A machine learning project that predicts the publication year of a book based on its metadata (publisher, author, genre, etc.).

This project tackles a regression problem: predicting the year a book was published using features such as publisher, author, book type, and other metadata. Five different models and an ML pipeline were trained and evaluated.

├── Group 4 code-1.py                    # Main implementation
├── Machine Learning Assignment Group 4-1.pdf   # Detailed report
├── train.zip                            # Training data
├── test.json                            # Test data
└── README.md

pip install pandas numpy scikit-learn

1. Extract train.zip for the training dataset
2. Place test.json in the project directory
3. Run the Python script:

python "Group 4 code-1.py"

The implementation includes:

• Data preprocessing and feature engineering
• Model comparison across 5 different algorithms
• ML pipeline for reproducible experiments
• MAE-based evaluation

For detailed methodology, model comparison, and analysis, refer to the PDF report.

Machine Learning Assignment – Group 4

This project is available for educational purposes.

⭐ If you find this project useful, please consider giving it a star!