← All projects

2025 · Featured

Rwanda Malaria Analysis Dataset (2000–2022)

A reproducible Python pipeline building a 30-district, 23-year dataset from Malaria Atlas Project surfaces, DHS/MIS surveys and public climate data.

  • Python
  • R
  • pandas
  • Geospatial

Overview

The data foundation of the doctoral project. Combines Malaria Atlas Project raster surfaces, survey-weighted DHS and MIS indicators, and public climate data into a district-level panel covering all 30 Rwandan districts from 2000 to 2022. Everything is rebuilt from source by a reproducible pipeline under version control.

Highlights

  • 30 districts × 23 years of malaria incidence
  • Raster and vector processing in R (malariaAtlas, sf, terra) and Python
  • Survey-weighted analysis of DHS/MIS data
  • Fully reproducible, Git-tracked pipeline