I am new to machine learning and am trying to conceptualize how to effectively build a database of sports data for machine learning. I currently have a list of games and outcomes as well as separate 2D dataframes of player stats for each game (player name as dataframe index, stats as column headers). What I'd like to be able to do is use the 2D tables to model outcomes but I'm not sure how to effectively do this... (The only ML projects I've done have had independent and dependent variables all on the same row)
One thought I had was to condense each 2D dataframe into a single row. But again, since the players may vary between games, I'm not sure if this would work either...
Any feedback or advice would be greatly appreciated. Thanks for reading!
