# ====================================================
# Librerias
# ====================================================
library(readxl)
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(gt)
# ====================================================
# Cargar base de datos
# ====================================================
datos_nuevoartes <- read_excel("datos_nuevoartes.xlsx")
# ====================================================
# VARIABLE: LONGITUDE
# ====================================================
longitude <- datos_nuevoartes$longitude
longitude <- longitude[!is.na(longitude)]
# ====================================================
# PARÁMETROS DE CLASIFICACIÓN
# ====================================================
k_long <- 12
n_long <- length(longitude)
min_long <- min(longitude)
max_long <- max(longitude)
R_long <- max_long - min_long
A_real <- R_long / k_long
# ====================================================
# AJUSTE DE AMPLITUD ("BONITA")
# ====================================================
A_long <- ifelse(
A_real <= 2, 2,
ifelse(
A_real <= 5, 5,
ifelse(
A_real <= 10, 10,
ceiling(A_real / 10) * 10
)
)
)
# ====================================================
# LÍMITES DE CLASE
# ====================================================
Li0 <- floor(min_long / A_long) * A_long
Li_long <- seq(Li0, by = A_long, length.out = k_long)
Ls_long <- Li_long + A_long
MC_long <- round((Li_long + Ls_long) / 2, 2)
# ====================================================
# FRECUENCIAS
# ====================================================
ni_long <- numeric(k_long)
for (i in 1:k_long) {
if (i < k_long) {
ni_long[i] <- sum(longitude >= Li_long[i] & longitude < Ls_long[i])
} else {
ni_long[i] <- sum(longitude >= Li_long[i] & longitude <= max_long)
}
}
hi_long <- round((ni_long / sum(ni_long)) * 100, 2)
Ni_asc_long <- cumsum(ni_long)
Ni_dsc_long <- rev(cumsum(rev(ni_long)))
Hi_asc_long <- round(cumsum(hi_long), 2)
Hi_dsc_long <- round(rev(cumsum(rev(hi_long))), 2)
# ====================================================
# TABLA DE FRECUENCIAS
# ====================================================
TDF_longitude <- data.frame(
Li = Li_long,
Ls = Ls_long,
MC = MC_long,
ni = ni_long,
hi = hi_long,
Ni_asc = Ni_asc_long,
Ni_dsc = Ni_dsc_long,
Hi_asc = Hi_asc_long,
Hi_dsc = Hi_dsc_long
)
TDF_longitude <- rbind(
TDF_longitude,
data.frame(
Li = "TOTAL",
Ls = "",
MC = "",
ni = sum(ni_long),
hi = 100,
Ni_asc = "",
Ni_dsc = "",
Hi_asc = "",
Hi_dsc = ""
)
)
# ====================================================
# FORMATO GT
# ====================================================
tabla_longitude <- TDF_longitude %>%
gt() %>%
fmt_number(columns = MC, decimals = 2) %>%
tab_header(
title = md("Tabla N° 1"),
subtitle = md("Distribución de frecuencias de Longitude (12 clases)")
) %>%
tab_source_note(
source_note = md("Autor: Grupo Geología")
) %>%
tab_style(
style = cell_text(weight = "bold"),
locations = cells_body(rows = Li == "TOTAL")
)
tabla_longitude
| Tabla N° 1 |
| Distribución de frecuencias de Longitude (12 clases) |
| Li |
Ls |
MC |
ni |
hi |
Ni_asc |
Ni_dsc |
Hi_asc |
Hi_dsc |
| -180 |
-150 |
-165 |
85 |
0.77 |
85 |
11033 |
0.77 |
100.02 |
| -150 |
-120 |
-135 |
1893 |
17.16 |
1978 |
10948 |
17.93 |
99.25 |
| -120 |
-90 |
-105 |
1221 |
11.07 |
3199 |
9055 |
29 |
82.09 |
| -90 |
-60 |
-75 |
1526 |
13.83 |
4725 |
7834 |
42.83 |
71.02 |
| -60 |
-30 |
-45 |
228 |
2.07 |
4953 |
6308 |
44.9 |
57.19 |
| -30 |
0 |
-15 |
318 |
2.88 |
5271 |
6080 |
47.78 |
55.12 |
| 0 |
30 |
15 |
334 |
3.03 |
5605 |
5762 |
50.81 |
52.24 |
| 30 |
60 |
45 |
279 |
2.53 |
5884 |
5428 |
53.34 |
49.21 |
| 60 |
90 |
75 |
2034 |
18.44 |
7918 |
5149 |
71.78 |
46.68 |
| 90 |
120 |
105 |
1784 |
16.17 |
9702 |
3115 |
87.95 |
28.24 |
| 120 |
150 |
135 |
1083 |
9.82 |
10785 |
1331 |
97.77 |
12.07 |
| 150 |
180 |
165 |
248 |
2.25 |
11033 |
248 |
100.02 |
2.25 |
| TOTAL |
|
|
11033 |
100.00 |
|
|
|
|
| Autor: Grupo Geología |
# ====================================================
# HISTOGRAMAS – LONGITUDE
# ====================================================
# HISTOGRAMA LOCAL – ni
hist(
longitude,
breaks = c(Li_long, max(Ls_long)),
right = FALSE,
freq = TRUE,
col = "grey",
border = "black",
main = "Histograma local de Longitude (ni)",
xlab = "Longitude (°)",
ylab = "Frecuencia absoluta (ni)"
)
# HISTOGRAMA GLOBAL – ni
hist(
longitude,
breaks = c(Li_long, max(Ls_long)),
right = FALSE,
freq = TRUE,
col = "grey",
border = "black",
ylim = c(0, sum(ni_long)),
main = "Histograma global de Longitude (ni)",
xlab = "Longitude (°)",
ylab = "Frecuencia absoluta acumulable"
)
# HISTOGRAMA LOCAL – hi (%)
hist(
longitude,
breaks = c(Li_long, max(Ls_long)),
right = FALSE,
freq = FALSE, # <- frecuencia relativa
col = "grey",
border = "black",
main = "Histograma local de Longitude (hi)",
xlab = "Longitude (°)",
ylab = "Frecuencia relativa"
)
# HISTOGRAMA GLOBAL – hi (%)
hist(
longitude,
breaks = c(Li_long, max(Ls_long)),
right = FALSE,
freq = FALSE, # <- frecuencia relativa
col = "grey",
border = "black",
ylim = c(0, max(hi_long) / 100 * 1.2),
main = "Histograma global de Longitude (hi)",
xlab = "Longitude (°)",
ylab = "Frecuencia relativa"
)
# ==========================================
# OJIVA COMBINADA – LONGITUDE
# ==========================================
plot(
Ls_long,
Ni_asc_long,
type = "o",
pch = 19,
col = "blue",
ylim = c(0, max(Ni_asc_long)),
main = "Ojiva combinada de Longitude",
xlab = "Límites de clase (°)",
ylab = "Frecuencia acumulada"
)
lines(
Li_long,
Ni_dsc_long,
type = "o",
pch = 17,
col = "red"
)
legend(
"right",
legend = c("Ojiva ascendente (Ni ≤)", "Ojiva descendente (Ni ≥)"),
col = c("blue", "red"),
pch = c(19, 17),
lty = 1,
cex = 0.8,
bty = "b"
)
# =============================
# DIAGRAMA DE CAJA – LONGITUDE
# =============================
boxplot(
longitude,
horizontal = TRUE,
col = "grey",
border = "black",
main = "Diagrama de caja de Longitude (con outliers)",
xlab = "Longitude (°)",
outline = TRUE, # asegura que se muestren los outliers
pch = 19, # símbolo de los outliers
outcol = "red" # color de los outliers
)
# ====================================================
# INDICADORES ESTADÍSTICOS
# ====================================================
ri <- -180
rs <- 180
x <- mean(longitude)
Me <- median(longitude)
Mo <- as.numeric(
names(sort(table(round(longitude, 1)), decreasing = TRUE)[1])
)
sd_long <- sd(longitude)
CV <- (sd_long / x) * 100
As <- mean((longitude - x)^3) / sd_long^3
K <- mean((longitude - x)^4) / sd_long^4 - 3
TablaIndicadores_longitude <- data.frame(
Var = "Longitude",
ri = ri,
rs = rs,
x = round(x, 2),
Me = round(Me, 2),
Mo = round(Mo, 2),
sd = round(sd_long, 2),
CV = round(CV, 2),
As = round(As, 2),
K = round(K, 2)
)
tabla_longitude_indicadores <- TablaIndicadores_longitude %>%
gt() %>%
tab_header(
title = md("Tabla N° X"),
subtitle = md("Indicadores estadísticos de la variable Longitude")
) %>%
tab_source_note(
source_note = md("Autor: Grupo Geología")
)
tabla_longitude_indicadores
| Tabla N° X |
| Indicadores estadísticos de la variable Longitude |
| Var |
ri |
rs |
x |
Me |
Mo |
sd |
CV |
As |
K |
| Longitude |
-180 |
180 |
2.52 |
19.69 |
-122.3 |
100.91 |
4003.6 |
-0.06 |
-1.67 |
| Autor: Grupo Geología |
# ====================================================
# DETECCIÓN DE OUTLIERS – VARIABLE LONGITUDE (IQR)
# ====================================================
# =========================
# CUARTILES E IQR
# =========================
Q1 <- quantile(longitude, 0.25)
Q3 <- quantile(longitude, 0.75)
IQR_long <- Q3 - Q1
# =========================
# LÍMITES DE OUTLIERS
# =========================
minimo <- Q1 - 1.5 * IQR_long
maximo <- Q3 + 1.5 * IQR_long
# =========================
# IDENTIFICAR OUTLIERS
# =========================
outliers <- longitude[longitude < minimo | longitude > maximo]
n_outliers <- length(outliers)
# =========================
# TABLA DE OUTLIERS
# =========================
Tabla_outliers <- data.frame(
Outliers = ifelse(n_outliers == 0, "No se detectan", n_outliers),
minimo = round(minimo, 2),
máximo = round(maximo, 2)
)
# =========================
# TABLA PLOTEADA (GT)
# =========================
tabla_outliers_gt <- Tabla_outliers %>%
gt() %>%
tab_header(
title = md("Tabla 11.1"),
subtitle = md("Detección de outliers – Variable Longitude (método IQR)")
) %>%
cols_label(
Outliers = "Outliers",
minimo = "Límite inferior",
máximo = "Límite superior"
) %>%
tab_source_note(
source_note = md("Autor: Grupo Geología")
) %>%
tab_options(
table.border.top.color = "black",
table.border.bottom.color = "black",
column_labels.border.bottom.color = "black",
heading.border.bottom.color = "black"
)
tabla_outliers_gt
| Tabla 11.1 |
| Detección de outliers – Variable Longitude (método IQR) |
| Outliers |
Límite inferior |
Límite superior |
| No se detectan |
-410.6 |
396.68 |
| Autor: Grupo Geología |