James McCool
Add team lineup filtering in hedging_preset.py to enhance lineup generation. Introduced logic to separate teams and calculate removed lineups, improving the accuracy of team-based strategies.
ef7a8b2
| 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() | |
| 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] | |
| print(removed_df.head(10)) | |
| locked_df = working_df[lock_mask] | |
| print(locked_df.head(10)) | |
| removed_lineups = small_field_preset(removed_df, math.ceil(lineup_target / (list_size * 3)), excluded_cols) | |
| locked_lineups = large_field_preset(locked_df, math.ceil(lineup_target / (list_size * 3)), excluded_cols) | |
| concat_portfolio = pd.concat([concat_portfolio, removed_lineups, locked_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 * 3)), excluded_cols) | |
| team_lineups = large_field_preset(teams_df, math.ceil(lineup_target / (list_size * 3)), excluded_cols) | |
| concat_portfolio = pd.concat([concat_portfolio, team_lineups]) | |
| return concat_portfolio.head(lineup_target) |