true-skill.ipynb

true-skill.py

# Fetch the data
df = pd.read_csv('http://horse-data-abcd.s3.amazonaws.com/game_results.csv')

# Create a holding DataFrame for our TrueRank
df_truerank_columns = ['game_id', 'player_id', 'position', 'mu', 'sigma', 'post_mu', 'post_sigma']
df_truerank = pd.DataFrame(columns=df_truerank_columns)

# Use a sample of 1000
#df = df.head(1000)

# Group by the game_id
games = df.groupby('game_id')

# Now iterate the games
for game_id, game in games:
    # Setup lists so we can zip them back up at the end
    trueskills = []    
    player_ids = []
    game_ids = []  
    mus = []    
    sigmas = []
    post_mus = []
    post_sigmas = []
    
    # Now iterate over each player in a game
    for index, row in game.iterrows():
        
        # Create a game_ids arary for zipping up
        game_ids.append(game_id)
    
        # Now push the player_id onto the player_ids array for zipping up
        player_ids.append(int(row['player_id']))
        
        # Get the players last game, hence tail(1)
        filter = (df_truerank['game_id'] < game_id) & (df_truerank['player_id'] == row['player_id'])                            
        df_player = df_truerank[filter].tail(1)
        
        # If there isnt a game then just use the TrueSkill defaults
        if (len(df_player) == 0):
            mu=25
            sigma=8.333
        else:
            # Otherwise get the mu and sigma from the players last game
            row = df_player.iloc[0]
            mu = row['post_mu']
            sigma = row['post_sigma']
        
        # Keep lists of pre mu and sigmas
        mus.append(mu)
        sigmas.append(sigma)
        
        # Now create a TrueSkull Rating() class and pass it into the trueskills dictionary
        trueskills.append(Rating(mu=mu, sigma=sigma))
                                    
    # Create tuples out of the trueskills array
    trueskills_tuples = [(x,) for x in trueskills]
    
    # Use the positions as ranks, they are 0 based so -1 from all of them
    ranks = [x - 1 for x in list(game['position'])]
    
    # Get the results from the TrueSkill rate method
    results = rate(trueskills_tuples, ranks=ranks)
    
    # Loop the TrueSkill results and get the new mu and sigma for each player
    for result in results:
        post_mus.append(round(result[0].mu, 2))
        post_sigmas.append(round(result[0].sigma, 2))
    
    # Change the positions back to non 0 based
    positions = [x + 1 for x in ranks]
    
    # Now zip together all our lists 
    data = list(zip(game_ids, player_ids, positions, mus, sigmas, post_mus, post_sigmas))
    
    # Create a temp DataFrame the same as df_truerank and add data to the DataFrame
    df_temp = pd.DataFrame(data, columns=df_truerank_columns)
        
    # Add df_temp to our df_truerank
    df_truerank = df_truerank.append(df_temp)