search

krishnakartik1 / LSTM-footballMatchWinner

This repository contains the code for a conference paper "Predicting the football match winner using LSTM model of Recurrent Neural Networks" that we wrote
57 stars 25 forks source link

Dropped seasons in "dataCleaning" #3

Closed trendgiver111 closed 3 years ago

trendgiver111 commented 4 years ago

There is something i do not quite understand. When you append last standings, you actually assign to "playing_statistics_4" and all others below "playing_statistics_3". Shouldnt it be 3 to 3, 4 to 4, etc. ?

playing_statistics_1 = get_last(playing_statistics_1, Standings, 0)

playing_statistics_2 = get_last(playing_statistics_2, Standings, "15") playing_statistics_3 = get_last(playing_statistics_3, Standings, "14") playing_statistics_4 = get_last(playing_statistics_3, Standings, "13") playing_statistics_5 = get_last(playing_statistics_3, Standings, "12") playing_statistics_6 = get_last(playing_statistics_3, Standings, "11") playing_statistics_7 = get_last(playing_statistics_3, Standings, "10") playing_statistics_8 = get_last(playing_statistics_3, Standings, "9")

Cyki89 commented 4 years ago

@trendgiver111 You are right. Of course, it is a big mistake in here. It cause that test and train set have almost identical data. This results in surprisingly good results.

krishnakartik1 commented 4 years ago

Oh no. This does look fishy, I'll look into this. Thanks for bringing it to my notice.