Exploración y Producción de los Pozos Petrolíferos en Brasil
Leonardo Ruiz
2026-03-08
knitr::opts_chunk$set(echo = TRUE)
setwd("C:/Users/LEO/Documents/ESTA")
Datos <- read.csv("tabela_de_pocos_janeiro_2018.csv", header = TRUE, sep = ";" , dec = ".", fileEncoding = "Latin1")1 Carga de librerias
library(readxl)
library(dplyr)
library(gt)
library(e1071)2 Carga de datos
Datos_Brutos <- read_xlsx("C:/Users/LEO/Documents/ESTA/tabela_de_pocos_janeiro_2018.xlsx", sheet = 1)
colnames(Datos_Brutos) <- trimws(colnames(Datos_Brutos))3 Selección de variable
Datos <- Datos_Brutos %>%
select(any_of(c("POCO", "LONGITUDE_BASE_DD"))) %>%
mutate(lon_base_gd = as.numeric(gsub(",", ".", as.character(LONGITUDE_BASE_DD))))
Variable <- na.omit(Datos$lon_base_gd)
Variable <- Variable[Variable >= -75 & Variable <= -30]
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 (Mantenemos los valores reales sin redondear para la tabla)
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_Longitud <- 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
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_Longitud %>%
gt(rowname_col = "Li") %>%
tab_header(
title = md("**DISTRIBUCIÓN DE FRECUENCIAS: LONGITUD BASE**"),
subtitle = md("Variable: **lon_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: LONGITUD BASE | ||||||||
| Variable: lon_base_gd | ||||||||
| Lím. Inf | Lím. Sup | Marca Clase (Xi) | ni | hi (%) | Ni (Asc) | Ni (Desc) | Hi (Asc) | Hi (Desc) |
|---|---|---|---|---|---|---|---|---|
| -73.38 | -70.81 | -72.09 | 12 | 0.04 | 12 | 29,575 | 0.04 | 100.00 |
| -70.81 | -68.24 | -69.52 | 9 | 0.03 | 21 | 29,563 | 0.07 | 99.96 |
| -68.24 | -65.67 | -66.95 | 71 | 0.24 | 92 | 29,554 | 0.31 | 99.93 |
| -65.67 | -63.10 | -64.38 | 281 | 0.95 | 373 | 29,483 | 1.26 | 99.69 |
| -63.10 | -60.53 | -61.81 | 19 | 0.06 | 392 | 29,202 | 1.33 | 98.74 |
| -60.53 | -57.96 | -59.24 | 136 | 0.46 | 528 | 29,183 | 1.79 | 98.67 |
| -57.96 | -55.39 | -56.67 | 54 | 0.18 | 582 | 29,047 | 1.97 | 98.21 |
| -55.39 | -52.82 | -54.10 | 31 | 0.10 | 613 | 28,993 | 2.07 | 98.03 |
| -52.82 | -50.25 | -51.53 | 121 | 0.41 | 734 | 28,962 | 2.48 | 97.93 |
| -50.25 | -47.68 | -48.96 | 128 | 0.43 | 862 | 28,841 | 2.91 | 97.52 |
| -47.68 | -45.11 | -46.39 | 260 | 0.88 | 1,122 | 28,713 | 3.79 | 97.09 |
| -45.11 | -42.54 | -43.82 | 704 | 2.38 | 1,826 | 28,453 | 6.17 | 96.21 |
| -42.54 | -39.97 | -41.25 | 2,812 | 9.51 | 4,638 | 27,749 | 15.68 | 93.83 |
| -39.97 | -37.40 | -38.68 | 11,902 | 40.24 | 16,540 | 24,937 | 55.93 | 84.32 |
| -37.40 | -34.83 | -36.11 | 13,035 | 44.07 | 29,575 | 13,035 | 100.00 | 44.07 |
| TOTAL | — | — | 29575 | 100 | — | — | — | — |
| Fuente: Datos ANP 2018 | ||||||||
5.2 Tabla simplificada
min_val <- floor(min(Variable) / 2) * 2
max_val <- ceiling(max(Variable) / 2) * 2
breaks_table <- seq(min_val, max_val, by = 2)
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_Longitud <- 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_Longitud %>%
gt(rowname_col = "Li") %>%
tab_header(
title = md("**DISTRIBUCIÓN DE FRECUENCIAS SIMPLIFICADA: LONGITUD BASE **"),
subtitle = md("Variable: **lon_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: LONGITUD BASE ** | ||||||||
| Variable: lon_base_gd | ||||||||
| Lím. Inf | Lím. Sup | Marca Clase (Xi) | ni | hi (%) | Ni (Asc) | Ni (Desc) | Hi (Asc) | Hi (Desc) |
|---|---|---|---|---|---|---|---|---|
| -74 | -72 | -73 | 11 | 0.04 | 11 | 29,575 | 0.04 | 100.00 |
| -72 | -70 | -71 | 4 | 0.01 | 15 | 29,564 | 0.05 | 99.96 |
| -70 | -68 | -69 | 7 | 0.02 | 22 | 29,560 | 0.07 | 99.95 |
| -68 | -66 | -67 | 57 | 0.19 | 79 | 29,553 | 0.27 | 99.93 |
| -66 | -64 | -65 | 290 | 0.98 | 369 | 29,496 | 1.25 | 99.73 |
| -64 | -62 | -63 | 9 | 0.03 | 378 | 29,206 | 1.28 | 98.75 |
| -62 | -60 | -61 | 21 | 0.07 | 399 | 29,197 | 1.35 | 98.72 |
| -60 | -58 | -59 | 125 | 0.42 | 524 | 29,176 | 1.77 | 98.65 |
| -58 | -56 | -57 | 40 | 0.14 | 564 | 29,051 | 1.91 | 98.23 |
| -56 | -54 | -55 | 40 | 0.14 | 604 | 29,011 | 2.04 | 98.09 |
| -54 | -52 | -53 | 44 | 0.15 | 648 | 28,971 | 2.19 | 97.96 |
| -52 | -50 | -51 | 96 | 0.32 | 744 | 28,927 | 2.52 | 97.81 |
| -50 | -48 | -49 | 110 | 0.37 | 854 | 28,831 | 2.89 | 97.48 |
| -48 | -46 | -47 | 167 | 0.56 | 1,021 | 28,721 | 3.45 | 97.11 |
| -46 | -44 | -45 | 376 | 1.27 | 1,397 | 28,554 | 4.72 | 96.55 |
| -44 | -42 | -43 | 558 | 1.89 | 1,955 | 28,178 | 6.61 | 95.28 |
| -42 | -40 | -41 | 2,563 | 8.67 | 4,518 | 27,620 | 15.28 | 93.39 |
| -40 | -38 | -39 | 9,255 | 31.29 | 13,773 | 25,057 | 46.57 | 84.72 |
| -38 | -36 | -37 | 15,275 | 51.65 | 29,048 | 15,802 | 98.22 | 53.43 |
| -36 | -34 | -35 | 527 | 1.78 | 29,575 | 527 | 100.00 | 1.78 |
| TOTAL | — | — | 29575 | 100 | — | — | — | — |
| Fuente: Datos ANP 2018 | ||||||||
6 Gráficas De Distribución De Frecuencias
min_val <- floor(min(Variable) / 2) * 2
max_val <- ceiling(max(Variable) / 2) * 2
breaks_graficas <- seq(min_val, max_val, by = 2)
limite_x <- c(min_val, max_val)6.1 GRÁFICO 1: Histograma Absoluto
par(mar = c(8, 5, 4, 2))
h_abs <- hist(
Variable,
breaks = breaks_graficas,
main = "Gráfica No.1: Distribución de lon_base_gd de Pozos Petroleros de Brasil",
xlab = "Longitud Base - lon_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 = 2), 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_graficas,
main = "Gráfica N°2: Distribución de lon_base_gd de Pozos Petroleros de Brasil",
xlab = "Longitud Base - lon_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 = 2), 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$counts <- hi
plot(
h_p3,
main = "Gráfica N°3: Distribución Porcentual de Longitud Base",
xlab = "Longitud Base - lon_base_gd (Grados)",
ylab = "Porcentaje (%)",
col = col_gris_azulado,
border = "white",
axes = FALSE,
ylim = c(0, 50),
xlim = limite_x,
freq = TRUE
)
axis(1, at = seq(min_val, max_val, by = 2), las = 2, cex.axis = 0.7)
axis(2, at = seq(0, 100, by = 20), labels = paste0(seq(0, 100, by = 20), "%"))
grid(nx = NA, ny = NULL, col = "#D7DBDD", lty = "dotted")
text(
x = h_p3$mids,
y = hi,
label = paste0(round(hi, 1), "%"),
pos = 3,
cex = 0.55,
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$counts <- hi
plot(
h_p4,
main = "Gráfica N°4: Distribución Porcentual de Longitud Base",
xlab = "Longitud Base - lon_base_gd (Grados)",
ylab = "Porcentaje (%)",
col = col_gris_azulado,
border = "white",
axes = FALSE,
ylim = c(0, 105),
xlim = limite_x,
freq = TRUE
)
axis(1, at = seq(min_val, max_val, by = 2), las = 2, cex.axis = 0.7)
axis(2, at = seq(0, 100, by = 20), labels = paste0(seq(0, 100, by = 20), "%"))
grid(nx = NA, ny = NULL, col = "#D7DBDD", lty = "dotted")
text(
x = h_p3$mids,
y = hi,
label = paste0(round(hi, 1), "%"),
pos = 3,
cex = 0.55,
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 (lon_base_gd)",
xlab = "Longitud Base - lon_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 = 2), 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_graficas
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 (lon_base_gd)",
xlab = "Longitud Base - lon_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 = 2), 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 = "lon_base_gd",
Rango = paste0("[", round(min(Variable), 2), " ; ", round(max(Variable), 2), "]"),
X = media_val,
Me = mediana_val,
Mo = paste(round(TDF_Longitud$MC[TDF_Longitud$hi == max(TDF_Longitud$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: lon_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: lon_base_gd | ||||||||||
| Variable | Rango | X | Me | Mo | Varianza | sd | CV | As | K | Valores atípicos |
|---|---|---|---|---|---|---|---|---|---|---|
| lon_base_gd | [-73.38 ; -34.83] | −38.80 | −37.78 | -37 | 16.71 | 4.09 | 10.54 | −4.8053 | 26.63 | 1787 [-73.38; -42.67] |
8 Conclusiones
Los valores de lon_base_gd fluctúan entre -73.38 y -34.83 y giran en torno a -37.78, con una desviación estándar de 4.09, con 1787 valores atípicos en el rango de -73.38 a -42.67, siendo un conjunto de datos homogéneo, cuyos valores se agrupan fuertemente en la parte alta de lon_base_gd. Por lo anterior, el comportamiento es beneficioso, ya que permite una alta densidad operativa en un rango espacial estrecho y bien delimitado.