ANÁLISIS ESTADÍSTICO SOBRE LA CALIDAD DE AIRE EN LA INDIA
UNIVERSIDAD CENTRAL DEL ECUADOR
PROYECTO:ANÁLISIS ESTADÍSTICO SOBRE LA CALIDAD DE AIRE EN LA INDIA
FECHA: 22/11/2025
# ==============================================================================
# 1. CARGA DE PAQUETES Y DATOS
# ==============================================================================
# Cargar librerías necesarias
library(gt)
library(dplyr)
# Carga de librería para Asimetría y Curtosis
# install.packages("e1071")
library(e1071)
# Carga de datos
# El archivo ya está cargado en el entorno
datos <- read.csv("C:/Users/WILLIAM/Pictures/overleaf/Datos Cambiados.csv",
header = TRUE,
sep = ",",
dec = ".")
# ==============================================================================
# 2. PREPARACIÓN Y LIMPIEZA DE DATOS DE PARTÍCULAS PM10
# ==============================================================================
# Extracción de los "-" (valores inexistentes) de la variable PM10
# NOTA: Asumimos que la columna se llama 'PM10'
pm10 <- datos$PM10[datos$PM10 != "-"]
# Tamaño muestral después de la limpieza
cat("Tamaño muestral de PM10 (sin '-'):", length(pm10), "\n")## Tamaño muestral de PM10 (sin '-'): 18391# Conversión a numérico
pm10 <- as.numeric(pm10)
# ==============================================================================
# 3. CÁLCULOS PARA LA DISTRIBUCIÓN DE FRECUENCIAS DETALLADA (34 CLASES) - PM10
# ==============================================================================
N_pm10 <- length(pm10)
min_pm10 <- min(pm10)
max_pm10 <- max(pm10)
R_pm10 <- max_pm10 - min_pm10
# Número de clases (k): Se mantienen 34 clases
k_detallado_pm10 <- 34
# Amplitud de clase (A)
A_pm10 <- R_pm10 / k_detallado_pm10
# Generación de límites de intervalos
Li_pm10 <- seq(from = min_pm10, to = max_pm10 - A_pm10, by = A_pm10)
Ls_pm10 <- c(seq(from = min_pm10 + A_pm10, to = max_pm10 - A_pm10, by = A_pm10), max_pm10)
# Redondeo para cálculos de intervalos precisos
pm10 <- round(pm10, 3)
Li_pm10 <- round(Li_pm10, 3)
Ls_pm10 <- round(Ls_pm10, 3)
# Marcas de Clase (MC)
MC_pm10 <- (Li_pm10 + Ls_pm10) / 2
# Creación de frecuencias absolutas (ni)
ni_pm10 <- numeric(length(Li_pm10))
for (i in 1:length(Li_pm10)) {
if (i < length(Li_pm10)) {
# Intervalo abierto por la derecha: [Li, Ls)
ni_pm10[i] <- sum(pm10 >= Li_pm10[i] & pm10 < Ls_pm10[i])
} else {
# Último intervalo cerrado: [Li, Ls]
ni_pm10[i] <- sum(pm10 >= Li_pm10[i] & pm10 <= Ls_pm10[i])
}
}
# Frecuencias relativas y acumuladas
hi_pm10 <- (ni_pm10 / N_pm10) * 100
Ni_asc_pm10 <- cumsum(ni_pm10)
Ni_desc_pm10 <- rev(cumsum(rev(ni_pm10)))
Hi_asc_pm10 <- cumsum(hi_pm10)
Hi_desc_pm10 <- rev(cumsum(rev(hi_pm10)))
# Formatear la columna Intervalo
Intervalo_pm10 <- paste0("[", round(Li_pm10, 2), " - ", round(Ls_pm10, 2), ")")
# Corregir el último intervalo para que sea cerrado
Intervalo_pm10[length(Intervalo_pm10)] <- paste0("[", round(Li_pm10[length(Li_pm10)], 2), " - ",
round(Ls_pm10[length(Ls_pm10)], 2), "]")
# Crear el Data Frame (TDF)
TDF_pm10 <- data.frame(
Intervalo = Intervalo_pm10,
MC = round(MC_pm10, 2),
ni = ni_pm10,
hi = round(hi_pm10, 2),
Ni_ascendente = Ni_asc_pm10,
Ni_descendente = Ni_desc_pm10,
Hi_ascendente = round(Hi_asc_pm10, 2),
Hi_descendente = round(Hi_desc_pm10, 2)
)
# Agregar la fila de totales
totales_pm10 <- data.frame(
Intervalo = "Totales",
MC = "-",
ni = sum(ni_pm10),
hi = sum(hi_pm10),
Ni_ascendente = "-",
Ni_descendente = "-",
Hi_ascendente = "-",
Hi_descendente = "-"
)
TDF_pm10_completa <- rbind(TDF_pm10, totales_pm10)
# ==============================================================================
# 4. TABLA DE FRECUENCIAS DETALLADA (Tabla Nro. 1)
# ==============================================================================
TDF_pm10_completa %>%
gt() %>%
tab_header(
title = "Tabla Nro. 1",
subtitle = "Distribución de frecuencia de concentración de Partículas PM₁₀, estudio calidad del aire en India entre 2015-2020"
) %>%
tab_source_note(
source_note = "Autor: Grupo 2\n Fuente: https://www.kaggle.com/datasets/rohanrao/air-quality-data-in-india"
) %>%
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. 1 | |||||||
| Distribución de frecuencia de concentración de Partículas PM₁₀, estudio calidad del aire en India entre 2015-2020 | |||||||
| Intervalo | MC | ni | hi | Ni_ascendente | Ni_descendente | Hi_ascendente | Hi_descendente |
|---|---|---|---|---|---|---|---|
| [0.01 - 29.42) | 14.72 | 1239 | 6.74 | 1239 | 18391 | 6.74 | 100 |
| [29.42 - 58.83) | 44.13 | 3672 | 19.97 | 4911 | 17152 | 26.7 | 93.26 |
| [58.83 - 88.24) | 73.54 | 3468 | 18.86 | 8379 | 13480 | 45.56 | 73.3 |
| [88.24 - 117.66) | 102.95 | 3166 | 17.21 | 11545 | 10012 | 62.78 | 54.44 |
| [117.66 - 147.07) | 132.36 | 2098 | 11.41 | 13643 | 6846 | 74.18 | 37.22 |
| [147.07 - 176.48) | 161.77 | 1458 | 7.93 | 15101 | 4748 | 82.11 | 25.82 |
| [176.48 - 205.89) | 191.18 | 930 | 5.06 | 16031 | 3290 | 87.17 | 17.89 |
| [205.89 - 235.3) | 220.6 | 588 | 3.20 | 16619 | 2360 | 90.36 | 12.83 |
| [235.3 - 264.71) | 250.01 | 427 | 2.32 | 17046 | 1772 | 92.69 | 9.64 |
| [264.71 - 294.12) | 279.42 | 336 | 1.83 | 17382 | 1345 | 94.51 | 7.31 |
| [294.12 - 323.54) | 308.83 | 241 | 1.31 | 17623 | 1009 | 95.82 | 5.49 |
| [323.54 - 352.95) | 338.24 | 214 | 1.16 | 17837 | 768 | 96.99 | 4.18 |
| [352.95 - 382.36) | 367.65 | 161 | 0.88 | 17998 | 554 | 97.86 | 3.01 |
| [382.36 - 411.77) | 397.06 | 120 | 0.65 | 18118 | 393 | 98.52 | 2.14 |
| [411.77 - 441.18) | 426.48 | 81 | 0.44 | 18199 | 273 | 98.96 | 1.48 |
| [441.18 - 470.59) | 455.89 | 50 | 0.27 | 18249 | 192 | 99.23 | 1.04 |
| [470.59 - 500) | 485.3 | 52 | 0.28 | 18301 | 142 | 99.51 | 0.77 |
| [500 - 529.42) | 514.71 | 33 | 0.18 | 18334 | 90 | 99.69 | 0.49 |
| [529.42 - 558.83) | 544.12 | 14 | 0.08 | 18348 | 57 | 99.77 | 0.31 |
| [558.83 - 588.24) | 573.53 | 11 | 0.06 | 18359 | 43 | 99.83 | 0.23 |
| [588.24 - 617.65) | 602.94 | 8 | 0.04 | 18367 | 32 | 99.87 | 0.17 |
| [617.65 - 647.06) | 632.36 | 5 | 0.03 | 18372 | 24 | 99.9 | 0.13 |
| [647.06 - 676.47) | 661.77 | 4 | 0.02 | 18376 | 19 | 99.92 | 0.1 |
| [676.47 - 705.88) | 691.18 | 1 | 0.01 | 18377 | 15 | 99.92 | 0.08 |
| [705.88 - 735.3) | 720.59 | 2 | 0.01 | 18379 | 14 | 99.93 | 0.08 |
| [735.3 - 764.71) | 750 | 4 | 0.02 | 18383 | 12 | 99.96 | 0.07 |
| [764.71 - 794.12) | 779.41 | 1 | 0.01 | 18384 | 8 | 99.96 | 0.04 |
| [794.12 - 823.53) | 808.83 | 2 | 0.01 | 18386 | 7 | 99.97 | 0.04 |
| [823.53 - 852.94) | 838.24 | 1 | 0.01 | 18387 | 5 | 99.98 | 0.03 |
| [852.94 - 882.35) | 867.65 | 0 | 0.00 | 18387 | 4 | 99.98 | 0.02 |
| [882.35 - 911.77) | 897.06 | 0 | 0.00 | 18387 | 4 | 99.98 | 0.02 |
| [911.77 - 941.18) | 926.47 | 1 | 0.01 | 18388 | 4 | 99.98 | 0.02 |
| [941.18 - 970.59) | 955.88 | 0 | 0.00 | 18388 | 3 | 99.98 | 0.02 |
| [970.59 - 1000] | 985.29 | 3 | 0.02 | 18391 | 3 | 100 | 0.02 |
| Totales | - | 18391 | 100.00 | - | - | - | - |
| Autor: Grupo 2 Fuente: https://www.kaggle.com/datasets/rohanrao/air-quality-data-in-india | |||||||
# ==============================================================================
# 5. CÁLCULOS PARA LA DISTRIBUCIÓN SIMPLIFICADA (13 CLASES) - PM10
# ==============================================================================
# Se utiliza la función hist() para obtener los intervalos simplificados
Histograma_pm10 <- hist(pm10, breaks = 13, plot = FALSE) # No mostrar la gráfica aún
# Extraer elementos simplificados
Lis_pm10 <- Histograma_pm10$breaks[1:(length(Histograma_pm10$breaks) - 1)]
Lss_pm10 <- Histograma_pm10$breaks[2:length(Histograma_pm10$breaks)]
MCs_pm10 <- (Lis_pm10 + Lss_pm10) / 2
nis_pm10 <- Histograma_pm10$counts
# Frecuencias relativas y acumuladas simplificadas
his_pm10 <- (nis_pm10 / N_pm10) * 100
Nis_asc_pm10 <- cumsum(nis_pm10)
His_asc_pm10 <- cumsum(his_pm10)
Nis_desc_pm10 <- rev(cumsum(rev(nis_pm10)))
His_desc_pm10 <- rev(cumsum(rev(his_pm10)))
# Crear el Data Frame Simplificado
TDF_pm10simplificado <- data.frame(
Intervalo = paste0("[", round(Lis_pm10, 2), " - ", round(Lss_pm10, 2), ")"),
MC = round(MCs_pm10, 2),
ni = nis_pm10,
hi = round(his_pm10, 2),
Ni_asc = Nis_asc_pm10,
Hi_asc = round(His_asc_pm10, 2),
Ni_desc = Nis_desc_pm10,
Hi_desc = round(His_desc_pm10, 2)
)
# Renombrar columnas con los nombres finales (usando comillas invertidas para % en R)
colnames(TDF_pm10simplificado) <- c("Intervalo", "MC", "ni", "hi(%)",
"Ni_asc", "Hi_asc (%)", "Ni_desc", "Hi_desc (%)")
# Agregar la fila de totales
totaless_pm10 <- data.frame(
Intervalo = "Totales",
MC = "-",
ni = sum(nis_pm10),
`hi(%)` = sum(his_pm10),
Ni_asc = "-",
`Hi_asc (%)` = "-",
Ni_desc = "-",
`Hi_desc (%)` = "-"
)
# Asegurar que las columnas de totaless coincidan con los nombres finales
colnames(totaless_pm10) <- colnames(TDF_pm10simplificado)
# Unir los data frames
TDF_pm10simplificado_completa <- rbind(TDF_pm10simplificado, totaless_pm10)
# ==============================================================================
# 6. TABLA DE FRECUENCIAS SIMPLIFICADA (Tabla Nro. 2)
# ==============================================================================
TDF_pm10simplificado_completa %>%
gt() %>%
tab_header(
title = "Tabla Nro. 2",
subtitle = "Distribución de frecuencia simplificada de concentración de Partículas PM₁₀, estudio calidad del aire en India entre 2015-2020"
) %>%
tab_source_note(
source_note = "Autor: Grupo 2\n Fuente: https://www.kaggle.com/datasets/rohanrao/air-quality-data-in-india"
) %>%
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. 2 | |||||||
| Distribución de frecuencia simplificada de concentración de Partículas PM₁₀, estudio calidad del aire en India entre 2015-2020 | |||||||
| Intervalo | MC | ni | hi(%) | Ni_asc | Hi_asc (%) | Ni_desc | Hi_desc (%) |
|---|---|---|---|---|---|---|---|
| [0 - 100) | 50 | 9704 | 52.76 | 9704 | 52.76 | 18391 | 100 |
| [100 - 200) | 150 | 6172 | 33.56 | 15876 | 86.32 | 8687 | 47.24 |
| [200 - 300) | 250 | 1571 | 8.54 | 17447 | 94.87 | 2515 | 13.68 |
| [300 - 400) | 350 | 633 | 3.44 | 18080 | 98.31 | 944 | 5.13 |
| [400 - 500) | 450 | 221 | 1.20 | 18301 | 99.51 | 311 | 1.69 |
| [500 - 600) | 550 | 62 | 0.34 | 18363 | 99.85 | 90 | 0.49 |
| [600 - 700) | 650 | 14 | 0.08 | 18377 | 99.92 | 28 | 0.15 |
| [700 - 800) | 750 | 8 | 0.04 | 18385 | 99.97 | 14 | 0.08 |
| [800 - 900) | 850 | 2 | 0.01 | 18387 | 99.98 | 6 | 0.03 |
| [900 - 1000) | 950 | 4 | 0.02 | 18391 | 100 | 4 | 0.02 |
| Totales | - | 18391 | 100.00 | - | - | - | - |
| Autor: Grupo 2 Fuente: https://www.kaggle.com/datasets/rohanrao/air-quality-data-in-india | |||||||
# ==============================================================================
# 7. GENERACIÓN DE GRÁFICOS (PM10)
# ==============================================================================
# ==============================================================================
# 7. GRÁFICA N°1: Histograma Local (PM10)
# ==============================================================================
hist(pm10, breaks = 13,
main = "Gr\u00E1fica N\u00B01: Distribuci\u00F3n de la Concentraci\u00F3n de Partículas PM₁₀\npresente en el estudio sobre calidad del aire en India entre 2015-2020",
xlab = "PM₁₀ (\u00B5g/m\u00B3)",
ylab = "Cantidad",
# max(nis_pm10) es la altura máxima para el histograma 'local'
ylim = c(0, max(nis_pm10)),
col = "darkseagreen3", # Nuevo color
cex.main = 0.9,
cex.lab = 1,
cex.axis = 0.9,
xaxt = "n")
axis(1, at = Histograma_pm10$breaks,
labels = round(Histograma_pm10$breaks, 0), las = 1,
cex.axis = 0.9)
# ----------------------------------
# Gráfica N°2: Histograma Global (Frecuencia Absoluta) - PM10
# ----------------------------------
hist(pm10, breaks = 13,
main = "Gr\u00E1fica N\u00B02: Distribuci\u00F3n de la Concentraci\u00F3n de Partículas PM₁₀\npresente en el estudio sobre calidad del aire en India entre 2015-2020",
xlab = "PM₁₀ (\u00B5g/m\u00B3)",
ylab = "Cantidad",
# length(pm10) es la altura máxima
ylim = c(0, length(pm10)),
col = "darkseagreen",
cex.main = 1,
cex.lab = 1,
cex.axis = 0.9,
xaxt = "n")
axis(1, at = Histograma_pm10$breaks,
labels = round(Histograma_pm10$breaks, 0), las = 1,
cex.axis = 0.9)
# ------------------------------------------------------------------------------
# Gráfica N°3: Histograma Porcentual Global (PM10)
# ------------------------------------------------------------------------------
# Para esta gráfica, usaremos el 'hi(%)' de la tabla simplificada.
porcentajes_pm10 <- TDF_pm10simplificado$`hi(%)`[1:(nrow(TDF_pm10simplificado)-1)]
marcas_clase_pm10 <- TDF_pm10simplificado$MC[1:(nrow(TDF_pm10simplificado)-1)]
post_pm10 <- barplot(porcentajes_pm10,
space = 0,
col = "skyblue",
main = "Gr\u00E1fica N\u00B03: Distribuci\u00F3n Porcentual Global de PM₁₀\nEstudio Calidad del Aire en India, 2015-2020",
xlab = "PM₁₀ (\u00B5g/m\u00B3)",
ylab = "Porcentaje (%)",
ylim = c(0, 100),
cex.main = 0.9,
cex.lab = 1,
xaxt = "n",
yaxt = "n")
# Dibujamos las etiquetas del Eje X (Marca de Clase) rotadas y pequeñas
axis(side = 1,
at = post_pm10,
labels = marcas_clase_pm10,
tck = -0.02,
las = 2,
cex.axis = 0.6)
# Dibujamos las marcas del Eje Y de forma explícita
axis(side = 2,
at = seq(0, 100, by = 20),
las = 1,
cex.axis = 0.9)
# ------------------------------------------------------------------------------
# Gráfica N°4: Histograma Porcentual Local (PM10)
# ------------------------------------------------------------------------------
n_pm10_sim <- as.numeric(nrow(TDF_pm10simplificado))
porcentajes_pm10_local <- TDF_pm10simplificado$`hi(%)`[1:(n_pm10_sim-1)]
marcas_clase_pm10_local <- TDF_pm10simplificado$MC[1:(n_pm10_sim-1)]
pos_pm10 <- barplot(
porcentajes_pm10_local,
space = 0,
main = "Gr\u00E1fica N\u00B04: Distribuci\u00F3n Porcentual de Concentraci\u00F3n de Partículas PM₁₀\nEstudio Calidad del Aire en India, 2015-2020",
ylab = "Porcentaje (%)",
xlab = "PM₁₀ (\u00B5g/m\u00B3)",
# Ajuste de Y para que la barra más alta sobresalga ligeramente si es > 80
ylim = c(0, max(porcentajes_pm10_local) * 1.1),
col = "darkseagreen",
cex.main = 0.9,
cex.lab = 1,
# Ocultamos etiquetas automáticas para control manual
xaxt = "n",
yaxt = "n"
)
# Dibujamos las etiquetas del Eje X (Marca de Clase)
axis(side = 1,
at = pos_pm10,
labels = marcas_clase_pm10_local,
tck = -0.04,
las = 2,
cex.axis = 0.6)
# Dibujamos las marcas del Eje Y
axis(side = 2,
at = seq(0, round(max(porcentajes_pm10_local) * 1.1), by = 20),
las = 1,
cex.axis = 0.9)
# ------------------------------------------------------------------------------
# Gráfica N°5: Diagrama de Caja (Box Plot) para PM10
# ------------------------------------------------------------------------------
CajaPM10 <- boxplot(pm10,
horizontal = T,
col = "turquoise",
border = "black",
main = "Gr\u00E1fica N\u00B05: Distribuci\u00F3n de la concentraci\u00F3n de Partículas PM₁₀,\nestudio calidad del aire en India desde 2015-2020",
xlab = "PM₁₀ (\u00B5g/m\u00B3)",
cex.main = 0.9,
cex.lab = 1)
# ------------------------------------------------------------------------------
# Gráfica N°6: Ojiva Ascendente y Descendente (Cantidad) - PM10
# ------------------------------------------------------------------------------
# 1. Definir los límites de clase extendidos (añadiendo el punto cero)
Limites_X_pm10 <- c(Lis_pm10[1], Lss_pm10)
# 2. Definir frecuencias acumuladas extendidas (Cantidad)
Frec_Asc_Ext_pm10 <- c(0, Nis_asc_pm10)
Frec_Desc_Ext_pm10 <- c(Nis_desc_pm10, 0)
# Ojiva ascendente
plot(Limites_X_pm10, Frec_Asc_Ext_pm10,
type = "b",
main = "Gr\u00E1fica N\u00B06: Ojiva ascendente y descendente de la
distribuci\u00F3n de la concentraci\u00F3n de Partículas PM₁₀",
xlab = "PM₁₀ (\u00B5g/m\u00B3)",
ylab = "Cantidad",
pch = 19,
col = "turquoise",
ylim = c(0, N_pm10),
xlim = c(0, max(Lss_pm10)),
cex.main = 0.9,
cex.lab = 1,
cex.axis = 0.9
)
# Ojiva descendente
lines(Limites_X_pm10, Frec_Desc_Ext_pm10,
type = "b",
col = "black",
pch = 19)
# ------------------------------------------------------------------------------
# Gráfica N°7: Ojiva Ascendente y Descendente PORCENTUAL (PM10)
# ------------------------------------------------------------------------------
# 1. Definir los límites de clase extendidos
Limites_X_pm10 <- c(Lis_pm10[1], Lss_pm10)
# 2. Definir frecuencias PORCENTUALES acumuladas extendidas
Frec_H_Asc_Ext_pm10 <- c(0, His_asc_pm10)
Frec_H_Desc_Ext_pm10 <- c(His_desc_pm10, 0)
# Ojiva ascendente
plot(Limites_X_pm10, Frec_H_Asc_Ext_pm10,
type = "b",
main = "Gr\u00E1fica N\u00B07: Ojiva ascendente y descendente de la distribuci\u00F3n PORCENTUAL de Partículas PM₁₀",
xlab = "PM₁₀ (\u00B5g/m\u00B3)",
ylab = "Porcentaje (%)",
pch = 19,
col = "blue",
ylim = c(0, 100),
xlim = c(0, max(Lss_pm10)),
cex.main = 0.9,
cex.lab = 1,
cex.axis = 0.9
)
# Ojiva descendente
lines(Limites_X_pm10, Frec_H_Desc_Ext_pm10,
type = "b",
col = "red",
pch = 19)
# Opcional: Añadir leyenda para claridad
legend("topright",
legend = c("Ojiva Ascendente", "Ojiva Descendente"),
col = c("blue", "red"),
pch = 19,
bty = "n")
# ==============================================================================
# 8. CÁLCULO DE INDICADORES ESTADÍSTICOS (PM10)
# ==============================================================================
# --------------------------------
# Indicadores de Tendencia Central
# --------------------------------
# Mediana (Me)
Me_pm10 <- median(pm10)
# Media (X)
X_pm10 <- mean(pm10)
# Moda (Mo)
moda_index_pm10 <- which.max(TDF_pm10simplificado$ni[1:(nrow(TDF_pm10simplificado)-1)])
Mo_pm10 <- TDF_pm10simplificado$Intervalo[moda_index_pm10]
# --------------------------------
# Indicadores de Dispersión
# --------------------------------
# Varianza
Var_pm10 <- var(pm10)
# Desviación estándar (sd)
desv_pm10 <- sd(pm10)
# Coeficiente de variación (CV)
CV_pm10 <- (desv_pm10 / X_pm10) * 100
# --------------------------------
# Indicadores de Forma
# --------------------------------
# Coeficiente de Asimetría (As)
As_pm10 <- skewness(pm10)
# Curtosis (K)
K_pm10 <- kurtosis(pm10)
# --------------------------------
# Creación del Data Frame (Tabla_indicadores_PM10)
# --------------------------------
Variable_PM10 <- "Partículas PM₁₀"
Rango_PM10 <- paste0("[", round(min_pm10, 2), " - ", round(max_pm10, 2), "]")
Tabla_indicadores_PM10 <- data.frame(
Variable = Variable_PM10,
Rango = Rango_PM10,
X = round(X_pm10, 3),
Me = round(Me_pm10, 3),
Mo = Mo_pm10,
sd = round(desv_pm10, 2),
CV = round(CV_pm10, 2),
As = round(As_pm10, 2),
K = round(K_pm10, 2)
)
# Renombrar columnas para la tabla
colnames(Tabla_indicadores_PM10) <- c("Variable", "Rango", "Media (X)", "Mediana (Me)", "Moda (Mo)", "Desv. Est. (sd)", "CV (%)", "Asimetría (As)", "Curtosis (K)")
# ==============================================================================
# 9. TABLA DE INDICADORES ESTADÍSTICOS (Tabla Nro. 3) - Usando GT
# ==============================================================================
Tabla_indicadores_PM10 %>%
gt() %>%
tab_header(
title = md("Tabla Nro. 3"),
subtitle = md("*Indicadores Estadísticos de concentración de Partículas PM₁₀, estudio calidad del aire en India entre 2015-2020 *")
) %>%
tab_source_note(
source_note = md("Autor: Grupo 2\n Fuente:https://www.kaggle.com/datasets/rohanrao/air-quality-data-in-india")
) %>%
# Agrupamos las columnas por categoría
tab_spanner(
label = "Tendencia Central",
columns = c("Media (X)", "Mediana (Me)", "Moda (Mo)")
) %>%
tab_spanner(
label = "Dispersión",
columns = c("Desv. Est. (sd)", "CV (%)")
) %>%
tab_spanner(
label = "Forma",
columns = c("Asimetría (As)", "Curtosis (K)")
) %>%
# Formateo de números
fmt_number(
columns = c("Media (X)", "Mediana (Me)", "Desv. Est. (sd)", "CV (%)", "Asimetría (As)", "Curtosis (K)"),
decimals = 2
) %>%
# Opciones de estilo
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 | ||||||||
| *Indicadores Estadísticos de concentración de Partículas PM₁₀, estudio calidad del aire en India entre 2015-2020 * | ||||||||
| Variable | Rango |
Tendencia Central
|
Dispersión
|
Forma
|
||||
|---|---|---|---|---|---|---|---|---|
| Media (X) | Mediana (Me) | Moda (Mo) | Desv. Est. (sd) | CV (%) | Asimetría (As) | Curtosis (K) | ||
| Partículas PM₁₀ | [0.01 - 1000] | 118.13 | 95.68 | [0 - 100) | 90.61 | 76.70 | 2.05 | 6.74 |
| Autor: Grupo 2 Fuente:https://www.kaggle.com/datasets/rohanrao/air-quality-data-in-india | ||||||||