PEAK_POWER_PER_HOUR
MARTIN SARMIENTO
2025-12-02
1 Configuración y Carga de Datos
##### UNIVERSIDAD CENTRAL DEL ECUADOR #####
#### AUTOR: MARTIN SARMIENTO ####
### CARRERA: INGENIERÍA EN PETRÓLEOS #####
#### VARIABLE POTENCIA PICO ####
## DATASET ##
setwd("~/R/PEAK_POWER_PER_HOUR")
# Cargar dataset
Datos <- read.csv("DataSet_.csv", sep = ";", fileEncoding = "latin1")
# Estructura de los datos
str(Datos)## 'data.frame': 7142 obs. of 26 variables:
## $ fid : int 1 2 3 4 5 6 7 8 9 10 ...
## $ objectid : int 127 128 129 130 131 132 133 134 135 136 ...
## $ code : chr "Arg-00001" "Arg-00002" "Arg-00003" "Arg-00004" ...
## $ country : chr "Argentina" "Argentina" "Argentina" "Argentina" ...
## $ plant_name : chr "Aconcagua solar farm" "Aconcagua solar farm" "Altiplano 200 Solar Power Plant" "Altiplano 200 Solar Power Plant" ...
## $ operational_status : chr "announced" "announced" "operating" "operating" ...
## $ longitude : num -68.9 -68.9 -66.9 -66.9 -68.9 ...
## $ latitude : num -33 -33 -24.1 -24.1 -33.3 ...
## $ elevation : int 929 929 4000 4000 937 865 858 858 858 858 ...
## $ area : num 0 0 4397290 5774 0 ...
## $ slope : num 0.574 0.574 1.603 6.243 0.903 ...
## $ slope_type : chr "Plano o casi plano" "Plano o casi plano" "Plano o casi plano" "Moderado" ...
## $ curvature : num 0.000795 0.000795 -0.002781 -0.043699 0.002781 ...
## $ curvature_type : chr "Superficies planas o intermedias" "Superficies planas o intermedias" "Superficies planas o intermedias" "Superficies cóncavas / Valles" ...
## $ aspect : num 55.1 55.1 188.7 270.9 108.4 ...
## $ aspect_type : chr "Northeast" "Northeast" "South" "West" ...
## $ ghi : num 6.11 6.11 8.01 7.88 6.12 ...
## $ solar_aptitude : num 0.746 0.746 0.8 0.727 0.595 ...
## $ solar_aptittude_class: chr "Alta" "Alta" "Alta" "Alta" ...
## $ humidity : num 0 0 53.7 53.7 0 ...
## $ wind_speed : num 3.78 3.78 7.02 8.33 3.87 ...
## $ wind_direction : num 0 0 55.1 55.1 0 ...
## $ ambient_temperature : num 12.6 12.6 6.8 6.8 13.1 ...
## $ optimal_tilt : int 31 31 26 26 31 33 30 30 30 30 ...
## $ peak_power_per_hour : num 4.98 4.98 6.39 6.39 4.97 ...
## $ total_power : num 25 66.2 101 107 180 ...##
## 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, union2 Cálculo de Intervalos y Frecuencias
#Extraer variable
Variable <- na.omit(Datos$peak_power_per_hour)
N <- length(Variable)
# Cálculos básicos
min_val <- min(Variable)
max_val <- max(Variable)
Rango <- max_val - min_val
K <- floor(1 + 3.322 * log10(N))
Amplitud <- Rango / K
# Creación de Límites
lim_inf <- round(seq(from = min_val, to = max_val - Amplitud, by = Amplitud), 2)
# Ajuste para el último límite
lim_sup <- round(seq(from = min_val + Amplitud, to = max_val, by = Amplitud), 2)
lim_sup[K] <- round(max_val, 2)
# Marca de Clase
MC <- (lim_inf + lim_sup) / 2
# Conteo de Frecuencias (ni)
ni <- numeric(K)
for (i in 1:K) {
if (i < K) {
ni[i] <- length(subset(Variable, Variable >= lim_inf[i] & Variable < lim_sup[i]))
} else {
ni[i] <- length(subset(Variable, Variable >= lim_inf[i] & Variable <= lim_sup[i] + 0.001))
}
}
# Cálculos de Frecuencias
sum_ni <- sum(ni)
hi <- (ni / sum_ni) * 100
Ni_asc <- cumsum(ni)
Hi_asc <- cumsum(hi)
# Acumuladas Descendentes
Ni_desc <- rev(cumsum(rev(ni)))
Hi_desc <- rev(cumsum(rev(hi)))
# Construcción del Dataframe
TDF_Potencia <- data.frame(
Li = lim_inf,
Ls = lim_sup,
MC = MC,
ni = ni,
hi = round(hi, 2),
Ni_asc = Ni_asc,
Ni_desc = Ni_desc,
Hi_asc = round(Hi_asc, 2),
Hi_desc = round(Hi_desc, 2)
)3 Tabla de Distribución de Frecuencias
#### Crear de fila de totales ####
totales <- c("TOTAL", "-", "-", sum(ni), sum(hi), "-", "-", "-", "-")
TDF_Potencia_Char <- TDF_Potencia %>% mutate(across(everything(), as.character))
TDF_Final <- rbind(TDF_Potencia_Char, totales)
# TABLA DE FRECUENCIAS GT
tabla_gt <- TDF_Final %>%
gt() %>%
tab_header(
title = md("**TABLA DE DISTRIBUCIÓN DE FRECUENCIAS**"),
subtitle = "Variable: Potencia Pico por Hora"
) %>%
tab_source_note(source_note = "Autor: Martin Sarmiento") %>%
cols_label(
Li = "Lim. Inf",
Ls = "Lim. Sup",
MC = "Marca Clase",
ni = "Frec. Abs (ni)",
hi = "Frec. Rel (%)",
Ni_asc = "Ni (Asc)",
Ni_desc = "Ni (Desc)",
Hi_asc = "Hi Asc (%)",
Hi_desc = "Hi Desc (%)"
) %>%
tab_options(
heading.title.font.size = px(16),
column_labels.background.color = "#f0f0f0",
table.font.size = px(14)
)
tabla_gt| TABLA DE DISTRIBUCIÓN DE FRECUENCIAS | ||||||||
| Variable: Potencia Pico por Hora | ||||||||
| Lim. Inf | Lim. Sup | Marca Clase | Frec. Abs (ni) | Frec. Rel (%) | Ni (Asc) | Ni (Desc) | Hi Asc (%) | Hi Desc (%) |
|---|---|---|---|---|---|---|---|---|
| 0 | 0.49 | 0.245 | 3 | 0.04 | 3 | 7135 | 0.04 | 100 |
| 0.49 | 0.98 | 0.735 | 0 | 0 | 3 | 7132 | 0.04 | 99.96 |
| 0.98 | 1.48 | 1.23 | 0 | 0 | 3 | 7132 | 0.04 | 99.96 |
| 1.48 | 1.97 | 1.725 | 0 | 0 | 3 | 7132 | 0.04 | 99.96 |
| 1.97 | 2.46 | 2.215 | 0 | 0 | 3 | 7132 | 0.04 | 99.96 |
| 2.46 | 2.95 | 2.705 | 0 | 0 | 3 | 7132 | 0.04 | 99.96 |
| 2.95 | 3.44 | 3.195 | 16 | 0.22 | 19 | 7132 | 0.27 | 99.96 |
| 3.44 | 3.93 | 3.685 | 116 | 1.63 | 135 | 7116 | 1.89 | 99.73 |
| 3.93 | 4.43 | 4.18 | 1542 | 21.61 | 1677 | 7000 | 23.5 | 98.11 |
| 4.43 | 4.92 | 4.675 | 5077 | 71.16 | 6754 | 5458 | 94.66 | 76.5 |
| 4.92 | 5.41 | 5.165 | 130 | 1.82 | 6884 | 381 | 96.48 | 5.34 |
| 5.41 | 5.9 | 5.655 | 128 | 1.79 | 7012 | 251 | 98.28 | 3.52 |
| 5.9 | 6.39 | 6.145 | 123 | 1.72 | 7135 | 123 | 100 | 1.72 |
| TOTAL | - | - | 7135 | 100 | - | - | - | - |
| Autor: Martin Sarmiento | ||||||||
4 Gráfico 1 – Frecuencia Local
color_sutil <- "#B3EE3A"
par(mar = c(8, 5, 4, 2))
barplot(TDF_Potencia$ni,
names.arg = TDF_Potencia$MC,
main = "Gráfica N°1: Frecuencia de Potencia Pico en Proyectos",
cex.main = 0.9,
xlab = "",
ylab = "Cantidad",
col = color_sutil,
space = 0,
las = 2,
cex.names = 0.7)
mtext("Potencia Pico", side = 1, line = 4)
5 Gráfico 2 – Frecuencia Global
color_grafico <- "#B3EE3A"
par(mar = c(8, 5, 4, 2))
barplot(TDF_Potencia$ni,
main = "Gráfica N°2: Frecuencia Global de Potencia Pico",
xlab = "",
ylab = "Cantidad",
names.arg = TDF_Potencia$MC,
col = color_sutil,
space = 0,
cex.main = 0.9,
cex.axis = 0.7,
cex.names = 0.7,
las = 2,
ylim = c(0, sum(TDF_Potencia$ni)))
mtext("Potencia Pico", side = 1, line = 4)
6 Gráfico 3 – Porcentaje Local
color_grafico <- "#B3EE3A"
par(mar = c(8, 5, 4, 2))
barplot(TDF_Potencia$hi,
main = "Gráfica N°3: Porcentaje de Frecuencia de Potencia Pico",
xlab = "",
ylab = "Porcentaje (%)",
col = color_sutil,
space = 0,
names.arg = TDF_Potencia$MC,
cex.main = 0.9,
cex.axis = 0.7,
cex.names = 0.7,
las = 2,
ylim = c(0, max(TDF_Potencia$hi) * 1.1))
mtext("Potencia Pico", side = 1, line = 4)
7 Gráfico 4 – Porcentaje Global
color_grafico <- "#B3EE3A"
par(mar = c(8, 5, 4, 2))
barplot(TDF_Potencia$hi,
main = "Gráfica N°4: Porcentaje Global de Potencia Pico",
xlab = "",
ylab = "Porcentaje (%)",
col = color_sutil,
space = 0,
cex.main = 0.9,
names.arg = TDF_Potencia$MC,
las = 2,
cex.names = 0.7,
ylim = c(0, 100))
mtext("Potencia Pico", side = 1, line = 4)
8 Gráfico 5 – Diagrama de Cajas (Boxplot)
par(mar = c(5, 5, 4, 2))
boxplot(Variable,
horizontal = TRUE,
col = color_sutil,
xlab = "Potencia Pico",
cex.main = 0.9,
main = "Gráfica N°5: Variabilidad de la Potencia Pico")
9 Gráfico 6 – Ojivas de Frecuencia Acumulada
par(mar = c(5, 5, 4, 10), xpd = TRUE)
# Coordenadas
x_asc <- TDF_Potencia$Ls
x_desc <- TDF_Potencia$Li
y_asc <- TDF_Potencia$Ni_asc
y_desc <- TDF_Potencia$Ni_desc
# 1. Dibujar la Ascendente
plot(x_asc, y_asc,
type = "b",
main = "Gráfica N°6: Ojiva de Frecuencia Acumulada (Potencia)",
cex.main = 0.9,
xlab = "Potencia Pico (Límites Superiores)",
ylab = "Frecuencia acumulada (Ni)",
col = "black",
pch = 19,
xlim = c(min(TDF_Potencia$Li), max(x_asc)),
ylim = c(0, sum(ni)),
bty = "l"
)
# 2. Agregar la Descendente
lines(x_desc, y_desc, col = "#9ACD32", type = "b", pch = 19)
grid()
legend("left",
legend = c("Ascendente", "Descendente"),
col = c("black", "#9ACD32"),
lty = 1,
pch = 1,
cex = 0.6,
inset = c(0.05, 0.05),
bty = "n")
10 Indicadores Estadísticos
## INDICADORES DE TENDENCIA CENTRAL
# Media aritmética
media <- round(mean(Variable), 2)
# Moda
max_frecuencia <- max(TDF_Potencia$ni)
moda_vals <- TDF_Potencia$MC[TDF_Potencia$ni == max_frecuencia]
moda_txt <- paste(round(moda_vals, 2), collapse = ", ")
# Mediana
mediana <- round(median(Variable), 2)
## INDICADORES DE DISPERSIÓN
# Varianza
varianza <- var(Variable)
# Desviación Estándar
sd_val <- sd(Variable)
# Coeficiente de Variación
cv <- round((sd_val / abs(media)) * 100, 2)
## INDICADORES DE FORMA
# Coeficiente de Asimetría
asimetria <- skewness(Variable, type = 2)
# Curtosis
curtosis <- kurtosis(Variable)
outliers <- boxplot.stats(Variable)$out
msg_atipicos <- if(length(outliers) > 0) "Presencia de valores atípicos" else "No hay presencia de valores atípicos"
tabla_indicadores <- data.frame(
"Variable" = c("Potencia Pico"),
"Rango" = paste0("[", round(min(Variable), 2), "; ", round(max(Variable), 2), "]"),
"X" = c(media),
"Me" = c(round(mediana, 2)),
"Mo" = c(moda_txt),
"V" = c(round(varianza, 2)),
"Sd" = c(round(sd_val, 2)),
"Cv" = c(cv),
"As" = c(round(asimetria, 4)),
"K" = c(round(curtosis, 2)),
"Valores_Atipicos" = msg_atipicos
)
# Generar Tabla GT
tabla_conclusiones_gt <- tabla_indicadores %>%
gt() %>%
tab_header(
title = md("**CONCLUSIONES ESTADÍSTICAS**"),
subtitle = "Resumen de la variable Potencia Pico"
) %>%
tab_source_note(source_note = "Autor: Martin Sarmiento") %>%
cols_label(
Variable = "Variable",
Rango = "Rango",
X = "Media (X)",
Me = "Mediana (Me)",
Mo = "Moda (Mo)",
V = "Varianza (V)",
Sd = "Desv. Est. (Sd)",
Cv = "C.V. (%)",
As = "Asimetría (As)",
K = "Curtosis (K)",
Valores_Atipicos = "Valores Atípicos"
) %>%
tab_options(
heading.title.font.size = px(16),
column_labels.background.color = "#f0f0f0"
)
tabla_conclusiones_gt| CONCLUSIONES ESTADÍSTICAS | ||||||||||
| Resumen de la variable Potencia Pico | ||||||||||
| Variable | Rango | Media (X) | Mediana (Me) | Moda (Mo) | Varianza (V) | Desv. Est. (Sd) | C.V. (%) | Asimetría (As) | Curtosis (K) | Valores Atípicos |
|---|---|---|---|---|---|---|---|---|---|---|
| Potencia Pico | [0; 6.39] | 4.6 | 4.6 | 4.68 | 0.14 | 0.37 | 8.03 | 0.4848 | 15.43 | Presencia de valores atípicos |
| Autor: Martin Sarmiento | ||||||||||