This is a k-means clustering project that aims to cluster batsmen and bowlers from 9 seasons of IPL performance data by creating new features that define the performance metrics: strike rate and economy rate.
The datasets are present in the repository and can also be downloaded from here. While there are five datasets present on the linked web page, only two of which are relevant for this project, and they are included in this repository.
The first of the two files is named 'Ball_by_Ball.csv' which contains details about the match event for every ball thrown. The second file is named 'Player.csv' and it contains a numbered code and corresponding name of the cricketer.
The project was done in Jupyter Notebook, Python 3.