def calc_features(regular_season_data, season, team1, team2, tourney_seeds=None, wp_data=None):
relevant_data = get_relevant_data(regular_season_data, season=season, team1=team1, team2=team2)
columns_with_winning_team_data = np.concatenate((np.array([3]), np.arange(8, 21)))
columns_with_losing_team_data = np.concatenate((np.array([5]), np.arange(21, 34)))
effective_team1_stats = []
effective_team2_stats = []
team1_wins = 0
team1_loses = 0
team2_wins = 0
team2_loses = 0
for record in relevant_data:
winning_stats = record[columns_with_winning_team_data]
losing_stats = record[columns_with_losing_team_data]
if record[2] == team1: # team1 was the winner
team1_wins += 1.0
effective_team1_stats.append(winning_stats)
effective_team2_stats.append(losing_stats)
elif record[4] == team1: # team1 was the loser
team1_loses += 1.0
effective_team1_stats.append(losing_stats)
effective_team2_stats.append(winning_stats)
elif record[2] == team2: # team2 was the winner
team2_wins += 1.0
effective_team2_stats.append(winning_stats)
effective_team1_stats.append(losing_stats)
elif record[4] == team2: # team1 was the loser
team2_loses += 1.0
effective_team2_stats.append(losing_stats)
effective_team1_stats.append(winning_stats)
effective_team1_stats = np.array(effective_team1_stats).astype(float)
effective_team2_stats = np.array(effective_team2_stats).astype(float)
# features are the average over the difference of effective stats
features = np.average(effective_team1_stats, axis=0) - np.average(effective_team2_stats, axis=0)
#add probability of team1 outscoring team2, assuming gaussian stats
# scores are in column 0 of effective stats
mean = np.mean(effective_team1_stats[:, 0]) - np.mean(effective_team2_stats[:, 0])
covariance_matrix = np.cov(effective_team1_stats[:, 0], effective_team2_stats[:, 0])
variance = covariance_matrix[0, 0] + covariance_matrix[1, 1] - 2.0*covariance_matrix[1, 0]
# probability that team 1 outscores team 2
features = np.concatenate((features, np.array([0.5*(sps.erfc(-mean/np.sqrt(2.0*variance)))])))
# add team winning percentages to the feature list
# should change this so that home win and away wins are weighted differently
features = np.concatenate(
(
features,
np.array([team1_wins/(team1_loses+team1_wins),
team2_wins/(team2_loses+team2_wins)])
)
)
# add team seeds to feature list
if tourney_seeds is not None:
keep_seeds = np.where(tourney_seeds[:, 0] == season)[0]
tourney_seeds = tourney_seeds[keep_seeds]
# get team1's seed, if it exists
seed1 = tourney_seeds[np.where(tourney_seeds[:, 2] == team1)[0], 1]
# get team2's seed, if it exists
seed2 = tourney_seeds[np.where(tourney_seeds[:, 2] == team2)[0], 1]
# if unseeded, set seed to C17 (C will is a placeholder for conference and will be taken out shortly)
seed1 = (seed1[0] if len(seed1) == 1 else 'C17')
seed2 = (seed2[0] if len(seed2) == 1 else 'C17')
# take out conference and convert to int
seed1 = int(seed1[1:3])
seed2 = int(seed2[1:3])
features = np.concatenate(
(
features,
np.array([seed1, seed2])
)
)
return features
def calc_new_features(regular_season_data, season, team1, team2, tuning_params):
relevant_data = get_relevant_data(regular_season_data, season=season, team1=team1, team2=team2)
model_params = model_params_from_game_data(relevant_data)
columns_with_winning_team_data = np.arange(0, 5)
columns_with_losing_team_data = np.arange(5, 10)
effective_team1_stats = []
effective_team2_stats = []
team1_wins = 0
team1_loses = 0
team2_wins = 0
team2_loses = 0
team1_erpi = RelativePowerIndexLookupTable.lookup(season, team1, 'erpi')
team2_erpi = RelativePowerIndexLookupTable.lookup(season, team2, 'erpi')
effective_team1_erpi = []
effective_team2_erpi = []
for i, record in enumerate(relevant_data):
winning_team_erpi = RelativePowerIndexLookupTable.lookup(season, record[2], 'erpi')
losing_team_erpi = RelativePowerIndexLookupTable.lookup(season, record[4], 'erpi')
winning_stats = model_params[i, columns_with_winning_team_data]
losing_stats = model_params[i, columns_with_losing_team_data]
if record[2] == team1: # team1 was the winner
team1_wins += 1.0
effective_team1_stats.append(winning_stats)
effective_team2_stats.append(losing_stats)
effective_team1_erpi.append(winning_team_erpi)
effective_team2_erpi.append(losing_team_erpi)
elif record[4] == team1: # team1 was the loser
team1_loses += 1.0
effective_team1_stats.append(losing_stats)
effective_team2_stats.append(winning_stats)
effective_team1_erpi.append(losing_team_erpi)
effective_team2_erpi.append(winning_team_erpi)
elif record[2] == team2: # team2 was the winner
team2_wins += 1.0
effective_team2_stats.append(winning_stats)
effective_team1_stats.append(losing_stats)
effective_team2_erpi.append(winning_team_erpi)
effective_team1_erpi.append(losing_team_erpi)
elif record[4] == team2: # team2 was the loser
team2_loses += 1.0
effective_team2_stats.append(losing_stats)
effective_team1_stats.append(winning_stats)
effective_team2_erpi.append(losing_team_erpi)
effective_team1_erpi.append(winning_team_erpi)
effective_team1_rpi = np.array(effective_team1_erpi)
effective_team2_rpi = np.array(effective_team2_erpi)
weights = np.exp(-0.5*(
(effective_team1_rpi - team1_erpi)**2
+ (effective_team2_rpi - team2_erpi)**2
)/tuning_params['std']**2)
weights /= np.sum(weights)
effective_team1_stats = np.array(effective_team1_stats)
effective_team2_stats = np.array(effective_team2_stats)
# model_params = np.concatenate((np.average(effective_team1_stats, axis=0),
# np.average(effective_team2_stats, axis=0)))
model_params = np.concatenate(
(np.sum(weights[:, np.newaxis]*effective_team1_stats, axis=0),
np.sum(weights[:, np.newaxis]*effective_team2_stats, axis=0)))
possessions = int(0.5*(model_params[0] + model_params[5]))
ot_possessions = int(0.5*(model_params[0] + model_params[5])/8.0)
team1_dist = scoring_distribution(model_params[1:5], possessions)
team1_ot_dist = scoring_distribution(model_params[1:5], ot_possessions)
team2_dist = scoring_distribution(model_params[6:10], possessions)
team2_ot_dist = scoring_distribution(model_params[6:10], ot_possessions)
feature = np.sum(np.cumsum(team2_dist)[:-1]*team1_dist[1:]) \
+ np.sum(team2_dist*team1_dist)/(1.0 - np.sum(team2_ot_dist*team1_ot_dist))*\
np.sum(np.cumsum(team2_ot_dist)[:-1]*team1_ot_dist[1:])
feature_erpi_ratio = team1_erpi/team2_erpi
mean_score1 = np.sum(np.arange(len(team1_dist))*team1_dist)
mean_score2 = np.sum(np.arange(len(team2_dist))*team2_dist)
return [feature, feature_erpi_ratio, mean_score1, mean_score2]
