library(readr)
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
library(knitr)
library(kableExtra)
##
## Adjuntando el paquete: 'kableExtra'
## The following object is masked from 'package:dplyr':
##
## group_rows
# Cargar datos
datasetf <- read_csv("datasetf.csv", show_col_types = FALSE)
## Warning: One or more parsing issues, call `problems()` on your data frame for details,
## e.g.:
## dat <- vroom(...)
## problems(dat)
# Usar Restart Date/Time
raw_dates <- datasetf$`Restart Date/Time`
raw_dates <- raw_dates[raw_dates != ""]
raw_dates <- na.omit(raw_dates)
# Convertir a fecha/hora
fechas_obj <- as.POSIXct(raw_dates, format = "%m/%d/%Y %H:%M")
# Convertir a numérico (segundos desde 1970)
amperaje <- as.numeric(fechas_obj)
amperaje <- na.omit(amperaje)
fechas_obj <- fechas_obj[!is.na(amperaje)]
# --- CÁLCULOS MATEMÁTICOS DE LOS INTERVALOS ---
k <- 1 + (3.322 * log10(length(amperaje)))
k <- floor(k)
min_val <- min(amperaje)
max_val <- max(amperaje)
R <- max_val - min_val
A <- R / k
# Definir los cortes numéricos
Li_num <- seq(from = min_val, to = max_val - A, by = A)
if(length(Li_num) < k) {
Li_num <- c(Li_num, Li_num[length(Li_num)] + A)
}
if(max(Li_num) + A < max_val) {
Li_num <- c(Li_num, tail(Li_num, 1) + A)
}
Ls_num <- Li_num + A
MC_num <- (Li_num + Ls_num) / 2
# Contar frecuencias
ni <- numeric(length(Li_num))
for (i in 1:length(Li_num)) {
if (i == length(Li_num)) {
ni[i] <- sum(amperaje >= Li_num[i] & amperaje <= (max_val + 100000))
} else {
ni[i] <- sum(amperaje >= Li_num[i] & amperaje < Ls_num[i])
}
}
# Cálculos de frecuencias
hi <- round(ni / sum(ni) * 100, 2) # Redondeado a 2 decimales
Niasc <- cumsum(ni)
Nidsc <- rev(cumsum(rev(ni)))
Hiasc <- round(cumsum(hi), 2)
Hidsc <- round(rev(cumsum(rev(hi))), 2)
# Convertir a formato fecha/hora
Li_fecha <- format(structure(Li_num, class = c("POSIXct", "POSIXt")), "%m/%d/%Y %H:%M")
Ls_fecha <- format(structure(Ls_num, class = c("POSIXct", "POSIXt")), "%m/%d/%Y %H:%M")
MC_fecha <- format(structure(MC_num, class = c("POSIXct", "POSIXt")), "%m/%d/%Y %H:%M")
# Crear data frame con nombres CORREGIDOS
TDFRestart <- data.frame(
Li = Li_fecha, # Cambiado: Desde -> Li
Ls = Ls_fecha, # Cambiado: Hasta -> Ls
MC = MC_fecha, # Cambiado: Marca_Clase -> MC
ni = ni, # Mantenido: ni
hi = hi, # Mantenido: hi (minúscula)
Ni = Niasc, # Simplificado
Hi = Hiasc # Simplificado
)
# TABLA 1: Distribución de Frecuencias con kableExtra
tabla1_sturges <- TDFRestart %>%
kable(
format = "html",
caption = "<b>Tabla 1: Distribución de Frecuencias</b><br><span style='font-size:14px'><b>Variable: Restart Date/Time</b></span>",
align = c('l', 'l', 'l', 'r', 'r', 'r', 'r'),
col.names = c("Li", "Ls", "MC", "ni", "hi", "Ni", "Hi") # Nombres CORREGIDOS
) %>%
kable_styling(
bootstrap_options = c("striped", "hover", "condensed", "responsive"),
full_width = FALSE,
font_size = 13,
position = "center"
) %>%
column_spec(1:3, width = "20%") %>%
column_spec(4, bold = TRUE, background = "#e6f3ff") %>%
column_spec(5, bold = TRUE, background = "#fff0e6") %>%
add_header_above(c("Intervalos" = 3, "Frecuencias" = 4))
# Mostrar Tabla 1
tabla1_sturges
Tabla 1: Distribución de Frecuencias
Variable: Restart Date/Time
|
Intervalos
|
Frecuencias
|
|
Li
|
Ls
|
MC
|
ni
|
hi
|
Ni
|
Hi
|
|
01/11/2010 22:08
|
08/31/2010 21:41
|
05/07/2010 21:54
|
98
|
7.31
|
98
|
7.31
|
|
08/31/2010 21:41
|
04/20/2011 21:14
|
12/25/2010 21:28
|
94
|
7.01
|
192
|
14.32
|
|
04/20/2011 21:14
|
12/08/2011 20:48
|
08/14/2011 21:01
|
99
|
7.38
|
291
|
21.70
|
|
12/08/2011 20:48
|
07/27/2012 20:21
|
04/02/2012 20:35
|
97
|
7.23
|
388
|
28.93
|
|
07/27/2012 20:21
|
03/16/2013 19:55
|
11/20/2012 20:08
|
133
|
9.92
|
521
|
38.85
|
|
03/16/2013 19:55
|
11/03/2013 19:28
|
07/10/2013 19:42
|
120
|
8.95
|
641
|
47.80
|
|
11/03/2013 19:28
|
06/23/2014 19:02
|
02/27/2014 19:15
|
131
|
9.77
|
772
|
57.57
|
|
06/23/2014 19:02
|
02/10/2015 18:35
|
10/17/2014 18:48
|
130
|
9.69
|
902
|
67.26
|
|
02/10/2015 18:35
|
09/30/2015 18:09
|
06/06/2015 18:22
|
173
|
12.90
|
1075
|
80.16
|
|
09/30/2015 18:09
|
05/19/2016 17:42
|
01/24/2016 17:55
|
138
|
10.29
|
1213
|
90.45
|
|
05/19/2016 17:42
|
01/06/2017 17:16
|
09/12/2016 17:29
|
128
|
9.55
|
1341
|
100.00
|
# Totales SOLO de ni y hi
total_ni <- sum(TDFRestart$ni)
total_hi <- sum(TDFRestart$hi)
# Añadir fila total SOLO con ni y hi
TDF_Completo <- rbind(
TDFRestart,
data.frame(
Li = "TOTAL",
Ls = "",
MC = "",
ni = total_ni,
hi = total_hi,
Ni = "", # Vacío para total
Hi = "" # Vacío para total
)
)
# TABLA 2: Distribución Completa con kableExtra
tabla2_total <- TDF_Completo %>%
kable(
format = "html",
caption = "<b>Tabla 2: Distribución Completa</b><br><span style='font-size:14px'><b>Con Totales</b></span>",
align = c('l', 'l', 'l', 'r', 'r', 'r', 'r'),
col.names = c("Li", "Ls", "MC", "ni", "hi", "Ni", "Hi")
) %>%
kable_styling(
bootstrap_options = c("striped", "hover", "condensed", "responsive"),
full_width = FALSE,
font_size = 13,
position = "center"
) %>%
row_spec(
nrow(TDF_Completo),
bold = TRUE,
color = "white",
background = "#2E86AB",
align = "c"
) %>%
column_spec(1:3, width = "20%") %>%
column_spec(4, background = "#e6f3ff") %>%
column_spec(5, background = "#fff0e6") %>%
add_header_above(c("Intervalos" = 3, "Frecuencias" = 4))
# Mostrar Tabla 2
tabla2_total
Tabla 2: Distribución Completa
Con Totales
|
Intervalos
|
Frecuencias
|
|
Li
|
Ls
|
MC
|
ni
|
hi
|
Ni
|
Hi
|
|
01/11/2010 22:08
|
08/31/2010 21:41
|
05/07/2010 21:54
|
98
|
7.31
|
98
|
7.31
|
|
08/31/2010 21:41
|
04/20/2011 21:14
|
12/25/2010 21:28
|
94
|
7.01
|
192
|
14.32
|
|
04/20/2011 21:14
|
12/08/2011 20:48
|
08/14/2011 21:01
|
99
|
7.38
|
291
|
21.7
|
|
12/08/2011 20:48
|
07/27/2012 20:21
|
04/02/2012 20:35
|
97
|
7.23
|
388
|
28.93
|
|
07/27/2012 20:21
|
03/16/2013 19:55
|
11/20/2012 20:08
|
133
|
9.92
|
521
|
38.85
|
|
03/16/2013 19:55
|
11/03/2013 19:28
|
07/10/2013 19:42
|
120
|
8.95
|
641
|
47.8
|
|
11/03/2013 19:28
|
06/23/2014 19:02
|
02/27/2014 19:15
|
131
|
9.77
|
772
|
57.57
|
|
06/23/2014 19:02
|
02/10/2015 18:35
|
10/17/2014 18:48
|
130
|
9.69
|
902
|
67.26
|
|
02/10/2015 18:35
|
09/30/2015 18:09
|
06/06/2015 18:22
|
173
|
12.90
|
1075
|
80.16
|
|
09/30/2015 18:09
|
05/19/2016 17:42
|
01/24/2016 17:55
|
138
|
10.29
|
1213
|
90.45
|
|
05/19/2016 17:42
|
01/06/2017 17:16
|
09/12/2016 17:29
|
128
|
9.55
|
1341
|
100
|
|
TOTAL
|
|
|
1341
|
100.00
|
|
|
# Guardar tablas
save_kable(tabla1_sturges, "tabla1_restart_li_ls.html")
save_kable(tabla2_total, "tabla2_restart_total.html")
# --- GRÁFICOS ---
# 1. Histograma anual automático
hist(fechas_obj,
breaks = "years",
freq = TRUE,
main = "Distribución Anual - Restart Date/Time",
xlab = "Año",
col = "lightblue",
las = 1,
format = "%Y")
# 2. Histograma usando los intervalos calculados
hist(amperaje,
breaks = c(Li_num, tail(Ls_num, 1)),
main = "Histograma - Restart Date/Time",
col = "blue",
xaxt = "n",
xlab = "Fecha",
ylab = "Frecuencia")
# Eje X con fechas
axis(1, at = Li_num,
labels = format(structure(Li_num, class = c("POSIXct", "POSIXt")), "%m/%d/%Y"),
las = 2,
cex.axis = 0.7)
# 3. Ojivas Temporales
ejex_fecha <- structure(Li_num, class = c("POSIXct", "POSIXt"))
plot(ejex_fecha, Nidsc,
type = "o",
pch = 16,
col = "blue",
main = "Ojivas - Restart Date/Time",
xlab = "Fecha",
ylab = "Frecuencia Acumulada")
lines(ejex_fecha, Niasc,
type = "b",
pch = 16,
col = "black")
legend("topright",
legend = c("Descendente", "Ascendente"),
col = c("blue", "black"),
lty = 1)
# 4. Boxplot
boxplot(fechas_obj,
horizontal = TRUE,
col = "blue",
main = "Boxplot - Restart Date/Time",
xlab = "Fecha")
# --- RESUMEN ESTADÍSTICO ---
cat("\n")
cat("============================================================\n")
## ============================================================
cat("RESUMEN ESTADÍSTICO - Restart Date/Time\n")
## RESUMEN ESTADÍSTICO - Restart Date/Time
cat("============================================================\n")
## ============================================================
cat("n =", length(amperaje), "\n")
## n = 1341
cat("k =", k, "\n")
## k = 11
cat("R (rango) =", round(R/86400, 2), "días\n")
## R (rango) = 2551.8 días
cat("A (amplitud) =", round(A/86400, 2), "días\n")
## A (amplitud) = 231.98 días
cat("∑ni =", total_ni, "\n")
## ∑ni = 1341
cat("∑hi =", total_hi, "%\n")
## ∑hi = 100 %
cat("Fecha mínima =", format(min(fechas_obj), "%m/%d/%Y %H:%M"), "\n")
## Fecha mínima = 01/11/2010 22:08
cat("Fecha máxima =", format(max(fechas_obj), "%m/%d/%Y %H:%M"), "\n")
## Fecha máxima = 01/06/2017 17:16
cat("============================================================\n")
## ============================================================
# Mostrar también en View
View(TDF_Completo)