Survive the Titanic 🚢

Welcome to the Survive the Titanic project! This project predicts the survival chances of Titanic passengers using machine learning models. It integrates data ingestion, processing, model training, and deployment into a seamless pipeline.

---

🚀 Technologies Used

---

📂 Project Structure

application.py          # Flask application for predictions
config/                 # Configuration files for database and paths
dags/                   # Airflow DAGs for data extraction and transformation
notebook/               # Jupyter notebooks for exploratory data analysis
pipeline/               # Training pipeline scripts
src/                    # Core source code for data processing, training, and logging
static/                 # Static files (CSS)
templates/              # HTML templates for the web app
artifacts/              # Generated models and raw data

---

🛠️ Features

• Data Ingestion: Extracts Titanic data from PostgreSQL and stores it in Redis.
• Data Processing: Handles missing values, feature engineering, and data balancing.
• Model Training: Trains a Random Forest model with hyperparameter tuning.
• Web Application: Flask-based app for survival prediction.
• Monitoring: Prometheus and Grafana for metrics and visualization.
• Orchestration: Apache Airflow for pipeline automation.

---

🏗️ How to Run

1. Clone the Repository:

   git clone <repository-url>
   cd survive-the-titanic

2. Install Dependencies:

   pip install -r requirements.txt

3. Run the Flask Application:

   python application.py

4. Access the Web App: Open your browser and navigate to http://localhost:5000.

5. Start Monitoring:

   • Prometheus: http://localhost:9090
   • Grafana: http://localhost:3000 (Default credentials: admin/admin)

---

📊 Example Prediction

1. Fill in the passenger details on the web form.
2. Click Predict.
3. View the survival prediction result.

---

📜 License

This project is licensed under the MIT License.