• Line plot of global average CO₂ per capita over time

Prerequisites

• R ≥ 4.0
• Internet access to fetch OWID data

R Packages

• ggplot2, dplyr, lubridate, tidyr, forcats, scales, viridis, zoo, corrplot

The main script auto-installs any missing packages.

Installation

1. Clone this repository:

   git clone https://github.com/yourusername/co2-analysis.git
   cd co2-analysis
   

2. Optional: copy .env.example → .env to set DATA_DIR if you prefer a custom data folder.

Usage

From R or RStudio

# Set working directory to the project root
setwd("path/to/co2-analysis")

# Source the analysis script
source("CO2_Analysis.R")

All charts will render in sequence and the regression summary will print to the console.

Via Make

make report

This will:

1. Fetch the CO₂ CSV into data/
2. Run CO2_Analysis.R
3. Render CO2_Analysis.Rmd → CO2_report.html

Via Docker

docker-compose up --build

This runs the entire pipeline in a reproducible container.

Script Breakdown

1. Setup

   • Defines package list, auto-installs, and loads libraries.

2. Data Fetch & Prep

   • Downloads OWID CSV, filters to years ≥1960, computes co2_pc, total_co2, gdp_pc.
   • Derives date from year.

3. Visualization Sections

   • Global trend, GDP relationship, top emitter charts, quartile analyses, cumulative sums, YOY change, total vs. per-capita.

4. Regression

   • Fits lm(co2_pc ~ gdp_pc), prints summary(), and generates an annotated plot.

Interpreting the Outputs

• Global Average: captures long-term trends in per-capita emissions.
• GDP vs CO₂: shows the positive correlation between wealth and emissions.
• Top Emitters: highlights the countries with the highest per-capita footprint.
• Quartile Plots: reveal distributional differences across income strata.
• Cumulative & YOY: expose acceleration or deceleration in emission growth.
• Regression: quantifies how much GDP per capita explains variation in emissions.

Extending & Customizing

• Adjust filters (e.g., include earlier years).
• Swap color palettes or themes.
• Add new predictors (population density, energy mix).
• Save plots by adding ggsave() calls.
• Integrate regional maps using sf and rnaturalearth.

Data Source & Citations

• Our World in Data CO₂ dataset: https://github.com/owid/co2-data
• R & Packages: R Core Team (2023). R: A language and environment for statistical computing.
• Visualization: Wickham H. et al. “ggplot2: Elegant Graphics for Data Analysis.”

License

This project is released under the MIT License. See LICENSE for details.