Exploración y Producción de los Pozos Petrolíferos en Brasil
Leonardo Ruiz
2026-04-09
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", "PROFUNDIDADE_MEDIDA_M"))) %>%
mutate(Variable_Analisis = as.numeric(gsub(",", ".", as.character(PROFUNDIDADE_MEDIDA_M))))
Variable <- na.omit(Datos$Variable_Analisis)
# Filtro razonable para profundidades de pozos (valores mayores a 0 y menores a 7000 metros)
Variable <- Variable[Variable > 0 & Variable < 7000]
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
Creación de la Tabla de distribución de frecuencias.
5.1 Tabla General
# Creación de la Tabla de Distribución de Frecuencias (TDF)
TDF_Mesa <- 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
)
TDF_Mesa %>%
gt(rowname_col = "Li") %>%
tab_header(
title = md("**DISTRIBUCIÓN DE FRECUENCIAS: PROFUNDIDADE_MEDIDA_M**"),
subtitle = md("Variable: **md_m**")
) %>%
tab_source_note(source_note = "Fuente: Datos ANP 2018") %>%
# Corrección de compatibilidad para totales
summary_rows(
groups = NULL,
columns = c("ni", "hi"),
fns = list("TOTAL" = ~sum(., na.rm = TRUE))
) %>%
# Formateamos números enteros con comillas
fmt_number(
columns = c("ni", "Ni_asc", "Ni_desc"),
decimals = 0,
use_seps = TRUE
) %>%
# Formateamos los porcentajes con comillas
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: PROFUNDIDADE_MEDIDA_M | ||||||||
| Variable: md_m | ||||||||
| Lím. Inf | Lím. Sup | Marca Clase (Xi) | ni | hi (%) | Ni (Asc) | Ni (Desc) | Hi (Asc) | Hi (Desc) |
|---|---|---|---|---|---|---|---|---|
| 32.50 | 526.07 | 279.29 | 2,042 | 22.77 | 2,042 | 8,969 | 22.77 | 100.00 |
| 526.07 | 1019.64 | 772.86 | 2,254 | 25.13 | 4,296 | 6,927 | 47.90 | 77.23 |
| 1019.64 | 1513.21 | 1266.43 | 985 | 10.98 | 5,281 | 4,673 | 58.88 | 52.10 |
| 1513.21 | 2006.79 | 1760.00 | 617 | 6.88 | 5,898 | 3,688 | 65.76 | 41.12 |
| 2006.79 | 2500.36 | 2253.57 | 388 | 4.33 | 6,286 | 3,071 | 70.09 | 34.24 |
| 2500.36 | 2993.93 | 2747.14 | 496 | 5.53 | 6,782 | 2,683 | 75.62 | 29.91 |
| 2993.93 | 3487.50 | 3240.71 | 682 | 7.60 | 7,464 | 2,187 | 83.22 | 24.38 |
| 3487.50 | 3981.07 | 3734.29 | 504 | 5.62 | 7,968 | 1,505 | 88.84 | 16.78 |
| 3981.07 | 4474.64 | 4227.86 | 289 | 3.22 | 8,257 | 1,001 | 92.06 | 11.16 |
| 4474.64 | 4968.21 | 4721.43 | 256 | 2.85 | 8,513 | 712 | 94.92 | 7.94 |
| 4968.21 | 5461.79 | 5215.00 | 196 | 2.19 | 8,709 | 456 | 97.10 | 5.08 |
| 5461.79 | 5955.36 | 5708.57 | 163 | 1.82 | 8,872 | 260 | 98.92 | 2.90 |
| 5955.36 | 6448.93 | 6202.14 | 69 | 0.77 | 8,941 | 97 | 99.69 | 1.08 |
| 6448.93 | 6942.50 | 6695.71 | 28 | 0.31 | 8,969 | 28 | 100.00 | 0.31 |
| TOTAL | — | — | 8969 | 100 | — | — | — | — |
| Fuente: Datos ANP 2018 | ||||||||
5.2 Tabla Simplificada
breaks_fijos <- seq(0, 7000, by = 1000)
ni_fijo <- as.vector(table(cut(Variable, breaks = breaks_fijos, include.lowest = TRUE, right = FALSE)))
hi_fijo <- (ni_fijo / sum(ni_fijo)) * 100
Ni_asc_fijo <- cumsum(ni_fijo)
Ni_desc_fijo <- rev(cumsum(rev(ni_fijo)))
Hi_asc_fijo <- cumsum(hi_fijo)
Hi_desc_fijo <- rev(cumsum(rev(hi_fijo)))
# Tabla Simplificada
TDF_Simplificada <- data.frame(
Li = round(breaks_fijos[1:7], 2),
Ls = round(breaks_fijos[2:8], 2),
MC = round((breaks_fijos[1:7] + breaks_fijos[2:8]) / 2, 2),
ni = ni_fijo,
hi = hi_fijo,
Ni_asc = Ni_asc_fijo,
Ni_desc = Ni_desc_fijo,
Hi_asc = Hi_asc_fijo,
Hi_desc = Hi_desc_fijo
)
TDF_Simplificada %>%
gt(rowname_col = "Li") %>%
tab_header(
title = md("**DISTRIBUCIÓN DE FRECUENCIAS SIMPLIFICADA**"),
subtitle = md("Variable: **md_m** ")
) %>%
tab_source_note(source_note = "Fuente: Datos ANP 2018") %>%
summary_rows(
groups = NULL,
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 = "solid",
table.border.bottom.style = "solid",
column_labels.background.color = "#1F4E5B",
data_row.padding = px(6)
) %>%
tab_style(
style = cell_borders(sides = "left", color = "#D3D3D3", weight = px(1)),
locations = cells_body(columns = everything())
) %>%
tab_style(
style = cell_borders(sides = "left", color = "#D3D3D3", weight = px(1)),
locations = cells_column_labels(columns = everything())
)| DISTRIBUCIÓN DE FRECUENCIAS SIMPLIFICADA | ||||||||
| Variable: md_m | ||||||||
| Lím. Inf | Lím. Sup | Marca Clase (Xi) | ni | hi (%) | Ni (Asc) | Ni (Desc) | Hi (Asc) | Hi (Desc) |
|---|---|---|---|---|---|---|---|---|
| 0 | 1000 | 500 | 4,240 | 47.27 | 4,240 | 8,969 | 47.27 | 100.00 |
| 1000 | 2000 | 1500 | 1,643 | 18.32 | 5,883 | 4,729 | 65.59 | 52.73 |
| 2000 | 3000 | 2500 | 904 | 10.08 | 6,787 | 3,086 | 75.67 | 34.41 |
| 3000 | 4000 | 3500 | 1,195 | 13.32 | 7,982 | 2,182 | 89.00 | 24.33 |
| 4000 | 5000 | 4500 | 537 | 5.99 | 8,519 | 987 | 94.98 | 11.00 |
| 5000 | 6000 | 5500 | 362 | 4.04 | 8,881 | 450 | 99.02 | 5.02 |
| 6000 | 7000 | 6500 | 88 | 0.98 | 8,969 | 88 | 100.00 | 0.98 |
| TOTAL | — | — | 8969 | 100 | — | — | — | — |
| Fuente: Datos ANP 2018 | ||||||||
h_base <- hist(Variable, breaks = breaks_fijos, plot = FALSE)
limite_x <- c(0, 7000)6 Gráfica De Distribución De Frecuencias
col_gris_azulado <- "#5D6D7E"
col_ejes <- "#2E4053"
max_var <- max(Variable)
min_var <- min(Variable)
breaks_500 <- seq(floor(min_var / 500) * 500, ceiling(max_var / 500) * 500, by = 500)
h_base <- hist(Variable, breaks = breaks_500, plot = FALSE)
limite_x <- c(min(breaks_500), max(breaks_500))6.1 GRÁFICO 1: Histograma Absoluto
par(mar = c(8, 5, 4, 2))
hist(Variable,
breaks = breaks_fijos,
main = "Gráfica No.1: Distribución de md_m de Pozos Petroleros de Brasil",
xlab = "Profundidad Medida - md_m (metros)", ylab = "Frecuencia Absoluta",
col = col_gris_azulado, border = "white", axes = FALSE,
ylim = c(0, max(h_base$counts) * 1.1),
xlim = limite_x, freq = TRUE)
axis(1, at = seq(limite_x[1], limite_x[2], by = 1000), 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))
hist(Variable,
breaks = breaks_fijos,
main = "Gráfica N°2: Distribución de md_m de Pozos Petroleros de Brasil",
xlab = "Profundidad Medida - md_m (metros)", ylab = "Frecuencia Total",
col = col_gris_azulado, border = "white", axes = FALSE,
ylim = c(0, sum(h_base$counts)),
xlim = limite_x, freq = TRUE)
axis(1, at = seq(limite_x[1], limite_x[2], by = 1000), las = 2, cex.axis = 0.7)
axis(2)
grid(nx = NA, ny = NULL, col = "#D7DBDD", lty = "dotted")
6.3 GRÁFICO 3: Porcentajes (Local)
h_base_1000 <- hist(Variable, breaks = seq(0, 7000, by = 1000), plot = FALSE)
h_porc <- h_base_1000
h_porc$counts <- (h_porc$counts / sum(h_porc$counts)) * 100
par(mar = c(8, 5, 4, 2))
plot(h_porc,
main = "Gráfica N°3: Distribución Porcentual de md_m de Pozos Petroleros de Brasil",
xlab = "Profundidad Medida - md_m (metros)", ylab = "Porcentaje (%)",
col = col_gris_azulado, border = "white", axes = FALSE, freq = TRUE,
ylim = c(0, max(h_porc$counts)*1.2),
xlim = limite_x)
axis(1, at = seq(0, limite_x[2], by = 1000), las = 2, cex.axis = 0.7)
axis(2)
text(x = h_base_1000$mids,
y = h_porc$counts,
label = paste0(round(h_porc$counts, 1), "%"),
pos = 3, cex = 0.6, col = col_ejes)
6.4 GRÁFICO 4: Global Porcentual
par(mar = c(8, 5, 4, 2))
plot(h_porc,
main = "Gráfica No.4: Distribución Porcentual de md_m de Pozos Petroleros de Brasil",
xlab = "Profundidad Medida - md_m (metros)", ylab = "% del Total",
col = col_gris_azulado, border = "white", axes = FALSE, freq = TRUE,
ylim = c(0, 100),
xlim = limite_x)
axis(1, at = seq(0, limite_x[2], by = 1000), las = 2, cex.axis = 0.7)
axis(2)
text(x = h_base_1000$mids,
y = h_porc$counts,
label = paste0(round(h_porc$counts, 1), "%"),
pos = 3, cex = 0.6, col = col_ejes)
6.5 GRÁFICO 5: Boxplot
col_gris_azulado <- "#5D6D7E"
col_acento <- "#C0392B"
par(mar = c(8, 5, 4, 2))
boxplot(Variable, horizontal = TRUE, col = col_gris_azulado,
main = "Gráfica No.5: Diagrama de Caja (md_m)",
xlab = "Profundidad Medida - md_m (metros)", outline = TRUE, outpch = 19,
outcol = col_acento, axes = FALSE, xlim = c(0.7, 1.3),
ylim = limite_x)
axis(1, at = seq(limite_x[1], limite_x[2], by = 1000), las = 2, cex.axis = 0.7)
box()
## GRÁFICO 6: Ojivas ##
col_azul_oscuro <- "#2E4053"
col_rojo_fuerte <- "#C0392B"
par(mar = c(8, 5, 4, 8), xpd = TRUE)
x_vals_ojiva <- breaks_table
plot(x_vals_ojiva, c(0, Ni_asc), type = "o", col = col_azul_oscuro,
lwd = 2, pch = 19, axes = FALSE,
main = "Gráfica No.6: Ojivas Ascendente y Descendente (md_m)",
xlab = "Profundidad Medida - md_m (metros)", ylab = "Frecuencia acumulada",
xlim = c(0, 7000),
ylim = c(0, 10000))
lines(x_vals_ojiva, c(Ni_desc, 0), type = "o", col = col_rojo_fuerte,
lwd = 2, pch = 19)
axis(1, at = seq(0, 7000, by = 1000), las = 2, cex.axis = 0.7)
axis(2)
legend("right", legend = c("Ascendente", "Descendente"),
col = c(col_azul_oscuro, col_rojo_fuerte),
lty = 1, pch = 19, cex = 0.7, lwd = 2,
inset = c(-0.15, 0), bty = "n")
grid()
7 Indicadores Estadísticos
media_val <- mean(Variable)
mediana_val <- median(Variable)
sd_val <- sd(Variable)
status_atipicos <- if(length(boxplot.stats(Variable)$out) > 0) {
paste0(length(boxplot.stats(Variable)$out), " [", round(min(boxplot.stats(Variable)$out), 2), "; ", round(max(boxplot.stats(Variable)$out), 2), "]")
} else { "0 (Sin atípicos)" }
df_resumen <- data.frame(
Variable = "md_m",
Rango = paste0("[", round(min(Variable), 2), "; ", round(max(Variable), 2), "]"),
X = media_val,
Me = mediana_val,
Mo = paste(round(TDF_Mesa$MC[TDF_Mesa$hi == max(TDF_Mesa$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),
Valores_atipicos = status_atipicos
)
df_resumen %>%
gt() %>%
tab_header(title = md("CONCLUSIONES Y ESTADÍSTICOS"), subtitle = "Variable: md_m") %>%
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(110),
Mo ~ px(100),
Valores_atipicos ~ px(140),
everything() ~ px(85)
) %>%
tab_options(
column_labels.background.color = "#2E4053",
table.border.top.style = "solid",
table.border.bottom.style = "solid",
row_group.border.top.style = "solid",
row_group.border.bottom.style = "solid"
) %>%
tab_style(
style = list(
cell_text(weight = "bold", color = "white")
),
locations = cells_column_labels()
) %>%
tab_style(
style = cell_borders(
sides = "left",
color = "#D3D3D3",
weight = px(1)
),
locations = cells_body(columns = everything())
) %>%
tab_style(
style = cell_borders(
sides = "left",
color = "#D3D3D3",
weight = px(1)
),
locations = cells_column_labels(columns = everything())
)| CONCLUSIONES Y ESTADÍSTICOS | ||||||||||
| Variable: md_m | ||||||||||
| Variable | Rango | X | Me | Mo | Varianza | sd | CV | As | K | Valores_atipicos |
|---|---|---|---|---|---|---|---|---|---|---|
| md_m | [32.5; 6942.5] | 1,797.38 | 1,116.00 | 772.86 | 2,394,429.24 | 1,547.39 | 86.09 | 1.0390 | 0.06 | 21 [6525; 6942.5] |
8 Conclusiones
Los valores de Profundidad Medida (m) fluctúan entre 32.5 y 6942.5 y giran en torno a 1,116.00, con una desviación estándar de 1,547.39, con 21 valores atípicos (en el rango de 6525 a 6942.5), siendo un conjunto de datos heterogéneo, cuyos valores se agrupan fuertemente en la parte baja de Profundidad Medida (m). Por lo anterior, el comportamiento es perjudicial, ya que más del 47% de los pozos se concentran en los primeros 1000 metros, evidenciando una escasez crítica de perforaciones profundas que limita la evaluación exploratoria a mayores extensiones.