Ongoing project, soon will be in my portfolio
# Zimbabwe DHS 2015: Community Sanitation & Child Diarrhea Analysis
## π Project Overview
This project analyzes the relationship between community-level sanitation coverage and child diarrhea prevalence using Zimbabwe DHS 2015 data.
### Research Question
> Does the sanitation level of a child's neighborhood affect their risk of diarrhea, independent of their own household's sanitation?
## ποΈ Repository Structure
```
zimbabwe-dhs-analysis/
βββ data/
β βββ raw/ # Original DHS files (not tracked in git)
β βββ processed/ # Cleaned intermediate files
βββ scripts/
β βββ 01_data_loading.py
β βββ 02_household_processing.py
β βββ 03_cluster_aggregation.py
β βββ 04_child_preparation.py
β βββ 05_data_merging.py
β βββ 06_analysis.py
βββ outputs/
β βββ figures/
β βββ tables/
β βββ policy_brief.md
βββ docs/
βββ .github/
β βββ copilot-instructions.md
βββ prompts/ # AI prompts for each phase
βββ requirements.txt
βββ README.md
```
## π Quick Start
1. **Clone repository**
```bash
git clone
github.com
```
2. **Install dependencies**
```bash
pip install -r requirements.txt
```
3. **Run analysis pipeline**
```bash
python scripts/01_data_loading.py
python scripts/02_household_processing.py
python scripts/03_cluster_aggregation.py
python scripts/04_child_preparation.py
python scripts/05_data_merging.py
python scripts/06_analysis.py
```
## π Key Outputs
- `cluster_metrics.csv` β Cluster-level indicators
- `spatial_maps.png` β Hotspot visualization
- `regression_results.txt` β Statistical model output
- `policy_brief.md` β Executive summary
## π Data Sources
- **Survey Data**: Zimbabwe DHS 2015
- **Geographic Data**: DHS GPS dataset (displaced for privacy)
- **Geospatial Covariates**: DHS Spatial Data Repository
## π Data Access
Raw DHS data requires registration at dhsprogram.com. Processed outputs are included in this repository.
## π License
This β¦