Refactor player removal logic in distribute_preset.py to utilize a list of players with the lowest lineup counts. This change enhances the portfolio distribution process by ensuring that the least favorable players are excluded from the lineup, improving overall selection accuracy.

global_func/distribute_preset.py

@@ -3,6 +3,7 @@ import pandas as pd
 def distribute_preset(portfolio: pd.DataFrame, lineup_target: int, exclude_cols: list):
     
     excluded_cols = ['salary', 'median', 'Own', 'Finish_percentile', 'Dupes', 'Stack', 'Size', 'Win%', 'Lineup Edge', 'Weighted Own', 'Geomean', 'Similarity Score']
+    player_columns = [col for col in init_portfolio.columns if col not in excluded_cols]
     for slack_var in range(1, 20):
         init_portfolio = pd.DataFrame(columns=portfolio.columns)
 
@@ -47,14 +48,18 @@ def distribute_preset(portfolio: pd.DataFrame, lineup_target: int, exclude_cols:
 
     player_summary = pd.DataFrame(player_stats)
     print(player_summary.sort_values('Lineup Count', ascending=False).head(10))
+    player_remove_list = player_summary.sort_values('Lineup Count', ascending=False).head(5)['Player'].tolist()
 
     for slack_var in range(1, 20):
         concat_portfolio = pd.DataFrame(columns=portfolio.columns)
 
-        for team in portfolio['Stack'].unique():
+        for player_out in player_remove_list:
             rows_to_drop = []
             working_portfolio = portfolio.copy()
-            working_portfolio = working_portfolio[working_portfolio['Stack'] == team].sort_values(by='median', ascending = False)
+            remove_mask = working_portfolio[player_columns].apply(
+                lambda row: not any(player in list(row) for player in player_out), axis=1
+            )
+            working_portfolio = working_portfolio[remove_mask]
             working_portfolio = working_portfolio.reset_index(drop=True)
             curr_own_type_max = working_portfolio.loc[0, 'Similarity Score'] + (slack_var / 20 * working_portfolio.loc[0, 'Similarity Score'])