Explainable ML for predicting household WASH access using 2024 NDHS Nigeria data
# Predicting Household WASH Access in Nigeria 2024
This repository contains the analysis code for:
**"Predicting household WASH access in Nigeria with explainable machine learning: Implications for NTD control"**
Submitted to PLOS Neglected Tropical Diseases
## Data
The 2024 Nigeria Demographic and Health Survey household dataset is available through the DHS Program:
dhsprogram.com
*Note: Due to DHS data use terms, raw data is not included here.*
## Methods
We compared 4 supervised ML models: Logistic Regression, Decision Tree, Random Forest, XGBoost.
Model explainability used SHAP and Feature Importance.
## How to Run
1. Install requirements: `pip install -r requirements.txt`
2. Open `NGHR8BDT_091301.ipynb` in Jupyter Notebook or JupyterLab
3. Python 3.10+ | Random seed: 42
## Author
Nneoma L. Dorbor, Department of Biology / Zoology, Federal University Lokoja