Algeria Data Lab 🇩🇿

Overview

Algeria Data Lab is a centralized repository for high-quality, cleaned, and reproducible datasets about Algeria.

This project provides:

1. Modern Administrative Maps
   Updated structures including the official 58 wilayas and the 69 administrative centers (2025).

2. Cleaned Socio-Economic Data
   Ready-to-use CSV files for population and education.

3. Reproducible Analysis Notebooks
   Notebooks for geospatial, demographic, and educational analysis.

Project Structure

Algeria-Data-Lab/
├── data/
│   ├── demographics/       # Population estimates & density data
│   ├── education/          # Cleaned education statistics
│   ├── geo/                # GeoJSON & Shapefiles
│   └── population/         # Cleaned population time-series
├── notebooks/
│   ├── 01_legacy_density_analysis_2020.ipynb
│   ├── 02_modern_density_map_2025.ipynb
│   ├── 03_population_analysis.ipynb
│   └── 04_education_analysis.ipynb
├── outputs/
│   ├── education/          # Plots & cleaned datasets
│   ├── geo/                # Generated GeoJSONs
│   ├── map2020/            # Legacy density maps
│   ├── map2025/            # Interactive density map
│   └── population/         # Plots & cleaned datasets
├── scripts/
├── kaggle/
├── LICENSE
├── README.md
└── requirements.txt

Data Sources & Attribution

1. WorldPop 2020 Population Density (Algeria)

• Source: WorldPop (University of Southampton)
• Dataset: Algeria 2020 Unconstrained 1km Population Density
• URL: https://hub.worldpop.org/geodata/summary?id=72321
• License: CC-BY-4.0
• Note: Raster was converted to XYZ and aggregated by wilaya.

2. Administrative Boundaries

• Source: GADM / adapted community sources
• Usage: 48 & 58 wilaya boundaries

3. Education & Demographic Data

• Source: Office National des Statistiques (ONS)
• Period: Various years

4. Population (data/population/)

• Population Statistics:
  Cleaned time-series data (1960-2022) covering various population indicators.

---

Visualizations (outputs/)

The project includes multiple outputs, organized by category:

• outputs/map2025.html: Interactive 2025 Administrative Density Map (Log-Scale).
• outputs/map2020/: Static maps of 2020 population density.
• outputs/population/: Time-series plots of population indicators.
• outputs/education/: Time-series plots of education indicators.

---

How to Run the Project

1. Create a virtual environment

python -m venv venv
source venv/bin/activate  # Linux/Mac
venv\Scripts\activate     # Windows

### 2. Install required packages
pip install -r requirements.txt

### 3. Run the notebook 
jupyter notebook notebooks/01_population_density_by_wilaya.ipynb

### 4. Outputs
data/

Maps and visualizations appear in:
outputs/

## Detailed Methodology
All steps are documented directly in the notebook.


## Published Datasets

This project also publishes processed datasets on Kaggle:
https://www.kaggle.com/faresls