slnnhn/wheels-clinics

K-means clustering and facility optimization tool for planning mobile health clinic routes in Malawi, using population data and PuLP linear programming. # Wheels Clinics - Malawi Population Clustering This repository contains scripts for analyzing and visualizing population distribution in Malawi using K-means clustering algorithms. The tools help identify optimal locations for mobile health clinics by clustering population data. ## 📋 Table of Contents - Overview - Prerequisites - Installation - Repository Structure - Quick Start - Available Scripts - Data Files - Outputs - Troubleshooting ## 🎯 Overview This project provides tools to: - Cluster population data for different demographic groups in Malawi - Visualize population distribution on interactive maps - Generate optimized cluster centers for service delivery planning - Create heat maps and density visualizations - Display Traditional Authorities (administrative) boundaries ## 🔧 Prerequisites - Python 3.8 or higher - Git with Git LFS (Large File Storage) support - Web browser (for viewing interactive maps) ## 📦 Installation ### 1. Clone the Repository ```bash git clone github.com cd wheels-clinics ``` ### 2. Set Up Git LFS The population data files are stored using Git LFS. Install and set up Git LFS: ```bash # Install Git LFS (if not already installed) # On Ubuntu/Debian: sudo apt-get install git-lfs # On macOS: brew install git-lfs # On Windows: # Download from git-lfs.github.com # Initialize Git LFS git lfs install # Pull the large data files git lfs pull ``` ### 3. Install Python Dependencies ```bash pip install -r requirements.txt ``` Required packages: - `pandas` - Data manipulation - `numpy` - Numerical computing - `scikit-learn` - Machine learning (K-means clustering) - `geopandas` - Geographic data processing - `matplotlib` - Static visualizations - `folium` - Interactive maps - `pulp` - Optimization solver - `dash` - Interactive dashboards - `plotly` - Interactive visualizations ## 🚀 One-Command Pipeline **NEW**: Run the entire optimization pipeline with a single command! ```bash # Make …