Skip to content

evildead23151/F1-Prediction-Models

Repository files navigation

#๐ŸŽ๏ธ F1 Race Prediction using Machine Learning

Welcome to the F1 Race Predictor repository! This project uses machine learning to predict outcomes of Formula 1 Grand Prix races based on historical data, driver/team stats, and real-time race conditions.

๐Ÿš€ The first deployed model is based on Gradient Boosting, with many more models to follow.


#๐Ÿ“‚ Repository Structure

F1_GradientBoosting_Model.ipynb โ†’ Colab notebook implementing & deploying the Gradient Boosting model.

data/ โ†’ Folder for race data (CSV, JSON, API responses).

models/ (coming soon) โ†’ Saved models, pipelines, or ONNX exports.

F1_Model_Comparison.ipynb (upcoming) โ†’ Notebook comparing model performance across various ML algorithms.


#๐Ÿ”ฎ Goals

This project aims to:

Build predictive ML models for F1 race outcomes (winner, podiums, points).

Explore various algorithms:

Gradient Boosting โœ…

Random Forest ๐ŸŒฑ

XGBoost โšก

Neural Networks ๐Ÿง 

Ensemble Blending ๐Ÿ”

Deploy top models via web interface or APIs.

Track feature importances: track type, weather, driver, team form, qualifying position.


#โœ… Current Model: Gradient Boosting

Status: โœ… Deployed

Features Used: Driver, constructor, qualifying position, previous form, etc.

Performance Metrics:

Accuracy: XX%

LogLoss: YY (To be updated with your results)


#๐Ÿงช Planned Enhancements

Add more seasons of data (2010โ€“2024)

Use real-time APIs for live predictions

Hyperparameter tuning with Optuna

Model dashboard with Streamlit or Gradio


#๐Ÿง  Tech Stack

Languages: Python

Libraries: pandas, scikit-learn, xgboost, matplotlib, seaborn

Deployment: Streamlit / Flask (optional)

Notebook Runtime: Google Colab


#๐Ÿ“ˆ Model Roadmap

Model Status Link

Gradient Boosting โœ… Done Random Forest ๐Ÿ”„ Coming Soon XGBoost ๐Ÿ”„ Coming Soon Ensemble Voting ๐Ÿ”„ Coming Soon


#โœจ How to Use

  1. Clone the repo or open .ipynb notebooks in Google Colab.

  2. Install required libraries (if needed):

!pip install pandas scikit-learn xgboost

  1. Run cells step-by-step to train and test.

  2. Use deployment code (Streamlit or Flask) to make predictions.


#๐Ÿค Contributing

If you'd like to contribute:

Fork the repo

Create a new branch

Submit a pull request


#๐Ÿ“ฌ Contact

Created with โค๏ธ by Gitesh Malik ๐Ÿ“ง Email: giteshmalik0410@gmail.com ๐Ÿ”— GitHub: github.com/evildead23151

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors