kibali-cell/Swahili-SMS-Filter

Filters incoming Swahili SMS messages for spam using a machine learning model. # SMS Gateway Spam Filter A Flask-based application that filters and processes incoming SMS messages using machine learning to detect spam. ## Features - Real-time SMS spam detection using a pre-trained machine learning model - Web dashboard to view message history and spam detection results - Integration with Africa's Talking SMS API - Environment-based configuration - Detailed logging for troubleshooting ## Setup and Installation ### Prerequisites - Python 3.7+ - pip (Python package manager) - Africa's Talking account with API credentials ### Installation 1. Clone the repository ```bash git clone github.com cd sms-gateway-filter ``` 2. Create and activate a virtual environment ```bash python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate ``` 3. Install dependencies ```bash pip install -r requirements.txt ``` 4. Create a `.env` file in the project root with your Africa's Talking credentials: ``` AT_USERNAME=your_africastalking_username AT_API_KEY=your_africastalking_api_key ``` 5. Ensure you have the required ML model files: - `spam_model.pkl` - `vectorizer.pkl` ## Usage ### Starting the Server Run the application: ```bash python app.py ``` The server will start on 127.0.0.1 by default. ### Available Endpoints - **GET /** - Web dashboard for viewing filtered messages - **POST /incoming-messages** - Endpoint for receiving SMS messages - **GET /test** - Simple endpoint to verify server status ### Sending Test Messages You can test the API by sending a POST request to the `/incoming-messages` endpoint: ```bash curl -X POST localhost \ -H "Content-Type: application/json" \ -d '{"from": "+1234567890", "text": "Hello, this is a test message", "to": "+0987654321"}' ``` ## Message Processing When a message is received: 1. The system extracts the sender, message content, and recipient 2. The machine learning model analyzes the message to …