NA NA NA NA
## mean 4.859400e+03 NA NA NA NA NA
## SE.mean 5.261514e+02 NA NA NA NA NA
## CI.mean.0.95 1.101248e+03 NA NA NA NA NA
## var 5.536707e+06 NA NA NA NA NA
## std.dev 2.353021e+03 NA NA NA NA NA
## coef.var 4.842204e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 2.000000e+01 NA 20.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 1.015000e+03 NA 0.7004800 NA
## max NA 4.749400e+04 NA 11.9652400 NA
## range NA 4.647900e+04 NA 11.2647600 NA
## sum NA 1.924900e+05 NA 113.1910400 NA
## median NA 7.014000e+03 NA 5.5051950 NA
## mean NA 9.624500e+03 NA 5.6595520 NA
## SE.mean NA 2.281502e+03 NA 0.6812501 NA
## CI.mean.0.95 NA 4.775238e+03 NA 1.4258729 NA
## var NA 1.041050e+08 NA 9.2820347 NA
## std.dev NA 1.020319e+04 NA 3.0466432 NA
## coef.var NA 1.060126e+00 NA 0.5383188 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 20.00000000 2.000000e+01 NA NA NA
## nbr.null 0.00000000 0.000000e+00 NA NA NA
## nbr.na 0.00000000 0.000000e+00 NA NA NA
## min 9.91890000 -8.501410e+01 NA NA NA
## max 10.89160000 -8.418070e+01 NA NA NA
## range 0.97270000 8.334000e-01 NA NA NA
## sum 202.24760000 -1.688552e+03 NA NA NA
## median 10.04315000 -8.444405e+01 NA NA NA
## mean 10.11238000 -8.442758e+01 NA NA NA
## SE.mean 0.05493583 4.594981e-02 NA NA NA
## CI.mean.0.95 0.11498201 9.617405e-02 NA NA NA
## var 0.06035891 4.222770e-02 NA NA NA
## std.dev 0.24568050 2.054938e-01 NA NA NA
## coef.var 0.02429502 -2.433965e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities
## nbr.val NA NA NA 11.0000000 18.0000000
## nbr.null NA NA NA 10.0000000 15.0000000
## nbr.na NA NA NA 9.0000000 2.0000000
## min NA NA NA 0.0000000 0.0000000
## max NA NA NA 3.0000000 14.0000000
## range NA NA NA 3.0000000 14.0000000
## sum NA NA NA 3.0000000 16.0000000
## median NA NA NA 0.0000000 0.0000000
## mean NA NA NA 0.2727273 0.8888889
## SE.mean NA NA NA 0.2727273 0.7749716
## CI.mean.0.95 NA NA NA 0.6076742 1.6350471
## var NA NA NA 0.8181818 10.8104575
## std.dev NA NA NA 0.9045340 3.2879260
## coef.var NA NA NA 3.3166248 3.6989168
## source_name source_link prop ypos
## nbr.val NA NA 20.0000000 20.0000000
## nbr.null NA NA 0.0000000 0.0000000
## nbr.na NA NA 0.0000000 0.0000000
## min NA NA 0.6188476 0.3094238
## max NA NA 10.5708367 97.5372476
## range NA NA 9.9519891 97.2278239
## sum NA NA 100.0000000 984.6035428
## median NA NA 4.8636314 51.7474020
## mean NA NA 5.0000000 49.2301771
## SE.mean NA NA 0.6018587 7.4144621
## CI.mean.0.95 NA NA 1.2597047 15.5186476
## var NA NA 7.2446780 1099.4849742
## std.dev NA NA 2.6915940 33.1584827
## coef.var NA NA 0.5383188 0.6735398boxplot(data, horizontal=TRUE, col='green')
Gráfico para Puntarenas (Costa Rica)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_CR <- subset(df, country_name == "Costa Rica")
knitr::kable(head(df_CR)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 249 | 9/9/07 | NA | NA | Costa Rica | CR | Heredia | 21947 | Heredia | 0.26208 | NA | 10.0000 | -84.1167 | (10, -84.116699999999994) | Landslide | Landslide | Medium | Rain | NA | NA | NA | ticotimes.net | http://www.ticotimes.net/dailyarchive/2007_09/0911072.htm |
| 299 | 10/9/07 | NA | NA | Costa Rica | CR | San José | 3072 | San Ignacio | 4.57763 | NA | 9.7789 | -84.1250 | (9.7789000000000001, -84.125) | Landslide | Complex | Medium | Rain | NA | NA | 4 | ticotimes.net | http://www.ticotimes.net/dailyarchive/2007_10/1010071.htm |
| 301 | 10/11/07 | NA | NA | Costa Rica | CR | Alajuela | 7014 | Atenas | 3.08459 | NA | 9.9869 | -84.4070 | (9.9869000000000003, -84.406999999999996) | Landslide | Mudslide | Large | Rain | NA | NA | 14 | Agence France-Presse, afp.google.com | http://afp.google.com/article/ALeqM5hu6a8oyAM1ycq9nU_6Zyj_l7F0AA |
| 302 | 10/11/07 | NA | NA | Costa Rica | CR | San José | 26669 | NA | 9.56251 | NA | 10.0214 | -83.9451 | (10.0214, -83.945099999999996) | Landslide | Landslide | Large | Rain | NA | NA | 10 | International Herald | http://www.iht.com/articles/ap/2007/10/12/america/LA-GEN-Costa-Rica-Mudslide.php |
| 323 | 10/24/07 | NA | NA | Costa Rica | CR | Puntarenas | 6540 | Miramar | 3.82425 | Mine construction | 10.0715 | -84.7575 | (10.0715, -84.757499999999993) | Landslide | Mudslide | Medium | Downpour | NA | NA | NA | Reuters - AlertNet.org | http://www.reuters.com/article/companyNewsAndPR/idUSN2435152820071025 |
| 556 | 5/29/08 | NA | NA | Costa Rica | CR | Guanacaste | 4108 | Bagaces | 17.65521 | NA | 10.4024 | -85.3555 | (10.4024, -85.355500000000006) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Alma | NA | NA | NA | http://www.reliefweb.int/rw/RWB.NSF/db900SID/ASAZ-7FHCHL?OpenDocument |
library(dplyr)
df_CR <- subset(df, state == "Puntarenas")
knitr::kable(head(df_CR))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 323 | 10/24/07 | NA | NA | Costa Rica | CR | Puntarenas | 6540 | Miramar | 3.82425 | Mine construction | 10.0715 | -84.7575 | (10.0715, -84.757499999999993) | Landslide | Mudslide | Medium | Downpour | NA | NA | NA | Reuters - AlertNet.org | http://www.reuters.com/article/companyNewsAndPR/idUSN2435152820071025 |
| 845 | 10/15/08 | NA | NA | Costa Rica | CR | Puntarenas | 6777 | Golfito | 11.74074 | NA | 8.6700 | -83.0640 | (8.67, -83.063999999999993) | Landslide | Landslide | Medium | Downpour | NA | NA | NA | NA | http://www.ticotimes.net/dailyarchive/2008_10/1016081.htm |
| 848 | 10/16/08 | NA | NA | Costa Rica | CR | Puntarenas | 6540 | Miramar | 8.92048 | NA | 10.1110 | -84.8090 | (10.111000000000001, -84.808999999999997) | Landslide | Complex | Medium | Downpour | NA | NA | NA | NA | http://insidecostarica.com/dailynews/2008/october/17/nac01.htm |
| 1296 | 11/13/09 | NA | NA | Costa Rica | CR | Puntarenas | 3981 | San Vito | 18.00524 | NA | 8.8021 | -83.1335 | (8.8020999999999994, -83.133499999999998) | Landslide | Landslide | Medium | Earthquake | NA | NA | 1 | NA | http://www.ticotimes.net/dailyarchive/2009_11/1116092.cfm |
| 2685 | 11/4/10 | NA | NA | Costa Rica | CR | Puntarenas | 6777 | Golfito | 7.87044 | NA | 8.6117 | -83.1000 | (8.6117000000000008, -83.1) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Tomas | NA | 0 | NA | http://fortunatimes.com/2010/11/06/no-passage-to-the-south-and-central-pacific/ |
| 2688 | 11/4/10 | NA | NA | Costa Rica | CR | Puntarenas | 7084 | Corredor | 4.93053 | NA | 8.6844 | -82.9418 | (8.6844000000000001, -82.941800000000001) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Tomas | NA | 0 | NA | http://fortunatimes.com/2010/11/14/12-roads-remain-closed/ |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_CR, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_CR, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_CR, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_CR <- df_CR %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_CR$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_CR, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_CR$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 18.00524 |
| 13.48919 |
| 3.82425 |
| 8.92048 |
| 11.74074 |
| 7.87044 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_CR$distance
names(distance) <- df_CR$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Ciudad Cortés 20.0663300 20.0663300 22.4960244 22.4960244
## San Vito 18.0052400 38.0715700 20.1853711 42.6813955
## Parrita 13.4891900 51.5607600 15.1225036 57.8038990
## Golfito 11.7407400 63.3015000 13.1623457 70.9662447
## Miramar 8.9204800 72.2219800 10.0005998 80.9668445
## Golfito 7.8704400 80.0924200 8.8234176 89.7902622
## Corredor 4.9305300 85.0229500 5.5275341 95.3177962
## Miramar 3.8242500 88.8472000 4.2873022 99.6050985
## Buenos Aires 0.3522500 89.1994500 0.3949015 100.0000000stem(df_CR$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 04
## 0 | 589
## 1 | 23
## 1 | 8
## 2 | 0head(df_CR)## # A tibble: 6 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 1296 11/13/09 <NA> <NA> Costa Rica CR Puntarenas 3981
## 2 2689 11/4/10 <NA> <NA> Costa Rica CR Puntarenas 3734
## 3 323 10/24/07 <NA> <NA> Costa Rica CR Puntarenas 6540
## 4 848 10/16/08 <NA> <NA> Costa Rica CR Puntarenas 6540
## 5 845 10/15/08 <NA> <NA> Costa Rica CR Puntarenas 6777
## 6 2685 11/4/10 <NA> <NA> Costa Rica CR Puntarenas 6777
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_CR))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1296 | 11/13/09 | NA | NA | Costa Rica | CR | Puntarenas | 3981 | San Vito | 18.00524 | NA | 8.8021 | -83.1335 | (8.8020999999999994, -83.133499999999998) | Landslide | Landslide | Medium | Earthquake | NA | NA | 1 | NA | http://www.ticotimes.net/dailyarchive/2009_11/1116092.cfm | 20.185371 | 10.09269 |
| 2689 | 11/4/10 | NA | NA | Costa Rica | CR | Puntarenas | 3734 | Parrita | 13.48919 | NA | 9.6341 | -84.3662 | (9.6341000000000001, -84.366200000000006) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Tomas | NA | 0 | NA | http://fortunatimes.com/2010/11/14/12-roads-remain-closed/ | 15.122504 | 27.74662 |
| 323 | 10/24/07 | NA | NA | Costa Rica | CR | Puntarenas | 6540 | Miramar | 3.82425 | Mine construction | 10.0715 | -84.7575 | (10.0715, -84.757499999999993) | Landslide | Mudslide | Medium | Downpour | NA | NA | NA | Reuters - AlertNet.org | http://www.reuters.com/article/companyNewsAndPR/idUSN2435152820071025 | 4.287302 | 37.45153 |
| 848 | 10/16/08 | NA | NA | Costa Rica | CR | Puntarenas | 6540 | Miramar | 8.92048 | NA | 10.1110 | -84.8090 | (10.111000000000001, -84.808999999999997) | Landslide | Complex | Medium | Downpour | NA | NA | NA | NA | http://insidecostarica.com/dailynews/2008/october/17/nac01.htm | 10.000600 | 44.59548 |
| 845 | 10/15/08 | NA | NA | Costa Rica | CR | Puntarenas | 6777 | Golfito | 11.74074 | NA | 8.6700 | -83.0640 | (8.67, -83.063999999999993) | Landslide | Landslide | Medium | Downpour | NA | NA | NA | NA | http://www.ticotimes.net/dailyarchive/2008_10/1016081.htm | 13.162346 | 56.17695 |
| 2685 | 11/4/10 | NA | NA | Costa Rica | CR | Puntarenas | 6777 | Golfito | 7.87044 | NA | 8.6117 | -83.1000 | (8.6117000000000008, -83.1) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Tomas | NA | 0 | NA | http://fortunatimes.com/2010/11/06/no-passage-to-the-south-and-central-pacific/ | 8.823418 | 67.16983 |
stem(df_CR$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 04
## 0 | 589
## 1 | 23
## 1 | 8
## 2 | 0stem(df_CR$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 4
## 2 | 8
## 4 | 9
## 6 | 9
## 8 | 9
## 10 | 7
## 12 | 5
## 14 |
## 16 |
## 18 | 0
## 20 | 1Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.35225 | 1 | 11.1 | 11.1 | 11.1 | 11.1 |
| 3.82425 | 1 | 11.1 | 11.1 | 22.2 | 22.2 |
| 4.93053 | 1 | 11.1 | 11.1 | 33.3 | 33.3 |
| 7.87044 | 1 | 11.1 | 11.1 | 44.4 | 44.4 |
| 8.92048 | 1 | 11.1 | 11.1 | 55.6 | 55.6 |
| 11.74074 | 1 | 11.1 | 11.1 | 66.7 | 66.7 |
| 13.48919 | 1 | 11.1 | 11.1 | 77.8 | 77.8 |
| 18.00524 | 1 | 11.1 | 11.1 | 88.9 | 88.9 |
| 20.06633 | 1 | 11.1 | 11.1 | 100.0 | 100.0 |
| Total | 9 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 10 obs. of 5 variables:
## $ n : num 1 1 1 1 1 1 1 1 1 9
## $ % : num 11.1 11.1 11.1 11.1 11.1 11.1 11.1 11.1 11.1 100
## $ val% : num 11.1 11.1 11.1 11.1 11.1 11.1 11.1 11.1 11.1 100
## $ %cum : num 11.1 22.2 33.3 44.4 55.6 66.7 77.8 88.9 100 100
## $ val%cum: num 11.1 22.2 33.3 44.4 55.6 66.7 77.8 88.9 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.35225 | 1 |
| 3.82425 | 1 |
| 4.93053 | 1 |
| 7.87044 | 1 |
| 8.92048 | 1 |
| 11.74074 | 1 |
| 13.48919 | 1 |
| 18.00524 | 1 |
| 20.06633 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.35225 4.35225 8.35225 12.35225 16.35225 20.35225distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.352,4.35] | 1 | 0.125 | 1 |
| (4.35,8.35] | 2 | 0.250 | 3 |
| (8.35,12.4] | 2 | 0.250 | 5 |
| (12.4,16.4] | 1 | 0.125 | 6 |
| (16.4,20.4] | 2 | 0.250 | 8 |
str(Freq_table)## 'data.frame': 5 obs. of 4 variables:
## $ distance: Factor w/ 5 levels "(0.352,4.35]",..: 1 2 3 4 5
## $ Freq : int 1 2 2 1 2
## $ Rel_Freq: num 0.125 0.25 0.25 0.125 0.25
## $ Cum_Freq: int 1 3 5 6 8df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.352,4.35] | 1 |
| (4.35,8.35] | 2 |
| (8.35,12.4] | 2 |
| (12.4,16.4] | 1 |
| (16.4,20.4] | 2 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_CR)## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 9.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 3.230000e+02 NA NA NA NA NA
## max 7.493000e+03 NA NA NA NA NA
## range 7.170000e+03 NA NA NA NA NA
## sum 2.155700e+04 NA NA NA NA NA
## median 2.685000e+03 NA NA NA NA NA
## mean 2.395222e+03 NA NA NA NA NA
## SE.mean 7.132643e+02 NA NA NA NA NA
## CI.mean.0.95 1.644790e+03 NA NA NA NA NA
## var 4.578713e+06 NA NA NA NA NA
## std.dev 2.139793e+03 NA NA NA NA NA
## coef.var 8.933588e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 9.000000e+00 NA 9.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 3.734000e+03 NA 0.3522500 NA
## max NA 1.168000e+04 NA 20.0663300 NA
## range NA 7.946000e+03 NA 19.7140800 NA
## sum NA 5.696300e+04 NA 89.1994500 NA
## median NA 6.540000e+03 NA 8.9204800 NA
## mean NA 6.329222e+03 NA 9.9110500 NA
## SE.mean NA 8.172298e+02 NA 2.1831653 NA
## CI.mean.0.95 NA 1.884535e+03 NA 5.0343882 NA
## var NA 6.010781e+06 NA 42.8958955 NA
## std.dev NA 2.451689e+03 NA 6.5494958 NA
## coef.var NA 3.873603e-01 NA 0.6608276 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 9.00000000 9.000000e+00 NA NA NA
## nbr.null 0.00000000 0.000000e+00 NA NA NA
## nbr.na 0.00000000 0.000000e+00 NA NA NA
## min 8.61170000 -8.480900e+01 NA NA NA
## max 10.11100000 -8.294180e+01 NA NA NA
## range 1.49930000 1.867200e+00 NA NA NA
## sum 82.72080000 -7.528426e+02 NA NA NA
## median 8.98960000 -8.332680e+01 NA NA NA
## mean 9.19120000 -8.364918e+01 NA NA NA
## SE.mean 0.19984316 2.553648e-01 NA NA NA
## CI.mean.0.95 0.46083916 5.888723e-01 NA NA NA
## var 0.35943561 5.869007e-01 NA NA NA
## std.dev 0.59952949 7.660945e-01 NA NA NA
## coef.var 0.06522864 -9.158422e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 1 6.0000000 NA
## nbr.null NA NA NA 1 5.0000000 NA
## nbr.na NA NA NA 8 3.0000000 NA
## min NA NA NA 0 0.0000000 NA
## max NA NA NA 0 1.0000000 NA
## range NA NA NA 0 1.0000000 NA
## sum NA NA NA 0 1.0000000 NA
## median NA NA NA 0 0.0000000 NA
## mean NA NA NA 0 0.1666667 NA
## SE.mean NA NA NA NA 0.1666667 NA
## CI.mean.0.95 NA NA NA NaN 0.4284303 NA
## var NA NA NA NA 0.1666667 NA
## std.dev NA NA NA NA 0.4082483 NA
## coef.var NA NA NA NA 2.4494897 NA
## source_link prop ypos
## nbr.val NA 9.0000000 9.0000000
## nbr.null NA 0.0000000 0.0000000
## nbr.na NA 0.0000000 0.0000000
## min NA 0.3949015 10.0926855
## max NA 22.4960244 99.8025492
## range NA 22.1011228 89.7098637
## sum NA 100.0000000 505.7380343
## median NA 10.0005998 56.1769495
## mean NA 11.1111111 56.1931149
## SE.mean NA 2.4475098 9.7228963
## CI.mean.0.95 NA 5.6439677 22.4210391
## var NA 53.9127377 850.8124161
## std.dev NA 7.3425294 29.1686890
## coef.var NA 0.6608276 0.5190794boxplot(data, horizontal=TRUE, col='green')
Gráfico para Guanacaste (Costa Rica)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_CR <- subset(df, country_name == "Costa Rica")
knitr::kable(head(df_CR)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 249 | 9/9/07 | NA | NA | Costa Rica | CR | Heredia | 21947 | Heredia | 0.26208 | NA | 10.0000 | -84.1167 | (10, -84.116699999999994) | Landslide | Landslide | Medium | Rain | NA | NA | NA | ticotimes.net | http://www.ticotimes.net/dailyarchive/2007_09/0911072.htm |
| 299 | 10/9/07 | NA | NA | Costa Rica | CR | San José | 3072 | San Ignacio | 4.57763 | NA | 9.7789 | -84.1250 | (9.7789000000000001, -84.125) | Landslide | Complex | Medium | Rain | NA | NA | 4 | ticotimes.net | http://www.ticotimes.net/dailyarchive/2007_10/1010071.htm |
| 301 | 10/11/07 | NA | NA | Costa Rica | CR | Alajuela | 7014 | Atenas | 3.08459 | NA | 9.9869 | -84.4070 | (9.9869000000000003, -84.406999999999996) | Landslide | Mudslide | Large | Rain | NA | NA | 14 | Agence France-Presse, afp.google.com | http://afp.google.com/article/ALeqM5hu6a8oyAM1ycq9nU_6Zyj_l7F0AA |
| 302 | 10/11/07 | NA | NA | Costa Rica | CR | San José | 26669 | NA | 9.56251 | NA | 10.0214 | -83.9451 | (10.0214, -83.945099999999996) | Landslide | Landslide | Large | Rain | NA | NA | 10 | International Herald | http://www.iht.com/articles/ap/2007/10/12/america/LA-GEN-Costa-Rica-Mudslide.php |
| 323 | 10/24/07 | NA | NA | Costa Rica | CR | Puntarenas | 6540 | Miramar | 3.82425 | Mine construction | 10.0715 | -84.7575 | (10.0715, -84.757499999999993) | Landslide | Mudslide | Medium | Downpour | NA | NA | NA | Reuters - AlertNet.org | http://www.reuters.com/article/companyNewsAndPR/idUSN2435152820071025 |
| 556 | 5/29/08 | NA | NA | Costa Rica | CR | Guanacaste | 4108 | Bagaces | 17.65521 | NA | 10.4024 | -85.3555 | (10.4024, -85.355500000000006) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Alma | NA | NA | NA | http://www.reliefweb.int/rw/RWB.NSF/db900SID/ASAZ-7FHCHL?OpenDocument |
library(dplyr)
df_CR <- subset(df, state == "Guanacaste")
knitr::kable(head(df_CR))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 556 | 5/29/08 | NA | NA | Costa Rica | CR | Guanacaste | 4108 | Bagaces | 17.65521 | NA | 10.4024 | -85.3555 | (10.4024, -85.355500000000006) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Alma | NA | NA | NA | http://www.reliefweb.int/rw/RWB.NSF/db900SID/ASAZ-7FHCHL?OpenDocument |
| 2683 | 11/4/10 | NA | NA | Costa Rica | CR | Guanacaste | 7301 | Tilarán | 10.21631 | NA | 10.4548 | -84.8751 | (10.454800000000001, -84.875100000000003) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Tomas | NA | 0 | NA | http://fortunatimes.com/2010/11/06/no-passage-to-the-south-and-central-pacific/ |
| 4375 | 5/31/12 | NA | NA | Costa Rica | CR | Guanacaste | 7301 | Tilarán | 12.33807 | NA | 10.5562 | -84.8952 | (10.5562, -84.895200000000003) | Landslide | Landslide | Large | Downpour | NA | NA | NA | NA | http://thecostaricanews.com/landslides-and-wash-outs-continue-to-cause-problems-in-northern-costa-rica/12129 |
| 5571 | 10/3/13 | NA | NA | Costa Rica | CR | Guanacaste | 7301 | Tilarán | 12.21952 | NA | 10.5543 | -84.8946 | (10.5543, -84.894599999999997) | Landslide | Landslide | Medium | Mining digging | NA | NA | NA | www.ticotimes.net | http://www.ticotimes.net/More-news/News-Briefs/TRAVEL-ALERT-UPDATE-Rains-landslides-close-eight-routes-across-Costa-Rica_Friday-October-04-2013 |
| 5591 | 10/8/13 | Morning | NA | Costa Rica | CR | Guanacaste | 7301 | Tilarán | 12.18115 | NA | 10.5546 | -84.8955 | (10.554600000000001, -84.895499999999998) | Landslide | Landslide | Medium | Rain | NA | NA | 2 | insidecostarica.com | http://insidecostarica.com/2013/10/14/bodies-man-son-buried-landslide-nuevo-arenal-located/ |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_CR, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_CR, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_CR, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_CR <- df_CR %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_CR$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_CR, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_CR$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 10.21631 |
| 12.33807 |
| 12.21952 |
| 12.18115 |
| 17.65521 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_CR$distance
names(distance) <- df_CR$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Bagaces 17.65521 17.65521 27.32571 27.32571
## Tilarán 12.33807 29.99328 19.09615 46.42185
## Tilarán 12.21952 42.21280 18.91266 65.33451
## Tilarán 12.18115 54.39395 18.85328 84.18779
## Tilarán 10.21631 64.61026 15.81221 100.00000stem(df_CR$"distance")##
## The decimal point is at the |
##
## 10 | 2
## 12 | 223
## 14 |
## 16 | 7head(df_CR)## # A tibble: 5 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 2683 11/4/10 <NA> <NA> Costa Rica CR Guan~ 7301
## 2 4375 5/31/12 <NA> <NA> Costa Rica CR Guan~ 7301
## 3 5571 10/3/13 <NA> <NA> Costa Rica CR Guan~ 7301
## 4 5591 10/8/13 Morning <NA> Costa Rica CR Guan~ 7301
## 5 556 5/29/08 <NA> <NA> Costa Rica CR Guan~ 4108
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_CR))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2683 | 11/4/10 | NA | NA | Costa Rica | CR | Guanacaste | 7301 | Tilarán | 10.21631 | NA | 10.4548 | -84.8751 | (10.454800000000001, -84.875100000000003) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Tomas | NA | 0 | NA | http://fortunatimes.com/2010/11/06/no-passage-to-the-south-and-central-pacific/ | 15.81221 | 7.906105 |
| 4375 | 5/31/12 | NA | NA | Costa Rica | CR | Guanacaste | 7301 | Tilarán | 12.33807 | NA | 10.5562 | -84.8952 | (10.5562, -84.895200000000003) | Landslide | Landslide | Large | Downpour | NA | NA | NA | NA | http://thecostaricanews.com/landslides-and-wash-outs-continue-to-cause-problems-in-northern-costa-rica/12129 | 19.09615 | 25.360283 |
| 5571 | 10/3/13 | NA | NA | Costa Rica | CR | Guanacaste | 7301 | Tilarán | 12.21952 | NA | 10.5543 | -84.8946 | (10.5543, -84.894599999999997) | Landslide | Landslide | Medium | Mining digging | NA | NA | NA | www.ticotimes.net | http://www.ticotimes.net/More-news/News-Briefs/TRAVEL-ALERT-UPDATE-Rains-landslides-close-eight-routes-across-Costa-Rica_Friday-October-04-2013 | 18.91266 | 44.364688 |
| 5591 | 10/8/13 | Morning | NA | Costa Rica | CR | Guanacaste | 7301 | Tilarán | 12.18115 | NA | 10.5546 | -84.8955 | (10.554600000000001, -84.895499999999998) | Landslide | Landslide | Medium | Rain | NA | NA | 2 | insidecostarica.com | http://insidecostarica.com/2013/10/14/bodies-man-son-buried-landslide-nuevo-arenal-located/ | 18.85328 | 63.247656 |
| 556 | 5/29/08 | NA | NA | Costa Rica | CR | Guanacaste | 4108 | Bagaces | 17.65521 | NA | 10.4024 | -85.3555 | (10.4024, -85.355500000000006) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Alma | NA | NA | NA | http://www.reliefweb.int/rw/RWB.NSF/db900SID/ASAZ-7FHCHL?OpenDocument | 27.32571 | 86.337147 |
stem(df_CR$"distance")##
## The decimal point is at the |
##
## 10 | 2
## 12 | 223
## 14 |
## 16 | 7stem(df_CR$"distance", scale = 2)##
## The decimal point is at the |
##
## 10 | 2
## 11 |
## 12 | 223
## 13 |
## 14 |
## 15 |
## 16 |
## 17 | 7Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 10.21631 | 1 | 20 | 20 | 20 | 20 |
| 12.18115 | 1 | 20 | 20 | 40 | 40 |
| 12.21952 | 1 | 20 | 20 | 60 | 60 |
| 12.33807 | 1 | 20 | 20 | 80 | 80 |
| 17.65521 | 1 | 20 | 20 | 100 | 100 |
| Total | 5 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 6 obs. of 5 variables:
## $ n : num 1 1 1 1 1 5
## $ % : num 20 20 20 20 20 100
## $ val% : num 20 20 20 20 20 100
## $ %cum : num 20 40 60 80 100 100
## $ val%cum: num 20 40 60 80 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 10.21631 | 1 |
| 12.18115 | 1 |
| 12.21952 | 1 |
| 12.33807 | 1 |
| 17.65521 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 10.21631 13.21631 16.21631 19.21631distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (10.2,13.2] | 3 | 0.75 | 3 |
| (13.2,16.2] | 0 | 0.00 | 3 |
| (16.2,19.2] | 1 | 0.25 | 4 |
str(Freq_table)## 'data.frame': 3 obs. of 4 variables:
## $ distance: Factor w/ 3 levels "(10.2,13.2]",..: 1 2 3
## $ Freq : int 3 0 1
## $ Rel_Freq: num 0.75 0 0.25
## $ Cum_Freq: int 3 3 4df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (10.2,13.2] | 3 |
| (13.2,16.2] | 0 |
| (16.2,19.2] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_CR)## Warning in min(x): ningún argumento finito para min; retornando Inf## Warning in max(x): ningun argumento finito para max; retornando -Inf## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 5.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 5.560000e+02 NA NA NA NA NA
## max 5.591000e+03 NA NA NA NA NA
## range 5.035000e+03 NA NA NA NA NA
## sum 1.877600e+04 NA NA NA NA NA
## median 4.375000e+03 NA NA NA NA NA
## mean 3.755200e+03 NA NA NA NA NA
## SE.mean 9.601025e+02 NA NA NA NA NA
## CI.mean.0.95 2.665672e+03 NA NA NA NA NA
## var 4.608984e+06 NA NA NA NA NA
## std.dev 2.146854e+03 NA NA NA NA NA
## coef.var 5.717018e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 5.000000e+00 NA 5.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 4.108000e+03 NA 10.2163100 NA
## max NA 7.301000e+03 NA 17.6552100 NA
## range NA 3.193000e+03 NA 7.4389000 NA
## sum NA 3.331200e+04 NA 64.6102600 NA
## median NA 7.301000e+03 NA 12.2195200 NA
## mean NA 6.662400e+03 NA 12.9220520 NA
## SE.mean NA 6.386000e+02 NA 1.2471437 NA
## CI.mean.0.95 NA 1.773038e+03 NA 3.4626259 NA
## var NA 2.039050e+06 NA 7.7768366 NA
## std.dev NA 1.427953e+03 NA 2.7886980 NA
## coef.var NA 2.143301e-01 NA 0.2158092 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 5.000000000 5.000000e+00 NA NA NA
## nbr.null 0.000000000 0.000000e+00 NA NA NA
## nbr.na 0.000000000 0.000000e+00 NA NA NA
## min 10.402400000 -8.535550e+01 NA NA NA
## max 10.556200000 -8.487510e+01 NA NA NA
## range 0.153800000 4.804000e-01 NA NA NA
## sum 52.522300000 -4.249159e+02 NA NA NA
## median 10.554300000 -8.489520e+01 NA NA NA
## mean 10.504460000 -8.498318e+01 NA NA NA
## SE.mean 0.032060437 9.316065e-02 NA NA NA
## CI.mean.0.95 0.089014042 2.586554e-01 NA NA NA
## var 0.005139358 4.339454e-02 NA NA NA
## std.dev 0.071689316 2.083136e-01 NA NA NA
## coef.var 0.006824655 -2.451233e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 0 2.000000 NA
## nbr.null NA NA NA 0 1.000000 NA
## nbr.na NA NA NA 5 3.000000 NA
## min NA NA NA Inf 0.000000 NA
## max NA NA NA -Inf 2.000000 NA
## range NA NA NA -Inf 2.000000 NA
## sum NA NA NA 0 2.000000 NA
## median NA NA NA NA 1.000000 NA
## mean NA NA NA NaN 1.000000 NA
## SE.mean NA NA NA NA 1.000000 NA
## CI.mean.0.95 NA NA NA NaN 12.706205 NA
## var NA NA NA NA 2.000000 NA
## std.dev NA NA NA NA 1.414214 NA
## coef.var NA NA NA NA 1.414214 NA
## source_link prop ypos
## nbr.val NA 5.0000000 5.000000
## nbr.null NA 0.0000000 0.000000
## nbr.na NA 0.0000000 0.000000
## min NA 15.8122100 7.906105
## max NA 27.3257065 86.337147
## range NA 11.5134965 78.431042
## sum NA 100.0000000 227.215879
## median NA 18.9126619 44.364688
## mean NA 20.0000000 45.443176
## SE.mean NA 1.9302564 13.789187
## CI.mean.0.95 NA 5.3592509 38.284922
## var NA 18.6294484 950.708442
## std.dev NA 4.3161845 30.833560
## coef.var NA 0.2158092 0.678508boxplot(data, horizontal=TRUE, col='green')
Gráfico para Saint Lucia
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_SL <- subset(df, country_name == "Saint Lucia")
knitr::kable(head(df_SL))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 841 | 10/12/08 | NA | NA | Saint Lucia | LC | Vieux-Fort | 4574 | Vieux Fort | 2.61752 | NA | 13.7400 | -60.9460 | (13.74, -60.945999999999998) | Landslide | Landslide | Medium | Downpour | NA | NA | NA | NA | http://www.htsstlucia.com/2008_News/October/HTS_News_October_13th_2008.html |
| 2658 | 10/30/10 | NA | NA | Saint Lucia | LC | Laborie | 1131 | Laborie | 2.74715 | NA | 13.7705 | -60.9690 | (13.7705, -60.969000000000001) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Tomas | NA | 0 | NA | NA |
| 2659 | 10/31/10 | NA | NA | Saint Lucia | LC | Soufrière | 2918 | Soufrière | 1.56516 | NA | 13.8516 | -61.0429 | (13.851599999999999, -61.042900000000003) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Tomas | NA | 2 | NA | http://gocaribbean.about.com/b/2010/11/02/hurricane-triggers-deadly-landslides-on-st-lucia.htm |
| 2660 | 10/31/10 | NA | NA | Saint Lucia | LC | Soufrière | 2918 | Soufrière | 1.24758 | NA | 13.8491 | -61.0656 | (13.8491, -61.065600000000003) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Tomas | NA | 2 | NA | http://gocaribbean.about.com/b/2010/11/02/hurricane-triggers-deadly-landslides-on-st-lucia.htm |
| 2661 | 10/31/10 | NA | NA | Saint Lucia | LC | Dennery | 2870 | Dennery | 6.13309 | NA | 13.9210 | -60.9402 | (13.920999999999999, -60.940199999999997) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Tomas | NA | 0 | NA | http://www.youtube.com/watch?v=TbPh_Rh7hvE&feature=player_embedded |
| 2662 | 10/31/10 | NA | NA | Saint Lucia | LC | Soufrière | 2918 | Soufrière | 2.60663 | NA | 13.8328 | -61.0535 | (13.832800000000001, -61.0535) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Tomas | NA | 0 | NA | http://one-little-house.blogspot.com/2010/11/tomas-update.html |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_SL, aes(fill= state, y=distance, x=country_name)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_SL, aes(fill=state, y=distance, x=country_name)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_SL, aes(x=country_name, y=distance, fill=state)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_SL <- df_SL %>%
arrange(desc(state)) %>%
mutate(prop = distance / sum(df_SL$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_SL, aes(x=country_name, y=prop, fill=state)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_SL$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 2.61752 |
| 1.56516 |
| 1.24758 |
| 2.60663 |
| 0.96933 |
| 3.81469 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_SL$distance
names(distance) <- df_SL$state
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por estados"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Dennery 6.133090 6.133090 28.261590 28.261590
## Praslin 3.814690 9.947780 17.578285 45.839875
## Laborie 2.747150 12.694930 12.659007 58.498881
## Vieux-Fort 2.617520 15.312450 12.061665 70.560546
## Soufrière 2.606630 17.919080 12.011483 82.572030
## Soufrière 1.565160 19.484240 7.212337 89.784366
## Soufrière 1.247580 20.731820 5.748912 95.533278
## Soufrière 0.969330 21.701150 4.466722 100.000000stem(df_SL$"distance")##
## The decimal point is at the |
##
## 0 | 026
## 2 | 6678
## 4 |
## 6 | 1head(df_SL)## # A tibble: 6 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 841 10/12/08 <NA> <NA> Saint Lucia LC Vieux-Fort 4574
## 2 2659 10/31/10 <NA> <NA> Saint Lucia LC Soufrière 2918
## 3 2660 10/31/10 <NA> <NA> Saint Lucia LC Soufrière 2918
## 4 2662 10/31/10 <NA> <NA> Saint Lucia LC Soufrière 2918
## 5 2663 10/31/10 <NA> <NA> Saint Lucia LC Soufrière 2918
## 6 5718 12/24/13 Night <NA> Saint Lucia LC Praslin 1906
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_SL))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 841 | 10/12/08 | NA | NA | Saint Lucia | LC | Vieux-Fort | 4574 | Vieux Fort | 2.61752 | NA | 13.7400 | -60.9460 | (13.74, -60.945999999999998) | Landslide | Landslide | Medium | Downpour | NA | NA | NA | NA | http://www.htsstlucia.com/2008_News/October/HTS_News_October_13th_2008.html | 12.061665 | 6.030832 |
| 2659 | 10/31/10 | NA | NA | Saint Lucia | LC | Soufrière | 2918 | Soufrière | 1.56516 | NA | 13.8516 | -61.0429 | (13.851599999999999, -61.042900000000003) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Tomas | NA | 2 | NA | http://gocaribbean.about.com/b/2010/11/02/hurricane-triggers-deadly-landslides-on-st-lucia.htm | 7.212337 | 15.667833 |
| 2660 | 10/31/10 | NA | NA | Saint Lucia | LC | Soufrière | 2918 | Soufrière | 1.24758 | NA | 13.8491 | -61.0656 | (13.8491, -61.065600000000003) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Tomas | NA | 2 | NA | http://gocaribbean.about.com/b/2010/11/02/hurricane-triggers-deadly-landslides-on-st-lucia.htm | 5.748912 | 22.148458 |
| 2662 | 10/31/10 | NA | NA | Saint Lucia | LC | Soufrière | 2918 | Soufrière | 2.60663 | NA | 13.8328 | -61.0535 | (13.832800000000001, -61.0535) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Tomas | NA | 0 | NA | http://one-little-house.blogspot.com/2010/11/tomas-update.html | 12.011483 | 31.028655 |
| 2663 | 10/31/10 | NA | NA | Saint Lucia | LC | Soufrière | 2918 | Soufrière | 0.96933 | NA | 13.8487 | -61.0613 | (13.848699999999999, -61.061300000000003) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Tomas | NA | 0 | NA | http://one-little-house.blogspot.com/2010/11/tomas-update.html | 4.466722 | 39.267758 |
| 5718 | 12/24/13 | Night | NA | Saint Lucia | LC | Praslin | 1906 | Praslin | 3.81469 | NA | 13.8891 | -60.9268 | (13.889099999999999, -60.9268) | Landslide | Landslide | Large | Downpour | NA | NA | NA | reliefweb.int | NA | 17.578285 | 50.290261 |
stem(df_SL$"distance")##
## The decimal point is at the |
##
## 0 | 026
## 2 | 6678
## 4 |
## 6 | 1stem(df_SL$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 |
## 1 | 026
## 2 | 667
## 3 | 8
## 4 |
## 5 |
## 6 | 1Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.96933 | 1 | 12.5 | 12.5 | 12.5 | 12.5 |
| 1.24758 | 1 | 12.5 | 12.5 | 25.0 | 25.0 |
| 1.56516 | 1 | 12.5 | 12.5 | 37.5 | 37.5 |
| 2.60663 | 1 | 12.5 | 12.5 | 50.0 | 50.0 |
| 2.61752 | 1 | 12.5 | 12.5 | 62.5 | 62.5 |
| 2.74715 | 1 | 12.5 | 12.5 | 75.0 | 75.0 |
| 3.81469 | 1 | 12.5 | 12.5 | 87.5 | 87.5 |
| 6.13309 | 1 | 12.5 | 12.5 | 100.0 | 100.0 |
| Total | 8 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 9 obs. of 5 variables:
## $ n : num 1 1 1 1 1 1 1 1 8
## $ % : num 12.5 12.5 12.5 12.5 12.5 12.5 12.5 12.5 100
## $ val% : num 12.5 12.5 12.5 12.5 12.5 12.5 12.5 12.5 100
## $ %cum : num 12.5 25 37.5 50 62.5 75 87.5 100 100
## $ val%cum: num 12.5 25 37.5 50 62.5 75 87.5 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.96933 | 1 |
| 1.24758 | 1 |
| 1.56516 | 1 |
| 2.60663 | 1 |
| 2.61752 | 1 |
| 2.74715 | 1 |
| 3.81469 | 1 |
| 6.13309 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.96933 2.96933 4.96933 6.96933distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.969,2.97] | 5 | 0.7142857 | 5 |
| (2.97,4.97] | 1 | 0.1428571 | 6 |
| (4.97,6.97] | 1 | 0.1428571 | 7 |
str(Freq_table)## 'data.frame': 3 obs. of 4 variables:
## $ distance: Factor w/ 3 levels "(0.969,2.97]",..: 1 2 3
## $ Freq : int 5 1 1
## $ Rel_Freq: num 0.714 0.143 0.143
## $ Cum_Freq: int 5 6 7df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.969,2.97] | 5 |
| (2.97,4.97] | 1 |
| (4.97,6.97] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_SL)## Warning in min(x): ningún argumento finito para min; retornando Inf## Warning in max(x): ningun argumento finito para max; retornando -Inf## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 8.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 8.410000e+02 NA NA NA NA NA
## max 5.718000e+03 NA NA NA NA NA
## range 4.877000e+03 NA NA NA NA NA
## sum 2.252200e+04 NA NA NA NA NA
## median 2.660500e+03 NA NA NA NA NA
## mean 2.815250e+03 NA NA NA NA NA
## SE.mean 4.718377e+02 NA NA NA NA NA
## CI.mean.0.95 1.115719e+03 NA NA NA NA NA
## var 1.781046e+06 NA NA NA NA NA
## std.dev 1.334558e+03 NA NA NA NA NA
## coef.var 4.740462e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 8.000000e+00 NA 8.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 1.131000e+03 NA 0.9693300 NA
## max NA 4.574000e+03 NA 6.1330900 NA
## range NA 3.443000e+03 NA 5.1637600 NA
## sum NA 2.215300e+04 NA 21.7011500 NA
## median NA 2.918000e+03 NA 2.6120750 NA
## mean NA 2.769125e+03 NA 2.7126437 NA
## SE.mean NA 3.480774e+02 NA 0.5891536 NA
## CI.mean.0.95 NA 8.230724e+02 NA 1.3931269 NA
## var NA 9.692633e+05 NA 2.7768157 NA
## std.dev NA 9.845117e+02 NA 1.6663780 NA
## coef.var NA 3.555317e-01 NA 0.6143004 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 8.000000e+00 8.000000e+00 NA NA NA
## nbr.null 0.000000e+00 0.000000e+00 NA NA NA
## nbr.na 0.000000e+00 0.000000e+00 NA NA NA
## min 1.374000e+01 -6.106560e+01 NA NA NA
## max 1.392100e+01 -6.092680e+01 NA NA NA
## range 1.810000e-01 1.388000e-01 NA NA NA
## sum 1.107028e+02 -4.880053e+02 NA NA NA
## median 1.384890e+01 -6.100595e+01 NA NA NA
## mean 1.383785e+01 -6.100066e+01 NA NA NA
## SE.mean 2.074935e-02 2.136899e-02 NA NA NA
## CI.mean.0.95 4.906441e-02 5.052962e-02 NA NA NA
## var 3.444283e-03 3.653068e-03 NA NA NA
## std.dev 5.868801e-02 6.044062e-02 NA NA NA
## coef.var 4.241122e-03 -9.908191e-04 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 0 6.0000000 NA
## nbr.null NA NA NA 0 4.0000000 NA
## nbr.na NA NA NA 8 2.0000000 NA
## min NA NA NA Inf 0.0000000 NA
## max NA NA NA -Inf 2.0000000 NA
## range NA NA NA -Inf 2.0000000 NA
## sum NA NA NA 0 4.0000000 NA
## median NA NA NA NA 0.0000000 NA
## mean NA NA NA NaN 0.6666667 NA
## SE.mean NA NA NA NA 0.4216370 NA
## CI.mean.0.95 NA NA NA NaN 1.0838525 NA
## var NA NA NA NA 1.0666667 NA
## std.dev NA NA NA NA 1.0327956 NA
## coef.var NA NA NA NA 1.5491933 NA
## source_link prop ypos
## nbr.val NA 8.0000000 8.0000000
## nbr.null NA 0.0000000 0.0000000
## nbr.na NA 0.0000000 0.0000000
## min NA 4.4667218 6.0308325
## max NA 28.2615898 85.8692051
## range NA 23.7948680 79.8383726
## sum NA 100.0000000 315.7119093
## median NA 12.0365741 35.1482064
## mean NA 12.5000000 39.4639887
## SE.mean NA 2.7148497 9.4480204
## CI.mean.0.95 NA 6.4195994 22.3410181
## var NA 58.9632706 714.1207126
## std.dev NA 7.6787545 26.7230371
## coef.var NA 0.6143004 0.6771499boxplot(data, horizontal=TRUE, col='green')
Gráfico para Grenada
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_GN <- subset(df, country_name == "Grenada")
knitr::kable(head(df_GN))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 3355 | 4/12/11 | 3:00:00 | NA | Grenada | GD | Saint Mark | 2256 | Victoria | 1.19981 | NA | 12.1979 | -61.6990 | (12.197900000000001, -61.698999999999998) | Landslide | Landslide | Small | Downpour | NA | NA | 0 | NA | http://stormcarib.com/reports/current/report.php?id=1302618053_40629 |
| 3356 | 4/12/11 | Morning | NA | Grenada | GD | Saint John | 3378 | Gouyave | 5.65355 | NA | 12.1353 | -61.6871 | (12.135300000000001, -61.687100000000001) | Landslide | Landslide | Small | Downpour | NA | NA | 0 | NA | http://stormcarib.com/reports/current/report.php?id=1302618053_40629 |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_GN, aes(fill= state, y=distance, x=country_name)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_GN, aes(fill=state, y=distance, x=country_name)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_GN, aes(x=country_name, y=distance, fill=state)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_GN <- df_GN %>%
arrange(desc(state)) %>%
mutate(prop = distance / sum(df_GN$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_GN, aes(x=country_name, y=prop, fill=state)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_GN$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 1.19981 |
| 5.65355 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_GN$distance
names(distance) <- df_GN$state
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por estados"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Saint John 5.65355 5.65355 82.49311 82.49311
## Saint Mark 1.19981 6.85336 17.50689 100.00000stem(df_GN$"distance")##
## The decimal point is at the |
##
## 1 | 2
## 2 |
## 3 |
## 4 |
## 5 | 7head(df_GN)## # A tibble: 2 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 3355 4/12/11 3:00:00 <NA> Grenada GD Sain~ 2256
## 2 3356 4/12/11 Morning <NA> Grenada GD Sain~ 3378
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_GN))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 3355 | 4/12/11 | 3:00:00 | NA | Grenada | GD | Saint Mark | 2256 | Victoria | 1.19981 | NA | 12.1979 | -61.6990 | (12.197900000000001, -61.698999999999998) | Landslide | Landslide | Small | Downpour | NA | NA | 0 | NA | http://stormcarib.com/reports/current/report.php?id=1302618053_40629 | 17.50689 | 8.753444 |
| 3356 | 4/12/11 | Morning | NA | Grenada | GD | Saint John | 3378 | Gouyave | 5.65355 | NA | 12.1353 | -61.6871 | (12.135300000000001, -61.687100000000001) | Landslide | Landslide | Small | Downpour | NA | NA | 0 | NA | http://stormcarib.com/reports/current/report.php?id=1302618053_40629 | 82.49311 | 58.753444 |
stem(df_GN$"distance")##
## The decimal point is at the |
##
## 1 | 2
## 2 |
## 3 |
## 4 |
## 5 | 7stem(df_GN$"distance", scale = 2)##
## The decimal point is at the |
##
## 1 | 2
## 1 |
## 2 |
## 2 |
## 3 |
## 3 |
## 4 |
## 4 |
## 5 |
## 5 | 7Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 1.19981 | 1 | 50 | 50 | 50 | 50 |
| 5.65355 | 1 | 50 | 50 | 100 | 100 |
| Total | 2 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 3 obs. of 5 variables:
## $ n : num 1 1 2
## $ % : num 50 50 100
## $ val% : num 50 50 100
## $ %cum : num 50 100 100
## $ val%cum: num 50 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 1.19981 | 1 |
| 5.65355 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 1.19981 4.19981 7.19981distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (1.2,4.2] | 0 | 0 | 0 |
| (4.2,7.2] | 1 | 1 | 1 |
str(Freq_table)## 'data.frame': 2 obs. of 4 variables:
## $ distance: Factor w/ 2 levels "(1.2,4.2]","(4.2,7.2]": 1 2
## $ Freq : int 0 1
## $ Rel_Freq: num 0 1
## $ Cum_Freq: int 0 1df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (1.2,4.2] | 0 |
| (4.2,7.2] | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_GN)## Warning in min(x): ningún argumento finito para min; retornando Inf## Warning in max(x): ningun argumento finito para max; retornando -Inf## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 2.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 3.355000e+03 NA NA NA NA NA
## max 3.356000e+03 NA NA NA NA NA
## range 1.000000e+00 NA NA NA NA NA
## sum 6.711000e+03 NA NA NA NA NA
## median 3.355500e+03 NA NA NA NA NA
## mean 3.355500e+03 NA NA NA NA NA
## SE.mean 5.000000e-01 NA NA NA NA NA
## CI.mean.0.95 6.353102e+00 NA NA NA NA NA
## var 5.000000e-01 NA NA NA NA NA
## std.dev 7.071068e-01 NA NA NA NA NA
## coef.var 2.107307e-04 NA NA NA NA NA
## state population city distance location_description latitude
## nbr.val NA 2.000000e+00 NA 2.000000 NA 2.00000000
## nbr.null NA 0.000000e+00 NA 0.000000 NA 0.00000000
## nbr.na NA 0.000000e+00 NA 0.000000 NA 0.00000000
## min NA 2.256000e+03 NA 1.199810 NA 12.13530000
## max NA 3.378000e+03 NA 5.653550 NA 12.19790000
## range NA 1.122000e+03 NA 4.453740 NA 0.06260000
## sum NA 5.634000e+03 NA 6.853360 NA 24.33320000
## median NA 2.817000e+03 NA 3.426680 NA 12.16660000
## mean NA 2.817000e+03 NA 3.426680 NA 12.16660000
## SE.mean NA 5.610000e+02 NA 2.226870 NA 0.03130000
## CI.mean.0.95 NA 7.128181e+03 NA 28.295066 NA 0.39770421
## var NA 6.294420e+05 NA 9.917900 NA 0.00195938
## std.dev NA 7.933738e+02 NA 3.149270 NA 0.04426488
## coef.var NA 2.816378e-01 NA 0.919044 NA 0.00363823
## longitude geolocation hazard_type landslide_type
## nbr.val 2.000000e+00 NA NA NA
## nbr.null 0.000000e+00 NA NA NA
## nbr.na 0.000000e+00 NA NA NA
## min -6.169900e+01 NA NA NA
## max -6.168710e+01 NA NA NA
## range 1.190000e-02 NA NA NA
## sum -1.233861e+02 NA NA NA
## median -6.169305e+01 NA NA NA
## mean -6.169305e+01 NA NA NA
## SE.mean 5.950000e-03 NA NA NA
## CI.mean.0.95 7.560192e-02 NA NA NA
## var 7.080500e-05 NA NA NA
## std.dev 8.414571e-03 NA NA NA
## coef.var -1.363941e-04 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 0 2 NA
## nbr.null NA NA NA 0 2 NA
## nbr.na NA NA NA 2 0 NA
## min NA NA NA Inf 0 NA
## max NA NA NA -Inf 0 NA
## range NA NA NA -Inf 0 NA
## sum NA NA NA 0 0 NA
## median NA NA NA NA 0 NA
## mean NA NA NA NaN 0 NA
## SE.mean NA NA NA NA 0 NA
## CI.mean.0.95 NA NA NA NaN 0 NA
## var NA NA NA NA 0 NA
## std.dev NA NA NA NA 0 NA
## coef.var NA NA NA NA NaN NA
## source_link prop ypos
## nbr.val NA 2.000000 2.000000
## nbr.null NA 0.000000 0.000000
## nbr.na NA 0.000000 0.000000
## min NA 17.506887 8.753444
## max NA 82.493113 58.753444
## range NA 64.986226 50.000000
## sum NA 100.000000 67.506887
## median NA 50.000000 33.753444
## mean NA 50.000000 33.753444
## SE.mean NA 32.493113 25.000000
## CI.mean.0.95 NA 412.864145 317.655118
## var NA 2111.604768 1250.000000
## std.dev NA 45.952201 35.355339
## coef.var NA 0.919044 1.047459boxplot(data, horizontal=TRUE, col='green')
Gráfico para Cuba
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_CB <- subset(df, country_name == "Cuba")
knitr::kable(head(df_CB))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2611 | 10/18/10 | NA | NA | Cuba | CU | Provincia de La Habana | 132351 | Cerro | 0.89865 | NA | 23.1098 | -82.3691 | (23.1098, -82.369100000000003) | Landslide | Complex | Medium | Tropical cyclone | Tropical Storm Paula | NA | 0 | NA | http://www.reliefweb.int/rw/RWFiles2010.nsf/FilesByRWDocUnidFilename/VDUX-8ADM53-full_report.pdf/$File/full_report.pdf |
| 2706 | 11/7/10 | NA | NA | Cuba | CU | Guantanamo | 48362 | Baracoa | 10.45795 | NA | 20.2526 | -74.4867 | (20.252600000000001, -74.486699999999999) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Tomas | NA | 0 | NA | http://www.solvision.co.cu/english/index.php?option=com_content&view=article&id=1631:viaduct-la-farola-in-baracoa-traffic-restored&catid=34:portada&Itemid=171 |
| 5067 | 7/9/13 | NA | NA | Cuba | CU | Artemisa Province | 7205 | Soroa | 11.87914 | NA | 22.7943 | -83.1322 | (22.7943, -83.132199999999997) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | www.havanatimes.org | http://www.havanatimes.org/?p=96131 |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_CB, aes(fill= state, y=distance, x=country_name)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_CB, aes(fill=state, y=distance, x=country_name)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_CB, aes(x=country_name, y=distance, fill=state)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_CB <- df_CB %>%
arrange(desc(state)) %>%
mutate(prop = distance / sum(df_CB$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_CB, aes(x=country_name, y=prop, fill=state)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_CB$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 0.89865 |
| 10.45795 |
| 11.87914 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_CB$distance
names(distance) <- df_CB$state
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por estados"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Artemisa Province 11.879140 11.879140 51.124432 51.124432
## Guantanamo 10.457950 22.337090 45.008035 96.132467
## Provincia de La Habana 0.898650 23.235740 3.867533 100.000000stem(df_CB$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 1
## 0 |
## 1 | 02head(df_CB)## # A tibble: 3 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 2611 10/18/10 <NA> <NA> Cuba CU Prov~ 132351
## 2 2706 11/7/10 <NA> <NA> Cuba CU Guan~ 48362
## 3 5067 7/9/13 <NA> <NA> Cuba CU Arte~ 7205
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_CB))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2611 | 10/18/10 | NA | NA | Cuba | CU | Provincia de La Habana | 132351 | Cerro | 0.89865 | NA | 23.1098 | -82.3691 | (23.1098, -82.369100000000003) | Landslide | Complex | Medium | Tropical cyclone | Tropical Storm Paula | NA | 0 | NA | http://www.reliefweb.int/rw/RWFiles2010.nsf/FilesByRWDocUnidFilename/VDUX-8ADM53-full_report.pdf/$File/full_report.pdf | 3.867533 | 1.933767 |
| 2706 | 11/7/10 | NA | NA | Cuba | CU | Guantanamo | 48362 | Baracoa | 10.45795 | NA | 20.2526 | -74.4867 | (20.252600000000001, -74.486699999999999) | Landslide | Landslide | Medium | Tropical cyclone | Hurricane Tomas | NA | 0 | NA | http://www.solvision.co.cu/english/index.php?option=com_content&view=article&id=1631:viaduct-la-farola-in-baracoa-traffic-restored&catid=34:portada&Itemid=171 | 45.008035 | 26.371551 |
| 5067 | 7/9/13 | NA | NA | Cuba | CU | Artemisa Province | 7205 | Soroa | 11.87914 | NA | 22.7943 | -83.1322 | (22.7943, -83.132199999999997) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | www.havanatimes.org | http://www.havanatimes.org/?p=96131 | 51.124432 | 74.437784 |
stem(df_CB$"distance")##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 1
## 0 |
## 1 | 02stem(df_CB$"distance", scale = 2)##
## The decimal point is at the |
##
## 0 | 9
## 2 |
## 4 |
## 6 |
## 8 |
## 10 | 59Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 0.89865 | 1 | 33.3 | 33.3 | 33.3 | 33.3 |
| 10.45795 | 1 | 33.3 | 33.3 | 66.7 | 66.7 |
| 11.87914 | 1 | 33.3 | 33.3 | 100.0 | 100.0 |
| Total | 3 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 4 obs. of 5 variables:
## $ n : num 1 1 1 3
## $ % : num 33.3 33.3 33.3 100
## $ val% : num 33.3 33.3 33.3 100
## $ %cum : num 33.3 66.7 100 100
## $ val%cum: num 33.3 66.7 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 0.89865 | 1 |
| 10.45795 | 1 |
| 11.87914 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 0.89865 4.89865 8.89865 12.89865distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (0.899,4.9] | 0 | 0 | 0 |
| (4.9,8.9] | 0 | 0 | 0 |
| (8.9,12.9] | 2 | 1 | 2 |
str(Freq_table)## 'data.frame': 3 obs. of 4 variables:
## $ distance: Factor w/ 3 levels "(0.899,4.9]",..: 1 2 3
## $ Freq : int 0 0 2
## $ Rel_Freq: num 0 0 1
## $ Cum_Freq: int 0 0 2df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (0.899,4.9] | 0 |
| (4.9,8.9] | 0 |
| (8.9,12.9] | 2 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_CB)## Warning in min(x): ningún argumento finito para min; retornando Inf## Warning in max(x): ningun argumento finito para max; retornando -Inf## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 3.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 2.611000e+03 NA NA NA NA NA
## max 5.067000e+03 NA NA NA NA NA
## range 2.456000e+03 NA NA NA NA NA
## sum 1.038400e+04 NA NA NA NA NA
## median 2.706000e+03 NA NA NA NA NA
## mean 3.461333e+03 NA NA NA NA NA
## SE.mean 8.033016e+02 NA NA NA NA NA
## CI.mean.0.95 3.456328e+03 NA NA NA NA NA
## var 1.935880e+06 NA NA NA NA NA
## std.dev 1.391359e+03 NA NA NA NA NA
## coef.var 4.019720e-01 NA NA NA NA NA
## state population city distance location_description latitude
## nbr.val NA 3.000000e+00 NA 3.0000000 NA 3.0000000
## nbr.null NA 0.000000e+00 NA 0.0000000 NA 0.0000000
## nbr.na NA 0.000000e+00 NA 0.0000000 NA 0.0000000
## min NA 7.205000e+03 NA 0.8986500 NA 20.2526000
## max NA 1.323510e+05 NA 11.8791400 NA 23.1098000
## range NA 1.251460e+05 NA 10.9804900 NA 2.8572000
## sum NA 1.879180e+05 NA 23.2357400 NA 66.1567000
## median NA 4.836200e+04 NA 10.4579500 NA 22.7943000
## mean NA 6.263933e+04 NA 7.7452467 NA 22.0522333
## SE.mean NA 3.682509e+04 NA 3.4477944 NA 0.9044142
## CI.mean.0.95 NA 1.584456e+05 NA 14.8346622 NA 3.8913802
## var NA 4.068262e+09 NA 35.6618597 NA 2.4538952
## std.dev NA 6.378293e+04 NA 5.9717552 NA 1.5664914
## coef.var NA 1.018257e+00 NA 0.7710219 NA 0.0710355
## longitude geolocation hazard_type landslide_type
## nbr.val 3.00000000 NA NA NA
## nbr.null 0.00000000 NA NA NA
## nbr.na 0.00000000 NA NA NA
## min -83.13220000 NA NA NA
## max -74.48670000 NA NA NA
## range 8.64550000 NA NA NA
## sum -239.98800000 NA NA NA
## median -82.36910000 NA NA NA
## mean -79.99600000 NA NA NA
## SE.mean 2.76344412 NA NA NA
## CI.mean.0.95 11.89014040 NA NA NA
## var 22.90987027 NA NA NA
## std.dev 4.78642563 NA NA NA
## coef.var -0.05983331 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 0 3 NA
## nbr.null NA NA NA 0 3 NA
## nbr.na NA NA NA 3 0 NA
## min NA NA NA Inf 0 NA
## max NA NA NA -Inf 0 NA
## range NA NA NA -Inf 0 NA
## sum NA NA NA 0 0 NA
## median NA NA NA NA 0 NA
## mean NA NA NA NaN 0 NA
## SE.mean NA NA NA NA 0 NA
## CI.mean.0.95 NA NA NA NaN 0 NA
## var NA NA NA NA 0 NA
## std.dev NA NA NA NA 0 NA
## coef.var NA NA NA NA NaN NA
## source_link prop ypos
## nbr.val NA 3.0000000 3.000000
## nbr.null NA 0.0000000 0.000000
## nbr.na NA 0.0000000 0.000000
## min NA 3.8675334 1.933767
## max NA 51.1244316 74.437784
## range NA 47.2568982 72.504018
## sum NA 100.0000000 102.743102
## median NA 45.0080350 26.371551
## mean NA 33.3333333 34.247701
## SE.mean NA 14.8383243 21.297366
## CI.mean.0.95 NA 63.8441565 91.635171
## var NA 660.5276020 1360.733440
## std.dev NA 25.7007315 36.888121
## coef.var NA 0.7710219 1.077098boxplot(data, horizontal=TRUE, col='green')
Gráfico para Puerto Rico
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_PR <- subset(df, country_name == "Puerto Rico")
knitr::kable(head(df_PR))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 393 | 12/12/07 | NA | NA | Puerto Rico | PR | San Juan | 418140 | San Juan | 6.91777 | NA | 18.4320 | -66.0510 | (18.431999999999999, -66.051000000000002) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Olga | NA | NA | AP.google.com | http://ap.google.com/article/ALeqM5gVWjsPEiqe1tEu2mhBIRaxxGi8owD8TFVR600 |
| 2550 | 10/6/10 | NA | NA | Puerto Rico | PR | Orocovis | 944 | Orocovis | 6.85760 | NA | 18.1652 | -66.3969 | (18.165199999999999, -66.396900000000002) | Landslide | Complex | Medium | Tropical cyclone | Tropical Storm Otto | NA | 0 | NA | http://www.whitehouse.gov/the-press-office/2010/10/26/president-obama-signs-puerto-rico-disaster-declaration |
| 6708 | 5/18/14 | 16:30 | NA | Puerto Rico | PR | Vega Alta | 12036 | Vega Alta | 3.49090 | Mine construction | 18.3806 | -66.3319 | (18.380600000000001, -66.331900000000005) | Landslide | Other | Small | Rain | NA | 0 | 0 | Telemundo | http://www.telemundopr.com/telenoticias/puerto-rico/Deslizamiento-deja-a-familias-incomunicadas-en-Vega-Alta-258522361.html |
| 6709 | 9/24/14 | NA | NA | Puerto Rico | PR | Aguada | 4040 | Aguada | 1.40257 | Unknown | 18.3711 | -67.1782 | (18.371099999999998, -67.178200000000004) | Landslide | Landslide | Medium | Downpour | NA | 0 | 0 | Telemundo | http://www.telemundopr.com/telenoticias/puerto-rico/Viviendas-inhabitables-luego-de-deslizamiento-de-tierras-en-Aguada-277123031.html |
| 6710 | 8/24/14 | 3:00 | NA | Puerto Rico | PR | Ponce | 5080 | Adjuntas | 5.78872 | Unknown | 18.1283 | -66.6810 | (18.128299999999999, -66.680999999999997) | Landslide | Landslide | Small | Downpour | NA | 0 | 0 | Perla del Sur | http://www.periodicolaperla.com/index.php?option=com_content&view=article&id=6371:surgen-nuevos-deslizamientos-en-ponce&catid=135:actualidad-del-sur&Itemid=423 |
| 6711 | 8/24/14 | NA | NA | Puerto Rico | PR | Ponce | 5080 | Adjuntas | 6.89036 | Unknown | 18.1254 | -66.6700 | (18.125399999999999, -66.67) | Landslide | Landslide | Medium | Downpour | NA | 0 | 0 | Perla del Sur | http://www.periodicolaperla.com/index.php?option=com_content&view=article&id=6371:surgen-nuevos-deslizamientos-en-ponce&catid=135:actualidad-del-sur&Itemid=423 |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_PR, aes(fill= state, y=distance, x=country_name)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_PR, aes(fill=state, y=distance, x=country_name)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_PR, aes(x=country_name, y=distance, fill=state)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_PR <- df_PR %>%
arrange(desc(state)) %>%
mutate(prop = distance / sum(df_PR$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_PR, aes(x=country_name, y=prop, fill=state)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_PR$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 3.65535 |
| 3.49090 |
| 6.91777 |
| 5.78872 |
| 6.89036 |
| 6.85760 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_PR$distance
names(distance) <- df_PR$state
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por estados"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## San Juan 6.917770 6.917770 19.763211 19.763211
## Ponce 6.890360 13.808130 19.684904 39.448114
## Orocovis 6.857600 20.665730 19.591312 59.039427
## Ponce 5.788720 26.454450 16.537655 75.577082
## Villalba 3.655350 30.109800 10.442881 86.019963
## Vega Alta 3.490900 33.600700 9.973068 95.993032
## Aguada 1.402570 35.003270 4.006968 100.000000stem(df_PR$"distance")##
## The decimal point is at the |
##
## 0 | 4
## 2 | 57
## 4 | 8
## 6 | 999head(df_PR)## # A tibble: 6 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 6712 11/7/14 Afternoon <NA> Puerto Rico PR Vill~ 4555
## 2 6708 5/18/14 16:30 <NA> Puerto Rico PR Vega~ 12036
## 3 393 12/12/07 <NA> <NA> Puerto Rico PR San ~ 418140
## 4 6710 8/24/14 3:00 <NA> Puerto Rico PR Ponce 5080
## 5 6711 8/24/14 <NA> <NA> Puerto Rico PR Ponce 5080
## 6 2550 10/6/10 <NA> <NA> Puerto Rico PR Oroc~ 944
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_PR))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 6712 | 11/7/14 | Afternoon | NA | Puerto Rico | PR | Villalba | 4555 | Villalba | 3.65535 | Unknown | 18.1578 | -66.4790 | (18.157800000000002, -66.478999999999999) | Landslide | Landslide | Medium | Unknown | NA | 0 | 0 | Villalba Online | http://www.18norte66oeste.com/index.php/ley-y-orden/955-reportan-deslizamiento-de-tierra-en-barrio-mogote | 10.442882 | 5.221441 |
| 6708 | 5/18/14 | 16:30 | NA | Puerto Rico | PR | Vega Alta | 12036 | Vega Alta | 3.49090 | Mine construction | 18.3806 | -66.3319 | (18.380600000000001, -66.331900000000005) | Landslide | Other | Small | Rain | NA | 0 | 0 | Telemundo | http://www.telemundopr.com/telenoticias/puerto-rico/Deslizamiento-deja-a-familias-incomunicadas-en-Vega-Alta-258522361.html | 9.973068 | 15.429416 |
| 393 | 12/12/07 | NA | NA | Puerto Rico | PR | San Juan | 418140 | San Juan | 6.91777 | NA | 18.4320 | -66.0510 | (18.431999999999999, -66.051000000000002) | Landslide | Landslide | Medium | Tropical cyclone | Tropical Storm Olga | NA | NA | AP.google.com | http://ap.google.com/article/ALeqM5gVWjsPEiqe1tEu2mhBIRaxxGi8owD8TFVR600 | 19.763211 | 30.297555 |
| 6710 | 8/24/14 | 3:00 | NA | Puerto Rico | PR | Ponce | 5080 | Adjuntas | 5.78872 | Unknown | 18.1283 | -66.6810 | (18.128299999999999, -66.680999999999997) | Landslide | Landslide | Small | Downpour | NA | 0 | 0 | Perla del Sur | http://www.periodicolaperla.com/index.php?option=com_content&view=article&id=6371:surgen-nuevos-deslizamientos-en-ponce&catid=135:actualidad-del-sur&Itemid=423 | 16.537655 | 48.447988 |
| 6711 | 8/24/14 | NA | NA | Puerto Rico | PR | Ponce | 5080 | Adjuntas | 6.89036 | Unknown | 18.1254 | -66.6700 | (18.125399999999999, -66.67) | Landslide | Landslide | Medium | Downpour | NA | 0 | 0 | Perla del Sur | http://www.periodicolaperla.com/index.php?option=com_content&view=article&id=6371:surgen-nuevos-deslizamientos-en-ponce&catid=135:actualidad-del-sur&Itemid=423 | 19.684904 | 66.559267 |
| 2550 | 10/6/10 | NA | NA | Puerto Rico | PR | Orocovis | 944 | Orocovis | 6.85760 | NA | 18.1652 | -66.3969 | (18.165199999999999, -66.396900000000002) | Landslide | Complex | Medium | Tropical cyclone | Tropical Storm Otto | NA | 0 | NA | http://www.whitehouse.gov/the-press-office/2010/10/26/president-obama-signs-puerto-rico-disaster-declaration | 19.591313 | 86.197375 |
stem(df_PR$"distance")##
## The decimal point is at the |
##
## 0 | 4
## 2 | 57
## 4 | 8
## 6 | 999stem(df_PR$"distance", scale = 2)##
## The decimal point is at the |
##
## 1 | 4
## 2 |
## 3 | 57
## 4 |
## 5 | 8
## 6 | 999Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 1.40257 | 1 | 14.3 | 14.3 | 14.3 | 14.3 |
| 3.4909 | 1 | 14.3 | 14.3 | 28.6 | 28.6 |
| 3.65535 | 1 | 14.3 | 14.3 | 42.9 | 42.9 |
| 5.78872 | 1 | 14.3 | 14.3 | 57.1 | 57.1 |
| 6.8576 | 1 | 14.3 | 14.3 | 71.4 | 71.4 |
| 6.89036 | 1 | 14.3 | 14.3 | 85.7 | 85.7 |
| 6.91777 | 1 | 14.3 | 14.3 | 100.0 | 100.0 |
| Total | 7 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 8 obs. of 5 variables:
## $ n : num 1 1 1 1 1 1 1 7
## $ % : num 14.3 14.3 14.3 14.3 14.3 14.3 14.3 100
## $ val% : num 14.3 14.3 14.3 14.3 14.3 14.3 14.3 100
## $ %cum : num 14.3 28.6 42.9 57.1 71.4 85.7 100 100
## $ val%cum: num 14.3 28.6 42.9 57.1 71.4 85.7 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 1.40257 | 1 |
| 3.4909 | 1 |
| 3.65535 | 1 |
| 5.78872 | 1 |
| 6.8576 | 1 |
| 6.89036 | 1 |
| 6.91777 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 1.40257 3.40257 5.40257 7.40257distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (1.4,3.4] | 0 | 0.0000000 | 0 |
| (3.4,5.4] | 2 | 0.3333333 | 2 |
| (5.4,7.4] | 4 | 0.6666667 | 6 |
str(Freq_table)## 'data.frame': 3 obs. of 4 variables:
## $ distance: Factor w/ 3 levels "(1.4,3.4]","(3.4,5.4]",..: 1 2 3
## $ Freq : int 0 2 4
## $ Rel_Freq: num 0 0.333 0.667
## $ Cum_Freq: int 0 2 6df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (1.4,3.4] | 0 |
| (3.4,5.4] | 2 |
| (5.4,7.4] | 4 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_PR)## id date time continent_code country_name country_code
## nbr.val 7.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 3.930000e+02 NA NA NA NA NA
## max 6.712000e+03 NA NA NA NA NA
## range 6.319000e+03 NA NA NA NA NA
## sum 3.649300e+04 NA NA NA NA NA
## median 6.709000e+03 NA NA NA NA NA
## mean 5.213286e+03 NA NA NA NA NA
## SE.mean 9.943773e+02 NA NA NA NA NA
## CI.mean.0.95 2.433154e+03 NA NA NA NA NA
## var 6.921504e+06 NA NA NA NA NA
## std.dev 2.630875e+03 NA NA NA NA NA
## coef.var 5.046482e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 7.000000e+00 NA 7.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 9.440000e+02 NA 1.4025700 NA
## max NA 4.181400e+05 NA 6.9177700 NA
## range NA 4.171960e+05 NA 5.5152000 NA
## sum NA 4.498750e+05 NA 35.0032700 NA
## median NA 5.080000e+03 NA 5.7887200 NA
## mean NA 6.426786e+04 NA 5.0004671 NA
## SE.mean NA 5.899213e+04 NA 0.8215987 NA
## CI.mean.0.95 NA 1.443485e+05 NA 2.0103796 NA
## var NA 2.436050e+10 NA 4.7251712 NA
## std.dev NA 1.560785e+05 NA 2.1737459 NA
## coef.var NA 2.428562e+00 NA 0.4347086 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 7.000000e+00 7.000000e+00 NA NA NA
## nbr.null 0.000000e+00 0.000000e+00 NA NA NA
## nbr.na 0.000000e+00 0.000000e+00 NA NA NA
## min 1.812540e+01 -6.717820e+01 NA NA NA
## max 1.843200e+01 -6.605100e+01 NA NA NA
## range 3.066000e-01 1.127200e+00 NA NA NA
## sum 1.277604e+02 -4.657880e+02 NA NA NA
## median 1.816520e+01 -6.647900e+01 NA NA NA
## mean 1.825149e+01 -6.654114e+01 NA NA NA
## SE.mean 5.137584e-02 1.336926e-01 NA NA NA
## CI.mean.0.95 1.257122e-01 3.271341e-01 NA NA NA
## var 1.847634e-02 1.251161e-01 NA NA NA
## std.dev 1.359277e-01 3.537175e-01 NA NA NA
## coef.var 7.447487e-03 -5.315771e-03 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 5 6 NA
## nbr.null NA NA NA 5 6 NA
## nbr.na NA NA NA 2 1 NA
## min NA NA NA 0 0 NA
## max NA NA NA 0 0 NA
## range NA NA NA 0 0 NA
## sum NA NA NA 0 0 NA
## median NA NA NA 0 0 NA
## mean NA NA NA 0 0 NA
## SE.mean NA NA NA 0 0 NA
## CI.mean.0.95 NA NA NA 0 0 NA
## var NA NA NA 0 0 NA
## std.dev NA NA NA 0 0 NA
## coef.var NA NA NA NaN NaN NA
## source_link prop ypos
## nbr.val NA 7.0000000 7.0000000
## nbr.null NA 0.0000000 0.0000000
## nbr.na NA 0.0000000 0.0000000
## min NA 4.0069685 5.2214407
## max NA 19.7632107 97.9965158
## range NA 15.7562422 92.7750750
## sum NA 100.0000000 350.1495575
## median NA 16.5376549 48.4479879
## mean NA 14.2857143 50.0213654
## SE.mean NA 2.3472056 13.3443062
## CI.mean.0.95 NA 5.7434052 32.6523411
## var NA 38.5656195 1246.4935649
## std.dev NA 6.2101223 35.3057158
## coef.var NA 0.4347086 0.7058127boxplot(data, horizontal=TRUE, col='green')
Gráfico para Dominica
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_DO <- subset(df, country_name == "Dominica")
knitr::kable(head(df_DO))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 186 | 8/17/07 | NA | NA | Dominica | DM | Saint Paul | 702 | Pont Cassé | 3.39516 | NA | 15.3379 | -61.3610 | (15.337899999999999, -61.360999999999997) | Landslide | Mudslide | Small | Tropical cyclone | Hurricane Dean | NA | 2 | Tribune India | http://www.tribuneindia.com/2007/20070817/himachal.htm |
| 250 | 9/9/07 | NA | NA | Dominica | DM | Saint George | 16571 | Roseau | 2.59849 | NA | 15.3055 | -61.3642 | (15.3055, -61.364199999999997) | Landslide | Landslide | Medium | Rain | Tropical Wave | NA | NA | RadioJamaica | http://www.radiojamaica.com/content/view/1156/88/ |
| 1552 | 3/11/10 | NA | NA | Dominica | DM | Saint Paul | 702 | Pont Cassé | 3.98646 | NA | 15.3356 | -61.3312 | (15.335599999999999, -61.331200000000003) | Landslide | Landslide | Medium | Rain | NA | NA | 0 | NA | http://stormcarib.com/reports/current/report.php?id=1268397271_8827 |
| 1743 | 4/12/10 | NA | NA | Dominica | DM | Saint Patrick | 2608 | Berekua | 2.08997 | NA | 15.2454 | -61.3017 | (15.2454, -61.301699999999997) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.dominicacentral.com/general/community/heavy-overnight-rains-cause-landslides-across-island.html |
| 1744 | 4/12/10 | NA | NA | Dominica | DM | Saint Paul | 702 | Pont Cassé | 3.78784 | NA | 15.4004 | -61.3440 | (15.400399999999999, -61.344000000000001) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.dominicacentral.com/general/community/heavy-overnight-rains-cause-landslides-across-island.html |
| 1745 | 4/12/10 | NA | NA | Dominica | DM | Saint Patrick | 2608 | Berekua | 4.08252 | NA | 15.2458 | -61.2809 | (15.245799999999999, -61.280900000000003) | Landslide | Landslide | Small | Downpour | NA | NA | 0 | NA | http://www.dominicacentral.com/general/community/heavy-overnight-rains-cause-landslides-across-island.html |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_DO, aes(fill= state, y=distance, x=country_name)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_DO, aes(fill=state, y=distance, x=country_name)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_DO, aes(x=country_name, y=distance, fill=state)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_DO <- df_DO %>%
arrange(desc(state)) %>%
mutate(prop = distance / sum(df_DO$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_DO, aes(x=country_name, y=prop, fill=state)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_DO$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 3.39516 |
| 3.98646 |
| 3.78784 |
| 6.45930 |
| 4.20239 |
| 2.08997 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_DO$distance
names(distance) <- df_DO$state
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por estados"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Saint Paul 6.459300 6.459300 11.938173 11.938173
## Saint John 5.929940 12.389240 10.959802 22.897975
## Saint Patrick 5.614950 18.004190 10.377633 33.275607
## Saint Patrick 5.116000 23.120190 9.455466 42.731073
## Saint Paul 4.202390 27.322580 7.766919 50.497992
## Saint Patrick 4.082520 31.405100 7.545373 58.043365
## Saint Paul 3.986460 35.391560 7.367834 65.411199
## Saint Paul 3.787840 39.179400 7.000741 72.411940
## Saint Paul 3.395160 42.574560 6.274984 78.686925
## Saint Andrew 2.648730 45.223290 4.895422 83.582346
## Saint George 2.598490 47.821780 4.802567 88.384914
## Saint Joseph 2.386050 50.207830 4.409933 92.794846
## Saint Patrick 2.089970 52.297800 3.862713 96.657559
## Saint Mark 1.808470 54.106270 3.342441 100.000000stem(df_DO$"distance")##
## The decimal point is at the |
##
## 1 | 8
## 2 | 1466
## 3 | 48
## 4 | 012
## 5 | 169
## 6 | 5head(df_DO)## # A tibble: 6 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 186 8/17/07 <NA> <NA> Dominica DM Sain~ 702
## 2 1552 3/11/10 <NA> <NA> Dominica DM Sain~ 702
## 3 1744 4/12/10 <NA> <NA> Dominica DM Sain~ 702
## 4 1754 4/16/10 <NA> <NA> Dominica DM Sain~ 702
## 5 5715 12/24/13 2:00:00 <NA> Dominica DM Sain~ 702
## 6 1743 4/12/10 <NA> <NA> Dominica DM Sain~ 2608
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_DO))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 186 | 8/17/07 | NA | NA | Dominica | DM | Saint Paul | 702 | Pont Cassé | 3.39516 | NA | 15.3379 | -61.3610 | (15.337899999999999, -61.360999999999997) | Landslide | Mudslide | Small | Tropical cyclone | Hurricane Dean | NA | 2 | Tribune India | http://www.tribuneindia.com/2007/20070817/himachal.htm | 6.274984 | 3.137492 |
| 1552 | 3/11/10 | NA | NA | Dominica | DM | Saint Paul | 702 | Pont Cassé | 3.98646 | NA | 15.3356 | -61.3312 | (15.335599999999999, -61.331200000000003) | Landslide | Landslide | Medium | Rain | NA | NA | 0 | NA | http://stormcarib.com/reports/current/report.php?id=1268397271_8827 | 7.367834 | 9.958901 |
| 1744 | 4/12/10 | NA | NA | Dominica | DM | Saint Paul | 702 | Pont Cassé | 3.78784 | NA | 15.4004 | -61.3440 | (15.400399999999999, -61.344000000000001) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.dominicacentral.com/general/community/heavy-overnight-rains-cause-landslides-across-island.html | 7.000741 | 17.143189 |
| 1754 | 4/16/10 | NA | NA | Dominica | DM | Saint Paul | 702 | Pont Cassé | 6.45930 | NA | 15.3211 | -61.3124 | (15.321099999999999, -61.312399999999997) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.thejakartapost.com/news/2010/04/17/landslides-block-main-road-west-sumatra.html | 11.938173 | 26.612646 |
| 5715 | 12/24/13 | 2:00:00 | NA | Dominica | DM | Saint Paul | 702 | Pont Cassé | 4.20239 | NA | 15.3288 | -61.3470 | (15.328799999999999, -61.347000000000001) | Landslide | Mudslide | Large | Downpour | NA | NA | 0 | www.cdema.org | NA | 7.766919 | 36.465192 |
| 1743 | 4/12/10 | NA | NA | Dominica | DM | Saint Patrick | 2608 | Berekua | 2.08997 | NA | 15.2454 | -61.3017 | (15.2454, -61.301699999999997) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.dominicacentral.com/general/community/heavy-overnight-rains-cause-landslides-across-island.html | 3.862713 | 42.280008 |
stem(df_DO$"distance")##
## The decimal point is at the |
##
## 1 | 8
## 2 | 1466
## 3 | 48
## 4 | 012
## 5 | 169
## 6 | 5stem(df_DO$"distance", scale = 2)##
## The decimal point is at the |
##
## 1 | 8
## 2 | 14
## 2 | 66
## 3 | 4
## 3 | 8
## 4 | 012
## 4 |
## 5 | 1
## 5 | 69
## 6 |
## 6 | 5Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 1.80847 | 1 | 7.1 | 7.1 | 7.1 | 7.1 |
| 2.08997 | 1 | 7.1 | 7.1 | 14.3 | 14.3 |
| 2.38605 | 1 | 7.1 | 7.1 | 21.4 | 21.4 |
| 2.59849 | 1 | 7.1 | 7.1 | 28.6 | 28.6 |
| 2.64873 | 1 | 7.1 | 7.1 | 35.7 | 35.7 |
| 3.39516 | 1 | 7.1 | 7.1 | 42.9 | 42.9 |
| 3.78784 | 1 | 7.1 | 7.1 | 50.0 | 50.0 |
| 3.98646 | 1 | 7.1 | 7.1 | 57.1 | 57.1 |
| 4.08252 | 1 | 7.1 | 7.1 | 64.3 | 64.3 |
| 4.20239 | 1 | 7.1 | 7.1 | 71.4 | 71.4 |
| 5.116 | 1 | 7.1 | 7.1 | 78.6 | 78.6 |
| 5.61495 | 1 | 7.1 | 7.1 | 85.7 | 85.7 |
| 5.92994 | 1 | 7.1 | 7.1 | 92.9 | 92.9 |
| 6.4593 | 1 | 7.1 | 7.1 | 100.0 | 100.0 |
| Total | 14 | 100.0 | 100.0 | 100.0 | 100.0 |
str(table)## Classes 'freqtab' and 'data.frame': 15 obs. of 5 variables:
## $ n : num 1 1 1 1 1 1 1 1 1 1 ...
## $ % : num 7.1 7.1 7.1 7.1 7.1 7.1 7.1 7.1 7.1 7.1 ...
## $ val% : num 7.1 7.1 7.1 7.1 7.1 7.1 7.1 7.1 7.1 7.1 ...
## $ %cum : num 7.1 14.3 21.4 28.6 35.7 42.9 50 57.1 64.3 71.4 ...
## $ val%cum: num 7.1 14.3 21.4 28.6 35.7 42.9 50 57.1 64.3 71.4 ...x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 1.80847 | 1 |
| 2.08997 | 1 |
| 2.38605 | 1 |
| 2.59849 | 1 |
| 2.64873 | 1 |
| 3.39516 | 1 |
| 3.78784 | 1 |
| 3.98646 | 1 |
| 4.08252 | 1 |
| 4.20239 | 1 |
| 5.116 | 1 |
| 5.61495 | 1 |
| 5.92994 | 1 |
| 6.4593 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 1.80847 2.80847 3.80847 4.80847 5.80847 6.80847distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (1.81,2.81] | 4 | 0.3076923 | 4 |
| (2.81,3.81] | 2 | 0.1538462 | 6 |
| (3.81,4.81] | 3 | 0.2307692 | 9 |
| (4.81,5.81] | 2 | 0.1538462 | 11 |
| (5.81,6.81] | 2 | 0.1538462 | 13 |
str(Freq_table)## 'data.frame': 5 obs. of 4 variables:
## $ distance: Factor w/ 5 levels "(1.81,2.81]",..: 1 2 3 4 5
## $ Freq : int 4 2 3 2 2
## $ Rel_Freq: num 0.308 0.154 0.231 0.154 0.154
## $ Cum_Freq: int 4 6 9 11 13df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (1.81,2.81] | 4 |
| (2.81,3.81] | 2 |
| (3.81,4.81] | 3 |
| (4.81,5.81] | 2 |
| (5.81,6.81] | 2 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_DO)## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 1.400000e+01 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 1.860000e+02 NA NA NA NA NA
## max 5.754000e+03 NA NA NA NA NA
## range 5.568000e+03 NA NA NA NA NA
## sum 3.792400e+04 NA NA NA NA NA
## median 1.746500e+03 NA NA NA NA NA
## mean 2.708857e+03 NA NA NA NA NA
## SE.mean 5.536192e+02 NA NA NA NA NA
## CI.mean.0.95 1.196022e+03 NA NA NA NA NA
## var 4.290919e+06 NA NA NA NA NA
## std.dev 2.071453e+03 NA NA NA NA NA
## coef.var 7.646964e-01 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 1.400000e+01 NA 14.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 7.020000e+02 NA 1.8084700 NA
## max NA 1.657100e+04 NA 6.4593000 NA
## range NA 1.586900e+04 NA 4.6508300 NA
## sum NA 3.749000e+04 NA 54.1062700 NA
## median NA 1.374000e+03 NA 3.8871500 NA
## mean NA 2.677857e+03 NA 3.8647336 NA
## SE.mean NA 1.099107e+03 NA 0.3969319 NA
## CI.mean.0.95 NA 2.374475e+03 NA 0.8575192 NA
## var NA 1.691249e+07 NA 2.2057691 NA
## std.dev NA 4.112480e+03 NA 1.4851832 NA
## coef.var NA 1.535735e+00 NA 0.3842912 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 1.400000e+01 1.400000e+01 NA NA NA
## nbr.null 0.000000e+00 0.000000e+00 NA NA NA
## nbr.na 0.000000e+00 0.000000e+00 NA NA NA
## min 1.521740e+01 -6.144100e+01 NA NA NA
## max 1.563080e+01 -6.126420e+01 NA NA NA
## range 4.134000e-01 1.768000e-01 NA NA NA
## sum 2.149263e+02 -8.587772e+02 NA NA NA
## median 1.532495e+01 -6.134550e+01 NA NA NA
## mean 1.535188e+01 -6.134123e+01 NA NA NA
## SE.mean 3.318744e-02 1.426224e-02 NA NA NA
## CI.mean.0.95 7.169709e-02 3.081170e-02 NA NA NA
## var 1.541968e-02 2.847761e-03 NA NA NA
## std.dev 1.241760e-01 5.336441e-02 NA NA NA
## coef.var 8.088653e-03 -8.699600e-04 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 1 13.0000000 NA
## nbr.null NA NA NA 1 12.0000000 NA
## nbr.na NA NA NA 13 1.0000000 NA
## min NA NA NA 0 0.0000000 NA
## max NA NA NA 0 2.0000000 NA
## range NA NA NA 0 2.0000000 NA
## sum NA NA NA 0 2.0000000 NA
## median NA NA NA 0 0.0000000 NA
## mean NA NA NA 0 0.1538462 NA
## SE.mean NA NA NA NA 0.1538462 NA
## CI.mean.0.95 NA NA NA NaN 0.3352020 NA
## var NA NA NA NA 0.3076923 NA
## std.dev NA NA NA NA 0.5547002 NA
## coef.var NA NA NA NA 3.6055513 NA
## source_link prop ypos
## nbr.val NA 14.0000000 14.000000
## nbr.null NA 0.0000000 0.000000
## nbr.na NA 0.0000000 0.000000
## min NA 3.3424407 3.137492
## max NA 11.9381728 97.552289
## range NA 8.5957321 94.414797
## sum NA 100.0000000 732.865128
## median NA 7.1842875 52.464802
## mean NA 7.1428571 52.347509
## SE.mean NA 0.7336153 8.288438
## CI.mean.0.95 NA 1.5848796 17.906082
## var NA 7.5346807 961.774900
## std.dev NA 2.7449373 31.012496
## coef.var NA 0.3842912 0.592435boxplot(data, horizontal=TRUE, col='green')
Gráfico para Saint Patrick (Dominica)
library(readr)
library(knitr)
df <- read_csv("https://raw.githubusercontent.com/lihkir/AnalisisEstadisticoUN/main/Data/catalog.csv")## Rows: 1693 Columns: 23## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (16): date, time, continent_code, country_name, country_code, state/prov...
## dbl (7): id, population, distance, latitude, longitude, injuries, fatalities##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.library(dplyr)
colnames(df)[7] <- "state"
colnames(df)[9] <- "city"
df_DO <- subset(df, country_name == "Dominica")
knitr::kable(head(df_DO)) | id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 186 | 8/17/07 | NA | NA | Dominica | DM | Saint Paul | 702 | Pont Cassé | 3.39516 | NA | 15.3379 | -61.3610 | (15.337899999999999, -61.360999999999997) | Landslide | Mudslide | Small | Tropical cyclone | Hurricane Dean | NA | 2 | Tribune India | http://www.tribuneindia.com/2007/20070817/himachal.htm |
| 250 | 9/9/07 | NA | NA | Dominica | DM | Saint George | 16571 | Roseau | 2.59849 | NA | 15.3055 | -61.3642 | (15.3055, -61.364199999999997) | Landslide | Landslide | Medium | Rain | Tropical Wave | NA | NA | RadioJamaica | http://www.radiojamaica.com/content/view/1156/88/ |
| 1552 | 3/11/10 | NA | NA | Dominica | DM | Saint Paul | 702 | Pont Cassé | 3.98646 | NA | 15.3356 | -61.3312 | (15.335599999999999, -61.331200000000003) | Landslide | Landslide | Medium | Rain | NA | NA | 0 | NA | http://stormcarib.com/reports/current/report.php?id=1268397271_8827 |
| 1743 | 4/12/10 | NA | NA | Dominica | DM | Saint Patrick | 2608 | Berekua | 2.08997 | NA | 15.2454 | -61.3017 | (15.2454, -61.301699999999997) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.dominicacentral.com/general/community/heavy-overnight-rains-cause-landslides-across-island.html |
| 1744 | 4/12/10 | NA | NA | Dominica | DM | Saint Paul | 702 | Pont Cassé | 3.78784 | NA | 15.4004 | -61.3440 | (15.400399999999999, -61.344000000000001) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.dominicacentral.com/general/community/heavy-overnight-rains-cause-landslides-across-island.html |
| 1745 | 4/12/10 | NA | NA | Dominica | DM | Saint Patrick | 2608 | Berekua | 4.08252 | NA | 15.2458 | -61.2809 | (15.245799999999999, -61.280900000000003) | Landslide | Landslide | Small | Downpour | NA | NA | 0 | NA | http://www.dominicacentral.com/general/community/heavy-overnight-rains-cause-landslides-across-island.html |
library(dplyr)
df_DO <- subset(df, state == "Saint Patrick")
knitr::kable(head(df_DO))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1743 | 4/12/10 | NA | NA | Dominica | DM | Saint Patrick | 2608 | Berekua | 2.08997 | NA | 15.2454 | -61.3017 | (15.2454, -61.301699999999997) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.dominicacentral.com/general/community/heavy-overnight-rains-cause-landslides-across-island.html |
| 1745 | 4/12/10 | NA | NA | Dominica | DM | Saint Patrick | 2608 | Berekua | 4.08252 | NA | 15.2458 | -61.2809 | (15.245799999999999, -61.280900000000003) | Landslide | Landslide | Small | Downpour | NA | NA | 0 | NA | http://www.dominicacentral.com/general/community/heavy-overnight-rains-cause-landslides-across-island.html |
| 1746 | 4/12/10 | NA | NA | Dominica | DM | Saint Patrick | 2608 | Berekua | 5.61495 | NA | 15.2556 | -61.2697 | (15.255599999999999, -61.2697) | Landslide | Landslide | Small | Downpour | NA | NA | 0 | NA | http://www.dominicacentral.com/general/community/heavy-overnight-rains-cause-landslides-across-island.html |
| 1747 | 4/12/10 | NA | NA | Dominica | DM | Saint Patrick | 1332 | La Plaine | 5.11600 | NA | 15.2892 | -61.2642 | (15.289199999999999, -61.264200000000002) | Landslide | Landslide | Small | Downpour | NA | NA | 0 | NA | http://www.dominicacentral.com/general/community/heavy-overnight-rains-cause-landslides-across-island.html |
Gráfico de barras agrupados
library(ggplot2)
library(dplyr)
ggplot(df_DO, aes(fill=city, y=distance, x=state)) +
geom_bar(position="dodge", stat="identity")
Gráfico de barras apilados
library(ggplot2)
library(dplyr)
ggplot(df_DO, aes(fill=city, y=distance, x=state)) +
geom_bar(position="stack", stat="identity")
Gráfico circular
library(ggplot2)
library(dplyr)
ggplot(df_DO, aes(x=state, y=distance, fill=city)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0)
library(ggplot2)
library(dplyr)
df_DO <- df_DO %>%
arrange(desc(city)) %>%
mutate(prop = distance / sum(df_DO$distance) *100) %>%
mutate(ypos = cumsum(prop)- 0.5*prop )require(scales)
ggplot(df_DO, aes(x=state, y = prop, fill=city)) +
geom_bar(stat="identity", width=1, color="black") +
coord_polar("y", start=0) +
theme_void() +
theme(legend.position="none") +
geom_text(aes(y = ypos, label = percent(prop/100)), color = "black", size=3) +
scale_fill_brewer(palette="Set4")## Warning in pal_name(palette, type): Unknown palette Set4
Grafico de series temporales
library(forecast)
data<- ts(df_DO$distance, frequency=12, start=2008)
knitr::kable(head(data))| x |
|---|
| 5.11600 |
| 2.08997 |
| 4.08252 |
| 5.61495 |
autoplot(data) + labs(title = "Gráfico de series temporales", x="date", y = "distancia", colour = "green") +theme_bw()
Diagrama de pareto
library(qcc)
distance <- df_DO$distance
names(distance) <- df_DO$city
pareto.chart(distance,
ylab="distance",
col = heat.colors(length(distance)),
cumperc = seq(0, 100, by = 10),
ylab2 = "Porcentaje acumulado",
main = "Grafico de Pareto por ciudades"
)
##
## Pareto chart analysis for distance
## Frequency Cum.Freq. Percentage Cum.Percent.
## Berekua 5.61495 5.61495 33.21779 33.21779
## La Plaine 5.11600 10.73095 30.26603 63.48382
## Berekua 4.08252 14.81347 24.15201 87.63583
## Berekua 2.08997 16.90344 12.36417 100.00000stem(df_DO$"distance")##
## The decimal point is at the |
##
## 2 | 1
## 3 |
## 4 | 1
## 5 | 16head(df_DO)## # A tibble: 4 x 25
## id date time continent_code country_name country_code state population
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 1747 4/12/10 <NA> <NA> Dominica DM Saint~ 1332
## 2 1743 4/12/10 <NA> <NA> Dominica DM Saint~ 2608
## 3 1745 4/12/10 <NA> <NA> Dominica DM Saint~ 2608
## 4 1746 4/12/10 <NA> <NA> Dominica DM Saint~ 2608
## # ... with 17 more variables: city <chr>, distance <dbl>,
## # location_description <chr>, latitude <dbl>, longitude <dbl>,
## # geolocation <chr>, hazard_type <chr>, landslide_type <chr>,
## # landslide_size <chr>, trigger <chr>, storm_name <chr>, injuries <dbl>,
## # fatalities <dbl>, source_name <chr>, source_link <chr>, prop <dbl>,
## # ypos <dbl>knitr::kable(head(df_DO))| id | date | time | continent_code | country_name | country_code | state | population | city | distance | location_description | latitude | longitude | geolocation | hazard_type | landslide_type | landslide_size | trigger | storm_name | injuries | fatalities | source_name | source_link | prop | ypos |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1747 | 4/12/10 | NA | NA | Dominica | DM | Saint Patrick | 1332 | La Plaine | 5.11600 | NA | 15.2892 | -61.2642 | (15.289199999999999, -61.264200000000002) | Landslide | Landslide | Small | Downpour | NA | NA | 0 | NA | http://www.dominicacentral.com/general/community/heavy-overnight-rains-cause-landslides-across-island.html | 30.26603 | 15.13301 |
| 1743 | 4/12/10 | NA | NA | Dominica | DM | Saint Patrick | 2608 | Berekua | 2.08997 | NA | 15.2454 | -61.3017 | (15.2454, -61.301699999999997) | Landslide | Landslide | Medium | Downpour | NA | NA | 0 | NA | http://www.dominicacentral.com/general/community/heavy-overnight-rains-cause-landslides-across-island.html | 12.36417 | 36.44811 |
| 1745 | 4/12/10 | NA | NA | Dominica | DM | Saint Patrick | 2608 | Berekua | 4.08252 | NA | 15.2458 | -61.2809 | (15.245799999999999, -61.280900000000003) | Landslide | Landslide | Small | Downpour | NA | NA | 0 | NA | http://www.dominicacentral.com/general/community/heavy-overnight-rains-cause-landslides-across-island.html | 24.15201 | 54.70620 |
| 1746 | 4/12/10 | NA | NA | Dominica | DM | Saint Patrick | 2608 | Berekua | 5.61495 | NA | 15.2556 | -61.2697 | (15.255599999999999, -61.2697) | Landslide | Landslide | Small | Downpour | NA | NA | 0 | NA | http://www.dominicacentral.com/general/community/heavy-overnight-rains-cause-landslides-across-island.html | 33.21779 | 83.39110 |
stem(df_DO$"distance")##
## The decimal point is at the |
##
## 2 | 1
## 3 |
## 4 | 1
## 5 | 16stem(df_DO$"distance", scale = 2)##
## The decimal point is at the |
##
## 2 | 1
## 2 |
## 3 |
## 3 |
## 4 | 1
## 4 |
## 5 | 1
## 5 | 6Tablas de frecuencia
library(questionr)
table <- questionr::freq(distance, cum = TRUE, sort = "dec", total = TRUE)
knitr::kable(table)| n | % | val% | %cum | val%cum | |
|---|---|---|---|---|---|
| 2.08997 | 1 | 25 | 25 | 25 | 25 |
| 4.08252 | 1 | 25 | 25 | 50 | 50 |
| 5.116 | 1 | 25 | 25 | 75 | 75 |
| 5.61495 | 1 | 25 | 25 | 100 | 100 |
| Total | 4 | 100 | 100 | 100 | 100 |
str(table)## Classes 'freqtab' and 'data.frame': 5 obs. of 5 variables:
## $ n : num 1 1 1 1 4
## $ % : num 25 25 25 25 100
## $ val% : num 25 25 25 25 100
## $ %cum : num 25 50 75 100 100
## $ val%cum: num 25 50 75 100 100x <- row.names(table)
y <- table$n
names <- x[1:(length(x)-1)]
freqs <- y[1:(length(y)-1)]
df <- data.frame(x = names, y = freqs)
knitr::kable(df)| x | y |
|---|---|
| 2.08997 | 1 |
| 4.08252 | 1 |
| 5.116 | 1 |
| 5.61495 | 1 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Distancia") +
ylab("Frecuencia de deslizamientos") + theme(axis.text.x = element_text(angle = 90))
Tabla de frecuencias agrupada
n_sturges = 1 + log(length(distance))/log(2)
n_sturgesc = ceiling(n_sturges)
n_sturgesf = floor(n_sturges)
n_clases = 0
if (n_sturgesc%%2 == 0) {
n_clases = n_sturgesf
} else {
n_clases = n_sturgesc
}
R = max(distance) - min(distance)
w = ceiling(R/n_clases)bins <- seq(min(distance), max(distance)+w, by = w)
bins## [1] 2.08997 4.08997 6.08997distance <- cut(distance, bins)
Freq_table <- transform(table(distance), Rel_Freq=prop.table(Freq), Cum_Freq=cumsum(Freq))
knitr::kable(Freq_table)| distance | Freq | Rel_Freq | Cum_Freq |
|---|---|---|---|
| (2.09,4.09] | 1 | 0.3333333 | 1 |
| (4.09,6.09] | 2 | 0.6666667 | 3 |
str(Freq_table)## 'data.frame': 2 obs. of 4 variables:
## $ distance: Factor w/ 2 levels "(2.09,4.09]",..: 1 2
## $ Freq : int 1 2
## $ Rel_Freq: num 0.333 0.667
## $ Cum_Freq: int 1 3df <- data.frame(x = Freq_table$distance, y = Freq_table$Freq)
knitr::kable(df)| x | y |
|---|---|
| (2.09,4.09] | 1 |
| (4.09,6.09] | 2 |
library(ggplot2)
ggplot(data=df, aes(x=x, y=y)) +
geom_bar(stat="identity", color="green", fill="aquamarine") +
xlab("Rango de deslizamiento") +
ylab("Frecuencia")
library(pastecs)
stat.desc(df_DO)## Warning in min(x): ningún argumento finito para min; retornando Inf## Warning in max(x): ningun argumento finito para max; retornando -Inf## Warning in qt((0.5 + p/2), (Nbrval - 1)): NaNs produced## id date time continent_code country_name country_code
## nbr.val 4.000000e+00 NA NA NA NA NA
## nbr.null 0.000000e+00 NA NA NA NA NA
## nbr.na 0.000000e+00 NA NA NA NA NA
## min 1.743000e+03 NA NA NA NA NA
## max 1.747000e+03 NA NA NA NA NA
## range 4.000000e+00 NA NA NA NA NA
## sum 6.981000e+03 NA NA NA NA NA
## median 1.745500e+03 NA NA NA NA NA
## mean 1.745250e+03 NA NA NA NA NA
## SE.mean 8.539126e-01 NA NA NA NA NA
## CI.mean.0.95 2.717531e+00 NA NA NA NA NA
## var 2.916667e+00 NA NA NA NA NA
## std.dev 1.707825e+00 NA NA NA NA NA
## coef.var 9.785562e-04 NA NA NA NA NA
## state population city distance location_description
## nbr.val NA 4.000000e+00 NA 4.0000000 NA
## nbr.null NA 0.000000e+00 NA 0.0000000 NA
## nbr.na NA 0.000000e+00 NA 0.0000000 NA
## min NA 1.332000e+03 NA 2.0899700 NA
## max NA 2.608000e+03 NA 5.6149500 NA
## range NA 1.276000e+03 NA 3.5249800 NA
## sum NA 9.156000e+03 NA 16.9034400 NA
## median NA 2.608000e+03 NA 4.5992600 NA
## mean NA 2.289000e+03 NA 4.2258600 NA
## SE.mean NA 3.190000e+02 NA 0.7801972 NA
## CI.mean.0.95 NA 1.015200e+03 NA 2.4829358 NA
## var NA 4.070440e+05 NA 2.4348309 NA
## std.dev NA 6.380000e+02 NA 1.5603945 NA
## coef.var NA 2.787243e-01 NA 0.3692490 NA
## latitude longitude geolocation hazard_type landslide_type
## nbr.val 4.000000000 4.000000e+00 NA NA NA
## nbr.null 0.000000000 0.000000e+00 NA NA NA
## nbr.na 0.000000000 0.000000e+00 NA NA NA
## min 15.245400000 -6.130170e+01 NA NA NA
## max 15.289200000 -6.126420e+01 NA NA NA
## range 0.043800000 3.750000e-02 NA NA NA
## sum 61.036000000 -2.451165e+02 NA NA NA
## median 15.250700000 -6.127530e+01 NA NA NA
## mean 15.259000000 -6.127913e+01 NA NA NA
## SE.mean 0.010339246 8.288383e-03 NA NA NA
## CI.mean.0.95 0.032904094 2.637733e-02 NA NA NA
## var 0.000427600 2.747892e-04 NA NA NA
## std.dev 0.020678491 1.657677e-02 NA NA NA
## coef.var 0.001355167 -2.705124e-04 NA NA NA
## landslide_size trigger storm_name injuries fatalities source_name
## nbr.val NA NA NA 0 4 NA
## nbr.null NA NA NA 0 4 NA
## nbr.na NA NA NA 4 0 NA
## min NA NA NA Inf 0 NA
## max NA NA NA -Inf 0 NA
## range NA NA NA -Inf 0 NA
## sum NA NA NA 0 0 NA
## median NA NA NA NA 0 NA
## mean NA NA NA NaN 0 NA
## SE.mean NA NA NA NA 0 NA
## CI.mean.0.95 NA NA NA NaN 0 NA
## var NA NA NA NA 0 NA
## std.dev NA NA NA NA 0 NA
## coef.var NA NA NA NA NaN NA
## source_link prop ypos
## nbr.val NA 4.000000 4.0000000
## nbr.null NA 0.000000 0.0000000
## nbr.na NA 0.000000 0.0000000
## min NA 12.364170 15.1330143
## max NA 33.217795 83.3911026
## range NA 20.853625 68.2580883
## sum NA 100.000000 189.6784323
## median NA 27.209018 45.5771577
## mean NA 25.000000 47.4196081
## SE.mean NA 4.615612 14.4621365
## CI.mean.0.95 NA 14.688938 46.0249728
## var NA 85.215503 836.6135657
## std.dev NA 9.231224 28.9242729
## coef.var NA 0.369249 0.6099644boxplot(data, horizontal=TRUE, col='green')
Conclusión
- Finalizado el informe, cuyo énfasis es el manejo adecuado del lenguaje de programación R, y que tiene como fin el buen manejo y la correcta aplicación de las herramientas que nos facilita el programa R Studio, el buen manejo del programa se puede observar en el informe recién presentado, donde se utilizaron las longitudes de deslizamiento de América Central, y por medio de esta se desarrollaron los diferentes tipos de gráficas y diagramas, aplicando los códigos necesarios, ya que gracias a la gran variedad de herramientas que nos permite utilizar la aplicación, se logró crear los diferentes tipos de gráficos y diagramas, un ejemplo de estos diagramas y gráficas son: el diagrama de pareto y la gráfica circular. Junto a esto, el lograr comprender los objetivos, cuyo fin es que cada estudiante adquiera el conocimiento y el manejo adecuado de este lenguaje de programación, para que puedan ser utilizado de manera clara y concisa en las áreas laborales o en casos de la vida cotidiana. Cabe resaltar que dicho programa nos presta una amplia base de datos, y una variabilidad de códigos, para que puedan ser manejadas por las comunidades de programación o personas con interés en aprender, todo esto se debe a su fácil y didáctico manejo.