Beyond pitch control: valuing player actions and passing options.

Поделиться
HTML-код
  • Опубликовано: 18 янв 2025

Комментарии • 8

  • @aidanrandall8951
    @aidanrandall8951 Год назад

    I keep receiving the error - ValueError: axis must be fewer than the number of dimensions (1)-- When I run -- tracking_home,tracking_away,events = mio.to_single_playing_direction(tracking_home,tracking_away,events) -- I'm not sure what this means or how to fix it.

  • @ashayshah7
    @ashayshah7 4 года назад +1

    Is it possible to share how you built the EPV model (the transition matrix basically)? I can only see the final product EPV_grid.csv on the github.

    • @Gedls
      @Gedls 4 года назад +3

      I didn't share the code for that as there isn't public data to run it on. I may well release it at some point, though. The methodology was very similar to that described here nessis.org/nessis11/rudd.pdf (although I broke down the pitch into more zones).

  • @Albyedw88
    @Albyedw88 4 года назад

    If pitch control is the probability of keeping the ball when passing to a certain location, I don't understand how to interpret the pitch control at the current location? Is it the probability of keeping the ball if you pass it to someone in the same 'grid' as you?

    • @Albyedw88
      @Albyedw88 4 года назад

      i.e. is it essentially the probability of not being tackled if you have the ball in a certain location?

    • @Gedls
      @Gedls 4 года назад +2

      @@Albyedw88 You can interpret it in that way. It's essentially the probability that you retain control of the ball if you were to pass it to yourself.

  • @alsonraj
    @alsonraj 4 года назад

    Which app it is

  • @ahmedsomir
    @ahmedsomir 3 года назад

    where are the previous videos?