Selam46/ethiopian-medical-data

# Ethiopian Medical Data Analysis Project This project collects, processes, and analyzes medical data from Ethiopian Telegram channels, performs object detection on medical images, and exposes the data through a REST API. ## Features 1. **Data Collection** - Scrapes medical data from Ethiopian Telegram channels - Stores raw data in JSON format 2. **Data Cleaning** - Processes raw JSON data - Extracts relevant information - Performs language detection (Amharic/English) - Calculates message statistics 3. **Object Detection** - Uses YOLOv5 for object detection in medical images - Processes images from Telegram messages - Stores detection results in database 4. **REST API** - Exposes processed data through FastAPI - Provides endpoints for messages and detections - Includes statistical analysis endpoints ## Setup 1. **Environment Setup** # Clone the repository git clone [repository-url] cd ethiopian_medical_data # Create and activate virtual environment python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate # Install dependencies pip install -r requirements.txt 2. **Database Configuration** # Create .env file with database credentials DB_USER=your_username DB_PASSWORD=your_password DB_HOST=localhost DB_PORT=5432 DB_NAME=medical_data 3. **YOLOv5 Setup** # Install YOLOv5 dependencies git clone github.com cd yolov5 pip install -r requirements.txt cd .. ## Usage 1. **Data Processing Pipeline** # Run the data cleaning pipeline python src/cleaning/cleaner.py # Run object detection python src/object_detection/main.py 2. **API Server** # Start the FastAPI server python src/run_api.py ## API Endpoints - `GET /`: Welcome message - `GET /messages/`: List all messages - Query parameters: - `skip`: Number of records to skip - `limit`: Number of records to return - `channel`: Filter by channel name - `language`: Filter by language - `GET /messages/{message_id}`: Get specific message - `GET /detections/`: …