medilin-njoki/unesco-africa-study

# Global Education Statistics: Focus on Africa **Data Engineering & Visualization Project** ## Description This project provides a comprehensive analysis of global education statistics, with a deep focus on the African continent. It utilizes international datasets—primarily from UNESCO Institute for Statistics—encompassing over 1.2 million data points from more than 250 countries, covering around 30 years of educational indicators. ## Technical Implementation **Data Sources:** - UNESCO Institute for Statistics (UIS) SDG 4 dataset (February 2025 release) - Over 1.2 million data points covering 250+ countries - 30+ years of educational indicators (1970-2024) - Additional country-continent mapping data **Technology Stack:** - **Python**: Data processing and analysis - **Pandas**: Data manipulation and cleaning - **Matplotlib/Seaborn**: Statistical visualizations - **DuckDB**: High-performance data querying - **Colorcet**: Advanced color palettes for visualizations - **Tableau**: Interactive dashboard creation - **Jupyter Notebook**: Analysis workflow documentation **Key Data Processing:** - Filtered 2,647 education indicators to focus on 13 key metrics - Extracted and categorized demographic dimensions (age, gender, location, wealth quintiles) - Regional classification of African countries (North, West, East, Central, South) - Time series analysis spanning 2000-2023 - Gender Parity Index calculations and trend analysis **Project Structure:** ``` final_project/ ├── source/ # Raw UNESCO data files ├── education_DE.ipynb # Main analysis notebook ├── AfricaFinal.twb # Tableau workbook ├── requirements.txt # Python dependencies └── README.md # Project documentation ``` ## Content Breakdown - **Data Overview:** Introduction to sources, dataset size, geographic, and temporal coverage. - **Data Wrangling:** Steps taken for cleaning, merging, and validating the data to focus on relevant education indicators and …