CARGA DE DATOS
library(dplyr)
library(gt)
datos <- read.csv("D:/dataset_CMIO_geologico.csv")
ASIGNACION DE VARIABLES
df_ley <- data.frame(
nivel_ley = trimws(toupper(datos$Ley_Categoria))
)
orden_ley <- c("BAJA", "MEDIA", "ALTA", "MUY ALTA")
df_ley$nivel_ley <- factor(
df_ley$nivel_ley,
levels = orden_ley,
ordered = TRUE
)
TABLA DE DISTRIBUCION DE CANTIDAD
TDF_ley <- df_ley %>%
count(nivel_ley, name = "ni") %>%
arrange(nivel_ley) %>%
mutate(hi = round(ni / sum(ni) * 100, 0))
tabla_ley <- TDF_ley %>%
gt() %>%
tab_header(
title = "Tabla N° 1",
subtitle = "Distribución de la Ley Mineral (Variable Ordinal)"
)
tabla_ley
| Tabla N° 1 | ||
| Distribución de la Ley Mineral (Variable Ordinal) | ||
| nivel_ley | ni | hi |
|---|---|---|
| BAJA | 1024 | 41 |
| MEDIA | 975 | 39 |
| ALTA | 501 | 20 |
# Agregamos fila TOTAL
tabla_final_ley <- TDF_ley %>%
mutate(
nivel_ley = as.character(nivel_ley)
)
tabla_final_ley <- bind_rows(
tabla_final_ley,
data.frame(
nivel_ley = "TOTAL",
ni = sum(tabla_final_ley$ni),
hi = sum(tabla_final_ley$hi)
)
)
# TABLA ESQUELETO
tabla_ley_gt <- tabla_final_ley %>%
gt() %>%
tab_header(
title = md("**Tabla Nº2**"),
subtitle = md("Distribución ordinal de la ley mineral")
) %>%
cols_label(
nivel_ley = "Nivel de Ley",
ni = "Frecuencia",
hi = "Porcentaje (%)"
) %>%
cols_align(
align = "center",
columns = everything()
) %>%
fmt_number(
columns = c(ni, hi),
decimals = 0
) %>%
tab_style(
style = cell_text(weight = "bold"),
locations = cells_body(
rows = nivel_ley == "TOTAL"
)
) %>%
tab_source_note(
source_note = md("Autor: Grupo 2")
)
tabla_ley_gt
| Tabla Nº2 | ||
| Distribución ordinal de la ley mineral | ||
| Nivel de Ley | Frecuencia | Porcentaje (%) |
|---|---|---|
| BAJA | 1,024 | 41 |
| MEDIA | 975 | 39 |
| ALTA | 501 | 20 |
| TOTAL | 2,500 | 100 |
| Autor: Grupo 2 | ||
barplot(TDF_ley$ni,
main = "Gráfica Nº1: Frecuencia de la Ley Mineral",
xlab = "Nivel de Ley",
ylab = "Cantidad (ni)",
col = "steelblue",
names.arg = TDF_ley$nivel_ley,
cex.names = 0.7,
las = 2)
barplot(TDF_ley$ni,
main = "Gráfica Nº2: Frecuencia de la Ley Mineral (Escala Ajustada)",
xlab = "Nivel de Ley",
ylab = "Cantidad (ni)",
col = "steelblue",
names.arg = TDF_ley$nivel_ley,
cex.names = 0.7,
las = 2,
ylim = c(0, max(TDF_ley$ni)*1.2))
barplot(TDF_ley$hi,
main = "Gráfica Nº3: Porcentaje de la Ley Mineral",
xlab = "Nivel de Ley",
ylab = "Porcentaje (%)",
col = "steelblue",
names.arg = TDF_ley$nivel_ley,
cex.names = 0.7,
las = 2)
barplot(TDF_ley$hi,
main = "Gráfica Nº4: Porcentaje del Nivel de Ley (Escala Completa)",
xlab = "Nivel de Ley",
ylab = "Porcentaje (%)",
col = "steelblue",
names.arg = TDF_ley$nivel_ley,
cex.names = 0.7,
las = 2,
ylim = c(0, 100))
par(mar = c(4,4,4,8))
colores <- rainbow(length(TDF_ley$hi))
pie(TDF_ley$hi,
col = colores,
main = "Distribución de la Ley Mineral",
labels = NA)
legend("right",
legend = paste(TDF_ley$nivel_ley, TDF_ley$hi, "%"),
fill = colores,
title = "NIVELES",
bty = "o",
xpd = TRUE,
inset = c(-0.15,0))
moda_ley <- TDF_ley[TDF_ley$ni == max(TDF_ley$ni), ]
moda_ley
## nivel_ley ni hi
## 1 BAJA 1024 41
TDF_ley <- TDF_ley %>%
mutate(Ni = cumsum(ni))
N <- sum(TDF_ley$ni)
mediana_ley <- TDF_ley %>%
filter(Ni >= N/2) %>%
slice(1)
mediana_ley
## nivel_ley ni hi Ni
## 1 MEDIA 975 39 1999
#conclucion