#==============================ENCABEZADO=======================================
# TEMA: ED Variables Cuantitativas - Vida Estimada (Estimated lifetime)
# AUTOR: GRUPO 4
# FECHA: 18-12-2025
#==============================CARGA DE DATOS===================================
options(encoding = "UTF-8")
library(gt)
library(dplyr)
##
## Adjuntando el paquete: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(e1071)
setwd("C:/Users/HP/Documents/PROYECTO ESTADISTICA/RStudio")
datos <- read.csv("tablap.csv", header = TRUE, dec = ",", sep = ";", fileEncoding = "UTF-8")
# Funcion Moda
get_mode <- function(v) {
uniqv <- unique(v)
uniqv[which.max(tabulate(match(v, uniqv)))]
}
#===============PROCESAMIENTO DE LA VARIABLE: ESTIMATED LIFETIME================
# Asegurarnos de que el nombre de la columna coincida con tu CSV
v_lifetime <- datos$Estimated.lifetime
# Creamos intervalos de clase
min_life <- min(v_lifetime, na.rm = TRUE)
max_life <- max(v_lifetime, na.rm = TRUE)
# Definimos el ancho del intervalo
ancho <- 5
start_val <- floor(min_life / ancho) * ancho
end_val <- ceiling(max_life / ancho) * ancho
breaks_life <- seq(start_val, end_val + ancho, by = ancho)
labels_life <- paste0("", breaks_life[1:(length(breaks_life)-1)], " - ", breaks_life[2:length(breaks_life)])
# =========================Agrupamos los datos==============================
life_categorizada <- cut(v_lifetime, breaks = breaks_life, labels = labels_life, right = FALSE)
TDF_life_base <- as.data.frame(table(life_categorizada))
names(TDF_life_base) <- c("Rango_Vida", "ni")
# Calculos de Frecuencias
hi_life <- (TDF_life_base$ni / sum(TDF_life_base$ni)) * 100
Niasc_life <- cumsum(TDF_life_base$ni)
Hiasc_life <- cumsum(hi_life)
Nidsc_life <- rev(cumsum(rev(TDF_life_base$ni)))
Hidsc_life <- rev(cumsum(rev(hi_life)))
#==============================TABLA DE DATOS===================================
Tabla_Life_Final <- data.frame(
N = 1:nrow(TDF_life_base),
Rango_Vida = as.character(TDF_life_base$Rango_Vida),
ni = TDF_life_base$ni,
hi = round(hi_life, 2),
Niasc = Niasc_life,
Hiasc = round(Hiasc_life, 2),
Nidsc = Nidsc_life,
Hidsc = round(Hidsc_life, 2)
)
# Fila Total
Fila_Total_Life <- data.frame(
N = NA, Rango_Vida = "TOTAL", ni = sum(Tabla_Life_Final$ni), hi = 100,
Niasc = NA, Hiasc = NA, Nidsc = NA, Hidsc = NA
)
TDF_Life_Completa <- rbind(Tabla_Life_Final, Fila_Total_Life)
#=====================TABLA PROFESIONAL (GT)====================================
tabla_gt_life <- TDF_Life_Completa %>%
gt() %>%
tab_header(
title = "DISTRIBUCION DE VIDA ESTIMADA ",
) %>%
cols_label(
N = "N", Rango_Vida = "Rangos", ni = "ni", hi = "hi",
Niasc = "Ni_asc", Hiasc = "Hi_asc",
Nidsc = "Ni_des", Hidsc = "Hi_des"
) %>%
sub_missing(columns = everything(), missing_text = "") %>%
tab_style(
style = list(cell_fill(color = "gray95"), cell_text(weight = "bold")),
locations = cells_body(rows = Rango_Vida == "TOTAL")
) %>%
cols_align(align = "center", columns = everything())
tabla_gt_life
| DISTRIBUCION DE VIDA ESTIMADA |
| N |
Rangos |
ni |
hi |
Ni_asc |
Hi_asc |
Ni_des |
Hi_des |
| 1 |
25 - 30 |
178 |
1.42 |
178 |
1.42 |
12561 |
100.00 |
| 2 |
30 - 35 |
0 |
0.00 |
178 |
1.42 |
12383 |
98.58 |
| 3 |
35 - 40 |
0 |
0.00 |
178 |
1.42 |
12383 |
98.58 |
| 4 |
40 - 45 |
0 |
0.00 |
178 |
1.42 |
12383 |
98.58 |
| 5 |
45 - 50 |
0 |
0.00 |
178 |
1.42 |
12383 |
98.58 |
| 6 |
50 - 55 |
10460 |
83.27 |
10638 |
84.69 |
12383 |
98.58 |
| 7 |
55 - 60 |
394 |
3.14 |
11032 |
87.83 |
1923 |
15.31 |
| 8 |
60 - 65 |
549 |
4.37 |
11581 |
92.20 |
1529 |
12.17 |
| 9 |
65 - 70 |
699 |
5.56 |
12280 |
97.76 |
980 |
7.80 |
| 10 |
70 - 75 |
281 |
2.24 |
12561 |
100.00 |
281 |
2.24 |
| 11 |
75 - 80 |
0 |
0.00 |
12561 |
100.00 |
0 |
0.00 |
|
TOTAL |
12561 |
100.00 |
|
|
|
|
#===============================GRAFICO DE BARRAS==============================
par(mar = c(8, 4, 4, 2) + 0.1)
# BARRAS ABSOLUTA LOCAL
barplot(Tabla_Life_Final$ni, names.arg = Tabla_Life_Final$Rango_Vida, las = 2,
main = "DISTRIBUCION DE VIDA ESTIMADA ", col = "skyblue", ylab = "ni", cex.names = 0.7)
#BARRAS ABSOLUTA GLOBAL
barplot(Tabla_Life_Final$ni, names.arg = Tabla_Life_Final$Rango_Vida, las = 2,
main = "DISTRIBUCION DE VIDA ESTIMADA ", col = "darkgrey",
ylab = "ni", ylim = c(0, sum(Tabla_Life_Final$ni)), cex.names = 0.7)
# BARRAS RELATIVA LOCAL
barplot(Tabla_Life_Final$hi, names.arg = Tabla_Life_Final$Rango_Vida, las = 2,
main = "DISTRIBUCION DE VIDA ESTIMADA ", col = "lightgreen", ylab = "hi (%)", cex.names = 0.7)
# BARRAS RELATIVA LOCAL
barplot(Tabla_Life_Final$hi, names.arg = Tabla_Life_Final$Rango_Vida, las = 2,
main = "DISTRIBUCION DE VIDA ESTIMADA ", col = "grey50",
ylab = "hi (%)", ylim = c(0, 100), cex.names = 0.7)
# ===================Grafico Ojivas Absoluta (Ni)==============================
x_life <- 1:nrow(Tabla_Life_Final)
plot(x_life, Tabla_Life_Final$Niasc, type = "p", pch = 19, col = "blue",
main = "DISTRIBUCION DE VIDA ESTIMADA",
xlab = "Rangos", ylab = "Cantidad Acumulada", xaxt = 'n')
axis(side = 1, at = x_life, labels = Tabla_Life_Final$Rango_Vida, las = 2, cex.axis = 0.7)
points(x_life, Tabla_Life_Final$Nidsc, col = "darkred", pch = 18)
legend("topright", legend = c("Ni Asc", "Ni Des"), col = c("blue", "darkred"), pch = c(19, 18), bty = "n")
#
plot(x_life, Tabla_Life_Final$Hiasc, type = "p", pch = 19, col = "blue",
main = "DISTRIBUCION DE VIDA ESTIMADA ",
xlab = "Rangos", ylab = "Porcentaje Acumulado (%)", xaxt = 'n', ylim = c(0, 100))
axis(side = 1, at = x_life, labels = Tabla_Life_Final$Rango_Vida, las = 2, cex.axis = 0.7)
points(x_life, Tabla_Life_Final$Hidsc, col = "darkred", pch = 18)
legend("right", legend = c("Hi Asc", "Hi Des"), col = c("blue", "darkred"), pch = c(19, 18), bty = "n")
#===============================BOXPLOT=======================================
boxplot(v_lifetime, horizontal = TRUE, col = "orange",
main = "DISTRIBUCION DE VIDA ESTIMADA", xlab = "Unidades de Tiempo")
# ========================INDICADORES ESTADISTICOS===========================
mean_life <- mean(v_lifetime, na.rm = TRUE)
sd_life <- sd(v_lifetime, na.rm = TRUE)
indicadores_life_df <- data.frame(
Indicador = c("Moda", "Mediana", "Media", "Desviacion Estandar",
"Varianza", "Coef. Variacion (%)", "Asimetria", "Curtosis"),
Valor = c(
round(get_mode(v_lifetime), 2),
round(median(v_lifetime, na.rm = TRUE), 2),
round(mean_life, 2),
round(sd_life, 2),
round(var(v_lifetime, na.rm = TRUE), 2),
round((sd_life / mean_life) * 100, 2),
round(skewness(v_lifetime, na.rm = TRUE), 2),
round(kurtosis(v_lifetime, na.rm = TRUE), 2)
)
)
gt(indicadores_life_df) %>%
tab_header(title = "INDICADORES: ESTIMATED LIFETIME")
| INDICADORES: ESTIMATED LIFETIME |
| Indicador |
Valor |
| Moda |
50.00 |
| Mediana |
50.00 |
| Media |
51.86 |
| Desviacion Estandar |
6.30 |
| Varianza |
39.64 |
| Coef. Variacion (%) |
12.14 |
| Asimetria |
0.51 |
| Curtosis |
5.89 |