patrick-paul/ssd

Swahili Spam Detection # Swahili Spam Detection A Flask-based web application for detecting spam messages in Swahili communications using machine learning. Maintains clean communication channels with real-time analysis and user feedback capabilities. ## Features - Real-time Swahili message spam detection - User authentication system - Feedback submission and storage - Message history tracking - Machine learning model integration - Responsive web interface ## Technical Stack - **Backend**: Python/Flask - **Frontend**: HTML5, CSS3, JavaScript - **Machine Learning**: scikit-learn (Pickle model) - **Data Storage**: JSON (users & feedback) - **Styling**: Custom CSS with Flexbox layout - **Deployment**: WSGI compatible ## Project Structure ```bash ├── ssd/ │ ├── db/ # JSON databases │ │ ├── feedback.json │ │ └── users.json │ ├── logs/ # Application logs │ ├── model/ # ML models │ │ ├── newlyTrainedModel_27_jan_25/ │ │ └── swahiliSpamDetectionModel.pkl │ ├── static/ # Static assets │ │ ├── assets/ # Images │ │ ├── js/ # JavaScript modules │ │ ├── styles/ # CSS files │ │ └── sweetalert/ # Alert library │ ├── templates/ # Flask templates │ │ ├── 404.html │ │ ├── index.html │ │ └── login.html │ ├── app.py # Main application │ ├── wsgi.py # WSGI entry point │ └── requirements.txt # Dependencies ``` ## Getting Started ### Prerequisites - Python 3.8+ - pip package manager - Modern web browser ### Installation 1. Clone the repository ```bash git clone github.com cd ssd ``` 2. Create 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 ``` ### Configure Environment 1. Create `.env` file in project root: ```env SECRET_KEY=your-secure-key-here ``` 2. Gen …