Exploración y Producción de los Pozos Petrolíferos en Brasil
Leonardo Ruiz
2026-03-08
knitr::opts_chunk$set(echo = TRUE)
setwd("C:/Users/LEO/Documents/ESTA")
Datos <- read.csv("tabela_de_pocos_janeiro_2018.csv", header = TRUE, sep = ";" , dec = ".", fileEncoding = "Latin1")1 Carga de librerias
library(readxl)
library(dplyr)
library(gt)
library(e1071)2 Carga de datos
Datos_Brutos <- read_xlsx("C:/Users/LEO/Documents/ESTA/tabela_de_pocos_janeiro_2018.xlsx", sheet = 1)
colnames(Datos_Brutos) <- trimws(colnames(Datos_Brutos))3 Selección de variable
Datos <- Datos_Brutos %>%
select(any_of(c("POCO", "LAMINA_D_AGUA_M"))) %>%
mutate(Variable_Analisis = as.numeric(gsub(",", ".", as.character(LAMINA_D_AGUA_M))))
Variable <- na.omit(Datos$Variable_Analisis)
Variable <- Variable[Variable >= 0 & Variable < 4000]
if(length(Variable) == 0) {
stop("ERROR: No hay datos válidos para la variable seleccionada.")
}4 Frecuencia
N <- length(Variable)
K <- floor(1 + 3.322 * log10(N))
breaks_table <- seq(min(Variable), max(Variable), length.out = K + 1)
ni <- as.vector(table(cut(Variable, breaks = breaks_table, include.lowest = TRUE, right = FALSE)))
hi <- (ni / sum(ni)) * 100
Ni_asc <- cumsum(ni)
Ni_desc <- rev(cumsum(rev(ni)))
Hi_asc <- cumsum(hi)
Hi_desc <- rev(cumsum(rev(hi)))5 Tabla de Distribución de Frecuencia
Tabla de distribución de frecuencias.
5.1 Tabla General
TDF_Agua <- data.frame(
Li = round(breaks_table[1:K], 2),
Ls = round(breaks_table[2:(K+1)], 2),
MC = round((breaks_table[1:K] + breaks_table[2:(K+1)]) / 2, 2),
ni = ni,
hi = hi,
Ni_asc = Ni_asc,
Ni_desc = Ni_desc,
Hi_asc = Hi_asc,
Hi_desc = Hi_desc
)
col_gris_azulado <- "#5D6D7E"
col_ejes <- "#2E4053"
max_var <- max(Variable)
breaks_auto <- hist(Variable, plot = FALSE)$breaks
h_base <- hist(Variable, breaks = breaks_auto, plot = FALSE)
limite_x <- c(0, max(max_var, 100))
TDF_Agua %>%
gt(rowname_col = "Li") %>%
tab_header(
title = md("**DISTRIBUCIÓN DE FRECUENCIAS: LÁMINA DE AGUA**"),
subtitle = md("Variable: **col_agua_m**")
) %>%
tab_source_note(source_note = "Fuente: Datos ANP 2018") %>%
grand_summary_rows(
columns = c(ni, hi),
fns = list("TOTAL" = ~sum(., na.rm = TRUE))
) %>%
# Formateamos números enteros
fmt_number(
columns = c(ni, Ni_asc, Ni_desc),
decimals = 0,
use_seps = TRUE
) %>%
# Formateamos los porcentajes a 2 decimales
fmt_number(
columns = c(hi, Hi_asc, Hi_desc),
decimals = 2
) %>%
cols_label(
Ls = "Lím. Sup", MC = "Marca Clase (Xi)",
ni = "ni", hi = "hi (%)",
Ni_asc = "Ni (Asc)", Ni_desc = "Ni (Desc)",
Hi_asc = "Hi (Asc)", Hi_desc = "Hi (Desc)"
) %>%
tab_stubhead(label = "Lím. Inf") %>%
# Alineación de datos al centro
cols_align(align = "center", columns = everything()) %>%
# Alineación del Stub (Lím. Inf y la palabra TOTAL) al centro
tab_style(
style = cell_text(align = "center"),
locations = cells_stub()
) %>%
# Estética de los encabezados (Azul oscuro / Verde petróleo con texto blanco)
tab_style(
style = list(cell_fill(color = "#1F4E5B"), cell_text(color = "white", weight = "bold")),
locations = list(cells_title(), cells_column_labels(), cells_stubhead())
) %>%
tab_options(
table.border.top.style = "none",
table.border.bottom.color = "#2E4053",
column_labels.border.bottom.color = "#2E4053",
data_row.padding = px(6)
)| DISTRIBUCIÓN DE FRECUENCIAS: LÁMINA DE AGUA | ||||||||
| Variable: col_agua_m | ||||||||
| Lím. Inf | Lím. Sup | Marca Clase (Xi) | ni | hi (%) | Ni (Asc) | Ni (Desc) | Hi (Asc) | Hi (Desc) |
|---|---|---|---|---|---|---|---|---|
| 0.00 | 213.43 | 106.71 | 10,682 | 79.33 | 10,682 | 13,466 | 79.33 | 100.00 |
| 213.43 | 426.86 | 320.14 | 263 | 1.95 | 10,945 | 2,784 | 81.28 | 20.67 |
| 426.86 | 640.29 | 533.57 | 233 | 1.73 | 11,178 | 2,521 | 83.01 | 18.72 |
| 640.29 | 853.71 | 747.00 | 275 | 2.04 | 11,453 | 2,288 | 85.05 | 16.99 |
| 853.71 | 1067.14 | 960.43 | 416 | 3.09 | 11,869 | 2,013 | 88.14 | 14.95 |
| 1067.14 | 1280.57 | 1173.86 | 377 | 2.80 | 12,246 | 1,597 | 90.94 | 11.86 |
| 1280.57 | 1494.00 | 1387.29 | 380 | 2.82 | 12,626 | 1,220 | 93.76 | 9.06 |
| 1494.00 | 1707.43 | 1600.71 | 239 | 1.77 | 12,865 | 840 | 95.54 | 6.24 |
| 1707.43 | 1920.86 | 1814.14 | 241 | 1.79 | 13,106 | 601 | 97.33 | 4.46 |
| 1920.86 | 2134.29 | 2027.57 | 133 | 0.99 | 13,239 | 360 | 98.31 | 2.67 |
| 2134.29 | 2347.71 | 2241.00 | 160 | 1.19 | 13,399 | 227 | 99.50 | 1.69 |
| 2347.71 | 2561.14 | 2454.43 | 28 | 0.21 | 13,427 | 67 | 99.71 | 0.50 |
| 2561.14 | 2774.57 | 2667.86 | 22 | 0.16 | 13,449 | 39 | 99.87 | 0.29 |
| 2774.57 | 2988.00 | 2881.29 | 17 | 0.13 | 13,466 | 17 | 100.00 | 0.13 |
| TOTAL | — | — | 13466 | 100 | — | — | — | — |
| Fuente: Datos ANP 2018 | ||||||||
5.2 Tabla Simplificada
# =====================================================================
# BLOQUE 1: CÁLCULO DE FRECUENCIAS (INTERVALOS FIJOS DE 500 EN 500)
# =====================================================================
min_val <- 0
max_val <- ceiling(max(Variable) / 500) * 500 # Redondea al múltiplo de 500 superior
breaks_table <- seq(min_val, max_val, by = 500)
K <- length(breaks_table) - 1
ni <- as.vector(table(cut(Variable, breaks = breaks_table, include.lowest = TRUE, right = FALSE)))
hi <- (ni / sum(ni)) * 100
Ni_asc <- cumsum(ni)
Ni_desc <- rev(cumsum(rev(ni)))
Hi_asc <- cumsum(hi)
Hi_desc <- rev(cumsum(rev(hi)))
# =====================================================================
# BLOQUE 2: CREACIÓN Y ESTILIZADO DE LA TABLA CON gt()
# =====================================================================
TDF_Agua <- data.frame(
Li = round(breaks_table[1:K], 2),
Ls = round(breaks_table[2:(K+1)], 2),
MC = round((breaks_table[1:K] + breaks_table[2:(K+1)]) / 2, 2),
ni = ni,
hi = hi,
Ni_asc = Ni_asc,
Ni_desc = Ni_desc,
Hi_asc = Hi_asc,
Hi_desc = Hi_desc
)
col_gris_azulado <- "#5D6D7E"
max_var <- max(Variable)
limite_x <- c(0, max(max_var, 100))
TDF_Agua %>%
gt(rowname_col = "Li") %>%
tab_header(
title = md("**DISTRIBUCIÓN DE FRECUENCIAS: LÁMINA DE AGUA**"),
subtitle = md("Variable: **col_agua_m**")
) %>%
tab_source_note(source_note = "Fuente: Datos ANP 2018") %>%
grand_summary_rows(
columns = c(ni, hi),
fns = list("TOTAL" = ~sum(., na.rm = TRUE))
) %>%
# Formateamos números enteros
fmt_number(
columns = c(ni, Ni_asc, Ni_desc),
decimals = 0,
use_seps = TRUE
) %>%
# Formateamos los porcentajes a 2 decimales
fmt_number(
columns = c(hi, Hi_asc, Hi_desc),
decimals = 2
) %>%
cols_label(
Ls = "Lím. Sup", MC = "Marca Clase (Xi)",
ni = "ni", hi = "hi (%)",
Ni_asc = "Ni (Asc)", Ni_desc = "Ni (Desc)",
Hi_asc = "Hi (Asc)", Hi_desc = "Hi (Desc)"
) %>%
tab_stubhead(label = "Lím. Inf") %>%
# Alineación de datos al centro
cols_align(align = "center", columns = everything()) %>%
# Alineación del Stub al centro
tab_style(
style = cell_text(align = "center"),
locations = cells_stub()
) %>%
# Estética de los encabezados
tab_style(
style = list(cell_fill(color = "#1F4E5B"), cell_text(color = "white", weight = "bold")),
locations = list(cells_title(), cells_column_labels(), cells_stubhead())
) %>%
tab_options(
table.border.top.style = "none",
table.border.bottom.color = "#2E4053",
column_labels.border.bottom.color = "#2E4053",
data_row.padding = px(6)
)| DISTRIBUCIÓN DE FRECUENCIAS: LÁMINA DE AGUA | ||||||||
| Variable: col_agua_m | ||||||||
| Lím. Inf | Lím. Sup | Marca Clase (Xi) | ni | hi (%) | Ni (Asc) | Ni (Desc) | Hi (Asc) | Hi (Desc) |
|---|---|---|---|---|---|---|---|---|
| 0 | 500 | 250 | 11,035 | 81.95 | 11,035 | 13,466 | 81.95 | 100.00 |
| 500 | 1000 | 750 | 715 | 5.31 | 11,750 | 2,431 | 87.26 | 18.05 |
| 1000 | 1500 | 1250 | 887 | 6.59 | 12,637 | 1,716 | 93.84 | 12.74 |
| 1500 | 2000 | 1750 | 500 | 3.71 | 13,137 | 829 | 97.56 | 6.16 |
| 2000 | 2500 | 2250 | 287 | 2.13 | 13,424 | 329 | 99.69 | 2.44 |
| 2500 | 3000 | 2750 | 42 | 0.31 | 13,466 | 42 | 100.00 | 0.31 |
| TOTAL | — | — | 13466 | 100 | — | — | — | — |
| Fuente: Datos ANP 2018 | ||||||||
6 Gráficas de distribución de frecuencias
6.1 GRÁFICO 1: Histograma Absoluto
par(mar = c(8, 5, 4, 2))
h_abs <- hist(
Variable,
breaks = breaks_table,
main = "Gráfica No.1: Distribución de col_agua_m de Pozos Petroleros de Brasil",
xlab = "Lámina de Agua - col_agua_m (m)",
ylab = "Frecuencia Absoluta",
col = col_gris_azulado,
border = "white",
axes = FALSE,
ylim = c(0, max(ni) * 1.1),
xlim = limite_x
)
axis(1, at = seq(0, limite_x[2], by = 500), las = 2, cex.axis = 0.7)
axis(2)
grid(nx = NA, ny = NULL, col = "#D7DBDD", lty = "dotted")
6.2 GRÁFICO 2: Histograma Global
par(mar = c(8, 5, 4, 2))
h_glob <- hist(
Variable,
breaks = breaks_table,
main = "Gráfica N°2: Distribución de col_agua_m de Pozos Petroleros de Brasil",
xlab = "Lámina de Agua - col_agua_m (m)",
ylab = "Total Pozos",
col = col_gris_azulado,
border = "white",
axes = FALSE,
ylim = c(0, sum(ni)),
xlim = limite_x
)
axis(1, at = seq(0, limite_x[2], by = 500), las = 2, cex.axis = 0.7)
axis(2)
grid(nx = NA, ny = NULL, col = "#D7DBDD", lty = "dotted")
6.3 GRÁFICO 3: Porcentajes (Local)
par(mar = c(8, 5, 4, 2))
h_p3 <- hist(Variable, breaks = breaks_table, plot = FALSE)
# Reasignamos los counts para que representen el porcentaje real (0 a 100)
h_p3$counts <- hi
plot(
h_p3,
main = "Gráfica N°3: Distribución Porcentual de Lámina de Agua",
xlab = "Lámina de Agua - col_agua_m (m)",
ylab = "Porcentaje (%)",
col = col_gris_azulado,
border = "white",
axes = FALSE,
ylim = c(0, 60),
xlim = limite_x,
freq = TRUE
)
axis(1, at = seq(0, limite_x[2], by = 500), las = 2, cex.axis = 0.7)
axis(2, at = seq(0, 100, by = 20), labels = paste0(seq(0, 100, by = 20), "%"))
grid(nx = NA, ny = NULL, col = "#D7DBDD", lty = "dotted")
text(
x = h_p3$mids,
y = hi,
label = paste0(round(hi, 1), "%"),
pos = 3,
cex = 0.6,
col = col_ejes,
xpd = TRUE
)
box(bty = "l")
6.4 GRÁFICO 4: Global Porcentual
par(mar = c(8, 5, 4, 2))
h_p4 <- hist(Variable, breaks = breaks_table, plot = FALSE)
h_p4$counts <- hi
plot(
h_p4,
main = "Gráfica No.4: Distribución Porcentual de Lámina de Agua",
xlab = "Lámina de Agua - col_agua_m (m)",
ylab = "% del Total",
col = col_gris_azulado,
border = "white",
axes = FALSE,
ylim = c(0, 105),
xlim = limite_x,
freq = TRUE
)
axis(1, at = seq(0, limite_x[2], by = 500), las = 2, cex.axis = 0.7)
axis(2, at = seq(0, 100, by = 20), labels = paste0(seq(0, 100, by = 20), "%"))
grid(nx = NA, ny = NULL, col = "#D7DBDD", lty = "dotted")
text(
x = h_p4$mids,
y = hi,
label = paste0(round(hi, 1), "%"),
pos = 3,
cex = 0.6,
col = col_ejes,
xpd = TRUE
)
box(bty = "l")
6.5 GRÁFICO 5: Boxplot
col_acento <- "#C0392B"
par(mar = c(8, 5, 4, 2))
boxplot(Variable, horizontal = TRUE, col = col_gris_azulado,
main = "Gráfica No.5: Diagrama de Caja (col_agua_m)",
xlab = "Lámina de Agua - col_agua_m (m)", outline = TRUE, outpch = 19,
outcol = col_acento, axes = FALSE, xlim = c(0.7, 1.3),
ylim = limite_x)
axis(1, at = seq(0, limite_x[2], by = 500), las = 2, cex.axis = 0.7)
box()
6.6 GRÁFICO 6: Ojivas
col_azul_oscuro <- "#2E4053"
col_rojo_fuerte <- "#C0392B"
par(mar = c(8, 5, 4, 8), xpd = TRUE)
x_vals_ojiva <- breaks_table
plot(x_vals_ojiva, c(0, Ni_asc), type = "o", col = col_azul_oscuro,
lwd=2, pch=19, axes=F,
main = "Gráfica No.6: Ojivas Ascendente y Descendente (col_agua_m)",
xlab = "Lámina de Agua - col_agua_m (m)", ylab = "Frecuencia acumulada")
lines(x_vals_ojiva, c(Ni_desc, 0), type = "o", col = col_rojo_fuerte,
lwd=2, pch=19)
axis(1, at = seq(0, max(breaks_table), by = 500), las = 2, cex.axis = 0.6)
axis(2)
legend("right", legend = c("Ascendente", "Descendente"),
col = c(col_azul_oscuro, col_rojo_fuerte),
lty = 1, pch = 19, cex = 0.7, lwd=2,
inset = c(-0.15, 0), bty="n")
grid()
7 Indicadores Estadísticos
media_val <- mean(Variable)
mediana_val <- median(Variable)
sd_val <- sd(Variable)
status_atipicos <- if(length(boxplot.stats(Variable)$out) > 0) {
paste0(length(boxplot.stats(Variable)$out), " [", round(min(boxplot.stats(Variable)$out), 2), "; ", round(max(boxplot.stats(Variable)$out), 2), "]")
} else { "0 (Sin atípicos)" }
df_resumen <- data.frame(
Variable = "col_agua_m",
Rango = paste0("[", round(min(Variable), 2), " ; ", round(max(Variable), 2), "]"),
X = media_val,
Me = mediana_val,
Mo = paste(round(TDF_Agua$MC[TDF_Agua$hi == max(TDF_Agua$hi)], 2), collapse = ", "),
Varianza = var(Variable),
sd = sd_val,
CV = (sd_val / abs(media_val)) * 100,
As = skewness(Variable, type = 2),
K = kurtosis(Variable, type = 2),
Atipicos = status_atipicos
)
df_resumen %>%
gt() %>%
tab_header(title = md("**CONCLUSIONES Y ESTADÍSTICOS**"), subtitle = "Variable: col_agua_m") %>%
cols_label(
X = "X",
Me = "Me",
Mo = "Mo",
sd = "sd",
CV = "CV",
As = "As",
K = "K",
Atipicos = "Valores atípicos"
) %>%
fmt_number(columns = c(X, Me, Varianza, sd, CV, K), decimals = 2) %>%
fmt_number(columns = As, decimals = 4) %>%
cols_width(
Variable ~ px(140),
Rango ~ px(120),
Mo ~ px(100),
Atipicos ~ px(220),
everything() ~ px(85)
) %>%
tab_options(
column_labels.background.color = "#2E4053",
table.border.top.style = "solid",
table.border.bottom.style = "solid",
heading.border.bottom.style = "solid",
column_labels.border.top.style = "solid",
column_labels.border.bottom.style = "solid",
data_row.padding = px(8)
) %>%
tab_style(
style = list(
cell_text(weight = "bold", color = "white"),
cell_borders(sides = c("left", "right"), color = "#D3D3D3", weight = px(1))
),
locations = cells_column_labels()
) %>%
tab_style(
style = cell_borders(sides = c("left", "right"), color = "#D3D3D3", weight = px(1)),
locations = cells_body()
)| CONCLUSIONES Y ESTADÍSTICOS | ||||||||||
| Variable: col_agua_m | ||||||||||
| Variable | Rango | X | Me | Mo | Varianza | sd | CV | As | K | Valores atípicos |
|---|---|---|---|---|---|---|---|---|---|---|
| col_agua_m | [0 ; 2988] | 268.13 | 0.00 | 250 | 307,109.51 | 554.17 | 206.68 | 2.2107 | 3.97 | 2638 [296; 2988] |
8 Conclusiones
Los valores de col_agua_m fluctúan entre 0 y 2988 y giran en torno a 0.00, con una desviación estándar de 554.17, con 2638 valores atípicos en el rango de 296 a 2988, siendo un conjunto de datos heterogéneo, cuyos valores se agrupan fuertemente en la parte baja de col_agua_m; por lo anterior, el comportamiento es perjudicial porque el 81.9% de los pozos se concentran en el primer intervalo, lo que demuestra una alta asimetría y falta de dispersión en mayores profundidades, limitando la variabilidad operativa y de estudios geomecánicos.