A machine learning project exploring race prediction models using Formula 1 historical data.
Status: Data science learning project
Tech Stack: Python, Jupyter Notebooks, Scikit-learn, Pandas, Matplotlib
This project explores:
- Analyzing historical F1 race data
- Building predictive models for race outcomes
- Feature engineering from race statistics
- Model evaluation and performance analysis
├── 01_download_data... # Data collection scripts
├── 02_build_features... # Feature engineering notebooks
├── 03_train_and_anal... # Model training and analysis
├── R/ # R analysis files
├── results/ # Output and visualizations
├── results_extra/ # Additional analysis
└── holdout_extra/ # Holdout test data
- Language: Python
- Data Processing: Pandas
- Machine Learning: Scikit-learn
- Visualization: Matplotlib
- Notebooks: Jupyter
- Clone the repository
- Install Python dependencies:
pip install pandas scikit-learn matplotlib jupyter - Open Jupyter and explore the notebooks in order:
01_download_data...- Load and explore F1 data02_build_features...- Feature engineering03_train_and_anal...- Model training
✅ Data collection and preprocessing
✅ Feature engineering from race statistics
✅ Model training with multiple algorithms
✅ Performance evaluation and comparison
✅ Visualization of results
- Exploratory data analysis (EDA)
- Feature selection and engineering
- Model selection and hyperparameter tuning
- Evaluation metrics for classification/regression
- Jupyter-based data science workflow
- Deploy predictive model as API
- Real-time race prediction updates
- Incorporate live race data
- Advanced feature engineering
- Ensemble methods
Status: Actively exploring ML concepts
Last Updated: January 2026