COUNTRY

1 Configuración y Carga de Datos

##### UNIVERSIDAD CENTRAL DEL ECUADOR #####
#### AUTOR: MARTIN SARMIENTO ####
### CARRERA: INGENIERÍA EN PETRÓLEOS #####

#### VARIABLE PAISES (CONTINENTES) ####
## DATASET ##
setwd("~/R/COUNTRY")
# Cargar dataset
Datos <- read.csv("Data_Mundial_Final.csv", sep = ";", fileEncoding = "latin1")
## Estructura de los datos
str(Datos)

## 'data.frame':    58771 obs. of  29 variables:
##  $ OBJECTID              : int  127 129 131 132 133 137 138 139 140 145 ...
##  $ code                  : chr  "00127-ARG-P" "00129-ARG-G" "00131-ARG-P" "00132-ARG-P" ...
##  $ plant_name            : chr  "Aconcagua solar farm" "Altiplano 200 Solar Power Plant" "Anchoris solar farm" "Antu Newen solar farm" ...
##  $ country               : chr  "Argentina" "Argentina" "Argentina" "Argentina" ...
##  $ operational_status    : chr  "announced" "operating" "construction" "cancelled - inferred 4 y" ...
##  $ longitude             : chr  "-68,8713" "-66,895798" "-68,915001" "-70,269897" ...
##  $ latitude              : chr  "-32,998501" "-24,1392" "-33,330101" "-37,375801" ...
##  $ elevation             : int  929 4000 937 865 858 570 1612 665 3989 2640 ...
##  $ area                  : chr  "250,337006" "4397290" "645,163025" "241,276001" ...
##  $ size                  : chr  "Small" "Big" "Small" "Small" ...
##  $ slope                 : chr  "0,574179" "1,60257" "0,902748" "1,79147" ...
##  $ slope_type            : chr  "Plano o casi plano" "Plano o casi plano" "Plano o casi plano" "Plano o casi plano" ...
##  $ curvature             : chr  "0,000795" "-0,002781" "0,002781" "-0,002384" ...
##  $ curvature_type        : chr  "Superficies planas o intermedias" "Superficies planas o intermedias" "Superficies planas o intermedias" "Superficies planas o intermedias" ...
##  $ aspect                : chr  "55,124672" "188,707367" "108,434952" "239,349335" ...
##  $ aspect_type           : chr  "Northeast" "South" "East" "Southwest" ...
##  $ dist_to_road          : chr  "127,2827045" "56014,95403" "335,9280031" "34,00973342" ...
##  $ ambient_temperature   : chr  "12,6" "6,8" "13,1" "11,4" ...
##  $ ghi                   : chr  "6,11" "8,012" "6,119" "6,223" ...
##  $ humidity              : chr  "53,74" "53,74" "53,74" "53,74" ...
##  $ wind_speed            : chr  "3,7789" "7,02062" "3,87037" "6,55962" ...
##  $ wind_direction        : chr  "55,099998" "55,099998" "55,099998" "55,099998" ...
##  $ dt_wind               : chr  "Northeast" "Northeast" "Northeast" "Northeast" ...
##  $ solar_aptitude        : chr  "0,746197" "0,8" "0,595309" "0,657269" ...
##  $ solar_aptitude_rounded: int  7 8 6 7 7 7 8 7 8 6 ...
##  $ solar_aptittude_class : chr  "Alta" "Alta" "Media" "Alta" ...
##  $ capacity              : chr  "25" "101" "180" "20" ...
##  $ optimal_tilt          : chr  "31" "26" "31" "33" ...
##  $ pv_potential          : chr  "4,983" "6,389" "4,969" "5,002" ...

# Cargamos las librerias
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(ggplot2)
library(gt)

2 Extracción y Conteo Inicial

# Extraer variable
Pais <- Datos$country
# EDAvariable nominal
TDF_pais <- table(Pais)

tabla_pais <- as.data.frame(TDF_pais)
hi <- tabla_pais$Freq/sum(tabla_pais$Freq)
hi_porc <- hi*100
sum(hi_porc)

## [1] 100

tabla_PAIS <- data.frame(tabla_pais,hi_porc)
colnames(tabla_PAIS)[1] <- "Pais"

3 Categorización y Ordenamiento Lógico

### Agrupación ###
tabla_PAIS$grupo <- case_when(
  # América del Sur
  grepl("Argentina|Bolivia|Brazil|Chile|Colombia|Ecuador|Guyana|Paraguay|Peru|Suriname|Uruguay|Venezuela", 
        tabla_PAIS$Pais, ignore.case = TRUE) ~ "América del Sur",
  
  # América del Norte
  grepl("United States|USA|Canada|Mexico|México", 
        tabla_PAIS$Pais, ignore.case = TRUE) ~ "América del Norte",
  
  # América Central y Caribe
  grepl("Guatemala|Belize|Honduras|El Salvador|Nicaragua|Costa Rica|Panama|Panamá|Cuba|Dominican Republic|Haiti|Jamaica|Puerto Rico|Antigua and Barbuda|Cayman Islands|Bonaire|Virgin Islands|Saint Kitts and Nevis|Guadeloupe", 
        tabla_PAIS$Pais, ignore.case = TRUE) ~ "América Central y Caribe",
  
  # Europa
  grepl("Spain|España|France|Germany|Alemania|Italy|Italia|United Kingdom|UK|Portugal|Netherlands|Belgium|Poland|Sweden|Norway|Denmark|Finland|Greece|Russia|Ukraine|Albania|Andorra|Austria|Belarus|Bosnia and Herzegovina|Bulgaria|Croatia|Cyprus|Czech Republic|Estonia|Holy See|Hungary|Ireland|Isle of Man|Kosovo|Latvia|Lithuania|Luxembourg|Malta|Moldova|Montenegro|North Macedonia|Romania|Serbia|Slovakia|Slovenia|Switzerland", 
        tabla_PAIS$Pais, ignore.case = TRUE) ~ "Europa",
  
  # Asia
  grepl("China|India|Japan|Japón|Korea|Vietnam|Thailand|Indonesia|Malaysia|Philippines|Saudi Arabia|UAE|United Arab Emirates|Israel|Turkey|Turquía|Iran|Iraq|Afghanistan|Armenia|Azerbaijan|Bahrain|Bangladesh|Bhutan|Brunei|Cambodia|Georgia|Hong Kong|Jordan|Kazakhstan|Kuwait|Kyrgyzstan|Laos|Lebanon|Mongolia|Myanmar|Nepal|Oman|Pakistan|Palestine|Qatar|Singapore|Sri Lanka|Syria|Taiwan|Tajikistan|Timor-Leste|Türkiye|Uzbekistan|Yemen", 
        tabla_PAIS$Pais, ignore.case = TRUE) ~ "Asia",
  
  # África
  grepl("South Africa|Egypt|Egipto|Nigeria|Morocco|Marruecos|Algeria|Kenya|Ethiopia|Ghana|Senegal|Ivory Coast|Angola|Benin|Botswana|Burkina Faso|Burundi|Cabo Verde|Cameroon|Central African Republic|Chad|Comoros|Côte d'Ivoire|DR Congo|Republic of the Congo|Djibouti|Eritrea|Eswatini|Gabon|Guinea|Guinea-Bissau|Lesotho|Liberia|Libya|Madagascar|Malawi|Mali|Mauritania|Mauritius|Mayotte|Mozambique|Namibia|Niger|Réunion|Rwanda|Sao Tome and Principe|Seychelles|Sierra Leone|Somalia|South Sudan|Sudan|Tanzania|The Gambia|Togo|Tunisia|Uganda|Western Sahara|Zambia|Zimbabwe", 
        tabla_PAIS$Pais, ignore.case = TRUE) ~ "África",
  
  # Oceanía y Otros territorios
  grepl("Australia|New Zealand|Fiji|Papua|British Indian Ocean Territory", 
        tabla_PAIS$Pais, ignore.case = TRUE) ~ "Oceanía",
  
  TRUE ~ "Otros / No Especificado"
)

tabla_resumen <- tabla_PAIS %>%
  group_by(grupo) %>%
  summarise(
    Frecuencia = sum(Freq),
    Porcentaje = sum(hi_porc)) %>%
  arrange(desc(Frecuencia))

# Renombramos columnas
colnames(tabla_resumen) <- c("Continente","ni","hi (%)")

# Tabla Intermedia GT
tabla_resumen_gt <- tabla_resumen %>%
  gt() %>%
  tab_header(
    title = md("**Tabla N°1 de Agrupación por Continentes de las Plantas Solares**")) %>%
  tab_source_note(source_note = "Autor: Martin Sarmiento") %>%
  cols_label(
    Continente = "Continentes",
    ni = "Frecuencia (ni)",
    `hi (%)` = "Porcentaje (hi%)") %>%
  fmt_number(columns = c(`hi (%)`), decimals = 2) %>%
  tab_options(
    heading.title.font.size = px(16),
    column_labels.background.color = "#F0F0F0")

# Mostramos la tabla 
tabla_resumen_gt 

Tabla N°1 de Agrupación por Continentes de las Plantas Solares
Continentes	Frecuencia (ni)	Porcentaje (hi%)
Asia	28403	48.33
Europa	18787	31.97
América del Norte	7783	13.24
América del Sur	2347	3.99
África	1072	1.82
América Central y Caribe	379	0.64
Autor: Martin Sarmiento

4 Tabla de Distribución de Frecuencias

#### Crear fila de totales ####
totales <- c("TOTAL", sum(tabla_resumen$ni), sum(tabla_resumen$`hi (%)`))
tabla_Continente_Final <- rbind(tabla_resumen, totales)

# Convertir a números para GT
tabla_Continente_Final$ni <- as.numeric(tabla_Continente_Final$ni)
tabla_Continente_Final$`hi (%)` <- as.numeric(tabla_Continente_Final$`hi (%)`)

# TABLA 1 
tabla_final_gt <- tabla_Continente_Final %>%
  gt() %>%
  tab_header(
    title = md("**Tabla N°2 de Distribución de Frecuencias por Continentes de las Plantas Solares**")) %>%
  tab_source_note(source_note = "Autor: Martin Sarmiento") %>%
  cols_label(
    Continente = "Continentes",
    ni = "Frecuencia (ni)",
    `hi (%)` = "Porcentaje (hi%)") %>%
  fmt_number(columns = c(`hi (%)`), decimals = 2) %>%
  tab_options(
    heading.title.font.size = px(16),
    column_labels.background.color = "#F0F0F0")

tabla_final_gt

Tabla N°2 de Distribución de Frecuencias por Continentes de las Plantas Solares
Continentes	Frecuencia (ni)	Porcentaje (hi%)
Asia	28403	48.33
Europa	18787	31.97
América del Norte	7783	13.24
América del Sur	2347	3.99
África	1072	1.82
América Central y Caribe	379	0.64
TOTAL	58771	100.00
Autor: Martin Sarmiento

5 Análisis Gráfico

5.1 Diagramas de Barras de Cantidad

par(mar = c(13, 6, 4, 2)) 
barplot(tabla_resumen$ni,
        main="",
        xlab = "", 
        ylab = "", 
        col = "skyblue",
        ylim = c(0, max(tabla_resumen$ni) * 1.1),
        names.arg=tabla_resumen$Continente, 
        cex.names = 0.8, 
        las = 2)
mtext("Cantidad", side = 2, line = 4.5, cex = 1, font = 1)
mtext("Continentes", side = 1, line = 9)

mtext("Gráfica N°1: Distribución de Cantidad de Plantas Solares por Continentes", 
      side = 3, 
      line = 2, 
      adj = 0.5, 
      cex = 0.9, 
      font = 2)

par(mar = c(13, 6, 4, 2)) 
barplot(tabla_resumen$ni,
        main="",
        xlab = "", 
        ylab = "", 
        col = "skyblue", 
        ylim = c(0, 58771),
        names.arg=tabla_resumen$Continente, 
        cex.names = 0.8, 
        las = 2)
mtext("Cantidad", side = 2, line = 4.5, cex = 1, font = 1)
mtext("Continentes", side = 1, line = 11)

mtext("Gráfica N°2: Distribución de Cantidad de Plantas Solares por Continentes", 
      side = 3, 
      line = 2, 
      adj = 0.5, 
      cex = 0.9, 
      font = 2)

5.2 Diagramas de Barras Porcentual

par(mar = c(13, 4, 4, 2))
bp3 <- barplot(tabla_resumen$`hi (%)`,
        main="",
        xlab = "", 
        ylab = "Porcentaje %", 
        col = "skyblue",
        ylim = c(0, max(tabla_resumen$`hi (%)`) * 1.3),
        names.arg=tabla_resumen$Continente, 
        cex.names = 0.8, 
        las = 2)
mtext("Continentes", side = 1, line = 11)

mtext("Gráfica N°3: Distribución Porcentual de las Plantas Solares por Continentes", 
      side = 3, 
      line = 2, 
      adj = 0.5, 
      cex = 0.9, 
      font = 2)

text(x = bp3, y = tabla_resumen$`hi (%)`, 
     labels = paste0(round(tabla_resumen$`hi (%)`, 2), "%"), 
     pos = 3, cex = 0.8, col = "black")

par(mar = c(13, 4, 4, 2))
bp4 <- barplot(tabla_resumen$`hi (%)`,
        main="",
        xlab = "", 
        ylab = "Porcentaje %", 
        col = "skyblue", 
        ylim = c(0,100),
        names.arg=tabla_resumen$Continente, 
        cex.names = 0.8, 
        las = 2)
mtext("Continentes", side = 1, line = 11)

mtext("Gráfica N°4: Distribución Porcentual de las Plantas Solares por Continentes", 
      side = 3,
      line = 2, 
      adj = 0.5, 
      cex = 0.9, 
      font = 2)

text(x = bp4, y = tabla_resumen$`hi (%)`, 
     labels = paste0(round(tabla_resumen$`hi (%)`, 2), "%"), 
     pos = 3, cex = 0.8, col = "black")

5.3 Diagrama Circular

par(mar = c(5, 6, 4, 10), xpd = TRUE)

mis_colores_azules <- c(
  "#E1F5FE", 
  "#B3E5FC", 
  "#81D4FA", 
  "#4FC3F7", 
  "#29B6F6", 
  "#039BE5", 
  "#0277BD")

colores_finales <- rep(mis_colores_azules, length.out = length(tabla_resumen$Continente))

pie(tabla_resumen$`hi (%)`,
    main = "",
    radius = 0.9,
    labels = paste0(round(tabla_resumen$`hi (%)`, 1), "%"),
    col = colores_finales,
    cex = 0.7)

mtext("Gráfica N°5: Distribución Porcentual de las Plantas Solares por Continentes", 
      side = 3, 
      line = 2, 
      adj = 0.5,
      cex = 0.9, 
      font = 2)

legend(x = 1.3, y = 1.1,
       legend = tabla_resumen$Continente,
       fill = colores_finales,
       cex = 0.6,
       title = "Continentes",
       bty = "n")

6 Indicadores Estadísticos

# Cálculo de la Moda 
moda_continentes <- tabla_resumen$Continente[which.max(tabla_resumen$ni)]

# Tabla de Indicadores
tabla_indicadores <- data.frame(
  "Variable" = "País",
  "Rango" = "Continentes",
  "Media (X)" = "-", 
  "Mediana (Me)" = "-", 
  "Moda (Mo)" = moda_continentes, 
  "Varianza (V)" = "-", 
  "Desv. Est. (Sd)" = "-", 
  "C.V. (%)" = "-", 
  "Asimetría (As)" = "-", 
  "Curtosis (K)" = "-",
  check.names = FALSE)

# Generar Tabla de Indicadores
tabla_conclusiones_gt <- tabla_indicadores %>%
  gt() %>%
  tab_header(
    title = md("**Tabla N°3 de Conclusiones por Continentes de las Plantas Solares**")) %>%
  tab_source_note(source_note = "Autor: Martin Sarmiento") %>%
  tab_options(column_labels.background.color = "#F0F0F0")

tabla_conclusiones_gt

Tabla N°3 de Conclusiones por Continentes de las Plantas Solares
Variable	Rango	Media (X)	Mediana (Me)	Moda (Mo)	Varianza (V)	Desv. Est. (Sd)	C.V. (%)	Asimetría (As)	Curtosis (K)
País	Continentes	-	-	Asia	-	-	-	-	-
Autor: Martin Sarmiento

7 Conclusiones

La variable “País”, presenta como valor más frecuente Asia, con una participación destacada en la muestra.