Enhance duplicate prediction logic in predict_dupes.py by introducing 'own_rank_percentile' calculation. This addition improves the accuracy of the dupes calculation by factoring in player ownership rankings, ensuring more precise predictions across different contest types.

global_func/predict_dupes.py

@@ -295,7 +295,7 @@ def predict_dupes(portfolio, maps_dict, site_var, type_var, Contest_Size, streng
         if type_var == 'Showdown':
             dup_count_columns = ['CPT_Own_percent_rank', 'FLEX1_Own_percent_rank', 'FLEX2_Own_percent_rank', 'FLEX3_Own_percent_rank', 'FLEX4_Own_percent_rank']
             own_columns = ['CPT_Own', 'FLEX1_Own', 'FLEX2_Own', 'FLEX3_Own', 'FLEX4_Own']
-            calc_columns = ['own_product', 'own_average', 'own_sum', 'avg_own_rank', 'dupes_calc', 'low_own_count', 'own_ratio', 'Ref_Proj', 'Max_Proj', 'Min_Proj', 'Avg_Ref', 'own_ratio']
+            calc_columns = ['own_product', 'own_average', 'own_sum', 'avg_own_rank', 'own_rank_percentile', 'dupes_calc', 'low_own_count', 'own_ratio', 'Ref_Proj', 'Max_Proj', 'Min_Proj', 'Avg_Ref', 'own_ratio']
             # Get the original player columns (first 5 columns excluding salary, median, Own)
             player_columns = [col for col in portfolio.columns[:5] if col not in ['salary', 'median', 'Own']]
             
@@ -326,6 +326,7 @@ def predict_dupes(portfolio, maps_dict, site_var, type_var, Contest_Size, streng
             portfolio['own_average'] = (portfolio['Own'].max() * .33) / 100
             portfolio['own_sum'] = portfolio[own_columns].sum(axis=1)
             portfolio['avg_own_rank'] = portfolio[dup_count_columns].mean(axis=1)
+            portfolio['own_rank_percentile'] = portfolio[dup_count_columns].rank(pct=True)
             
             # Calculate dupes formula
             portfolio['dupes_calc'] = (portfolio['own_product'] * portfolio['avg_own_rank']) * (portfolio['Own'] / 100) * Contest_Size + ((portfolio['salary'] - (60000 - portfolio['Own'])) / 100) - ((60000 - portfolio['salary']) / 100)
@@ -335,13 +336,14 @@ def predict_dupes(portfolio, maps_dict, site_var, type_var, Contest_Size, streng
             portfolio['Dupes'] = np.where(
                 np.round(portfolio['dupes_calc'], 0) <= 0,
                 0, 
-                np.round(portfolio['dupes_calc'], 0) - 1
+                np.round((portfolio['dupes_calc'] * (1 + portfolio['own_rank_percentile'])), 0) - 1
             )
+            
         elif type_var == 'Classic':
             num_players = len([col for col in portfolio.columns if col not in ['salary', 'median', 'Own']])
             dup_count_columns = [f'player_{i}_percent_rank' for i in range(1, num_players + 1)]
             own_columns = [f'player_{i}_own' for i in range(1, num_players + 1)]
-            calc_columns = ['own_product', 'own_average', 'own_sum', 'avg_own_rank', 'dupes_calc', 'low_own_count', 'own_ratio', 'Ref_Proj', 'Max_Proj', 'Min_Proj', 'Avg_Ref', 'own_ratio']
+            calc_columns = ['own_product', 'own_average', 'own_sum', 'avg_own_rank', 'own_rank_percentile', 'dupes_calc', 'low_own_count', 'own_ratio', 'Ref_Proj', 'Max_Proj', 'Min_Proj', 'Avg_Ref', 'own_ratio']
             # Get the original player columns (first num_players columns excluding salary, median, Own)
             player_columns = [col for col in portfolio.columns[:num_players] if col not in ['salary', 'median', 'Own']]
             
@@ -353,6 +355,7 @@ def predict_dupes(portfolio, maps_dict, site_var, type_var, Contest_Size, streng
             portfolio['own_average'] = (portfolio['Own'].max() * .33) / 100
             portfolio['own_sum'] = portfolio[own_columns].sum(axis=1)
             portfolio['avg_own_rank'] = portfolio[dup_count_columns].mean(axis=1)
+            portfolio['own_rank_percentile'] = portfolio[dup_count_columns].rank(pct=True)
             
             portfolio['dupes_calc'] = (portfolio['own_product'] * portfolio['avg_own_rank']) * Contest_Size + ((portfolio['salary'] - (60000 - portfolio['Own'])) / 100) - ((60000 - portfolio['salary']) / 100)
             portfolio['dupes_calc'] = portfolio['dupes_calc'] * dupes_multiplier * (portfolio['Own'] / (100 + (Contest_Size / 1000)))
@@ -360,7 +363,7 @@ def predict_dupes(portfolio, maps_dict, site_var, type_var, Contest_Size, streng
             portfolio['Dupes'] = np.where(
                 np.round(portfolio['dupes_calc'], 0) <= 0,
                 0, 
-                np.round(portfolio['dupes_calc'], 0) - 1
+                np.round((portfolio['dupes_calc'] * (1 + portfolio['own_rank_percentile'])), 0) - 1
             )
 
     elif site_var == 'Draftkings':
@@ -371,7 +374,7 @@ def predict_dupes(portfolio, maps_dict, site_var, type_var, Contest_Size, streng
             else:
                 dup_count_columns = ['CPT_Own_percent_rank', 'FLEX1_Own_percent_rank', 'FLEX2_Own_percent_rank', 'FLEX3_Own_percent_rank', 'FLEX4_Own_percent_rank', 'FLEX5_Own_percent_rank']
                 own_columns = ['CPT_Own', 'FLEX1_Own', 'FLEX2_Own', 'FLEX3_Own', 'FLEX4_Own', 'FLEX5_Own']
-            calc_columns = ['own_product', 'own_average', 'own_sum', 'avg_own_rank', 'dupes_calc', 'low_own_count', 'Ref_Proj', 'Max_Proj', 'Min_Proj', 'Avg_Ref', 'own_ratio']
+            calc_columns = ['own_product', 'own_average', 'own_sum', 'avg_own_rank', 'own_rank_percentile', 'dupes_calc', 'low_own_count', 'Ref_Proj', 'Max_Proj', 'Min_Proj', 'Avg_Ref', 'own_ratio']
             # Get the original player columns (first 6 columns excluding salary, median, Own)
             player_columns = [col for col in portfolio.columns[:6] if col not in ['salary', 'median', 'Own']]
             if sport_var == 'GOLF':
@@ -427,6 +430,7 @@ def predict_dupes(portfolio, maps_dict, site_var, type_var, Contest_Size, streng
             portfolio['own_average'] = (portfolio['Own'].max() * .33) / 100
             portfolio['own_sum'] = portfolio[own_columns].sum(axis=1)
             portfolio['avg_own_rank'] = portfolio[dup_count_columns].mean(axis=1)
+            portfolio['own_rank_percentile'] = portfolio[dup_count_columns].rank(pct=True)
             
             # Calculate dupes formula
             portfolio['dupes_calc'] = (portfolio['own_product'] * portfolio['avg_own_rank']) * Contest_Size + ((portfolio['salary'] - (50000 - portfolio['Own'])) / 100) - ((50000 - portfolio['salary']) / 100)
@@ -436,13 +440,13 @@ def predict_dupes(portfolio, maps_dict, site_var, type_var, Contest_Size, streng
             portfolio['Dupes'] = np.where(
                 np.round(portfolio['dupes_calc'], 0) <= 0,
                 0, 
-                np.round(portfolio['dupes_calc'], 0) - 1
+                np.round((portfolio['dupes_calc'] * (1 + portfolio['own_rank_percentile'])), 0) - 1
             )
         elif type_var == 'Classic':
             if sport_var == 'CS2':
                 dup_count_columns = ['CPT_Own_percent_rank', 'FLEX1_Own_percent_rank', 'FLEX2_Own_percent_rank', 'FLEX3_Own_percent_rank', 'FLEX4_Own_percent_rank', 'FLEX5_Own_percent_rank']
                 own_columns = ['CPT_Own', 'FLEX1_Own', 'FLEX2_Own', 'FLEX3_Own', 'FLEX4_Own', 'FLEX5_Own']
-                calc_columns = ['own_product', 'own_average', 'own_sum', 'avg_own_rank', 'dupes_calc', 'low_own_count', 'Ref_Proj', 'Max_Proj', 'Min_Proj', 'Avg_Ref', 'own_ratio']
+                calc_columns = ['own_product', 'own_average', 'own_sum', 'avg_own_rank', 'own_rank_percentile', 'dupes_calc', 'low_own_count', 'Ref_Proj', 'Max_Proj', 'Min_Proj', 'Avg_Ref', 'own_ratio']
                 # Get the original player columns (first 6 columns excluding salary, median, Own)
                 player_columns = [col for col in portfolio.columns[:6] if col not in ['salary', 'median', 'Own']]
                 
@@ -474,6 +478,7 @@ def predict_dupes(portfolio, maps_dict, site_var, type_var, Contest_Size, streng
                 portfolio['own_average'] = (portfolio['Own'].max() * .33) / 100
                 portfolio['own_sum'] = portfolio[own_columns].sum(axis=1)
                 portfolio['avg_own_rank'] = portfolio[dup_count_columns].mean(axis=1)
+                portfolio['own_rank_percentile'] = portfolio[dup_count_columns].rank(pct=True)
                 
                 # Calculate dupes formula
                 portfolio['dupes_calc'] = ((portfolio['own_product'] * 10) * portfolio['avg_own_rank']) * Contest_Size + ((portfolio['salary'] - (50000 - portfolio['Own'])) / 50) - ((50000 - portfolio['salary']) / 50)
@@ -483,12 +488,12 @@ def predict_dupes(portfolio, maps_dict, site_var, type_var, Contest_Size, streng
                 portfolio['Dupes'] = np.where(
                     np.round(portfolio['dupes_calc'], 0) <= 0,
                     0, 
-                    np.round(portfolio['dupes_calc'], 0) - 1
+                    np.round((portfolio['dupes_calc'] * (1 + portfolio['own_rank_percentile'])), 0) - 1
                 )
             if sport_var == 'LOL':
                 dup_count_columns = ['CPT_Own_percent_rank', 'TOP_Own_percent_rank', 'JNG_Own_percent_rank', 'MID_Own_percent_rank', 'ADC_Own_percent_rank', 'SUP_Own_percent_rank', 'Team_Own_percent_rank']
                 own_columns = ['CPT_Own', 'TOP_Own', 'JNG_Own', 'MID_Own', 'ADC_Own', 'SUP_Own', 'Team_Own']
-                calc_columns = ['own_product', 'own_average', 'own_sum', 'avg_own_rank', 'dupes_calc', 'low_own_count', 'Ref_Proj', 'Max_Proj', 'Min_Proj', 'Avg_Ref', 'own_ratio']
+                calc_columns = ['own_product', 'own_average', 'own_sum', 'avg_own_rank', 'own_rank_percentile', 'dupes_calc', 'low_own_count', 'Ref_Proj', 'Max_Proj', 'Min_Proj', 'Avg_Ref', 'own_ratio']
                 # Get the original player columns (first 6 columns excluding salary, median, Own)
                 player_columns = [col for col in portfolio.columns[:7] if col not in ['salary', 'median', 'Own']]
                 
@@ -523,6 +528,7 @@ def predict_dupes(portfolio, maps_dict, site_var, type_var, Contest_Size, streng
                 portfolio['own_average'] = (portfolio['Own'].max() * .33) / 100
                 portfolio['own_sum'] = portfolio[own_columns].sum(axis=1)
                 portfolio['avg_own_rank'] = portfolio[dup_count_columns].mean(axis=1)
+                portfolio['own_rank_percentile'] = portfolio[dup_count_columns].rank(pct=True)
                 
                 # Calculate dupes formula
                 portfolio['dupes_calc'] = ((portfolio['own_product'] * 10) * portfolio['avg_own_rank']) * Contest_Size + ((portfolio['salary'] - (50000 - portfolio['Own'])) / 50) - ((50000 - portfolio['salary']) / 50)
@@ -532,13 +538,13 @@ def predict_dupes(portfolio, maps_dict, site_var, type_var, Contest_Size, streng
                 portfolio['Dupes'] = np.where(
                     np.round(portfolio['dupes_calc'], 0) <= 0,
                     0, 
-                    np.round(portfolio['dupes_calc'], 0) - 1
+                    np.round((portfolio['dupes_calc'] * (1 + portfolio['own_rank_percentile'])), 0) - 1
                 )
             elif sport_var != 'CS2' and sport_var != 'LOL':
                 num_players = len([col for col in portfolio.columns if col not in ['salary', 'median', 'Own']])
                 dup_count_columns = [f'player_{i}_percent_rank' for i in range(1, num_players + 1)]
                 own_columns = [f'player_{i}_own' for i in range(1, num_players + 1)]
-                calc_columns = ['own_product', 'own_average', 'own_sum', 'avg_own_rank', 'dupes_calc', 'low_own_count', 'Ref_Proj', 'Max_Proj', 'Min_Proj', 'Avg_Ref', 'own_ratio']
+                calc_columns = ['own_product', 'own_average', 'own_sum', 'avg_own_rank', 'own_rank_percentile', 'dupes_calc', 'low_own_count', 'Ref_Proj', 'Max_Proj', 'Min_Proj', 'Avg_Ref', 'own_ratio']
                 # Get the original player columns (first num_players columns excluding salary, median, Own)
                 player_columns = [col for col in portfolio.columns[:num_players] if col not in ['salary', 'median', 'Own']]
                 
@@ -550,6 +556,7 @@ def predict_dupes(portfolio, maps_dict, site_var, type_var, Contest_Size, streng
                 portfolio['own_average'] = (portfolio['Own'].max() * .33) / 100
                 portfolio['own_sum'] = portfolio[own_columns].sum(axis=1)
                 portfolio['avg_own_rank'] = portfolio[dup_count_columns].mean(axis=1)
+                portfolio['own_rank_percentile'] = portfolio[dup_count_columns].rank(pct=True)
                 
                 portfolio['dupes_calc'] = (portfolio['own_product'] * portfolio['avg_own_rank']) * Contest_Size + ((portfolio['salary'] - (50000 - portfolio['Own'])) / 100) - ((50000 - portfolio['salary']) / 100)
                 portfolio['dupes_calc'] = portfolio['dupes_calc'] * dupes_multiplier * (portfolio['Own'] / (100 + (Contest_Size / 1000)))
@@ -557,7 +564,7 @@ def predict_dupes(portfolio, maps_dict, site_var, type_var, Contest_Size, streng
                 portfolio['Dupes'] = np.where(
                     np.round(portfolio['dupes_calc'], 0) <= 0,
                     0, 
-                    np.round(portfolio['dupes_calc'], 0) - 1
+                    np.round((portfolio['dupes_calc'] * (1 + portfolio['own_rank_percentile'])), 0) - 1
                 )
 
     portfolio['Dupes'] = np.round(portfolio['Dupes'], 0)