def make():
fr = IntermediateFilePersistence('transformed/2019GeneratedMatchups.csv')
print("Generating test matchups...")
df_test = make_dataset.load_test_data()
df_a = df_test
df_b = df_test.drop('Season', axis=1)
df = df_a.assign(key=1).merge(df_b.assign(key=1), on='key').drop('key', 1)
df = df[df['TeamID_x'] != df['TeamID_y']]
df['GameID'] = feature_utils.create_game_key(df['Season'], df['TeamID_x'],
df['TeamID_y'])
df['TeamA_ID'] = feature_utils.create_key_from_season_team(
df['Season'], df['TeamID_x'])
df['TeamB_ID'] = feature_utils.create_key_from_season_team(
df['Season'], df['TeamID_y'])
df.drop(labels=['TeamID_x', 'TeamID_y'], inplace=True, axis=1)
print("Writing test values to disk...")
fr.write_to_csv(df)
return df
def load_seed_data():
df = pd.read_csv(tourney_seeds_csv)
df['TeamSeasonId'] = feature_utils.create_key_from_season_team(
df['Season'], df['TeamID'])
df = df.drop('TeamID', axis=1)
fr = IntermediateFilePersistence('transformed/SeedData.csv')
fr.write_to_csv(df)
return df
def load_advanced_team_data(start=START_YEAR, end=END_YEAR):
bball_ref_dir = base_dir + 'external/bball_reference/advanced/'
df_regular_season_aggregated_advanced = pd.DataFrame()
for year in range(start, end + 1):
advanced_csv = bball_ref_dir + str(year) + 'SchoolAdvanced.csv'
df_advanced = pd.read_csv(advanced_csv, header=1)
df_advanced['Year'] = year
df_regular_season_aggregated_advanced = df_regular_season_aggregated_advanced.append(
df_advanced)
df = helper.parse_advanced(df_regular_season_aggregated_advanced)
df = df.dropna(0)
fr = IntermediateFilePersistence('transformed/SeasonRatings.csv')
fr.write_to_csv(df)
return df
def load_season_team_data(start=START_YEAR, end=END_YEAR):
bball_ref_dir = base_dir + '/external/bball_reference/'
df_regular_season_aggregated = pd.DataFrame()
for year in range(start, end + 1):
regular_season_csv = bball_ref_dir + str(year) + '_season.csv'
df_regular_season = pd.read_csv(regular_season_csv, header=1)
df_regular_season['Year'] = year
df_regular_season_aggregated = df_regular_season_aggregated.append(
df_regular_season)
df = helper.parse_single_season_team_data(df_regular_season_aggregated)
fr = IntermediateFilePersistence('transformed/SeasonRawStats.csv')
fr.write_to_csv(df)
return df_regular_season_aggregated
def persist(df):
fr = IntermediateFilePersistence('NormalizedFeatureData.csv')
fr.write_to_csv(df)
def persist(df):
fr = IntermediateFilePersistence('CanonicalFeatureData.csv')
fr.write_to_csv(df)
def persist(df):
fp = IntermediateFilePersistence('TeamData.csv')
fp.write_to_csv(df)