#=============================ENCABEZADO========================================
# TEMA: ED Variables Cuantitativas - ANIO DE INICIO DE LA PERFORACION
# 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======================
a_perforacion <- datos$Spud.Initiation.year
min_year <- min(a_perforacion, na.rm = TRUE)
max_year <- max(a_perforacion, na.rm = TRUE)
start_decade <- floor(min_year / 10) * 10
end_decade <- ceiling(max_year / 10) * 10
breaks <- seq(start_decade, end_decade + 10, by = 10)
labels <- paste0(breaks[1:(length(breaks)-1)], "-", breaks[2:length(breaks)] - 1)
a_perforacion_decadas <- cut(a_perforacion, breaks = breaks, labels = labels, right = FALSE)
TDF_base <- as.data.frame(table(a_perforacion_decadas))
names(TDF_base) <- c("Decada", "ni")
hi <- (TDF_base$ni / sum(TDF_base$ni)) * 100
Niasc <- cumsum(TDF_base$ni)
Hiasc <- cumsum(hi)
Nidsc <- rev(cumsum(rev(TDF_base$ni)))
Hidsc <- rev(cumsum(rev(hi)))
Tabla_Final <- data.frame(
N = 1:nrow(TDF_base),
Decada = as.character(TDF_base$Decada),
ni = TDF_base$ni,
hi = round(hi, 2),
Niasc = Niasc,
Hiasc = round(Hiasc, 2),
Nidsc = Nidsc,
Hidsc = round(Hidsc, 2)
)
Fila_Total <- data.frame(
N = NA, Decada = "TOTAL", ni = sum(Tabla_Final$ni), hi = 100,
Niasc = NA, Hiasc = NA, Nidsc = NA, Hidsc = NA
)
TDF_Completa <- rbind(Tabla_Final, Fila_Total)
# =========================TABLA PROFESIONAL (GT)======================
tabla_gt_resultado <- TDF_Completa %>%
gt() %>%
tab_header(
title = "DISTRIBUCION DE ANIO DE INICIO DE LA PERFORACION",
) %>%
cols_label(
N = "N", Decada = "RANGO", 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 = Decada == "TOTAL")
) %>%
cols_align(align = "center", columns = everything())
tabla_gt_resultado
| DISTRIBUCION DE ANIO DE INICIO DE LA PERFORACION |
| N |
RANGO |
ni |
hi |
Ni_asc |
Hi_asc |
Ni_des |
Hi_des |
| 1 |
1950-1959 |
1130 |
9.00 |
1130 |
9.00 |
12561 |
100.00 |
| 2 |
1960-1969 |
873 |
6.95 |
2003 |
15.95 |
11431 |
91.00 |
| 3 |
1970-1979 |
1416 |
11.27 |
3419 |
27.22 |
10558 |
84.05 |
| 4 |
1980-1989 |
1741 |
13.86 |
5160 |
41.08 |
9142 |
72.78 |
| 5 |
1990-1999 |
1687 |
13.43 |
6847 |
54.51 |
7401 |
58.92 |
| 6 |
2000-2009 |
5223 |
41.58 |
12070 |
96.09 |
5714 |
45.49 |
| 7 |
2010-2019 |
477 |
3.80 |
12547 |
99.89 |
491 |
3.91 |
| 8 |
2020-2029 |
14 |
0.11 |
12561 |
100.00 |
14 |
0.11 |
|
TOTAL |
12561 |
100.00 |
|
|
|
|
#============================GRAFICOS=========================================
par(mar = c(8, 4, 4, 2) + 0.1)
#========================GRAFICO FRECUENCIA ABSOLUTA LOCAL====================
barplot(Tabla_Final$ni, names.arg = Tabla_Final$Decada, las = 2,
main = "DISTRIBUCION DE ANIO DE INICIO DE LA PERFORACION", col = "skyblue", ylab = "ni")
#=======================GRAFICO FRECUENCIA ABSOLUTA GLOBAL====================
barplot(Tabla_Final$ni, names.arg = Tabla_Final$Decada, las = 2,
main = "DISTRIBUCION DE ANIO DE INICIO DE LA PERFORACION", col = "darkgrey",
ylab = "ni", ylim = c(0, sum(Tabla_Final$ni)))
#=====================GRAFICO FRECUENCIA RELATIVA LOCAL=======================
barplot(Tabla_Final$hi, names.arg = Tabla_Final$Decada, las = 2,
main = "DISTRIBUCION DE ANIO DE INICIO DE LA PERFORACION", col = "lightgreen", ylab = "hi (%)")
#====================GRAFICO FRECUENCIA RELATIVA GLOBAL=======================
barplot(Tabla_Final$hi, names.arg = Tabla_Final$Decada, las = 2,
main = "DISTRIBUCION DE ANIO DE INICIO DE LA PERFORACION", col = "grey50",
ylab = "hi (%)", ylim = c(0, 100))
# OJIVAS 5-6 (REORDENADAS)
x_ojiva <- 1:nrow(Tabla_Final)
#=======================GRAFICO DE Ojiva Absoluta (Ni)======================
plot(x_ojiva, Tabla_Final$Niasc, type = "p", pch = 19, col = "blue",
main = "DISTRIBUCION DE ANIO DE INICIO DE LA PERFORACION",
xlab = "Decada", ylab = "Cantidad Acumulada", xaxt = 'n')
axis(side = 1, at = x_ojiva, labels = Tabla_Final$Decada, las = 2, cex.axis = 0.7)
points(x_ojiva, Tabla_Final$Nidsc, col = "darkred", pch = 18)
legend("topright", legend = c("Ni Asc", "Ni Des"), col = c("blue", "darkred"), pch = c(19, 18), bty = "n")
#=====================GRAFICO DE Ojiva Relativa (Hi)========================
plot(x_ojiva, Tabla_Final$Hiasc, type = "p", pch = 19, col = "blue",
main = "DISTRIBUCION DE ANIO DE INICIO DE LA PERFORACION",
xlab = "Decada", ylab = "Porcentaje Acumulado (%)", xaxt = 'n', ylim = c(0, 100))
axis(side = 1, at = x_ojiva, labels = Tabla_Final$Decada, las = 2, cex.axis = 0.7)
points(x_ojiva, Tabla_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 7===================================
boxplot(a_perforacion, horizontal = TRUE, col = "lightblue",
main = "DISTRIBUCION DE ANIO DE INICIO DE LA PERFORACION", xlab = "A??o")
#======================INDICADORES ESTADISTICOS=============================
mean_val <- mean(a_perforacion, na.rm = TRUE)
sd_val <- sd(a_perforacion, na.rm = TRUE)
indicadores_df <- data.frame(
Indicador = c("Moda", "Mediana", "Media", "Desviacion Estandar",
"Varianza", "Coef. Variacion (%)", "Asimetria", "Curtosis"),
Valor = c(
round(get_mode(a_perforacion), 2),
round(median(a_perforacion, na.rm = TRUE), 2),
round(mean_val, 2),
round(sd_val, 2),
round(var(a_perforacion, na.rm = TRUE), 2),
round((sd_val / mean_val) * 100, 2),
round(skewness(a_perforacion, na.rm = TRUE), 2),
round(kurtosis(a_perforacion, na.rm = TRUE), 2)
)
)
gt(indicadores_df) %>%
tab_header(title = "INDICADORES ESTADISTICOS GENERALES")
| INDICADORES ESTADISTICOS GENERALES |
| Indicador |
Valor |
| Moda |
2006.00 |
| Mediana |
1997.00 |
| Media |
1990.09 |
| Desviacion Estandar |
17.33 |
| Varianza |
300.28 |
| Coef. Variacion (%) |
0.87 |
| Asimetria |
-0.69 |
| Curtosis |
-0.71 |