Enhance portfolio distribution logic in distribute_preset.py by adding player exposure calculations and refining the handling of 'Similarity Score'. This update improves the accuracy of player selection and provides a summary of player exposure in the final output, ensuring a more comprehensive analysis of the lineup distribution process.

global_func/distribute_preset.py

@@ -2,6 +2,50 @@ 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']
+    for slack_var in range(1, 20):
+        init_portfolio = pd.DataFrame(columns=portfolio.columns)
+
+        for team in portfolio['Stack'].unique():
+            rows_to_drop = []
+            working_portfolio = portfolio.copy()
+            working_portfolio = working_portfolio[working_portfolio['Stack'] == team].sort_values(by='median', ascending = False)
+            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'])
+
+            for i in range(1, len(working_portfolio)):
+                if working_portfolio.loc[i, 'Similarity Score'] > curr_own_type_max:
+                    rows_to_drop.append(i)
+                else:
+                    curr_own_type_max = working_portfolio.loc[i, 'Similarity Score'] + (slack_var / 20 * working_portfolio.loc[i, 'Similarity Score'])
+            
+            working_portfolio = working_portfolio.drop(rows_to_drop).reset_index(drop=True)
+            init_portfolio = pd.concat([init_portfolio, working_portfolio])
+
+        if len(init_portfolio) >= lineup_target:
+            init_portfolio.sort_values(by='median', ascending=True).head(lineup_target)
+    
+    player_list = set()
+    player_stats = []
+    for cols in init_portfolio.columns:
+        if cols not in excluded_cols:
+            player_list.update(init_portfolio[cols].unique())
+    
+    for player in player_list:
+        player_mask = init_portfolio[~excluded_cols].apply(
+            lambda row: player in list(row), axis=1
+        )
+        
+        if player_mask.any():
+            player_stats.append({
+                'Player': player,
+                'Lineup Count': player_mask.sum(),
+                'Exposure': player_mask.sum() / len(init_portfolio)
+            })
+
+    player_summary = pd.DataFrame(player_stats)
+    print(player_summary.sort_values('Lineup Count', ascending=False).head(10))
+
     for slack_var in range(1, 20):
         concat_portfolio = pd.DataFrame(columns=portfolio.columns)
 
@@ -23,5 +67,5 @@ def distribute_preset(portfolio: pd.DataFrame, lineup_target: int, exclude_cols:
 
         if len(concat_portfolio) >= lineup_target:
             return concat_portfolio.sort_values(by='median', ascending=True).head(lineup_target)
-        
+
     return concat_portfolio.sort_values(by='median', ascending=True)