gistfile1.txt

# =============================================================================
# PART 2: RENEWABLE ENERGY TRANSITION (25 points)
# =============================================================================

# Load required libraries
library(readxl)
library(dplyr)
library(ggplot2)
library(gridExtra)


cat("PART 2: RENEWABLE ENERGY TRANSITION\n")
cat("===================================\n\n")

# Load energy mix data
energy_mix <- read_excel("energy_mix.xlsx")

# Question 1: Data quality issues
cat("Question 1: Missing data analysis\n")
missing_analysis <- energy_mix %>%
  summarise(
    renewable_missing = round(sum(is.na(renewable_pct)) / n() * 100, 1),
    nuclear_missing = round(sum(is.na(nuclear_pct)) / n() * 100, 1),
    coal_missing = round(sum(is.na(coal_pct)) / n() * 100, 1)
  )

cat("Percentage of missing observations:\n")
cat("renewable_pct:", missing_analysis$renewable_missing, "%\n")
cat("nuclear_pct:", missing_analysis$nuclear_missing, "%\n")
cat("coal_pct:", missing_analysis$coal_missing, "%\n\n")

# For remaining questions, exclude missing values
energy_clean <- energy_mix %>%
  filter(!is.na(renewable_pct) & !is.na(nuclear_pct) & !is.na(coal_pct))

# Question 2: High renewable adoption by year
cat("Question 2: Percentage of high renewable adoption countries by year\n")
high_renewable_by_year <- energy_clean %>%
  filter(year %in% c(2015, 2018, 2021, 2023)) %>%
  group_by(year) %>%
  summarise(
    total_countries = n(),
    high_renewable_countries = sum(renewable_pct > 50),
    pct_high_renewable = round(high_renewable_countries / total_countries * 100, 1),
    .groups = 'drop'
  )

cat("Year | % High Renewable Countries\n")
for(i in 1:nrow(high_renewable_by_year)) {
  cat(high_renewable_by_year$year[i], " | ", high_renewable_by_year$pct_high_renewable[i], "%\n")
}
cat("\n")

# Question 3: Correlation between renewable energy and economic development (2023)
cat("Question 3: Renewable energy vs economic development analysis (2023)\n")
energy_2023 <- energy_clean %>%
  filter(year == 2023) %>%
  filter(!is.na(gdp_per_capita))

# Correlation coefficient
correlation_coef <- round(cor(energy_2023$renewable_pct, energy_2023$gdp_per_capita, use = "complete.obs"), 3)
cat("Correlation coefficient (renewable % vs GDP per capita):", correlation_coef, "\n")

# Divide into terciles
energy_2023_terciles <- energy_2023 %>%
  mutate(
    gdp_tercile = ntile(gdp_per_capita, 3),
    income_level = case_when(
      gdp_tercile == 1 ~ "Low Income",
      gdp_tercile == 2 ~ "Middle Income", 
      gdp_tercile == 3 ~ "High Income"
    )
  ) %>%
  group_by(income_level) %>%
  summarise(mean_renewable = round(mean(renewable_pct, na.rm = TRUE), 1), .groups = 'drop') %>%
  arrange(match(income_level, c("Low Income", "Middle Income", "High Income")))

cat("\nMean renewable percentage by income tercile:\n")
print(energy_2023_terciles)
cat("\n")

# Question 4: Stacked bar chart of global energy mix evolution
cat("Question 4: Creating stacked bar chart of global energy mix evolution\n")

# Calculate global averages for selected years
global_energy_mix <- energy_clean %>%
  filter(year %in% c(2010, 2013, 2016, 2019, 2022, 2023)) %>%
  group_by(year) %>%
  summarise(
    Fossil_Fuels = round(mean(fossil_fuel_pct, na.rm = TRUE), 1),
    Renewables = round(mean(renewable_pct, na.rm = TRUE), 1),
    Nuclear = round(mean(nuclear_pct, na.rm = TRUE), 1),
    .groups = 'drop'
  ) %>%
  tidyr::pivot_longer(cols = c(Fossil_Fuels, Renewables, Nuclear), 
                      names_to = "Energy_Type", values_to = "Percentage")

# Create stacked bar chart
p2 <- ggplot(global_energy_mix, aes(x = factor(year), y = Percentage, fill = Energy_Type)) +
  geom_bar(stat = "identity", position = "stack") +
  scale_y_continuous(limits = c(0, 100), breaks = seq(0, 100, 20)) +
  scale_fill_manual(values = c("Fossil_Fuels" = "#8B4513", "Renewables" = "#228B22", "Nuclear" = "#4169E1")) +
  labs(
    title = "Global Energy Mix Evolution (2010-2023)",
    x = "Year",
    y = "Percentage of Global Energy Mix (%)",
    fill = "Energy Category"
  ) +
  theme_minimal() +
  theme(legend.position = "bottom")

print(p2)
cat("Stacked bar chart created showing energy mix evolution\n\n")