Refactor SE Score calculation in predict_dupes function to incorporate player diversity, enhancing the accuracy of the score. Removed redundant print statement for cleaner output.

global_func/predict_dupes.py

@@ -442,13 +442,13 @@ def predict_dupes(portfolio, maps_dict, site_var, type_var, Contest_Size, streng
     portfolio['Lineup Edge'] = 2 * max_edge * (portfolio['Lineup Edge'] - portfolio['Lineup Edge'].min()) / (portfolio['Lineup Edge'].max() - portfolio['Lineup Edge'].min()) - max_edge
     portfolio['Weighted Own'] = portfolio[own_columns].apply(calculate_weighted_ownership_wrapper, axis=1)
     portfolio['Geomean'] = np.power((portfolio[own_columns] * 100).product(axis=1), 1 / len(own_columns))
-    portfolio['SE Score'] = ((portfolio['median'] - portfolio['median'].mean()) * (portfolio['Weighted Own'] - portfolio['Weighted Own'].mean()))
-    portfolio['SE Score'] = (np.tanh(portfolio['SE Score'] / portfolio['SE Score'].std()) + 1) / 2
-
-    print(portfolio['SE Score'].head(10))
+    
     
     # Calculate similarity score based on actual player selection
     portfolio['Diversity'] = calculate_player_similarity_score_chunked(portfolio, player_columns)
+
+    portfolio['SE Score'] = ((portfolio['median'] - portfolio['median'].mean()) * (portfolio['Weighted Own'] - portfolio['Weighted Own'].mean())) * (1 - portfolio['Diversity'])
+    portfolio['SE Score'] = (np.tanh(portfolio['SE Score'] / portfolio['SE Score'].std()) + 1) / 2
     # check_portfolio = portfolio.copy()
     portfolio = portfolio.drop(columns=dup_count_columns)
     portfolio = portfolio.drop(columns=own_columns)