James McCool
Refactor lineup generation logic in hedging_preset.py to improve processing efficiency. Introduced an initialization counter for lineup adjustments and added checks for empty DataFrames before generating lineups. Enhanced debug messages for better visibility into the lineup concatenation process.
55b8b36
| import pandas as pd | |
| import math | |
| from global_func.small_field_preset import small_field_preset | |
| from global_func.large_field_preset import large_field_preset | |
| def hedging_preset(portfolio: pd.DataFrame, lineup_target: int, projections_file: pd.DataFrame): | |
| excluded_cols = ['salary', 'median', 'Own', 'Finish_percentile', 'Dupes', 'Stack', 'Size', 'Win%', 'Lineup Edge', 'Weighted Own', 'Geomean', 'Similarity Score'] | |
| list_size = 3 | |
| check_own_df = projections_file.copy() | |
| check_own_df = check_own_df.sort_values(by='ownership', ascending=False) | |
| top_owned = check_own_df['player_names'].head(list_size).tolist() | |
| def get_team_hitter_ownership(projections_file: pd.DataFrame): | |
| """ | |
| Calculate the sum ownership of hitters on each team. | |
| Excludes SP and P positions and sums ownership by team. | |
| Args: | |
| projections_file (pd.DataFrame): DataFrame with 'position', 'team', and 'ownership' columns | |
| Returns: | |
| pd.Series: Series with team names as index and total hitter ownership as values, sorted descending | |
| """ | |
| # Filter out pitchers (SP and P positions) | |
| hitters_df = projections_file[~projections_file['position'].isin(['P', 'SP'])] | |
| # Group by team and sum ownership | |
| team_ownership = hitters_df.groupby('team')['ownership'].sum().sort_values(ascending=False) | |
| return team_ownership | |
| team_ownership = get_team_hitter_ownership(projections_file) | |
| top_owned_teams = team_ownership.head(list_size).index.tolist() | |
| init_counter = 6 | |
| for runs in range(1, 5): | |
| concat_portfolio = pd.DataFrame(columns=portfolio.columns) | |
| for player in top_owned: | |
| print(player) | |
| working_df = portfolio.copy() | |
| # Create mask for lineups that contain any of the removed players | |
| player_columns = [col for col in working_df.columns if col not in excluded_cols] | |
| remove_mask = working_df[player_columns].apply( | |
| lambda row: player not in list(row), axis=1 | |
| ) | |
| lock_mask = working_df[player_columns].apply( | |
| lambda row: player in list(row), axis=1 | |
| ) | |
| removed_df = working_df[remove_mask] | |
| locked_df = working_df[lock_mask] | |
| removed_lineups = small_field_preset(removed_df, math.ceil(lineup_target / (list_size * init_counter)), excluded_cols) | |
| print(len(removed_lineups)) | |
| # Check if locked_df is empty before calling large_field_preset | |
| if not locked_df.empty: | |
| locked_lineups = large_field_preset(locked_df, math.ceil(lineup_target / (list_size * init_counter)), excluded_cols) | |
| print(len(locked_lineups)) | |
| concat_portfolio = pd.concat([concat_portfolio, removed_lineups, locked_lineups]) | |
| else: | |
| # If no lineups contain this player, just add the removed lineups | |
| print(f"No lineups found containing {player}") | |
| concat_portfolio = pd.concat([concat_portfolio, removed_lineups]) | |
| for team in top_owned_teams: | |
| working_df = portfolio.copy() | |
| removed_df = working_df[working_df['Stack'] != team] | |
| teams_df = working_df[working_df['Stack'] == team] | |
| removed_lineups = small_field_preset(removed_df, math.ceil(lineup_target / (list_size * init_counter)), excluded_cols) | |
| # Check if teams_df is empty before calling large_field_preset | |
| if not teams_df.empty: | |
| team_lineups = large_field_preset(teams_df, math.ceil(lineup_target / (list_size * init_counter)), excluded_cols) | |
| concat_portfolio = pd.concat([concat_portfolio, removed_lineups, team_lineups]) | |
| else: | |
| # If no lineups have this team stacked, just add the removed lineups | |
| print(f"No lineups found with {team} stacked") | |
| concat_portfolio = pd.concat([concat_portfolio, removed_lineups]) | |
| concat_portfolio = concat_portfolio.drop_duplicates(subset=['median', 'Own', 'Lineup Edge', 'Similarity Score']) | |
| if len(concat_portfolio) >= lineup_target: | |
| return concat_portfolio.head(lineup_target) | |
| else: | |
| init_counter -= 1 | |
| return concat_portfolio.head(lineup_target) |