Skip to content

An attempt to put value on passes through the probability of a goal being scored afterwards

Notifications You must be signed in to change notification settings

delara38/pass_value

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

pass_value

Attempting to find the value of passes depending on whether or not they will end up being a goal for/against within a minute using classification models. performs training and predicting on games from the 2018 world cup provided by statsbomb.com and implements a leave one out strategy to avoid predicting on training data.

main.py is all the actual python code needed in one file player_stats.csv is the result of main.py for every player after applying the pass value model.

dependencies

  • numpy

  • pandas

  • sklearn

  • seaborne

  • requests

  • math

About

An attempt to put value on passes through the probability of a goal being scored afterwards

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published