W-Nyaguthii/AnalystlLab-Africa-Week-8

# Education & Literacy in Kenya: A Regional Development Analytics Study **AnalystLab Internship - Week 8 Final Capstone Project** **Author:** Primrose Wambui An end-to-end data analytics project benchmarking Kenya's school enrollment, literacy, and education financing against six East & Southern African peer countries and global averages, using World Bank World Development Indicators (WDI) data from 1990–2024. --- ## Objective How does Kenya's education system compare to its regional peers, and where should stakeholders focus improvement efforts? This project applies the full data analytics workflow - sourcing, cleaning, analysis, visualization, and reporting - to answer that question using publicly available development data. ## Data Source - **World Bank World Development Indicators (WDI)** datatopics.worldbank.org - 13 indicators covering literacy, school enrollment (primary/secondary/tertiary), completion rates, gender parity, and government education spending - 9 countries/aggregates: Kenya, Uganda, Tanzania, Rwanda, Ethiopia, Nigeria, South Africa, Sub-Saharan Africa (regional aggregate), World - Coverage: 1990–2024 ## Tools Used - **Python** (pandas) — data cleaning, reshaping, and statistical analysis - **Power BI Desktop** — interactive dashboard with KPI cards, slicers, and cross-filtered visuals - **DAX** — custom measures to correctly surface each country's most recent reported value per indicator - **Excel** — clean data export formatted for Power BI import ## Methodology 1. **Scoping** — narrowed the ~1,400-indicator WDI bulk file down to 13 education/literacy indicators across 9 countries, rather than working with the full multi-gigabyte dataset. 2. **Cleaning** — reshaped from wide (year columns) to tidy long format, standardized types, checked for duplicates, and deliberately left missing values as null rather than imputing them. 3. **Calculated fields** — derived primary enrollment gender gap, litera …