# =====================================================
# 1️⃣ CARGA DE DATOS (RCLOUD)
# =====================================================
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)
# Leer archivo (debe estar subido al proyecto)
datos_nuevoartes <- read_excel("datos_nuevoartes.xlsx")
# Conversión de fecha
event_date <- as.Date(datos_nuevoartes$event_date)
# Eliminar valores NA
event_date <- event_date[!is.na(event_date)]
# =====================================================
# 1.1️⃣ ASIGNACIÓN DEL NOMBRE (MESES)
# =====================================================
mes_num <- as.numeric(format(event_date, "%m"))
meses <- c(
"Enero", "Febrero", "Marzo", "Abril",
"Mayo", "Junio", "Julio", "Agosto",
"Septiembre", "Octubre", "Noviembre", "Diciembre"
)
# =====================================================
# 2️⃣ TABLA DE DISTRIBUCIÓN DE FRECUENCIAS
# =====================================================
ni_m <- sapply(1:12, function(i) sum(mes_num == i))
hi_m <- round((ni_m / sum(ni_m)) * 100, 2)
Ni_m <- cumsum(ni_m)
Hi_m <- round(cumsum(hi_m), 2)
tabla_meses <- data.frame(
Mes = meses,
ni = ni_m,
Ni = Ni_m,
hi = hi_m,
Hi = Hi_m
)
# =====================================================
# TABLA CON gt (VISIBLE EN RCLOUD)
# =====================================================
tabla_meses %>%
gt() %>%
tab_header(
title = md("*Tabla Nro. 1*"),
subtitle = md("**Tabla de distribución de frecuencias simples y acumuladas de los eventos por mes**")
) %>%
tab_source_note(
source_note = md("Elaborado por: Grupo 2 de la carrera de Geología")
) %>%
cols_label(
Mes = "Mes",
ni = "ni",
Ni = "Ni",
hi = "hi (%)",
Hi = "Hi (%)"
)
| Tabla Nro. 1 |
| Tabla de distribución de frecuencias simples y acumuladas de los eventos por mes |
| Mes |
ni |
Ni |
hi (%) |
Hi (%) |
| Enero |
945 |
945 |
8.57 |
8.57 |
| Febrero |
797 |
1742 |
7.22 |
15.79 |
| Marzo |
985 |
2727 |
8.93 |
24.72 |
| Abril |
841 |
3568 |
7.62 |
32.34 |
| Mayo |
788 |
4356 |
7.14 |
39.48 |
| Junio |
974 |
5330 |
8.83 |
48.31 |
| Julio |
1243 |
6573 |
11.27 |
59.58 |
| Agosto |
1175 |
7748 |
10.65 |
70.23 |
| Septiembre |
896 |
8644 |
8.12 |
78.35 |
| Octubre |
761 |
9405 |
6.90 |
85.25 |
| Noviembre |
668 |
10073 |
6.05 |
91.30 |
| Diciembre |
960 |
11033 |
8.70 |
100.00 |
| Elaborado por: Grupo 2 de la carrera de Geología |
# =====================================================
# 2️⃣ DIAGRAMAS DE BARRAS
# =====================================================
barplot(ni_m, names.arg = meses, las = 2,
col = "gray", main = "Diagrama de barras local (ni)")
barplot(Ni_m, names.arg = meses, las = 2,
col = "darkgray", main = "Diagrama de barras global (Ni)")
barplot(hi_m, names.arg = meses, las = 2,
col = "lightblue", main = "Diagrama de barras local (hi)")
barplot(Hi_m, names.arg = meses, las = 2,
col = "steelblue", main = "Diagrama de barras global (Hi)")
# =====================================================
# 3️⃣ DIAGRAMA CIRCULAR
# =====================================================
colores <- c(
"#66c2a5", "#fc8d62", "#8da0cb", "#e78ac3",
"#a6d854", "#ffd92f", "#e5c494", "#b3b3b3",
"#1b9e77", "#d95f02", "#7570b3", "#e7298a"
)
pie(hi_m, col = colores,
labels = paste0(hi_m, " %"),
main = "Distribución porcentual de eventos por mes")
legend("topright", legend = meses,
fill = colores, cex = 0.7, bty = "n")
# =====================================================
# 4️⃣ INDICADOR ESTADÍSTICO (MODA)
# =====================================================
moda_mes <- meses[which.max(ni_m)]
cat("La moda de la variable Mes es:", moda_mes)
## La moda de la variable Mes es: Julio