Tchalino/malaria-ml-guinea-bissau

# malaria-ml-guinea-bissau # Machine Learning Models for Malaria Incidence Prediction in Guinea-Bissau This repository contains the R scripts used for data preprocessing, machine learning modeling (Random Forest, SVM, XGBoost), and residual diagnostics as part of the PhD research on malaria incidence in Guinea-Bissau (2016–2022). ## Repository Structure - `scripts/` : Contains all R scripts for data cleaning, model training, and evaluation. - `data/` : Instructions or synthetic datasets (due to data sharing policies, clinical data from the NMCP of Guinea-Bissau are available upon reasonable request). ## Requirements The analyses were performed in **R (version 4.x)**. The required packages include: - `tidyverse` - `caret` (or `randomForest`, `e1071`, `xgboost`) - `ggplot2` ## Usage Instructions 1. Clone or download this repository to your local machine. 2. Open the main project R script. 3. Ensure your working directory points to the repository folder. 4. Run the scripts sequentially to reproduce the figures and performance metrics presented in the manuscript. ## Data Availability - **Clinical data:** Provided by the National Malaria Control Programme (NMCP) of Guinea-Bissau (available upon request). - **Environmental data:** Sourced from NASA POWER (power.larc.nasa.gov). - **Demographic data:** Sourced from the National Institute of Statistics (INE).