Refactor large_field_preset function to streamline player removal logic by eliminating unnecessary iterations and simplifying the exposure tracking process. Ensure sufficient lineups are generated before finalizing selections, enhancing overall efficiency and accuracy.

global_func/large_field_preset.py

@@ -4,73 +4,24 @@ def large_field_preset(portfolio: pd.DataFrame, lineup_target: int, exclude_cols
     
     for slack_var in range(1, 20):
         concat_portfolio = pd.DataFrame(columns=portfolio.columns)
-        
-        # Define player columns (columns that contain player names)
-        player_columns = [col for col in portfolio.columns if col not in exclude_cols]
-        
-        # Track players to remove across iterations
-        remove_list = []
-        
-        # Iterate until no high-exposure players are found
-        max_iterations = 10  # Prevent infinite loops
-        for iteration in range(max_iterations):
-            concat_portfolio = pd.DataFrame(columns=portfolio.columns)
 
-            for team in portfolio['Stack'].unique():
-                rows_to_drop = []
-                working_portfolio = portfolio.copy()
-                
-                # Remove players from previous iteration if any
-                if remove_list:
-                    remove_mask = working_portfolio[player_columns].apply(
-                        lambda row: not any(player in list(row) for player in remove_list), axis=1
-                    )
-                    working_portfolio = working_portfolio[remove_mask]
-                
-                working_portfolio = working_portfolio[working_portfolio['Stack'] == team].sort_values(by='Finish_percentile', ascending = True)
-                working_portfolio = working_portfolio.reset_index(drop=True)
-                
-                if len(working_portfolio) == 0:
-                    continue
-                    
-                curr_own_type_max = working_portfolio.loc[0, 'Own'] + (slack_var / 20 * working_portfolio.loc[0, 'Own'])
+        for team in portfolio['Stack'].unique():
+            rows_to_drop = []
+            working_portfolio = portfolio.copy()
+            working_portfolio = working_portfolio[working_portfolio['Stack'] == team].sort_values(by='Finish_percentile', ascending = True)
+            working_portfolio = working_portfolio.reset_index(drop=True)
+            curr_own_type_max = working_portfolio.loc[0, 'Own'] + (slack_var / 20 * working_portfolio.loc[0, 'Own'])
 
-                for i in range(1, len(working_portfolio)):
-                    if working_portfolio.loc[i, 'Own'] > curr_own_type_max:
-                        rows_to_drop.append(i)
-                    else:
-                        curr_own_type_max = working_portfolio.loc[i, 'Own'] + (slack_var / 20 * working_portfolio.loc[i, 'Own'])
-                
-                working_portfolio = working_portfolio.drop(rows_to_drop).reset_index(drop=True)
-                concat_portfolio = pd.concat([concat_portfolio, working_portfolio])
-
-            # Check player exposure
-            if len(concat_portfolio) == 0:
-                break
-                
-            player_exposure = {}
-            for col in player_columns:
-                for player in concat_portfolio[col].unique():
-                    if pd.notna(player):  # Skip NaN values
-                        player_mask = concat_portfolio[player_columns].apply(
-                            lambda row: player in list(row), axis=1
-                        )
-                        exposure = player_mask.sum() / len(concat_portfolio)
-                        player_exposure[player] = exposure
-            
-            # Find players with exposure > 35%
-            high_exposure_players = [player for player, exposure in player_exposure.items() if exposure > 0.35]
+            for i in range(1, len(working_portfolio)):
+                if working_portfolio.loc[i, 'Own'] > curr_own_type_max:
+                    rows_to_drop.append(i)
+                else:
+                    curr_own_type_max = working_portfolio.loc[i, 'Own'] + (slack_var / 20 * working_portfolio.loc[i, 'Own'])
             
-            # If no high-exposure players, we're done
-            if not high_exposure_players:
-                break
-                
-            # Add high-exposure players to remove list
-            remove_list.extend(high_exposure_players)
-            remove_list = list(set(remove_list))  # Remove duplicates
+            working_portfolio = working_portfolio.drop(rows_to_drop).reset_index(drop=True)
+            concat_portfolio = pd.concat([concat_portfolio, working_portfolio])
 
-        # Check if we have enough lineups and no high-exposure players
-        if len(concat_portfolio) >= lineup_target and len(high_exposure_players) == 0:
+        if len(concat_portfolio) >= lineup_target:
             return concat_portfolio.sort_values(by='Finish_percentile', ascending=True).head(lineup_target)
         
     return concat_portfolio.sort_values(by='Finish_percentile', ascending=True)