Disclaimer: I'm not the author of the paper, just the code in this repository.
Python implementation of Finding repeatable progressive pass clusters and application in international football using Statsbomb Open Data. It's all in a Jupyter notebook because its not for production.
poetry install
cp env .envI've exported requirements.txt if you prefer using pip, but no guarantees are made.
In .env set OPEN_DATA_PATH to where you have Statsbomb Open Data cloned.