FECHA: 21/11/2025
#Estadística Descriptiva
#Ariana Viteri
#20/11/2025
library(gt)
library(dplyr)
library(RColorBrewer)
#Cargar los datos
datos <- read.csv("~/ariana tercer semestre/Estadistica/city_day.csv",
header = TRUE, dec = ".", sep = ",")
# ================================
# ORDENAR AQI_Bucket COMO VARIABLE ORDINARIA
# ================================
# ORDEN de jerarquía (del mejor al peor)
datos$AQI_Bucket <- factor(
datos$AQI_Bucket,
levels = c("Good", "Satisfactory", "Moderate",
"Poor", "Very Poor", "Severe","-"),
ordered = TRUE
)
# ================================
# TABLAS CUALITATIVAS NOMINALES
# ================================
AQI_Bucket <- datos$AQI_Bucket
#Tabla de distribución de frecuencia
TDF_AQI_Bucket <- data.frame(table(AQI_Bucket))
ni <- TDF_AQI_Bucket$Freq
hi <- round((ni / sum(ni)) * 100, 2)
AQI_Bucket <- TDF_AQI_Bucket$AQI_Bucket
TDF_AQI_Bucket <- data.frame(AQI_Bucket, ni, hi)
Summary <- data.frame(AQI_Bucket = "TOTAL", ni = sum(ni), hi = 100)
TDF_AQI_Bucket_suma <- rbind(TDF_AQI_Bucket, Summary)
colnames(TDF_AQI_Bucket_suma) <- c("AQI_Nivel", "ni", "hi(%)")
# ================================
# TABLA GT
# ================================
TDF_AQI_Bucket_suma %>%
gt() %>%
tab_header(
title = md("Tabla Nro. 5"),
subtitle = md("Tabla de distribución de frecuencias del nivel de contaminación")
) %>%
tab_source_note(
source_note = md("Fuente: Datos procesados por el autor a partir de archivo city.day.csv")
) %>%
tab_style(
style = cell_borders(sides = "left", color = "black", weight = px(2)),
locations = cells_body()
) %>%
tab_style(
style = cell_borders(sides = "right", color = "black", weight = px(2)),
locations = cells_body()
) %>%
tab_style(
style = cell_borders(sides = "left", color = "black", weight = px(2)),
locations = cells_column_labels()
) %>%
tab_style(
style = cell_borders(sides = "right", color = "black", weight = px(2)),
locations = cells_column_labels()
) %>%
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. 5 |
| Tabla de distribución de frecuencias del nivel de contaminación |
| AQI_Nivel |
ni |
hi(%) |
| Good |
1341 |
4.54 |
| Satisfactory |
8224 |
27.85 |
| Moderate |
8829 |
29.90 |
| Poor |
2781 |
9.42 |
| Very Poor |
2337 |
7.91 |
| Severe |
1338 |
4.53 |
| - |
4681 |
15.85 |
| TOTAL |
29531 |
100.00 |
| Fuente: Datos procesados por el autor a partir de archivo city.day.csv |
#DIAGRAMAS
# ================================
# GDF 1
TDF_AQI_Bucket$Zona <- iconv(TDF_AQI_Bucket$AQI_Bucket, from = "latin1", to = "UTF-8", sub = "")
library(RColorBrewer)
n <- length(TDF_AQI_Bucket$AQI_Bucket)
colores <- brewer.pal(min(n, 15), "Set3")
color <- adjustcolor(colores, alpha.f = 0.9)
barplot(
height = TDF_AQI_Bucket$ni,
names.arg = TDF_AQI_Bucket$AQI_Bucket,
main = "Gráfica No. 1.1: Distribución de AQI_Bucket",
xlab = "",
ylab = "Cantidad",
col = heat.colors(length(TDF_AQI_Bucket$ni)),
las = 2,
cex.names = 0.7
)
mtext("AQI_Bucket", side = 1, line = 4, cex = 1)
# DIAGRAMA DE BARRAS
library(RColorBrewer)
n <- length(TDF_AQI_Bucket$AQI_Bucket)
colores <- brewer.pal(min(n, 15), "Set3")
color <- adjustcolor(colores, alpha.f = 0.9)
barplot(
TDF_AQI_Bucket$hi,
main = "Gráfica No 1.3: Distribución en categoria de AQI_Bucket",
xlab = "",
ylab = "Porcentaje (%)",
col = colores,
names.arg = TDF_AQI_Bucket$AQI_Bucket,
ylim = c(0, 30),
las = 2,
cex.names = 0.7
)
mtext("AQI_Bucket", side = 1, line = 4, cex = 1)
# DIAGRAMA DE BARRAS
colores <- c("yellow", "orange")
library(RColorBrewer)
n <- length(TDF_AQI_Bucket$AQI_Bucket)
colores <- brewer.pal(min(n, 15), "Set3")
color <- adjustcolor(colores, alpha.f = 0.9)
barplot(
TDF_AQI_Bucket$hi,
main = "Gráfica N°1.4: Distribución de AQI_Bucket",
xlab = "",
ylab = "Porcentaje (%)",
col = colores,
names.arg = TDF_AQI_Bucket$AQI_Bucket,
ylim = c(0, 100),
las = 2,
cex.names = 0.7
)
mtext("AQI_Bucket", side = 1, line = 3, cex = 1)
# DIAGRAMA CIRCULAR
# ================================
n <- length(TDF_AQI_Bucket$AQI_Bucket)
colores <- brewer.pal(min(n, 15), "Set3")
color <- adjustcolor(colores, alpha.f = 0.9)
etiqueta <- paste(hi, "%")
library(RColorBrewer)
n <- length(TDF_AQI_Bucket$AQI_Bucket)
colores <- brewer.pal(min(n, 15), "Set3")
color <- adjustcolor(colores, alpha.f = 0.9)
pie(
hi,
labels = etiqueta,
radius = 0.8,
col = color,
main = "Gráfica No.1.5: Calidad de aire con AQI_Bucket"
)
legend(
x = 1.1, y = 1.07,
legend = TDF_AQI_Bucket$AQI_Bucket,
title = "Leyenda",
fill = color,
cex = 0.65
)
