Blackout-26/Bulawayo-Parking-Predictor

A machine learning app to predict parking availability in Bulawayo, Zimbabwe. # Smart Parking Space Availability Predictor (Bulawayo) ## Project Overview This project is a machine learning-powered application designed to help the City of Bulawayo tackle urban congestion by predicting parking availability. It utilizes historical data, event schedules (e.g., ZITF Trade Fair, Barbourfields matches), and real-time inputs to forecast open parking spots. ## Features * **Real-time Availability Dashboard:** A Streamlit interface for drivers and city planners to view current parking status. * **Event Impact Analysis:** Specifically accounts for major events like Football matches and Trade Fairs using distance-decay algorithms to adjust occupancy predictions. * **Geospatial Visualization:** Interactive map of Bulawayo parking venues including City Hall, Bulawayo Centre, and ZITF. ## Project Structure * `app.py`: The main dashboard application built with Streamlit. * `generate_data.py`: A script to generate realistic synthetic training data based on Bulawayo's geography and event patterns. * `train_model.py`: Trains a Random Forest Regressor to predict occupancy rates and saves the model. * `requirements.txt`: List of Python dependencies required to run the project. ## 🚀 Quick Start Workflow **Important:** To keep this repository lightweight, the large dataset and trained model files are **not** included. You must follow the steps below in order to generate them locally before running the app. ### Step 1: Installation Clone the repository and install the required dependencies. ```bash git clone github.com cd Bulawayo-Parking-Predictor pip install -r requirements.txt