Kloppy implemenents a standardized data model that can load event and tracking data from most common data providers, supporting both public and proprietary data. Moreover, it does not matter where and how the data is stored: kloppy can also handle compressed data, and load data from the cloud.
Video analysts spend a lot of time searching for bespoke moments. Often times, these moments can be described by a pattern: pass, pass, shot, etc. Kloppy provides a powerful search mechanism based on regular expressions to find these bespoke moments more quickly and easily.
Different data providers use different coordinate systems, making it difficult to combine datasets. Additionally, it can be convenient to change the orientation of the data or normalize the pitch dimensions for a particular analysis. Kloppy can do these data transformations for you.
Once you have all the data in the right shape, export it as a Polars or Pandas dataframe to perform efficient data analysis, or as SportsCode XML to support your video analysis workflow. Kloppy's data model is also compatible with other popular soccer analytics libraries.
Kloppy is powered by PySport, a non-profit organization (RSIN: 866294211) with the mission to unite practitioners, researchers, learners, and enthusiasts to share best practices and exchange ideas to advance the open-source sports analytics community.
Consider donating to help support PySport's mission and the ongoing development of kloppy. Thanks to our awesome sponsors, this project is actively maintained and kept in good shape.