Exploración y Producción de los Pozos Petrolíferos en Brasil
Leonardo Ruiz
2026-03-08
knitr::opts_chunk$set(echo = TRUE)
setwd("C:/Users/LEO/Documents/ESTA")
Datos <- read.csv("tabela_de_pocos_janeiro_2018.csv", header = TRUE, sep = ";" , dec = ".", fileEncoding = "Latin1")1 Carga de librerias
library(readxl)
library(dplyr)
library(gt)
library(e1071)2 Carga de datos
Datos_Brutos <- read_xlsx("C:/Users/LEO/Documents/ESTA/tabela_de_pocos_janeiro_2018.xlsx", sheet = 1)
colnames(Datos_Brutos) <- trimws(colnames(Datos_Brutos))3 Selección de Variable
Datos <- Datos_Brutos %>%
select(any_of(c("POCO", "LATITUDE_BASE_DD"))) %>%
mutate(lat_base_gd = as.numeric(gsub(",", ".", as.character(LATITUDE_BASE_DD))))
Variable <- na.omit(Datos$lat_base_gd)
Variable <- Variable[Variable >= -35 & Variable <= 5]
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
# Creación de la Tabla de Distribución de Frecuencias (TDF)
TDF_Latitud <- 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"
# Configuración de los breaks automáticos e histograma base para distribución geográfica
breaks_auto <- seq(min(Variable), max(Variable), length.out = K + 1)
h_base <- hist(Variable, breaks = breaks_auto, plot = FALSE)
limite_x <- c(min(breaks_auto), max(breaks_auto))
TDF_Latitud %>%
gt(rowname_col = "Li") %>%
tab_header(
title = md("**DISTRIBUCIÓN DE FRECUENCIAS: LATITUD BASE**"),
subtitle = md("Variable: **lat_base_gd**")
) %>%
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: LATITUD BASE | ||||||||
| Variable: lat_base_gd | ||||||||
| Lím. Inf | Lím. Sup | Marca Clase (Xi) | ni | hi (%) | Ni (Asc) | Ni (Desc) | Hi (Asc) | Hi (Desc) |
|---|---|---|---|---|---|---|---|---|
| -32.93 | -30.43 | -31.68 | 12 | 0.04 | 12 | 29,575 | 0.04 | 100.00 |
| -30.43 | -27.93 | -29.18 | 18 | 0.06 | 30 | 29,563 | 0.10 | 99.96 |
| -27.93 | -25.44 | -26.68 | 303 | 1.02 | 333 | 29,545 | 1.13 | 99.90 |
| -25.44 | -22.94 | -24.19 | 877 | 2.97 | 1,210 | 29,242 | 4.09 | 98.87 |
| -22.94 | -20.44 | -21.69 | 3,079 | 10.41 | 4,289 | 28,365 | 14.50 | 95.91 |
| -20.44 | -17.94 | -19.19 | 2,029 | 6.86 | 6,318 | 25,286 | 21.36 | 85.50 |
| -17.94 | -15.45 | -16.70 | 135 | 0.46 | 6,453 | 23,257 | 21.82 | 78.64 |
| -15.45 | -12.95 | -14.20 | 163 | 0.55 | 6,616 | 23,122 | 22.37 | 78.18 |
| -12.95 | -10.45 | -11.70 | 11,444 | 38.69 | 18,060 | 22,959 | 61.07 | 77.63 |
| -10.45 | -7.96 | -9.21 | 1,051 | 3.55 | 19,111 | 11,515 | 64.62 | 38.93 |
| -7.96 | -5.46 | -6.71 | 611 | 2.07 | 19,722 | 10,464 | 66.68 | 35.38 |
| -5.46 | -2.96 | -4.21 | 9,444 | 31.93 | 29,166 | 9,853 | 98.62 | 33.32 |
| -2.96 | -0.47 | -1.71 | 274 | 0.93 | 29,440 | 409 | 99.54 | 1.38 |
| -0.47 | 2.03 | 0.78 | 52 | 0.18 | 29,492 | 135 | 99.72 | 0.46 |
| 2.03 | 4.53 | 3.28 | 83 | 0.28 | 29,575 | 83 | 100.00 | 0.28 |
| TOTAL | — | — | 29575 | 100 | — | — | — | — |
| Fuente: Datos ANP 2018 | ||||||||
5.2 Tabla Simplificada
min_val <- floor(min(Variable) / 5) * 5
max_val <- ceiling(max(Variable) / 5) * 5
breaks_table <- seq(min_val, max_val, by = 5)
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)))
TDF_Latitud <- 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"
breaks_auto <- breaks_table
limite_x <- c(min(breaks_auto), max(breaks_auto))
TDF_Latitud %>%
gt(rowname_col = "Li") %>%
tab_header(
title = md("**DISTRIBUCIÓN DE FRECUENCIAS SIMPLIFICADA: LATITUD BASE **"),
subtitle = md("Variable: **lat_base_gd**")
) %>%
tab_source_note(source_note = "Fuente: Datos ANP 2018") %>%
grand_summary_rows(
columns = c(ni, hi),
fns = list("TOTAL" = ~sum(., na.rm = TRUE))
) %>%
fmt_number(
columns = c(ni, Ni_asc, Ni_desc),
decimals = 0,
use_seps = TRUE
) %>%
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") %>%
cols_align(align = "center", columns = everything()) %>%
tab_style(
style = cell_text(align = "center"),
locations = cells_stub()
) %>%
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 SIMPLIFICADA: LATITUD BASE ** | ||||||||
| Variable: lat_base_gd | ||||||||
| Lím. Inf | Lím. Sup | Marca Clase (Xi) | ni | hi (%) | Ni (Asc) | Ni (Desc) | Hi (Asc) | Hi (Desc) |
|---|---|---|---|---|---|---|---|---|
| -35 | -30 | -32.5 | 15 | 0.05 | 15 | 29,575 | 0.05 | 100.00 |
| -30 | -25 | -27.5 | 460 | 1.56 | 475 | 29,560 | 1.61 | 99.95 |
| -25 | -20 | -22.5 | 3,933 | 13.30 | 4,408 | 29,100 | 14.90 | 98.39 |
| -20 | -15 | -17.5 | 2,069 | 7.00 | 6,477 | 25,167 | 21.90 | 85.10 |
| -15 | -10 | -12.5 | 11,771 | 39.80 | 18,248 | 23,098 | 61.70 | 78.10 |
| -10 | -5 | -7.5 | 8,583 | 29.02 | 26,831 | 11,327 | 90.72 | 38.30 |
| -5 | 0 | -2.5 | 2,622 | 8.87 | 29,453 | 2,744 | 99.59 | 9.28 |
| 0 | 5 | 2.5 | 122 | 0.41 | 29,575 | 122 | 100.00 | 0.41 |
| TOTAL | — | — | 29575 | 100 | — | — | — | — |
| Fuente: Datos ANP 2018 | ||||||||
6 Gráficas de distribución de frecuencia
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 lat_base_gd de Pozos Petroleros de Brasil",
xlab = "Latitud Base - lat_base_gd (Grados)",
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(min_val, max_val, by = 5), 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 lat_base_gd de Pozos Petroleros de Brasil",
xlab = "Latitud Base - lat_base_gd (Grados)",
ylab = "Total Pozos",
col = col_gris_azulado,
border = "white",
axes = FALSE,
ylim = c(0, sum(ni)),
xlim = limite_x
)
axis(1, at = seq(min_val, max_val, by = 5), 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)
h_p3$counts <- hi
plot(
h_p3,
main = "Gráfica N°3: Distribución Porcentual de Latitud Base",
xlab = "Latitud Base - lat_base_gd (Grados)",
ylab = "Porcentaje (%)",
col = col_gris_azulado,
border = "white",
axes = FALSE,
ylim = c(0, max(hi) * 1.2),
xlim = limite_x,
freq = TRUE
)
axis(1, at = seq(min_val, max_val, by = 5), las = 2, cex.axis = 0.7)
axis(2, at = seq(0, max(hi) + 5, by = 5), labels = paste0(seq(0, max(hi) + 5, by = 5), "%"))
grid(nx = NA, ny = NULL, col = "#D7DBDD", lty = "dotted")
text(
x = h_p3$mids,
y = hi,
label = paste0(round(hi, 1), "%"),
pos = 3, cex = 0.55, 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$counts <- hi
plot(
h_p4,
main = "Gráfica N°4: Distribución Porcentual de Latitud Base",
xlab = "Latitud Base - lat_base_gd (Grados)",
ylab = "Porcentaje (%)",
col = col_gris_azulado,
border = "white",
axes = FALSE,
ylim = c(0, 105),
xlim = limite_x,
freq = TRUE
)
axis(1, at = seq(min_val, max_val, by = 5), las = 2, cex.axis = 0.7)
axis(2, at = seq(0, 100, by = 20), labels = paste0(seq(0, 100, by = 20), "%"))
grid(nx = NA, ny = NULL, col = "#D7DBDD", lty = "dotted")
text(
x = h_p4$mids,
y = hi,
label = paste0(round(hi, 1), "%"),
pos = 3,
cex = 0.55,
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 (lat_base_gd)",
xlab = "Latitud Base - lat_base_gd (Grados)", outline = TRUE, outpch = 19,
outcol = col_acento, axes = FALSE, xlim = c(0.7, 1.3),
ylim = limite_x)
axis(1, at = seq(min_val, max_val, by = 5), 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 (lat_base_gd)",
xlab = "Latitud Base - lat_base_gd (Grados)", 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(min_val, max_val, by = 5), 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 = "lat_base_gd",
Rango = paste0("[", round(min(Variable), 2), " ; ", round(max(Variable), 2), "]"),
X = media_val,
Me = mediana_val,
Mo = paste(round(TDF_Latitud$MC[TDF_Latitud$hi == max(TDF_Latitud$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: lat_base_gd") %>%
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: lat_base_gd | ||||||||||
| Variable | Rango | X | Me | Mo | Varianza | sd | CV | As | K | Valores atípicos |
|---|---|---|---|---|---|---|---|---|---|---|
| lat_base_gd | [-32.93 ; 4.53] | −11.41 | −10.71 | -12.5 | 39.50 | 6.28 | 55.06 | −0.6504 | −0.51 | 810 [-32.93; -23.71] |
8 Conclusiones
Los valores de lat_base_gd fluctúan entre -32.93 y 4.53 y giran en torno a -10.71, con una desviación estándar de 6.28, con 810 valores atípicos en el rango de -32.93 a -23.71, siendo un conjunto de datos heterogéneo, cuyos valores se agrupan medianamente en la parte media de lat_base_gd. Por lo anterior, el comportamiento es perjudicial, ya que más del 68% de los pozos se concentran de forma dispersa entre los -15 y -5 grados, impidiendo un control operativo centralizado.