FECHA: 06/12/2025
#Estadistica Descriptiva
#6/12/2025
datos<-read.csv("soil_pollution_diseases.csv",header = TRUE,dec = ".",
sep = ",")
#Extracción Variable Cuantitativa Continua
Temperatura <- datos$Temperature_C
min <-min(Temperatura)
max <-max(Temperatura)
R <-max-min
K <- floor(1+3.33*log10(length(Temperatura)))
A <-R/K
Li <-round(seq(from=min,to=max-A,by=A),2)
Ls <-round(seq(from=min+A,to=max,by=A),2)
Mc <-(Li+Ls)/2
ni<-c()
for (i in 1:K) {
if (i < K) {
ni[i] <- length(subset(Temperatura, Temperatura >= Li[i] & Temperatura < Ls[i]))
} else {
ni[i] <- length(subset(Temperatura, Temperatura >= Li[i] & Temperatura <= Ls[i]))
}
}
sum(ni)
## [1] 3000
hi <-ni/sum(ni)*100
Ni_asc<-cumsum(ni)
Hi_asc<-cumsum(hi)
Ni_desc<-rev(cumsum(rev(ni)))
Hi_desc<-rev(cumsum(rev(hi)))
TDF_Temperatura <- data.frame(
Li, Ls, Mc, ni, round(hi, 2), Ni_asc, Ni_desc, round(Hi_asc, 2), round(Hi_desc, 2)
)
colnames(TDF_Temperatura) <- c("Li","Ls","Mc","ni","hi","Ni_asc","Ni_desc","Hi_asc(%)","Hi_desc(%)")
#Crear fila de totales
totales<-c(
Li="TOTAL",
Ls="-",
Mc="-",
ni=sum(ni),
hi=sum(hi),
Ni_asc="-",
Ni_desc="-",
Hi_asc="-",
Hi_desc="-")
TDF_Temperatura <-rbind(TDF_Temperatura,totales)
library(dplyr)
library(gt)
TDF_Temperatura %>%
gt() %>%
tab_header(
title = md("Tabla Nro. 3"),
subtitle = md("*Tabla de distribución de la Temperatura (°C) del Suelo*")
) %>%
tab_source_note(
source_note = md("Autor: Grupo 3")
) %>%
tab_options(
table.border.top.color = "black",
table.border.bottom.color = "black",
table.border.top.style = "solid",
table.border.bottom.style = "solid",
column_labels.border.top.color = "black",
column_labels.border.bottom.color = "black",
column_labels.border.bottom.width = px(2),
row.striping.include_table_body = TRUE,
heading.border.bottom.color = "black",
heading.border.bottom.width = px(2),
table_body.hlines.color = "gray",
table_body.border.bottom.color = "black"
)
| Tabla Nro. 3 |
| Tabla de distribución de la Temperatura (°C) del Suelo |
| Li |
Ls |
Mc |
ni |
hi |
Ni_asc |
Ni_desc |
Hi_asc(%) |
Hi_desc(%) |
| 10 |
12.92 |
11.46 |
258 |
8.6 |
258 |
3000 |
8.6 |
100 |
| 12.92 |
15.83 |
14.375 |
266 |
8.87 |
524 |
2742 |
17.47 |
91.4 |
| 15.83 |
18.75 |
17.29 |
251 |
8.37 |
775 |
2476 |
25.83 |
82.53 |
| 18.75 |
21.67 |
20.21 |
241 |
8.03 |
1016 |
2225 |
33.87 |
74.17 |
| 21.67 |
24.58 |
23.125 |
262 |
8.73 |
1278 |
1984 |
42.6 |
66.13 |
| 24.58 |
27.5 |
26.04 |
260 |
8.67 |
1538 |
1722 |
51.27 |
57.4 |
| 27.5 |
30.42 |
28.96 |
234 |
7.8 |
1772 |
1462 |
59.07 |
48.73 |
| 30.42 |
33.33 |
31.875 |
257 |
8.57 |
2029 |
1228 |
67.63 |
40.93 |
| 33.33 |
36.25 |
34.79 |
253 |
8.43 |
2282 |
971 |
76.07 |
32.37 |
| 36.25 |
39.17 |
37.71 |
249 |
8.3 |
2531 |
718 |
84.37 |
23.93 |
| 39.17 |
42.08 |
40.625 |
218 |
7.27 |
2749 |
469 |
91.63 |
15.63 |
| 42.08 |
45 |
43.54 |
251 |
8.37 |
3000 |
251 |
100 |
8.37 |
| TOTAL |
- |
- |
3000 |
100 |
- |
- |
- |
- |
| Autor: Grupo 3 |
# Histograma
histoT <- hist(
Temperatura,
main = "Gráfica Nº17: Distribución de la Temperatura",
xlab = "Temperatura (°C)",
ylab = "Cantidad",
col = "blue"
)
#Simplificación con el histograma
Hist_Temperatura<-hist(Temperatura,breaks = 8,plot = F)
k<-length(Hist_Temperatura$breaks)
Li<-Hist_Temperatura$breaks[1:(length(Hist_Temperatura$breaks)-1)]
Ls<-Hist_Temperatura$breaks[2:length(Hist_Temperatura$breaks)]
ni<-Hist_Temperatura$counts
sum(ni)
## [1] 3000
Mc<-Hist_Temperatura$mids
hi<-(ni/sum(ni))
sum(hi)
## [1] 1
Ni_asc<-cumsum(ni)
Hi_asc<-cumsum(hi)
Ni_desc<-rev(cumsum(rev(ni)))
Hi_desc<-rev(cumsum(rev(hi)))
TDF_Temperatura<-data.frame(Li=round(Li,2),
Ls=round(Ls,2),
Mc=round(Mc,2),
ni=ni,
hi=round(hi*100,2),
Ni_asc=Ni_asc,
Ni_desc=Ni_desc,
Hi_asc=round(Hi_asc*100,2),
Hi_desc=round(Hi_desc*100,2))
colnames(TDF_Temperatura)<-c("Lim inf","Lim sup","MC","ni","hi(%)","Ni asc","Ni desc","Hi asc(%)","Hi desc(%)")
#Crear fila de totales
totales<-c(Li="TOTAL",
Ls="-",
Mc="-",
ni = sum(as.numeric(TDF_Temperatura$ni)),
hi = sum(as.numeric(TDF_Temperatura$hi)),
Ni_asc="-",
Ni_desc="-",
Hi_asc="-",
Hi_desc="-")
TDF_Temperatura<-rbind(TDF_Temperatura,totales)
library(dplyr)
library(gt)
TDF_Temperatura %>%
gt() %>%
tab_header(
title = md("Tabla Nro. 4"),
subtitle = md("*Tabla Simplificada de distribución de la Temperatura del Suelo*")
) %>%
tab_source_note(
source_note = md("Autor: Grupo 3")
) %>%
tab_options(
table.border.top.color = "black",
table.border.bottom.color = "black",
table.border.top.style = "solid",
table.border.bottom.style = "solid",
column_labels.border.top.color = "black",
column_labels.border.bottom.color = "black",
column_labels.border.bottom.width = px(2),
row.striping.include_table_body = TRUE,
heading.border.bottom.color = "black",
heading.border.bottom.width = px(2),
table_body.hlines.color = "gray",
table_body.border.bottom.color = "black"
)
| Tabla Nro. 4 |
| Tabla Simplificada de distribución de la Temperatura del Suelo |
| Lim inf |
Lim sup |
MC |
ni |
hi(%) |
Ni asc |
Ni desc |
Hi asc(%) |
Hi desc(%) |
| 10 |
15 |
12.5 |
448 |
14.93 |
448 |
3000 |
14.93 |
100 |
| 15 |
20 |
17.5 |
451 |
15.03 |
899 |
2552 |
29.97 |
85.07 |
| 20 |
25 |
22.5 |
429 |
14.3 |
1328 |
2101 |
44.27 |
70.03 |
| 25 |
30 |
27.5 |
417 |
13.9 |
1745 |
1672 |
58.17 |
55.73 |
| 30 |
35 |
32.5 |
428 |
14.27 |
2173 |
1255 |
72.43 |
41.83 |
| 35 |
40 |
37.5 |
414 |
13.8 |
2587 |
827 |
86.23 |
27.57 |
| 40 |
45 |
42.5 |
413 |
13.77 |
3000 |
413 |
100 |
13.77 |
| TOTAL |
- |
- |
3000 |
100 |
- |
- |
- |
- |
| Autor: Grupo 3 |
#Gráficas
hist(Temperatura, breaks = 10,
main = "Gráfica N°18 Distribución para la Temperatura del suelo ",
xlab = "Temperatura °C",
ylab = "Cantidad",
ylim = c(0,max(ni)),
col = "yellow",
cex.main = 0.9,
cex.lab = 1,
cex.axis = 0.9,
xaxt = "n")
axis(1, at = Hist_Temperatura$breaks,
labels = Hist_Temperatura$breaks, las = 1,
cex.axis = 0.9)
hist(Temperatura, breaks = 10,
main = "Gráfica N°19: Distribución de la Temperatura (°C) del Suelo",
xlab = "Temperatura °C",
ylab = "Cantidad",
ylim = c(0, length(Temperatura)),
col = "green",
cex.main = 0.9,
cex.lab = 1,
cex.axis = 0.9,
xaxt = "n")
axis(1, at = Hist_Temperatura$breaks,
labels = Hist_Temperatura$breaks, las = 1,
cex.axis = 0.9)
TDF_Temperatura$hi <- as.numeric(TDF_Temperatura$hi)
datos_grafico <- subset(TDF_Temperatura, !(MC %in% c("-", "TOTAL")))
barplot(datos_grafico$hi,
space = 0,
col = "blue",
main = "Gráfica N°20: Distribución porcentual de la Temperatura del suelo",
xlab = "Temperatura °C",
ylab = "Porcentaje (%)",
names.arg = datos_grafico$MC,
ylim = c(0, 20))
barplot(datos_grafico$hi,
space = 0,
col = "skyblue",
main = "Gráfica N°21: Distribución porcentual de la Temperatura del suelo",
xlab = "Temperatura °C",
ylab = "Porcentaje (%)",
names.arg = datos_grafico$MC,
ylim = c(0, 100))
# Boxplot
boxplot(
Temperatura_out,
horizontal = TRUE,
col = "pink",
main = "Gráfica Nº22: Distribución de la Temperatura",
xlab = "pH",
outline = TRUE,
pch = 19
)
# Ojivas
plot(
Li, Ni_desc,
main = "Gráfica Nº23: Distribución Ascendente y Descendente de la Temperatura",
xlab = "Temperatura (°C)",
ylab = "Cantidad",
xlim = c(0, 100),
col = "red",
type = "o",
lwd = 3
)
lines(
Ls, Ni_asc,
col = "green",
type = "o",
lwd = 3
)
# Ojiva Porcentual
plot(
Li, Hi_desc,
main = "Gráfica Nº24: Distribución Ascendente y Descendente de la Temperatura",
xlab = "Temperatura (°C)",
ylab = "Porcentaje (%)",
xlim = c(0, 100),
col = "red",
type = "o",
lwd = 2
)
lines(
Ls, Hi_asc,
col = "blue",
type = "o",
lwd = 3
)
# INDICADORES ESTADISTICOS
# Indicadores de Tendencia Central
# Media aritmética
media <- round(mean(Temperatura), 0)
media
## [1] 27
# Moda
# Moda
max_frecuencia <- max(TDF_Temperatura$ni)
moda <- TDF_Temperatura$MC[TDF_Temperatura$ni == max_frecuencia]
moda
## [1] "17.5"
# Mediana
mediana <- median(Temperatura)
mediana
## [1] 27
# INDICADORES DE DISPERSIÓN #
# Desviación Estándar
# Varianza
varianza <- var(Temperatura)
varianza
## [1] 101.6987
sd <- sd(Temperatura)
sd
## [1] 10.08458
# Coeficiente de Variación
cv <- round((sd / media) * 100, 2)
cv
## [1] 37.35
# INDICADORES DE FORMA #
# Coeficiente deAsimetría
library("e1071")
asimetria <- skewness(Temperatura, type = 2)
asimetria
## [1] 0.03241807
#Curtosis
curtosis <- kurtosis(Temperatura)
curtosis
## [1] -1.200746
# TABLA RESUMEN FINAL
tabla_indicadores <- data.frame(
"Variable" = c("Temperatura"),
"Rango" = c(paste0("[", min(Temperatura), " ; ", max(Temperatura), "]")),
"X" = c(round(media, 0)),
"Me" = c(round(mediana, 0)),
"Mo" = c(paste(moda, collapse = ", ")),
"V" = c(round(varianza,2)),
"Sd" = c(round(sd, 0)),
"Cv" = c(cv),
"As" = c(round(asimetria, 2)),
"K" = c(round(curtosis, 2)),
"Valores Atípicos" = "-"
)
library(gt)
tabla_indicadores_gt <- tabla_indicadores %>%
gt() %>%
tab_header(
title = md("Tabla N°18.1"),
subtitle = md("*Indicadores estadísticos de la variable Temperatura*")
) %>%
tab_source_note(
source_note = md("Autor: Grupo 3")
) %>%
tab_options(
table.border.top.color = "black",
table.border.bottom.color = "black",
table.border.top.style = "solid",
table.border.bottom.style = "solid",
column_labels.border.top.color = "black",
column_labels.border.bottom.color = "black",
table_body.hlines.color = "gray",
table_body.border.bottom.color = "black",
row.striping.include_table_body = TRUE,
heading.border.bottom.color = "black"
) %>%
tab_style(
style = cell_text(weight = "bold"),
locations = cells_body(
rows = Variable == "Temperatura"
)
)
tabla_indicadores_gt
| Tabla N°18.1 |
| Indicadores estadísticos de la variable Temperatura |
| Variable |
Rango |
X |
Me |
Mo |
V |
Sd |
Cv |
As |
K |
Valores.Atípicos |
| Temperatura |
[10 ; 45] |
27 |
27 |
17.5 |
101.7 |
10 |
37.35 |
0.03 |
-1.2 |
- |
| Autor: Grupo 3 |