UnravelSports/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.
Provides specialized modules for converting multi-source tracking data (Kloppy-compatible soccer formats, NFL BigDataBowl) into Polars DataFrames with computed features like velocity and acceleration. Enables graph neural network training via PyTorch Geometric or Spektral with built-in data splitting strategies (by match/possession/sequence) to prevent leakage, plus domain-specific analytics including pressing intensity metrics and elastic formation identification via research-backed algorithms.
233 stars and 111 monthly downloads. Available on PyPI.
Stars
233
Forks
32
Language
Python
License
MPL-2.0
Category
Last pushed
Jan 16, 2026
Monthly downloads
111
Commits (30d)
0
Dependencies
3
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/UnravelSports/unravelsports"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
oracle-devrel/leagueoflegends-optimizer
League of Legends Optimizer - Learn Artificial Intelligence with Gaming
Oleffa/LeagueAI
LeagueAI software framework for League of Legends that provides information about the state of...
andreiapostoae/dota2-predictor
Tool that predicts the outcome of a Dota 2 game using Machine Learning
CorvusCodex/RouletteAi
RouletteAi is a roulette artificial intelligence that uses machine learning to predict the next number.
masterhood13/dota2predictor
Dota 2 Match Result Predictor Telegram Bot Overview This project is a Telegram bot that...