Exploración y Producción de los Pozos Petrolíferos en Brasil
Leonardo Ruiz
2026-03-08
knitr::opts_chunk$set(echo = TRUE)
setwd("C:/Users/LEO/Documents/ESTA")
Datos <- read.csv("tabela_de_pocos_janeiro_2018.csv", header = TRUE, sep = ";" , dec = ".", fileEncoding = "Latin1")1 Carga de librerias
library(readxl)
library(dplyr)
library(gt)
library(e1071)2 Carga de Datos
Datos_Brutos <- read_xlsx("C:/Users/LEO/Documents/ESTA/tabela_de_pocos_janeiro_2018.xlsx", sheet = 1)
colnames(Datos_Brutos) <- trimws(colnames(Datos_Brutos))3 Selección de variable
Datos <- Datos_Brutos %>%
select(any_of(c("POCO", "MESA_ROTATIVA"))) %>%
mutate(Variable_Analisis = as.numeric(gsub(",", ".", as.character(MESA_ROTATIVA))))
Variable <- na.omit(Datos$Variable_Analisis)
Variable <- Variable[Variable >= 0 & Variable < 1000]
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_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: ELEV_MESA_ROT**"),
subtitle = md("Variable: **elev_mesa_rot**")
) %>%
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: ELEV_MESA_ROT | ||||||||
| Variable: elev_mesa_rot | ||||||||
| Lím. Inf | Lím. Sup | Marca Clase (Xi) | ni | hi (%) | Ni (Asc) | Ni (Desc) | Hi (Asc) | Hi (Desc) |
|---|---|---|---|---|---|---|---|---|
| 0.00 | 66.27 | 33.13 | 20,359 | 70.60 | 20,359 | 28,838 | 70.60 | 100.00 |
| 66.27 | 132.53 | 99.40 | 6,242 | 21.65 | 26,601 | 8,479 | 92.24 | 29.40 |
| 132.53 | 198.80 | 165.67 | 1,531 | 5.31 | 28,132 | 2,237 | 97.55 | 7.76 |
| 198.80 | 265.07 | 231.93 | 403 | 1.40 | 28,535 | 706 | 98.95 | 2.45 |
| 265.07 | 331.33 | 298.20 | 65 | 0.23 | 28,600 | 303 | 99.17 | 1.05 |
| 331.33 | 397.60 | 364.47 | 69 | 0.24 | 28,669 | 238 | 99.41 | 0.83 |
| 397.60 | 463.87 | 430.73 | 22 | 0.08 | 28,691 | 169 | 99.49 | 0.59 |
| 463.87 | 530.13 | 497.00 | 19 | 0.07 | 28,710 | 147 | 99.56 | 0.51 |
| 530.13 | 596.40 | 563.27 | 25 | 0.09 | 28,735 | 128 | 99.64 | 0.44 |
| 596.40 | 662.67 | 629.53 | 21 | 0.07 | 28,756 | 103 | 99.72 | 0.36 |
| 662.67 | 728.93 | 695.80 | 19 | 0.07 | 28,775 | 82 | 99.78 | 0.28 |
| 728.93 | 795.20 | 762.07 | 15 | 0.05 | 28,790 | 63 | 99.83 | 0.22 |
| 795.20 | 861.47 | 828.33 | 27 | 0.09 | 28,817 | 48 | 99.93 | 0.17 |
| 861.47 | 927.73 | 894.60 | 14 | 0.05 | 28,831 | 21 | 99.98 | 0.07 |
| 927.73 | 994.00 | 960.87 | 7 | 0.02 | 28,838 | 7 | 100.00 | 0.02 |
| TOTAL | — | — | 28838 | 100 | — | — | — | — |
| Fuente: Datos ANP 2018 | ||||||||
5.2 Tabla Simplificada
min_val <- 0
max_val <- ceiling(max(Variable) / 100) * 100
breaks_table <- seq(min_val, max_val, by = 100)
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_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 SIMPLIFICADA: ELEV_MESA_ROT**"),
subtitle = md("Variable: **elev_mesa_rot**")
) %>%
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: ELEV_MESA_ROT | ||||||||
| Variable: elev_mesa_rot | ||||||||
| Lím. Inf | Lím. Sup | Marca Clase (Xi) | ni | hi (%) | Ni (Asc) | Ni (Desc) | Hi (Asc) | Hi (Desc) |
|---|---|---|---|---|---|---|---|---|
| 0 | 100 | 50 | 24,204 | 83.93 | 24,204 | 28,838 | 83.93 | 100.00 |
| 100 | 200 | 150 | 3,944 | 13.68 | 28,148 | 4,634 | 97.61 | 16.07 |
| 200 | 300 | 250 | 425 | 1.47 | 28,573 | 690 | 99.08 | 2.39 |
| 300 | 400 | 350 | 98 | 0.34 | 28,671 | 265 | 99.42 | 0.92 |
| 400 | 500 | 450 | 32 | 0.11 | 28,703 | 167 | 99.53 | 0.58 |
| 500 | 600 | 550 | 33 | 0.11 | 28,736 | 135 | 99.65 | 0.47 |
| 600 | 700 | 650 | 30 | 0.10 | 28,766 | 102 | 99.75 | 0.35 |
| 700 | 800 | 750 | 24 | 0.08 | 28,790 | 72 | 99.83 | 0.25 |
| 800 | 900 | 850 | 31 | 0.11 | 28,821 | 48 | 99.94 | 0.17 |
| 900 | 1000 | 950 | 17 | 0.06 | 28,838 | 17 | 100.00 | 0.06 |
| TOTAL | — | — | 28838 | 100 | — | — | — | — |
| Fuente: Datos ANP 2018 | ||||||||
6 Gráficas De Distribución De Frecuencias
col_gris_azulado <- "#5D6D7E"
col_ejes <- "#2E4053"
max_var <- max(Variable)
breaks_50 <- seq(0, max_var + 50, by = 100)
limite_x <- c(0, max(max_var, 100))6.1 GRÁFICO 1: Histograma Absoluto
par(mar = c(8, 5, 4, 2))
hist(Variable,
breaks = breaks_50,
main = "Gráfica No.1: Distribución de Mesa Rotatoria (elev_mesa_rot)",
xlab = "Mesa Rotatoria - elev_mesa_rot (m)",
ylab = "Frecuencia Absoluta",
col = col_gris_azulado,
border = "white",
axes = FALSE,
ylim = c(0, max(table(cut(Variable, breaks = breaks_50, include.lowest = TRUE, right = FALSE))) * 1.1),
xlim = limite_x)
axis(1, at = seq(0, limite_x[2], by = 100), 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_50,
main = "Gráfica N°2: Distribución de Mesa Rotatoria (elev_mesa_rot)l",
xlab = "Mesa Rotatoria - elev_mesa_rot (m)",
ylab = "Total Pozos",
col = col_gris_azulado,
border = "white",
axes = FALSE,
ylim = c(0, length(Variable)),
xlim = limite_x)
axis(1, at = seq(0, limite_x[2], by = 100), 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_base_g3 <- hist(Variable, breaks = breaks_50, plot = FALSE)
h_base_g3$counts <- (h_base_g3$counts / length(Variable)) * 100
plot(h_base_g3,
main = "Gráfica N°3: Distribución Porcentual de Mesa Rotatoria (elev_mesa_rot)",
xlab = "Mesa Rotatoria - elev_mesa_rot (m)", ylab = "Porcentaje (%)",
col = col_gris_azulado, border = "white", axes = FALSE, freq = TRUE,
ylim = c(0, 60),
xlim = limite_x)
axis(1, at = seq(0, limite_x[2], by = 100), las = 2, cex.axis = 0.7)
axis(2)
text(x = h_base_g3$mids[h_base_g3$mids <= limite_x[2]],
y = h_base_g3$counts[h_base_g3$mids <= limite_x[2]],
label = paste0(round(h_base_g3$counts[h_base_g3$mids <= limite_x[2]], 1), "%"),
pos = 3, cex = 0.6, col = col_ejes)
6.4 GRÁFICO 4: Global Porcentual
par(mar = c(8, 5, 4, 2))
# 1. Creamos el histograma base para porcentajes
h_base_g4 <- hist(Variable, breaks = breaks_50, plot = FALSE)
h_base_g4$counts <- (h_base_g4$counts / length(Variable)) * 100
# 2. Dibujamos directamente con hist
plot(h_base_g4,
main = "Gráfica No.4: Distribución Porcentual de Mesa Rotatoria (elev_mesa_rot)",
xlab = "Mesa Rotatoria - elev_mesa_rot (m)", 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 = 100), las = 2, cex.axis = 0.7)
axis(2)
text(x = h_base_g4$mids[h_base_g4$mids <= limite_x[2]],
y = h_base_g4$counts[h_base_g4$mids <= limite_x[2]],
label = paste0(round(h_base_g4$counts[h_base_g4$mids <= limite_x[2]], 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 (elev_mesa_rot)",
xlab = "Mesa Rotatoria - elev_mesa_rot (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 = 100), 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 (elev_mesa_rot)",
xlab = "Mesa Rotatoria - elev_mesa_rot (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 = 100), 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 = "elev_mesa_rot",
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),
Atipicos = status_atipicos
)
df_resumen %>%
gt() %>%
tab_header(title = md("CONCLUSIONES Y ESTADÍSTICOS"), subtitle = "Variable: elev_mesa_rot") %>%
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(110),
Mo ~ px(100),
Atipicos ~ px(140),
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: elev_mesa_rot | ||||||||||
| Variable | Rango | X | Me | Mo | Varianza | sd | CV | As | K | Valores atípicos |
|---|---|---|---|---|---|---|---|---|---|---|
| elev_mesa_rot | [0; 994] | 56.16 | 32.00 | 50 | 4,829.68 | 69.50 | 123.76 | 5.4490 | 49.24 | 1269 [164.79; 994] |
8 Conclusiones
Los valores de elev_mesa_rot fluctúan entre 0 y 994 y giran en torno a 32.00, con una desviación estándar de 69.50, con 1269 valores atípicos en el rango de 164.79 a 994, siendo un conjunto de datos heterogéneo, cuyos valores se agrupan fuertemente en la parte baja de elev_mesa_rot. Por lo anterior, el comportamiento es perjudicial, ya que más del 84% de los pozos se concentran en elevaciones mínimas de la mesa rotatoria, limitando la diversificación operacional en distintas alturas de terreno y reduciendo el rango de cobertura en la perforación.