# =====================================================
# ANÁLISIS ESTADÍSTICO DE GRAVA - VERSIÓN LIMPIA
# Grupo 3 - Estadística
# =====================================================
# 1. Cargar datos
datos <- read.csv("ESTADISTICA/dataset_geologico_limpio_80.csv",
header = TRUE, sep = ",", dec = ".", stringsAsFactors = FALSE)
cat("✅ Columnas cargadas:", ncol(datos), "\n") # debe decir 58
## ✅ Columnas cargadas: 58
# 2. Variable GRAVA
grava_raw <- as.numeric(gsub("[^0-9.-]", "", datos$GRAVEL_PCT))
grava <- na.omit(grava_raw)
grava <- grava[grava >= 0 & grava <= 100]
cat("Valores válidos de grava:", length(grava), "\n\n")
## Valores válidos de grava: 27286
# 3. Cálculos básicos
n <- length(grava)
minimo <- min(grava)
maximo <- max(grava)
R <- maximo - minimo
k <- max(1, floor(1 + 3.3 * log10(n)))
A <- R / k
Li <- round(seq(minimo, maximo - A + 1e-6, by = A), 2)
Ls <- round(Li + A, 2)
Ls[length(Ls)] <- maximo
MC <- round((Li + Ls)/2, 2)
# Frecuencias
ni <- numeric(length(Li))
for(i in 1:length(Li)){
if(i == length(Li)){
ni[i] <- sum(grava >= Li[i] & grava <= Ls[i])
} else {
ni[i] <- sum(grava >= Li[i] & grava < Ls[i])
}
}
hi <- round(ni / sum(ni) * 100, 3)
Niasc <- cumsum(ni)
Nidsc <- rev(cumsum(rev(ni)))
Hiasc <- round(cumsum(hi), 2)
Hidsc <- round(rev(cumsum(rev(hi))), 2)
# 4. Tabla de Distribución (bonita con gt)
library(gt)
library(dplyr)
##
## Adjuntando el paquete: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
TDFgrava <- data.frame(Li, Ls, MC, ni, hi, Niasc, Nidsc, Hiasc, Hidsc)
fila_total <- data.frame(Li = "TOTAL", Ls = "", MC = "",
ni = sum(ni), hi = round(sum(hi),2),
Niasc = "", Nidsc = "", Hiasc = "", Hidsc = "")
TDFgrava_p <- rbind(TDFgrava, fila_total)
tabla_grava_p <- TDFgrava_p %>%
gt() %>%
tab_header(title = md("**Tabla Nº 1**"),
subtitle = md("Tabla de distribución de la grava de los sedimentos marinos")) %>%
tab_source_note(md("Autor: Grupo 3")) %>%
tab_options(
table.border.top.color = "black",
table.border.bottom.color = "black",
column_labels.border.bottom.color = "black",
column_labels.border.bottom.width = px(2),
row.striping.include_table_body = TRUE,
table_body.hlines.color = "gray"
)
tabla_grava_p
| Tabla Nº 1 |
| Tabla de distribución de la grava de los sedimentos marinos |
| Li |
Ls |
MC |
ni |
hi |
Niasc |
Nidsc |
Hiasc |
Hidsc |
| 0 |
6.67 |
3.34 |
22538 |
82.587 |
22538 |
27290 |
82.59 |
100 |
| 6.67 |
13.34 |
10 |
1488 |
5.453 |
24026 |
4752 |
88.04 |
17.41 |
| 13.33 |
20 |
16.66 |
926 |
3.393 |
24952 |
3264 |
91.43 |
11.96 |
| 20 |
26.67 |
23.34 |
620 |
2.272 |
25572 |
2338 |
93.7 |
8.57 |
| 26.67 |
33.34 |
30.01 |
421 |
1.543 |
25993 |
1718 |
95.25 |
6.3 |
| 33.33 |
40 |
36.66 |
281 |
1.030 |
26274 |
1297 |
96.28 |
4.75 |
| 40 |
46.67 |
43.34 |
230 |
0.843 |
26504 |
1016 |
97.12 |
3.72 |
| 46.67 |
53.34 |
50.01 |
170 |
0.623 |
26674 |
786 |
97.74 |
2.88 |
| 53.33 |
60 |
56.66 |
146 |
0.535 |
26820 |
616 |
98.28 |
2.26 |
| 60 |
66.67 |
63.34 |
108 |
0.396 |
26928 |
470 |
98.67 |
1.72 |
| 66.67 |
73.34 |
70 |
85 |
0.311 |
27013 |
362 |
98.99 |
1.33 |
| 73.33 |
80 |
76.66 |
75 |
0.275 |
27088 |
277 |
99.26 |
1.02 |
| 80 |
86.67 |
83.34 |
49 |
0.180 |
27137 |
202 |
99.44 |
0.74 |
| 86.67 |
93.34 |
90 |
65 |
0.238 |
27202 |
153 |
99.68 |
0.56 |
| 93.33 |
100 |
96.66 |
88 |
0.322 |
27290 |
88 |
100 |
0.32 |
| TOTAL |
|
|
27290 |
100.000 |
|
|
|
|
| Autor: Grupo 3 |
# 5. Gráficos
library(moments)
colores <- gray.colors(length(ni), start = 0.3, end = 0.9)
hist(grava, breaks = k, col = colores,
main = "Gráfica Nº2: Distribución de la grava",
xlab = "Grava (%)", ylab = "Frecuencia")
boxplot(grava, horizontal = TRUE, col = "lightgreen",
main = "Gráfica Nº6: Boxplot de la grava", xlab = "Grava (%)")
# 6. Indicadores estadísticos
x <- mean(grava)
Me <- median(grava)
sd_val <- sd(grava)
CV <- round((sd_val / x) * 100, 2)
As <- round(skewness(grava), 2)
K <- round(kurtosis(grava), 2)
TablaIndicadores <- data.frame(
Variable = "Grava (%)",
Mínimo = round(minimo,2),
Máximo = round(maximo,2),
Media = round(x,2),
Mediana = round(Me,2),
`Desv. Est.` = round(sd_val,2),
`CV (%)` = CV,
Asimetría = As,
Curtosis = K
)
library(knitr)
library(kableExtra)
##
## Adjuntando el paquete: 'kableExtra'
## The following object is masked from 'package:dplyr':
##
## group_rows
kable(TablaIndicadores, format = "markdown", align = "c",
caption = "Tabla N°3: Indicadores estadísticos de la variable grava") %>%
kable_styling(bootstrap_options = c("striped", "hover", "condensed"))
Tabla N°3: Indicadores estadísticos de la variable grava
|
Variable
|
Mínimo
|
Máximo
|
Media
|
Mediana
|
Desv..Est.
|
CV….
|
Asimetría
|
Curtosis
|
|
Grava (%)
|
0
|
100
|
5.38
|
0.03
|
13.62
|
252.94
|
3.86
|
20.01
|
# 7. Outliers
outliers <- boxplot.stats(grava)$out
num_outliers <- length(outliers)
min_out <- ifelse(num_outliers > 0, round(min(outliers),2), NA)
max_out <- ifelse(num_outliers > 0, round(max(outliers),2), NA)
TablaOutliers <- data.frame(
"Cantidad de outliers" = num_outliers,
"Mínimo" = min_out,
"Máximo" = max_out
)
kable(TablaOutliers, format = "markdown", align = "c",
caption = "Tabla N°4: Outliers de la variable grava") %>%
kable_styling(bootstrap_options = c("striped", "hover"))
Tabla N°4: Outliers de la variable grava
|
Cantidad.de.outliers
|
Mínimo
|
Máximo
|
|
4238
|
8.51
|
100
|
cat("\n✅ ¡ANÁLISIS DE GRAVA COMPLETADO CORRECTAMENTE!\n")
##
## ✅ ¡ANÁLISIS DE GRAVA COMPLETADO CORRECTAMENTE!