🎓 Student Performance Predictor

An end-to-end machine learning project that predicts student math scores based on various demographic and academic factors. This project implements a complete ML pipeline with a modern web interface for real-time predictions.

🌟 Features

• AI-Powered Predictions: Uses advanced machine learning algorithms (XGBoost, Random Forest, etc.)
• High Accuracy: Trained on comprehensive student data with multiple evaluation metrics
• Easy-to-Use Interface: Modern, responsive web application with intuitive design
• Complete ML Pipeline: Data ingestion, transformation, and model training components
• Advanced Hyperparameter Tuning: GridSearchCV and RandomizedSearchCV for optimal performance

🚀 Live Demo

Access the application at: http://127.0.0.1:5000

• Home Page: http://127.0.0.1:5000/ - Landing page with project overview
• Prediction Page: http://127.0.0.1:5000/predictdata - Interactive prediction form

0721.1.mp4

📁 Project Structure

mlproject/
├── application.py              # Flask web application
├── train_model.py             # Complete training pipeline
├── requirements.txt           # Project dependencies
├── setup.py                  # Package configuration
├── artifacts/                # Model artifacts
│   ├── model.pkl            # Trained ML model
│   ├── preprocessor.pkl     # Data preprocessing pipeline
│   ├── train.csv           # Training dataset
│   └── test.csv            # Test dataset
├── src/                     # Source code
│   ├── components/         # ML pipeline components
│   │   ├── data_ingestion.py
│   │   ├── data_transformation.py
│   │   └── model_trainer.py
│   ├── pipeline/           # Prediction pipeline
│   │   └── predict_pipeline.py
│   ├── exception.py        # Custom exception handling
│   ├── logger.py          # Logging configuration
│   └── utils.py           # Utility functions
├── templates/              # HTML templates
│   ├── index.html         # Home page
│   └── home.html          # Prediction form
└── logs/                  # Application logs

🛠️ Installation & Setup

Prerequisites

• Python 3.7+
• pip package manager

1. Clone the Repository

git clone https://github.com/Dulakshi-2002/mlproject.git
cd mlproject

2. Create Virtual Environment

# Create virtual environment
python -m venv venv

# Activate virtual environment
# On Windows:
venv\Scripts\activate
# On macOS/Linux:
source venv/bin/activate

3. Install Dependencies

pip install -r requirements.txt

4. Train the Model (if needed)

python train_model.py

5. Run the Application

python app.py

6. Access the Application

Open your web browser and navigate to:

• Home Page: http://127.0.0.1:5000/
• Prediction Interface: http://127.0.0.1:5000/predictdata

📊 Model Information

Algorithms Used

• Random Forest
• Decision Tree
• Gradient Boosting
• Linear Regression
• XGBoost
• CatBoost
• AdaBoost

Input Features

• Gender: Student's gender
• Race/Ethnicity: Student's ethnic background
• Parental Level of Education: Educational background of parents
• Lunch: Type of lunch (standard/free or reduced)
• Test Preparation Course: Completion status of test prep course
• Reading Score: Score in reading assessment
• Writing Score: Score in writing assessment

Output

• Math Score Prediction: Predicted mathematics score (0-100)

🎯 How to Use

Web Interface

1. Navigate to Home Page: Visit http://127.0.0.1:5000/
2. Click "Start Prediction": Access the prediction form
3. Fill Student Information:
   • Select demographic information
   • Enter reading and writing scores
4. Get Prediction: Click submit to receive math score prediction

API Usage

The application also supports direct POST requests to /predictdata with form data.

🧪 Model Performance

The model uses advanced hyperparameter tuning with:

• GridSearchCV for exhaustive parameter search
• RandomizedSearchCV for efficient optimization
• Cross-validation for robust performance evaluation
• R² Score as primary evaluation metric

🔧 Configuration

Environment Variables

• FLASK_ENV: Set to development for debug mode
• FLASK_APP: Set to application.py

Model Artifacts

• Models are saved in artifacts/ directory
• Preprocessor pipeline includes feature scaling and encoding
• Automatic model selection based on performance metrics

🚨 Troubleshooting

Common Issues

1. Module Import Errors

   # Ensure you're in the project root directory
   cd mlproject
   # Activate virtual environment
   venv\Scripts\activate

2. Missing Model Files

   # Retrain the model
   python train_model.py

3. Port Already in Use

   # The app runs on port 5000 by default
   # Check if another service is using the port

📈 Future Enhancements

• Add more ML algorithms
• Implement model versioning
• Add batch prediction capability
• Create REST API endpoints
• Add model explanation features
• Implement user authentication
• Add prediction confidence intervals

🤝 Contributing

1. Fork the repository
2. Create a feature branch (git checkout -b feature/AmazingFeature)
3. Commit your changes (git commit -m 'Add some AmazingFeature')
4. Push to the branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

📝 License

This project is licensed under the MIT License - see the LICENSE file for details.

👤 Author

Dulakshi-2002

• GitHub: @Dulakshi-2002

🙏 Acknowledgments

• Dataset source: Student Performance Dataset
• Libraries: scikit-learn, Flask, Bootstrap, XGBoost, CatBoost
• Icons: FontAwesome

---

⭐ Star this repository if you found it helpful!