unravelsports

The unravelsports package aims to aid researchers, analysts and enthusiasts by providing intermediary steps in the complex process of turning raw sports data in

What is unravelsports?

The unravelsports package aims to aid researchers, analysts and enthusiasts by providing intermediary steps in the complex process of turning raw sports data into meaningful information and actionable insights.

Overview of unravelsports

What it is

The unravelsports package aims to aid researchers, analysts and enthusiasts by providing intermediary steps in the complex process of converting raw sports data into meaningful information and actionable insights. It currently supports soccer and American football tracking data.

Key features

  • Polars DataFrames: Convert tracking data into Polars DataFrames for rapid data conversion and processing. For soccer, it relies on Kloppy and supports Sportec, SkillCorner, PFF / GradientSports, Metrica, StatsPerform, Tracab (CyronHego), SecondSpectrum, HawkEye and Signality tracking data. For American football, it uses BigDataBowl data directly.
  • Graph Neural Networks: Convert Polars DataFrames into graphs to train graph neural networks. Supports randomization and splitting of data into train, test, and validation sets along matches, sequences, or possessions. Works with PyTorch Geometric or Spektral.
  • Pressing Intensity: Compute Pressing Intensity for a whole game or segment of soccer tracking data.
  • Formation and Position Identification (EFPI): Compute Elastic Formation and Position Identification for individual frames, possessions, periods, or specific time intervals for soccer.

Use cases

  • Sports analytics research and analysis - Deriving actionable insights from raw tracking data - Training graph neural network models for sports applications - Tactical analysis such as pressing intensity and formation identification

Getting started

The easiest way to get started is: bash pip install unravelsports For detailed tutorials, see the Quick Start Jupyter Notebook and other notebooks referenced in the repository README.

License and pricing

This project is licensed under the Mozilla Public License Version 2.0 (MPL-2.0). It is open source.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/unravelsportsunravelsports.svg)](https://yunodb.com/tools/unravelsportsunravelsports?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/unravelsportsunravelsports?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/unravelsportsunravelsports.svg" alt="Featured on YunoDB" height="20"></a>