CodeBase Tracking Global CO2 Emissions (1990-2023)

library(dplyr)

Attaching package: 'dplyr'

The following objects are masked from 'package:stats':

    filter, lag

The following objects are masked from 'package:base':

    intersect, setdiff, setequal, union

library(tidyr)
library(ggplot2)
library(stringr)
library(janitor)

Attaching package: 'janitor'

The following objects are masked from 'package:stats':

    chisq.test, fisher.test

raw_data <- read.csv("https://raw.githubusercontent.com/Jeovany97/Data-607/refs/heads/main/Project%202/Tracking%20Global%20CO2%20Emissions%20(1990-2023)/wide_format_co2_emission_dataset.csv", check.names = FALSE)

Tidying the data

The tidying of this dataset was done with Anthropic LLM Claude

country_col <- names(raw_data)[1]
total_col <- names(raw_data)[ncol(raw_data)]

tidy_data <- raw_data %>%
  # Reshape: Pivot everything EXCEPT the country and the total sum column
  pivot_longer(
    cols = -c(all_of(country_col), all_of(total_col)), 
    names_to = "year", 
    values_to = "co2_emissions",
    # FIX: This prevents the 'Can't combine character and double' error
    values_transform = list(co2_emissions = as.character)
  ) %>%
  # Rename for consistency
  rename(country = !!sym(country_col), total_sum = !!sym(total_col)) %>%
  # Clean up data types
  mutate(
    year = as.numeric(year),
    country = str_trim(country),
    # Convert characters back to numbers (the '-' becomes NA automatically)
    co2_emissions = as.numeric(co2_emissions)
  ) %>%
  # Remove the NAs (the old dashes)
  filter(!is.na(co2_emissions)) %>%
  arrange(country, year)

Warning: There was 1 warning in `mutate()`.
ℹ In argument: `co2_emissions = as.numeric(co2_emissions)`.
Caused by warning:
! NAs introduced by coercion

# Preview results
head(tidy_data)

# A tibble: 6 × 4
  country     total_sum  year co2_emissions
  <chr>       <chr>     <dbl>         <dbl>
1 Afghanistan 8.35       1990           0.2
2 Afghanistan 8.35       1991           0.2
3 Afghanistan 8.35       1992           0.1
4 Afghanistan 8.35       1993           0.1
5 Afghanistan 8.35       1994           0.1
6 Afghanistan 8.35       1995           0.1

analysis of the top 10 CO2 Emissions

top_10_list <- tidy_data %>%
  distinct(country, total_sum) %>%
  slice_max(total_sum, n = 10) %>%
  pull(country)

plot_data <- tidy_data %>%
  filter(country %in% top_10_list)

ggplot(plot_data, aes(x = year, y = co2_emissions, color = country)) +
  geom_line(size = 1) +
  geom_point(size = 1.5, alpha = 0.5) + # Adds dots to see the specific data points
  theme_minimal() +
  labs(
    title = "CO2 Emission Trends: Top 10 Global Emitters",
    subtitle = "Data source: Tracking Global CO2 Emissions (1990-2023)",
    x = "Year",
    y = "Emissions (Metric Tons per Capita)",
    color = "Country"
  ) +
  theme(legend.position = "bottom")

Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
ℹ Please use `linewidth` instead.