TAREA FINAL
Mercedes Marcela Pincay Pilay
27 de marzo de 2018
library (psych)
getwd ()## [1] "C:/Users/Victoria/Desktop/archivos escritorio/PhD. Marcela/Primera estancia/MODULO 2"df<- read.csv ("http://gauss.inf.um.es/datos/paisesMundoRedC.csv", header=TRUE, sep = ";", dec = ".", stringsAsFactors = FALSE)
head (df)## Country EPI_regions
## AGO Angola Sub-Saharan Africa
## ALB Albania Central and Eastern Europ
## ARE United Arab Emirates Middle East and North Africa
## ARG Argentina Latin America and Caribbe
## ARM Armenia Middle East and North Africa
## AUS Australia East Asia and the Pacific
## GEO_subregion Population2005 GDP_capita.MRYA landarea EPI
## AGO Southern Africa 15941.4 2314.4 1251895.62 39.5
## ALB Central Europe 3129.7 4955.3 28346.12 84.0
## ARE Arabian Peninsula 4495.8 22698.3 74776.60 64.0
## ARG South America 38747.2 13652.4 2736296.00 81.8
## ARM Eastern Europe 3016.3 5011.0 28272.73 77.8
## AUS Australia + New Zealand 20155.1 30677.9 7634643.84 79.8
## FOREST FISH AGRICULTURE
## AGO 95.4 87.3 61.3
## ALB 100.0 62.5 75.6
## ARE 100.0 50.0 72.3
## ARG 75.9 58.8 79.9
## ARM 70.1 NA 94.2
## AUS 100.0 96.7 78.7dim(df)## [1] 149 10str (df)## 'data.frame': 149 obs. of 10 variables:
## $ Country : chr "Angola" "Albania" "United Arab Emirates" "Argentina" ...
## $ EPI_regions : chr "Sub-Saharan Africa" "Central and Eastern Europ" "Middle East and North Africa" "Latin America and Caribbe" ...
## $ GEO_subregion : chr "Southern Africa" "Central Europe" "Arabian Peninsula" "South America" ...
## $ Population2005 : num 15941 3130 4496 38747 3016 ...
## $ GDP_capita.MRYA: num 2314 4955 22698 13652 5011 ...
## $ landarea : num 1251896 28346 74777 2736296 28273 ...
## $ EPI : num 39.5 84 64 81.8 77.8 79.8 89.4 72.2 54.7 78.4 ...
## $ FOREST : num 95.4 100 100 75.9 70.1 100 100 100 0 100 ...
## $ FISH : num 87.3 62.5 50 58.8 NA 96.7 NA NA NA 47.4 ...
## $ AGRICULTURE : num 61.3 75.6 72.3 79.9 94.2 78.7 76.4 71.4 95.9 80.8 ...Las variables son de caracter (Country, EPI_regions, GEO_subregion) y también es numérica.
mediante la función str ()observamos como está formado el objeto df, que es un objeto de data frame que cuenta 149 observaciones y 10 variables y a su vez vemos las características de cada una de ellas.
## [1] "Southern Africa" "Central Europe"
## [3] "Arabian Peninsula" "South America"
## [5] "Eastern Europe" "Australia + New Zealand"
## [7] "Western Europe" "Eastern Europe"
## [9] "Eastern Africa" "Western Europe"
## [11] "Western Africa" "Western Africa"
## [13] "South Asia" "Central Europe"
## [15] "Central Europe" "Eastern Europe"
## [17] "Meso America" "South America"
## [19] "South America" "Southern Africa"
## [21] "Central Africa" "North America"
## [23] "Western Europe" "South America"
## [25] "Northeast Asia" "Western Africa"
## [27] "Central Africa" "Central Africa"
## [29] "Central Africa" "South America"
## [31] "Meso America" "Caribbean"
## [33] "Central Europe" "Central Europe"
## [35] "Western Europe" "Eastern Africa"
## [37] "Western Europe" "Caribbean"
## [39] "Northern Africa" "South America"
## [41] "Northern Africa" "Eastern Africa"
## [43] "Western Europe" "Central Europe"
## [45] "Eastern Africa" "Western Europe"
## [47] "South Pacific" "Western Europe"
## [49] "Central Africa" "Western Europe"
## [51] "Eastern Europe" "Western Africa"
## [53] "Western Africa" "Western Africa"
## [55] "Western Europe" "Meso America"
## [57] "South America" "Meso America"
## [59] "Central Europe" "Caribbean"
## [61] "Central Europe" "South East Asia"
## [63] "South Asia" "Western Europe"
## [65] "South Asia" "Mashriq"
## [67] "Western Europe" "Western Europe"
## [69] "Western Europe" "Caribbean"
## [71] "Mashriq" "Northeast Asia"
## [73] "Central Asia" "Eastern Africa"
## [75] "Central Asia" "South East Asia"
## [77] "Northeast Asia" "Arabian Peninsula"
## [79] "South East Asia" "Mashriq"
## [81] "South Asia" "Central Europe"
## [83] "Western Europe" "Central Europe"
## [85] "Northern Africa" "Eastern Europe"
## [87] "Western Indian Ocean" "Meso America"
## [89] "Central Europe" "Western Africa"
## [91] "South East Asia" "Northeast Asia"
## [93] "Southern Africa" "Western Africa"
## [95] "Western Indian Ocean" "Southern Africa"
## [97] "South East Asia" "Southern Africa"
## [99] "Western Africa" "Western Africa"
## [101] "Meso America" "Western Europe"
## [103] "Western Europe" "South Asia"
## [105] "Australia + New Zealand" "Arabian Peninsula"
## [107] "South Asia" "Meso America"
## [109] "South America" "South East Asia"
## [111] "South Pacific" "Central Europe"
## [113] "Western Europe" "South America"
## [115] "Central Europe" "Eastern Europe"
## [117] "Eastern Africa" "Arabian Peninsula"
## [119] "Northern Africa" "Western Africa"
## [121] "South Pacific" "Western Africa"
## [123] "Meso America" "Central Europe"
## [125] "Central Europe" "Western Europe"
## [127] "Southern Africa" "Mashriq"
## [129] "Central Africa" "Western Africa"
## [131] "South East Asia" "Central Asia"
## [133] "Central Asia" "Caribbean"
## [135] "Northern Africa" "Central Europe"
## [137] "Northeast Asia" "Southern Africa"
## [139] "Eastern Africa" "Eastern Europe"
## [141] "South America" "North America"
## [143] "Central Asia" "South America"
## [145] "South East Asia" "Arabian Peninsula"
## [147] "Southern Africa" "Southern Africa"
## [149] "Southern Africa"en la variable Geo_subregionse se visualiza las subregios de los continentes de de Africa, America, Asia, Europa y Oceanía
indicesAfrica <- grep( "Africa", df$GEO_subregion )
dfA <- df[ indicesAfrica, ]
str( dfA )## 'data.frame': 41 obs. of 10 variables:
## $ Country : chr "Angola" "Burundi" "Benin" "Burkina Faso" ...
## $ EPI_regions : chr "Sub-Saharan Africa" "Sub-Saharan Africa" "Sub-Saharan Africa" "Sub-Saharan Africa" ...
## $ GEO_subregion : chr "Southern Africa" "Eastern Africa" "Western Africa" "Western Africa" ...
## $ Population2005 : num 15941 7548 8439 13228 1765 ...
## $ GDP_capita.MRYA: num 2314 630 1016 1143 11313 ...
## $ landarea : num 1251896 25227 115828 275748 559516 ...
## $ EPI : num 39.5 54.7 56.1 44.3 68.7 56 65.2 63.8 47.3 69.7 ...
## $ FOREST : num 95.4 0 17.8 64.5 79.2 97.2 100 78.4 94.8 98.4 ...
## $ FISH : num 87.3 NA 91.5 NA NA NA 91.2 52.4 46.3 74.1 ...
## $ AGRICULTURE : num 61.3 95.9 88.2 87.7 72.3 71.8 88.7 69.9 70.8 99.1 ...con la función “factor” cambiamos las variables categóricas en factores y automáticamente se les asigna niveles. Para verificar los cambios lo hacemos con str()
sapply(dfA, FUN = typeof)## Country EPI_regions GEO_subregion Population2005
## "character" "character" "character" "double"
## GDP_capita.MRYA landarea EPI FOREST
## "double" "double" "double" "double"
## FISH AGRICULTURE
## "double" "double"dfA$Country <- factor (dfA$Country)
dfA$EPI_regions <- factor (dfA$EPI_regions)
dfA$GEO_subregion <- factor (dfA$GEO_subregion)
str(dfA)## 'data.frame': 41 obs. of 10 variables:
## $ Country : Factor w/ 41 levels "Algeria","Angola",..: 2 6 3 5 4 8 11 7 12 10 ...
## $ EPI_regions : Factor w/ 2 levels "Middle East and North Africa",..: 2 2 2 2 2 2 2 2 2 2 ...
## $ GEO_subregion : Factor w/ 5 levels "Central Africa",..: 4 2 5 5 4 1 5 1 1 1 ...
## $ Population2005 : num 15941 7548 8439 13228 1765 ...
## $ GDP_capita.MRYA: num 2314 630 1016 1143 11313 ...
## $ landarea : num 1251896 25227 115828 275748 559516 ...
## $ EPI : num 39.5 54.7 56.1 44.3 68.7 56 65.2 63.8 47.3 69.7 ...
## $ FOREST : num 95.4 0 17.8 64.5 79.2 97.2 100 78.4 94.8 98.4 ...
## $ FISH : num 87.3 NA 91.5 NA NA NA 91.2 52.4 46.3 74.1 ...
## $ AGRICULTURE : num 61.3 95.9 88.2 87.7 72.3 71.8 88.7 69.9 70.8 99.1 ...con la función summary del data frame dfA se puede observar los niveles de las variables que se le aplicó factores y los datos descriptivos de las variables numéricas. Se puede destacar que la Media de la poblacion del 2005 es de 21030 y de la agricultura de 74.87.
summary(dfA)## Country EPI_regions GEO_subregion
## Algeria : 1 Middle East and North Africa: 5 Central Africa : 6
## Angola : 1 Sub-Saharan Africa :36 Eastern Africa : 7
## Benin : 1 Northern Africa: 5
## Botswana : 1 Southern Africa:10
## Burkina Faso: 1 Western Africa :13
## Burundi : 1
## (Other) :35
## Population2005 GDP_capita.MRYA landarea EPI
## Min. : 793.1 Min. : 629.8 Min. : 17410 Min. :39.10
## 1st Qu.: 5525.5 1st Qu.: 1008.1 1st Qu.: 147882 1st Qu.:51.30
## Median : 12883.9 Median : 1312.8 Median : 403759 Median :59.40
## Mean : 21030.0 Mean : 2506.2 Mean : 642219 Mean :59.16
## 3rd Qu.: 28816.2 3rd Qu.: 2299.1 3rd Qu.: 968072 3rd Qu.:69.00
## Max. :131529.7 Max. :11313.3 Max. :2492385 Max. :78.10
##
## FOREST FISH AGRICULTURE
## Min. : 0.00 Min. :23.90 Min. :53.00
## 1st Qu.: 73.30 1st Qu.:72.60 1st Qu.:69.30
## Median : 86.40 Median :79.10 Median :73.90
## Mean : 78.51 Mean :75.11 Mean :74.87
## 3rd Qu.: 98.40 3rd Qu.:87.05 3rd Qu.:81.60
## Max. :100.00 Max. :91.60 Max. :99.10
## NA's :14Mediante la funcion tabular, cruzamos la variable GEO_subregion versus las Vabriables Population2005, landarea y GDP_capita.MRYA, y para cada grupo calcular la media, desviacion estandar, max, min.
#install.packages("tables")
library (tables)## Warning: package 'tables' was built under R version 3.4.4## Loading required package: Hmisc## Warning: package 'Hmisc' was built under R version 3.4.4## Loading required package: lattice## Loading required package: survival## Loading required package: Formula## Loading required package: ggplot2## Warning: package 'ggplot2' was built under R version 3.4.4##
## Attaching package: 'ggplot2'## The following objects are masked from 'package:psych':
##
## %+%, alpha##
## Attaching package: 'Hmisc'## The following object is masked from 'package:psych':
##
## describe## The following objects are masked from 'package:base':
##
## format.pval, unitstabla <- tabular (GEO_subregion ~ (Population2005+ landarea+ GDP_capita.MRYA)*((media=mean)+sd+max+min), data= dfA)
#tabla <- tabular (dfA$GEO_subregion ~ (dfA$Population2005+ dfA$landarea+ dfA$GDP_capita.MRYA)*((media=mean)+sd+max+min), data= dfA)
tabla##
## Population2005 landarea
## GEO_subregion media sd max min media sd
## Central Africa 15507 21283 57549 1383.8 875595 786168
## Eastern Africa 23183 27067 77431 793.1 300392 413610
## Northern Africa 36940 23147 74033 10102.5 1262919 1079434
## Southern Africa 16388 15487 47432 1032.4 676391 418233
## Western Africa 19871 34051 131530 1586.3 453551 453694
##
## GDP_capita.MRYA
## max min media sd max min
## 2313414 265146 2038 1914.5 5835 700.0
## 1123717 20904 1163 417.6 1982 629.8
## 2492385 147881 4912 2209.6 7758 2050.2
## 1251896 17410 4057 4095.1 11313 631.5
## 1248146 34106 1327 561.8 2299 700.3Calcula para la variable AGRICULTURE la media, mediana, desviación típica, el mínimo y el máximo según el factor GEO_subregion . Pon etiquetas representativas a las columnas.
tabla2 <- tabular( (Sub_Geog = GEO_subregion) ~ (Agricultura = AGRICULTURE) *( (Media = mean ) + (Desv. = sd) + (Max. = max) + (Min.= min)), data = dfA )
tabla2##
## Agricultura
## Sub_Geog Media Desv. Max. Min.
## Central Africa 79.28 11.174 99.1 69.9
## Eastern Africa 77.41 12.403 95.9 54.4
## Northern Africa 66.04 8.136 74.8 53.0
## Southern Africa 69.74 4.681 74.7 61.3
## Western Africa 78.82 7.131 88.7 65.9imprime la tabla de forma elegante.
html (tabla2, options = htmloptions( HTMLcaption = "Agricultura",pad = TRUE))| Agricultura | ||||
|---|---|---|---|---|
| Sub_Geog | Media | Desv. | Max. | Min. |
| Central Africa | 79.28 | 11.174 | 99.1 | 69.9 |
| Eastern Africa | 77.41 | 12.403 | 95.9 | 54.4 |
| Northern Africa | 66.04 | 8.136 | 74.8 | 53.0 |
| Southern Africa | 69.74 | 4.681 | 74.7 | 61.3 |
| Western Africa | 78.82 | 7.131 | 88.7 | 65.9 |
gráfico de dispersión para estudiar la relación entre el tamaño de la población de cada país (Population2005) y el producto interior bruto (GDP_capita.MRYA). Colorea los puntos según el factor GEO_subregion.
plot (dfA$Population2005, dfA$GDP_capita.MRYA, col=dfA$GEO_subregion)
#Realiza un gráfico de tu interés para el conjunto de datos empleando la librería ggplot2
library(ggplot2)
ggplot (dfA, aes (x= landarea, y = GDP_capita.MRYA))+
geom_point(na.rm=T,aes( colour = GEO_subregion ))+
stat_smooth( method = "lm" )
sessionInfo()## R version 3.4.3 (2017-11-30)
## Platform: x86_64-w64-mingw32/x64 (64-bit)
## Running under: Windows 7 x64 (build 7601) Service Pack 1
##
## Matrix products: default
##
## locale:
## [1] LC_COLLATE=Spanish_Ecuador.1252 LC_CTYPE=Spanish_Ecuador.1252
## [3] LC_MONETARY=Spanish_Ecuador.1252 LC_NUMERIC=C
## [5] LC_TIME=Spanish_Ecuador.1252
##
## attached base packages:
## [1] stats graphics grDevices utils datasets methods base
##
## other attached packages:
## [1] tables_0.8.3 Hmisc_4.1-1 ggplot2_2.2.1 Formula_1.2-2
## [5] survival_2.41-3 lattice_0.20-35 psych_1.7.8
##
## loaded via a namespace (and not attached):
## [1] Rcpp_0.12.15 compiler_3.4.3 pillar_1.2.1
## [4] RColorBrewer_1.1-2 plyr_1.8.4 base64enc_0.1-3
## [7] tools_3.4.3 rpart_4.1-11 digest_0.6.15
## [10] checkmate_1.8.5 htmlTable_1.11.2 evaluate_0.10.1
## [13] tibble_1.4.2 gtable_0.2.0 nlme_3.1-131
## [16] rlang_0.2.0 Matrix_1.2-12 rstudioapi_0.7
## [19] yaml_2.1.18 parallel_3.4.3 gridExtra_2.3
## [22] stringr_1.3.0 knitr_1.20 cluster_2.0.6
## [25] htmlwidgets_1.0 nnet_7.3-12 rprojroot_1.3-2
## [28] grid_3.4.3 data.table_1.10.4-3 foreign_0.8-69
## [31] rmarkdown_1.9 latticeExtra_0.6-28 magrittr_1.5
## [34] backports_1.1.2 scales_0.5.0 htmltools_0.3.6
## [37] splines_3.4.3 mnormt_1.5-5 colorspace_1.3-2
## [40] labeling_0.3 stringi_1.1.6 acepack_1.4.1
## [43] lazyeval_0.2.1 munsell_0.4.3Note that the echo = FALSE parameter was added to the code chunk to prevent printing of the R code that generated the plot.