Introduction to Football (Soccer) Data Analysis with Python

Introduction to Football (Soccer) Data Analysis with Python

Maintained by Indranil Ghosh

Personal Website

Description

This website is set up to teach introductory football (soccer) data analysis to those who are interested. The user will learn how to get open access football data and run analyses on them. Simple mathematical techniques from the fields of network analysis, computational geometry and introductory statistical analyses will be introduced and implemented on football event data and tracking data. The user will also learn how to draw football pitches and generate visualizations out of the data to draw conclusions. The programming language has been chosen to be Python because it is easy to learn, open-source and user friendly.

Logo courtesy: Swagata Chakraborty

Tools/Techniques

Python
Statistics
Computational Geometry
Network Analysis
Visualization

References

Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow- Concepts, Tools, and Techniques to Build Intelligent Systems
Aurélien Géron Oct 2019
Book Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow- Concepts, Tools, and Techniques to Build Intelligent Systems by Aurélien Géron.
Friends of Tracking
Friends of Tracking Jun 2018
Friends of Tracking youtube channel maintained by Dr. David Sumpter.
FCPython blog
FCPython Dec 2017
Blog on ootball data content & tutorials with Python.
Soccermatics
Soccermatics Mar 2017
Book Soccermatics Mathematical Adventures in the Beautiful Game Pro-Edition (Bloomsbury Sigma) by Dr. Sumpter.
Youtube Channel by McKay Johns
McKay Johns Dec 2011
Youtube Channel on Soccer Visualizations by McKay Johns.
Graph Theory and Complex Networks
Maarten van Steen Apr 2010
Book Graph Theory and Complex Networks An Introduction by Dr. Maarten van Steen.

Recent Posts

Statistical Analysis to Classify the Pass Outcomes
In this post, we will learn how to use statistical learning to build models for classifying pass outcomes. Classification is the operation of labeling a set of data into different classes, for example whether a pass from a player will be a successful or an unsuccessful pass depending on a set of particular features.
Last updated on May 5, 2021 24 min read Python, Classification, Statistical Learning, scikit-learn
Convex Hulls, Delaunay Triangulations and Voronoi Diagrams
In our last tutorial, we studied how to visualize a pass network for the teams from a particular match and how to analyse the networks using knowledge from complex network analysis literature.
Last updated on May 11, 2021 90 min read Python, visualization, Computational Geometry, spatial algorithms
Pass Network Analysis
In our last tutorial we studied how to draw a pass map, a shot map and their corresponding heat maps. We used statsbomb’s open even data from the match between Real Madrid and Barcelona, which Real Madrid ended up winning 2-0.
Last updated on May 11, 2021 133 min read Python, visualization, NetworkX
Draw a football pitch
If you do not want to recreate a football pitch manually using Python (which would be rather tedious) you can simply use the mplsoccer module without any concern. To my knowledge it provides with the best functionalities to draw a football pitch.
Last updated on Apr 26, 2021 4 min read Python, visualization
Draw a pass map, a shot map and their corresponding heat maps
In this post, we will learn how to draw simple pass maps and shot maps and visualize their corresponding heat maps. We will study use the event data from the Real Madrid vs.
Last updated on Apr 27, 2021 96 min read Python, visualization
See all posts