Each year in the NBA, some players have a "breakout season", where they improve the level of their game significantly, which is usually expressed in their statistics. Can breakout seasons be predicted before the season starts? This is the aim of this project.
This project started from an enthusiastic, yet frustrated fantasy-basketball player, who also happens to be a data scientist.
In the project I use machine learning models in order to predict breakout seasons. The data comes from the python NBA API.
Have fun!
Here, you can find the notebook containing the code. In addition, there are 2 csv files:
- nba_playes_data.csv - The data used for this project after some parsing.
- clean_ready_nba_players_data.csv - The data after all the cleaning and manipulations. Ready for the modeling part.
If you have any suggestions or ideas on how to improve the performance, or if you want to try other models to solve this problem, please go ahead. I would be happy to see it.
You may fork the repo and create a pull request. You can also simply open an issue with the tag "enhancement". Don't forget to give the project a star if you enjoyed reading it! Thanks again!
- Fork the Project
- Create your Feature Branch (
git checkout -b feature/AmazingFeature) - Commit your Changes (
git commit -m 'Add some AmazingFeature') - Push to the Branch (
git push origin feature/AmazingFeature) - Open a Pull Request
Roy Yanovski - [email protected]
Project Link: https://github.com/royyanovski/nba_players_breakout_project
I would like to add an honourable mention of my fantasy league mates that are pushing me to try and find new ways to beat them.