Boxplots Energy

Chart: Boxplot Capital Stock by Country

library(readxl)
# 📌 Cargar el archivo Excel
df <- read_excel("Data Energy 3.0.xlsx", sheet = "Datos")
library(ggplot2)
library(dplyr)

df_promedio <- df %>%
  filter(Año >= 2003 & Año <= 2019) %>%
  group_by(Año, País) %>%
  summarise(Capital_stock = mean(`Capital stock  at current PPPs (in millions. 2017US)`, na.rm = TRUE), 
            .groups = "drop")

ggplot(df_promedio, aes(x = factor(Año), y = Capital_stock)) +
  geom_boxplot(color = "black", fill = "lightblue", outlier.color = "red", outlier.size = 0.5) +
  theme_minimal() +
  labs(title = "Distribution of Capital Stock by Year (2003-2019)", 
       x = "Year", 
       y = "Capital Stock") +
  theme(axis.text.x = element_text(angle = 90, hjust = 1))  # Rotar etiquetas para mejor lectura

Chart: Boxplot Real GDP by Country

library(ggplot2)

ggplot(df %>% filter(Año >= 2003 & Año <= 2019), 
       aes(x = factor(Año), y = `GDP real dólar (millions)`)) +
  geom_boxplot(color = "black", fill = "lightblue", outlier.color = "red", outlier.size = 0.5) +
  labs(title = "Distribution of real GDP by Year (2003-2019)", 
       x = "Year", 
       y = "GDP (Millions of dollars)") +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 90, hjust = 1))  # Rotar etiquetas para mejor visibilidad

Chart: Boxplot Employment

library(readxl)
library(ggplot2)
library(dplyr)

# 📌 Cargar el archivo Excel
df <- read_excel("Data Energy 3.0.xlsx", sheet = "Datos")

# Filtrar solo los años 2003-2019 y calcular el promedio por país y año
df_promedio <- df %>%
  filter(Año >= 2003 & Año <= 2019) %>%
  group_by(Año, País) %>%
  summarise(Empleo = mean(`Empleo (thousand)`, na.rm = TRUE),
            .groups = "drop")

# Crear el boxplot
ggplot(df_promedio, aes(x = factor(Año), y = Empleo)) +
  geom_boxplot(color = "black", fill = "lightblue", outlier.color = "red", outlier.size = 0.5) +
  labs(title = "Employment Distribution by Year (2003-2019)", 
       x = "Year", 
       y = "Employment (thousand)") +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 90, hjust = 1))  # Rotar etiquetas para mejor legibilidad

Chart: Boxplot Per capita Final energy consumption (KGOE)

library(ggplot2)
library(dplyr)
library(readxl)  # Asegurar que se pueda leer el archivo Excel

# Cargar la base de datos
Data_Energy_3_0 <- read_excel("Data Energy 3.0.xlsx", sheet = "Datos")

# Convertir la columna de consumo de energía en hogares a formato numérico
Data_Energy_3_0 <- Data_Energy_3_0 %>%
  mutate(`Final energy consumption in households per capita (Kilogram of oil equivalent (KGOE))` = 
           as.numeric(gsub(",", "", `Final energy consumption in households per capita (Kilogram of oil equivalent (KGOE))`)))

# Filtrar los datos solo entre 2003 y 2019
df_filtered <- Data_Energy_3_0 %>%
  filter(Año >= 2003 & Año <= 2019)

# Agrupar por país y año para calcular el consumo promedio de energía en hogares por año
df_promedio <- df_filtered %>%
  group_by(Año, País) %>%
  summarise(Energy_Consumption = mean(`Final energy consumption in households per capita (Kilogram of oil equivalent (KGOE))`, 
                                      na.rm = TRUE),
            .groups = "drop")

# Crear el boxplot
ggplot(df_promedio, aes(x = factor(Año), y = Energy_Consumption)) +
  geom_boxplot(color = "black", fill = "lightblue", outlier.color = "red", outlier.size = 0.5) +
  labs(title = "Distribution of Energy Consumption per Year", 
       x = "Year", 
       y = "Energy Consumption (KGOE)") +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 90, hjust = 1))  # Rotar etiquetas para mejor legibilidad

## Chart: Boxplot Home adequaly warm

library(ggplot2)
library(dplyr)

# Filtrar los datos solo entre 2003 y 2019
df_filtered <- Data_Energy_3_0 %>%
  filter(Año >= 2003 & Año <= 2019)

# Convertir la columna "Home adequaly warm (Percentage)" a formato numérico
df_filtered <- df_filtered %>%
  mutate(`Home adequaly warm (Percentage)` = as.numeric(gsub(",", "", `Home adequaly warm (Percentage)`)))

# Agrupar por país y año para calcular el promedio
df_promedio <- df_filtered %>%
  group_by(Año, País) %>%
  summarise(Home_Warm_Percentage = mean(`Home adequaly warm (Percentage)`, na.rm = TRUE),
            .groups = "drop")

# Crear el boxplot
ggplot(df_promedio, aes(x = factor(Año), y = Home_Warm_Percentage)) +
  geom_boxplot(color = "black", fill = "lightblue", outlier.color = "red", outlier.size = 0.5) +
  labs(title = "Distribution of Home Adequacy for Heating by Year", 
       x = "Year", 
       y = "Percentage of Homes Adequately Heated") +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 90, hjust = 1))  # Rotar etiquetas para mejor legibilidad

Chart: Boxplot Final energy consumption

library(ggplot2)
library(dplyr)

# Filtrar los datos solo entre 2003 y 2019
df_filtered <- Data_Energy_3_0 %>%
  filter(Año >= 2003 & Año <= 2019)

# Convertir la columna "final energy consumption (Million tonnes of oil equivalent)" a formato numérico
df_filtered <- df_filtered %>%
  mutate(`final energy comsuption (Million tonnes of oil equivalent)` = 
           as.numeric(gsub(",", "", `final energy comsuption (Million tonnes of oil equivalent)`)))

# Agrupar por país y año para calcular el promedio
df_promedio <- df_filtered %>%
  group_by(Año, País) %>%
  summarise(Final_Energy_Consumption = mean(`final energy comsuption (Million tonnes of oil equivalent)`, 
                                            na.rm = TRUE),
            .groups = "drop")

# Crear el boxplot
ggplot(df_promedio, aes(x = factor(Año), y = Final_Energy_Consumption)) +
  geom_boxplot(color = "black", fill = "lightblue", outlier.color = "red", outlier.size = 0.5) +
  labs(title = "Final Energy Consumption Distribution by Year", 
       x = "Year", 
       y = "Final Energy Consumption (MTOE)") +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 90, hjust = 1))  # Rotar etiquetas para mejor legibilidad