Cierre de oleoductos

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(knitr)
library(kableExtra)

## 
## Adjuntando el paquete: 'kableExtra'

## The following object is masked from 'package:dplyr':
## 
##     group_rows

df_parcial <- datos %>%
  mutate(Pipeline.Shutdown = trimws(toupper(Pipeline.Shutdown)),
         Pipeline.Shutdown = ifelse(Pipeline.Shutdown == "YES", "SI", Pipeline.Shutdown)) %>%
  filter(Pipeline.Shutdown %in% c("SI", "NO")) %>%
  count(Pipeline.Shutdown, name = "ni")
total_objetivo <- 2795
suma_actual <- sum(df_parcial$ni)
n_restante <- total_objetivo - suma_actual
fila_restante <- data.frame(
  Pipeline.Shutdown = "NO IDENTIFICADOS",
  ni = n_restante
)
df_completo <- rbind(df_parcial, fila_restante) %>%
  mutate(hi_pct = round((ni / sum(ni)) * 100, 2)) %>%
  arrange(desc(ni))
fila_total <- data.frame(
  Pipeline.Shutdown = "TOTAL",
  ni = sum(df_completo$ni), 
  hi_pct = 100.00
)
tabla_final <- rbind(df_completo, fila_total)

kable(tabla_final, 
      digits = 2, 
      col.names = c("Estado", "Frecuencia (ni)", "Porcentaje (%)"),
      align = 'c', 
      caption = "Tabla: Distribución Total de Cierres") %>%
  
  kable_styling(full_width = FALSE, position = "center", 
                bootstrap_options = c("striped", "bordered")) %>%
  row_spec(nrow(tabla_final), bold = TRUE, background = "#f2f2f2") %>%
  row_spec(which(tabla_final$Pipeline.Shutdown == "NO IDENTIFICADOS"), color = "gray", italic = TRUE)

Tabla: Distribución Total de Cierres
Estado	Frecuencia (ni)	Porcentaje (%)
SI	1395	49.91
NO	1188	42.50
NO IDENTIFICADOS	212	7.58
TOTAL	2795	100.00

#barra local ni
library(ggplot2)
library(dplyr)
datos_grafico <- datos %>%
  mutate(Pipeline.Shutdown = trimws(toupper(Pipeline.Shutdown)),
         Pipeline.Shutdown = ifelse(Pipeline.Shutdown == "YES", "SI", Pipeline.Shutdown)) %>% 
  filter(Pipeline.Shutdown %in% c("SI", "NO")) %>%                  
  
  count(Pipeline.Shutdown, name = "ni")

ggplot(datos_grafico, aes(x = Pipeline.Shutdown, y = ni, fill = Pipeline.Shutdown)) +
  geom_bar(stat = "identity", width = 0.6) +
  scale_fill_manual(values = c("SI" = "skyblue", "NO" = "skyblue")) +
  
  labs(
    title = "Gráfica 1: Cierres de oleoductos SI/NO",
    x = "Cierre de oleoductos",
    y = "Número de Accidentes"
  ) +
  theme_classic() +
  theme(
    legend.position = "none", 
    axis.text.x = element_text(size = 12, face = "bold"), 
    plot.title = element_text(face = "bold", size = 14)
  )

#barra general
library(ggplot2)
library(dplyr)

datos_grafico <- datos %>%
  mutate(Pipeline.Shutdown = trimws(toupper(Pipeline.Shutdown)),
         Pipeline.Shutdown = ifelse(Pipeline.Shutdown == "YES", "SI", Pipeline.Shutdown)) %>% 
  filter(Pipeline.Shutdown %in% c("SI", "NO")) %>%                  
  count(Pipeline.Shutdown, name = "ni")
ggplot(datos_grafico, aes(x = Pipeline.Shutdown, y = ni, fill = Pipeline.Shutdown)) +
  
  geom_bar(stat = "identity", width = 0.6) +
  scale_fill_manual(values = c("SI" = "skyblue", "NO" = "skyblue")) +
  scale_y_continuous(limits = c(0, 2795), breaks = c(0, 1000, 2000, 2795)) +
  
  labs(
    title = "Gráfica 2: Cantidad de Cierres de oleoductos en general",
    x = "Cierre de oleoductos",
    y = "Número de Accidentes"
  ) +
  
  theme_classic() +
  
  theme(
    legend.position = "none", 
    axis.text.x = element_text(size = 12, face = "bold"), 
    plot.title = element_text(face = "bold", size = 14)
  )

library(ggplot2)
library(dplyr)
library(ggplot2)
library(dplyr)

datos_grafico <- datos %>%
  mutate(Pipeline.Shutdown = trimws(toupper(Pipeline.Shutdown)),
         Pipeline.Shutdown = ifelse(Pipeline.Shutdown == "YES", "SI", Pipeline.Shutdown)) %>% 
  filter(Pipeline.Shutdown %in% c("SI", "NO")) %>%                  
  
  count(Pipeline.Shutdown, name = "ni") %>%
  mutate(porcentaje = (ni / sum(ni)) * 100)

ggplot(datos_grafico, aes(x = Pipeline.Shutdown, y = porcentaje, fill = Pipeline.Shutdown)) +
  
  geom_bar(stat = "identity", width = 0.6) +
  scale_fill_manual(values = c("SI" = "skyblue", "NO" = "skyblue")) +
  
  scale_y_continuous(limits = c(0, 100), breaks = seq(0, 100, 10)) + 
  
  labs(
    title = "Gráfica 2: Porcentaje de Cierres de oleoductos",
    x = "Cierre de oleoductos",
    y = "Porcentaje (%)"
  ) +
  
  theme_classic() +
  
  theme(
    legend.position = "none", 
    axis.text.x = element_text(size = 12, face = "bold"), 
    plot.title = element_text(face = "bold", size = 14)
  )

#barra_local hi
library(ggplot2)
library(dplyr)

datos_grafico <- datos %>%
  mutate(Pipeline.Shutdown = trimws(toupper(Pipeline.Shutdown)),
         Pipeline.Shutdown = ifelse(Pipeline.Shutdown == "YES", "SI", Pipeline.Shutdown)) %>% 
  filter(Pipeline.Shutdown %in% c("SI", "NO")) %>%                  
  
  count(Pipeline.Shutdown, name = "ni") %>%
  mutate(hi_pct = (ni / sum(ni)) * 100) 

ggplot(datos_grafico, aes(x = Pipeline.Shutdown, y = hi_pct, fill = Pipeline.Shutdown)) +
  
  geom_bar(stat = "identity", width = 0.6) +
  scale_fill_manual(values = c("SI" = "skyblue", "NO" = "skyblue")) +
  scale_y_continuous(limits = c(0, 60), breaks = seq(0, 60, by = 10)) +
  
  labs(
    title = "Gráfica 4: Cantidad de porcentaje",
    x = "Cierre de oleoductos",
    y = "Porcentaje (%)"
  ) +
  
  theme_classic() +
  
  theme(
    legend.position = "none", 
    axis.text.x = element_text(size = 12, face = "bold"), 
    plot.title = element_text(face = "bold", size = 14)
  )

#diagrama circular
library(ggplot2)
library(dplyr)
df_clean <- datos %>%
  mutate(Pipeline.Shutdown = trimws(toupper(Pipeline.Shutdown)),
         Pipeline.Shutdown = ifelse(Pipeline.Shutdown == "YES", "SI", Pipeline.Shutdown)) %>% 
  filter(Pipeline.Shutdown %in% c("SI", "NO")) %>%
  count(Pipeline.Shutdown, name = "ni") %>%
  mutate(hi_pct = round((ni / sum(ni)) * 100, 1))
ggplot(df_clean, aes(x = "", y = hi_pct, fill = Pipeline.Shutdown)) +
  
  geom_bar(stat = "identity", width = 1, color = "white") +
  coord_polar("y", start = 0) +

  geom_text(aes(label = paste0(hi_pct, "%")), 
            position = position_stack(vjust = 0.5), 
            color = "white", fontface = "bold", size = 5) +
  scale_fill_manual(values = c("SI" = "skyblue", "NO" = "skyblue")) +
  
  labs(title = "Gráfico 5: Distribución de Cierres de oleoductos", fill = "Estado") +
  theme_void()

variable_limpia <- trimws(toupper(na.omit(datos$Pipeline.Shutdown)))
variable_limpia <- variable_limpia[variable_limpia != ""]

tabla_frecuencia <- table(variable_limpia)

mas_repetido <- names(tabla_frecuencia)[which.max(tabla_frecuencia)]
cantidad <- max(tabla_frecuencia)
total_validos <- sum(tabla_frecuencia)
porcentaje <- round((cantidad / total_validos) * 100, 2)

cat("El valor que más se repite es:", mas_repetido, "\n")

## El valor que más se repite es: YES

cat("Cantidad:", cantidad, "\n")

## Cantidad: 1395

cat("Representa el:", porcentaje, "% de los casos válidos\n")

## Representa el: 54.01 % de los casos válidos

#CONCLUSIONES
#El valor más frecuente de la variable Pipeline Shutdown es ‘YES’, con un total de 1,395 registros. Esto representa aproximadamente el 54.01% de los casos reportados (excluyendo valores nulos), lo que indica que en la mayoría de los incidentes registrados la severidad fue suficiente para requerir el cierre operativo de la tubería..

Cierre de oleoductos

Brandon

2025-12-17