Exploración y Producción de los Pozos Petrolíferos en Brasil
Leonardo Ruiz
2026-03-08
knitr::opts_chunk$set(echo = TRUE)
setwd("C:/Users/LEO/Documents/ESTA")
Datos <- read.csv("tabela_de_pocos_janeiro_2018.csv", header = TRUE, sep = ";" , dec = ".", fileEncoding = "Latin1")1 Carga de librerias
# 1. LIBRERÍAS Y CARGA DE DATOS
library(readxl)
library(dplyr)
library(gt)
library(e1071)2 Carga de datos
Datos_Brutos <- read_xlsx("C:/Users/LEO/Documents/ESTA/tabela_de_pocos_janeiro_2018.xlsx", sheet = 1)
colnames(Datos_Brutos) <- trimws(colnames(Datos_Brutos))
# Cambio de variable a PROFUNDIDADE_SONDADOR_M
Datos <- Datos_Brutos %>%
select(any_of(c("POCO", "PROFUNDIDADE_SONDADOR_M"))) %>%
mutate(Variable_Analisis = as.numeric(gsub(",", ".", as.character(PROFUNDIDADE_SONDADOR_M))))3 Selección de variable
Variable <- na.omit(Datos$Variable_Analisis)
Variable <- Variable[Variable > 0 & Variable < 15000]
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)
# Cálculo de ni usando cut
ni <- as.vector(table(cut(Variable, breaks = breaks_table, include.lowest = TRUE, right = FALSE)))
# Cálculo de vectores estadísticos
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
A continuación se presenta la tabla de distribución de frecuencias obtenida para la Profundidad del Sondador.
5.1 Tabla General
TDF_Sondador <- 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 = round(hi, 2),
Ni_asc = Ni_asc,
Ni_desc = Ni_desc,
Hi_asc = round(Hi_asc, 2),
Hi_desc = round(Hi_desc, 2)
)
TDF_Sondador %>%
gt(rowname_col = "Li") %>%
tab_header(
title = md("**DISTRIBUCIÓN DE FRECUENCIAS: PROFUNDIDAD SONDADOR**"),
subtitle = md("Variable: **PROFUNDIDADE_SONDADOR_M**")
) %>%
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 = list(cell_fill(color = "#2E4053"), cell_text(color = "white", weight = "bold")),
locations = list(cells_title(), cells_column_labels(), cells_stubhead())
) %>%
tab_options(
table.border.top.color = "#2E4053",
table.border.bottom.color = "#2E4053",
column_labels.border.bottom.color = "#2E4053",
data_row.padding = px(6)
)| DISTRIBUCIÓN DE FRECUENCIAS: PROFUNDIDAD SONDADOR | ||||||||
| Variable: PROFUNDIDADE_SONDADOR_M | ||||||||
| Lím. Inf | Lím. Sup | Marca Clase (Xi) | ni | hi (%) | Ni (Asc) | Ni (Desc) | Hi (Asc) | Hi (Desc) |
|---|---|---|---|---|---|---|---|---|
| 5.00 | 543.35 | 274.17 | 6,150 | 23.37 | 6,150 | 26,312 | 23.37 | 100.00 |
| 543.35 | 1081.69 | 812.52 | 6,823 | 25.93 | 12,973 | 20,162 | 49.30 | 76.63 |
| 1081.69 | 1620.04 | 1350.87 | 4,181 | 15.89 | 17,154 | 13,339 | 65.19 | 50.70 |
| 1620.04 | 2158.39 | 1889.21 | 2,117 | 8.05 | 19,271 | 9,158 | 73.24 | 34.81 |
| 2158.39 | 2696.73 | 2427.56 | 1,684 | 6.40 | 20,955 | 7,041 | 79.64 | 26.76 |
| 2696.73 | 3235.08 | 2965.91 | 2,131 | 8.10 | 23,086 | 5,357 | 87.74 | 20.36 |
| 3235.08 | 3773.43 | 3504.25 | 1,512 | 5.75 | 24,598 | 3,226 | 93.49 | 12.26 |
| 3773.43 | 4311.77 | 4042.60 | 687 | 2.61 | 25,285 | 1,714 | 96.10 | 6.51 |
| 4311.77 | 4850.12 | 4580.95 | 397 | 1.51 | 25,682 | 1,027 | 97.61 | 3.90 |
| 4850.12 | 5388.47 | 5119.29 | 290 | 1.10 | 25,972 | 630 | 98.71 | 2.39 |
| 5388.47 | 5926.81 | 5657.64 | 221 | 0.84 | 26,193 | 340 | 99.55 | 1.29 |
| 5926.81 | 6465.16 | 6195.99 | 80 | 0.30 | 26,273 | 119 | 99.85 | 0.45 |
| 6465.16 | 7003.51 | 6734.33 | 27 | 0.10 | 26,300 | 39 | 99.95 | 0.15 |
| 7003.51 | 7541.85 | 7272.68 | 9 | 0.03 | 26,309 | 12 | 99.99 | 0.05 |
| 7541.85 | 8080.20 | 7811.03 | 3 | 0.01 | 26,312 | 3 | 100.00 | 0.01 |
| TOTAL | — | — | 26312 | 99.99 | — | — | — | — |
| Fuente: Datos ANP 2018 | ||||||||
5.2 Tabla simplificada
# Frecuencia modificada de 400 en 400
min_val <- floor(min(Variable) / 400) * 400
max_val <- ceiling(max(Variable) / 400) * 400
breaks_table <- seq(min_val, max_val, by = 400)
K <- length(breaks_table) - 1
# Cálculo de ni usando cut
ni <- as.vector(table(cut(Variable, breaks = breaks_table, include.lowest = TRUE, right = FALSE)))
# Cálculo de vectores estadísticos
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_Sondador <- 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 = round(hi, 2),
Ni_asc = Ni_asc,
Ni_desc = Ni_desc,
Hi_asc = round(Hi_asc, 2),
Hi_desc = round(Hi_desc, 2)
)
TDF_Sondador %>%
gt(rowname_col = "Li") %>%
tab_header(
title = md("**DISTRIBUCIÓN DE FRECUENCIAS: PROFUNDIDAD SONDADOR**"),
subtitle = md("Variable: **PROFUNDIDADE_SONDADOR_M** (Amplitud = 400)")
) %>%
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 = list(cell_fill(color = "#2E4053"), cell_text(color = "white", weight = "bold")),
locations = list(cells_title(), cells_column_labels(), cells_stubhead())
) %>%
tab_options(
table.border.top.color = "#2E4053",
table.border.bottom.color = "#2E4053",
column_labels.border.bottom.color = "#2E4053",
data_row.padding = px(6)
)| DISTRIBUCIÓN DE FRECUENCIAS: PROFUNDIDAD SONDADOR | ||||||||
| Variable: PROFUNDIDADE_SONDADOR_M (Amplitud = 400) | ||||||||
| Lím. Inf | Lím. Sup | Marca Clase (Xi) | ni | hi (%) | Ni (Asc) | Ni (Desc) | Hi (Asc) | Hi (Desc) |
|---|---|---|---|---|---|---|---|---|
| 0 | 400 | 200 | 3,819 | 14.51 | 3,819 | 26,312 | 14.51 | 100.00 |
| 400 | 800 | 600 | 5,577 | 21.20 | 9,396 | 22,493 | 35.71 | 85.49 |
| 800 | 1200 | 1000 | 4,266 | 16.21 | 13,662 | 16,916 | 51.92 | 64.29 |
| 1200 | 1600 | 1400 | 3,355 | 12.75 | 17,017 | 12,650 | 64.67 | 48.08 |
| 1600 | 2000 | 1800 | 1,755 | 6.67 | 18,772 | 9,295 | 71.34 | 35.33 |
| 2000 | 2400 | 2200 | 1,196 | 4.55 | 19,968 | 7,540 | 75.89 | 28.66 |
| 2400 | 2800 | 2600 | 1,362 | 5.18 | 21,330 | 6,344 | 81.07 | 24.11 |
| 2800 | 3200 | 3000 | 1,642 | 6.24 | 22,972 | 4,982 | 87.31 | 18.93 |
| 3200 | 3600 | 3400 | 1,260 | 4.79 | 24,232 | 3,340 | 92.09 | 12.69 |
| 3600 | 4000 | 3800 | 718 | 2.73 | 24,950 | 2,080 | 94.82 | 7.91 |
| 4000 | 4400 | 4200 | 399 | 1.52 | 25,349 | 1,362 | 96.34 | 5.18 |
| 4400 | 4800 | 4600 | 296 | 1.12 | 25,645 | 963 | 97.47 | 3.66 |
| 4800 | 5200 | 5000 | 207 | 0.79 | 25,852 | 667 | 98.25 | 2.53 |
| 5200 | 5600 | 5400 | 229 | 0.87 | 26,081 | 460 | 99.12 | 1.75 |
| 5600 | 6000 | 5800 | 129 | 0.49 | 26,210 | 231 | 99.61 | 0.88 |
| 6000 | 6400 | 6200 | 56 | 0.21 | 26,266 | 102 | 99.83 | 0.39 |
| 6400 | 6800 | 6600 | 30 | 0.11 | 26,296 | 46 | 99.94 | 0.17 |
| 6800 | 7200 | 7000 | 12 | 0.05 | 26,308 | 16 | 99.98 | 0.06 |
| 7200 | 7600 | 7400 | 1 | 0.00 | 26,309 | 4 | 99.99 | 0.02 |
| 7600 | 8000 | 7800 | 2 | 0.01 | 26,311 | 3 | 100.00 | 0.01 |
| 8000 | 8400 | 8200 | 1 | 0.00 | 26,312 | 1 | 100.00 | 0.00 |
| TOTAL | — | — | 26312 | 100 | — | — | — | — |
| Fuente: Datos ANP 2018 | ||||||||
6 Gráficas De Distribución De Frecuencia
6.1 Histogramas de Frecuencia
col_gris_azulado <- "#5D6D7E"
col_ejes <- "#2E4053"
h_base <- hist(Variable, breaks = breaks_table, plot = FALSE)
# GRÁFICO 1: Histograma Absoluto
par(mar = c(8, 5, 4, 2))
plot(h_base,
main = "Gráfica No.1: Distribución Absoluta (Sondador)",
xlab = "Profundidad Sondador (m)", ylab = "Frecuencia Absoluta",
col = col_gris_azulado, border = "white", axes = FALSE,
ylim = c(0, max(h_base$counts) * 1.1))
axis(1, at = round(h_base$breaks, 0), las = 2, cex.axis = 0.7)
axis(2)
grid(nx=NA, ny=NULL, col="#D7DBDD", lty="dotted") 
# GRÁFICO 2: Histograma Global
par(mar = c(8, 5, 4, 2))
plot(h_base,
main = "Gráfica N°2: Distribución Global (Sondador)",
xlab = "Profundidad Sondador (m)", ylab = "Total Pozos",
col = col_gris_azulado, border = "white", axes = FALSE,
ylim = c(0, sum(h_base$counts)))
axis(1, at = round(h_base$breaks, 0), las = 2, cex.axis = 0.7)
axis(2)
grid(nx=NA, ny=NULL, col="#D7DBDD", lty="dotted")
6.2 Gráficos Porcentuales
h_porc <- h_base
h_porc$counts <- (h_porc$counts / sum(h_porc$counts)) * 100
# GRÁFICO 3: Porcentajes (Local)
par(mar = c(8, 5, 4, 2))
plot(h_porc,
main = "Gráfica N°3: Distribución Porcentual (Local)",
xlab = "Profundidad Sondador (m)", ylab = "Porcentaje (%)",
col = col_gris_azulado, border = "white", axes = FALSE, freq = TRUE,
ylim = c(0, max(h_porc$counts)*1.2))
axis(1, at = round(h_base$breaks, 0), las = 2, cex.axis = 0.7)
axis(2)
text(x = h_base$mids, y = h_porc$counts, label = paste0(round(h_porc$counts, 1), "%"), pos = 3, cex = 0.6, col = col_ejes)
# GRÁFICO 4: Global Porcentual
par(mar = c(8, 5, 4, 2))
plot(h_porc,
main = "Gráfica No.4: Distribución Porcentual (Global)",
xlab = "Profundidad Sondador (m)", ylab = "% del Total",
col = col_gris_azulado, border = "white", axes = FALSE, freq = TRUE,
ylim = c(0, 100))
axis(1, at = round(h_base$breaks, 0), las = 2, cex.axis = 0.7)
text(x = h_base$mids, y = h_porc$counts, label = paste0(round(h_porc$counts, 1), "%"), pos = 3, cex = 0.6, col = col_ejes)
axis(2)
6.3 Diagrama de Caja y Ojivas
# GRÁFICO 5: Boxplot
par(mar = c(5, 5, 4, 2))
boxplot(Variable, horizontal = TRUE, col = col_gris_azulado,
main = "Gráfica No.5: Diagrama de Caja (Sondador)",
xlab = "Profundidad Sondador (m)", outline = TRUE, outpch = 19, outcol = "#C0392B")
axis(1, at = pretty(Variable, n=20))
# GRÁFICO 6: Ojivas
par(mar = c(5, 5, 4, 8), xpd = TRUE)
x_vals <- breaks_table
plot(x_vals, c(0, Ni_asc), type = "o", col = "#2E4053", lwd=2, pch=19, axes=F,
main = "Gráfica No.6: Ojivas Ascendente y Descendente",
xlab = "Profundidad Sondador (m)", ylab = "Frecuencia acumulada")
lines(x_vals, c(Ni_desc, 0), type = "o", col = "#C0392B", lwd=2, pch=19)
axis(1, at = round(breaks_table,0), las=2, cex.axis=0.6)
axis(2)
legend("right", legend = c("Asc", "Desc"), col = c("#2E4053", "#C0392B"), lty = 1, pch = 19, 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 = "Profundidad Sondador (m)",
Rango = paste0("[", round(min(Variable), 2), "; ", round(max(Variable), 2), "]"),
X = media_val,
Me = mediana_val,
Mo = paste(round(TDF_Sondador$MC[TDF_Sondador$ni == max(TDF_Sondador$ni)], 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: PROFUNDIDADE_SONDADOR_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: PROFUNDIDADE_SONDADOR_M | ||||||||||
| Variable | Rango | X | Me | Mo | Varianza | sd | CV | As | K | Valores atípicos |
|---|---|---|---|---|---|---|---|---|---|---|
| Profundidad Sondador (m) | [5; 8080.2] | 1,557.01 | 1,119.00 | 600 | 1,615,037.78 | 1,270.84 | 81.62 | 1.2423 | 1.10 | 586 [4931; 8080.2] |
8 Conclusiones
Los valores de Profundidad Sondador (m) fluctúan entre 5 y 8080.2 y giran en torno a 1119.00, con una desviación estándar de 1270.84, con 586 valores atípicos en el rango de 4931 a 8080.2, siendo un conjunto de datos heterogéneo, cuyos valores se agrupan fuertemente en la parte baja de Profundidad Sondador (m). Por lo anterior, el comportamiento es perjudicial, ya que más del 64% de los pozos se concentran en los primeros 1200 metros, limitando el aprovechamiento de reservas profundas y la rentabilidad global de la perforación.