Refactor portfolio duplication prediction in predict_dupes.py: enhance the function to accommodate sport-specific logic for CS2, improving ownership calculations and ensuring accurate duplication metrics based on player ownership and salary. Update app.py to pass sport_var to predict_dupes for better context in calculations.

app.py

@@ -724,17 +724,30 @@ with tab2:
 
         if site_var == 'Draftkings':
             if type_var == 'Classic':
-                map_dict = {
-                    'pos_map':dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['position'])),
-                    'team_map':dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['team'])),
-                    'salary_map':dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['salary'])),
-                    'proj_map':dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['median'])),
-                    'own_map':dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['ownership'])),
-                    'own_percent_rank':dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['ownership'].rank(pct=True))),
-                    'cpt_salary_map':dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['salary'])),
-                    'cpt_proj_map':dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['median'] * 1.5)),
-                    'cpt_own_map':dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['captain ownership']))
-                }
+                if sport_var == 'CS2':
+                    map_dict = {
+                        'pos_map':dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['position'])),
+                        'team_map':dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['team'])),
+                        'salary_map':dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['salary'])),
+                        'proj_map':dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['median'])),
+                        'own_map':dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['ownership'])),
+                        'own_percent_rank':dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['ownership'].rank(pct=True))),
+                        'cpt_salary_map':dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['salary'] * 1.5)),
+                        'cpt_proj_map':dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['median'] * 1.5)),
+                        'cpt_own_map':dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['captain ownership']))
+                    }
+                elif sport_var != 'CS2':
+                    map_dict = {
+                        'pos_map':dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['position'])),
+                        'team_map':dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['team'])),
+                        'salary_map':dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['salary'])),
+                        'proj_map':dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['median'])),
+                        'own_map':dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['ownership'])),
+                        'own_percent_rank':dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['ownership'].rank(pct=True))),
+                        'cpt_salary_map':dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['salary'])),
+                        'cpt_proj_map':dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['median'] * 1.5)),
+                        'cpt_own_map':dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['captain ownership']))
+                    }
             elif type_var == 'Showdown':
                 if sport_var == 'NFL':
                     map_dict = {
@@ -831,7 +844,7 @@ with tab2:
                     submitted = st.form_submit_button("Trim")
                     if submitted:
                         st.write('initiated')
-                        st.session_state['portfolio'] = predict_dupes(st.session_state['portfolio'], map_dict, site_var, type_var, Contest_Size, strength_var)
+                        st.session_state['portfolio'] = predict_dupes(st.session_state['portfolio'], map_dict, site_var, type_var, Contest_Size, strength_var, sport_var)
                         st.session_state['portfolio'] = st.session_state['portfolio'][st.session_state['portfolio']['Dupes'] <= max_dupes]
                         st.session_state['portfolio'] = st.session_state['portfolio'][st.session_state['portfolio']['salary'] >= min_salary]
                         st.session_state['portfolio'] = st.session_state['portfolio'][st.session_state['portfolio']['salary'] <= max_salary]

global_func/predict_dupes.py

@@ -5,7 +5,7 @@ import time
 from fuzzywuzzy import process
 import math
 
-def predict_dupes(portfolio, maps_dict, site_var, type_var, Contest_Size, strength_var):
+def predict_dupes(portfolio, maps_dict, site_var, type_var, Contest_Size, strength_var, sport_var):
     if strength_var == 'Weak':
         dupes_multiplier = .75
         percentile_multiplier = .90
@@ -126,27 +126,68 @@ def predict_dupes(portfolio, maps_dict, site_var, type_var, Contest_Size, streng
                 np.round(portfolio['dupes_calc'], 0) - 1
             )
         if 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', 'Ref_Proj', 'Max_Proj', 'Min_Proj', 'Avg_Ref', 'own_ratio']
-            for i in range(1, num_players + 1):
-                portfolio[f'player_{i}_percent_rank'] = portfolio.iloc[:,i-1].map(maps_dict['own_percent_rank'])
-                portfolio[f'player_{i}_own'] = portfolio.iloc[:,i-1].map(maps_dict['own_map']) / 100
-            
-            portfolio['own_product'] = (portfolio[own_columns].product(axis=1))
-            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['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
-            # Round and handle negative values
-            portfolio['Dupes'] = np.where(
-                np.round(portfolio['dupes_calc'], 0) <= 0,
-                0, 
-                np.round(portfolio['dupes_calc'], 0) - 1
-            )
+            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']
+                flex_ownerships = pd.concat([
+                    portfolio.iloc[:,1].map(maps_dict['own_map']),
+                    portfolio.iloc[:,2].map(maps_dict['own_map']),
+                    portfolio.iloc[:,3].map(maps_dict['own_map']),
+                    portfolio.iloc[:,4].map(maps_dict['own_map'])
+                ])
+                flex_rank = flex_ownerships.rank(pct=True)
+                
+                # Assign ranks back to individual columns using the same rank scale
+                portfolio['CPT_Own_percent_rank'] = portfolio.iloc[:,0].map(maps_dict['cpt_own_map']).rank(pct=True)
+                portfolio['FLEX1_Own_percent_rank'] = portfolio.iloc[:,1].map(maps_dict['own_map']).map(lambda x: flex_rank[flex_ownerships == x].iloc[0])
+                portfolio['FLEX2_Own_percent_rank'] = portfolio.iloc[:,2].map(maps_dict['own_map']).map(lambda x: flex_rank[flex_ownerships == x].iloc[0])
+                portfolio['FLEX3_Own_percent_rank'] = portfolio.iloc[:,3].map(maps_dict['own_map']).map(lambda x: flex_rank[flex_ownerships == x].iloc[0])
+                portfolio['FLEX4_Own_percent_rank'] = portfolio.iloc[:,4].map(maps_dict['own_map']).map(lambda x: flex_rank[flex_ownerships == x].iloc[0])
+
+                portfolio['CPT_Own'] = portfolio.iloc[:,0].map(maps_dict['cpt_own_map']) / 100
+                portfolio['FLEX1_Own'] = portfolio.iloc[:,1].map(maps_dict['own_map']) / 100
+                portfolio['FLEX2_Own'] = portfolio.iloc[:,2].map(maps_dict['own_map']) / 100
+                portfolio['FLEX3_Own'] = portfolio.iloc[:,3].map(maps_dict['own_map']) / 100
+                portfolio['FLEX4_Own'] = portfolio.iloc[:,4].map(maps_dict['own_map']) / 100
+
+                portfolio['own_product'] = (portfolio[own_columns].product(axis=1))
+                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)
+                
+                # 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)
+                portfolio['dupes_calc'] = portfolio['dupes_calc'] * dupes_multiplier
+
+                # Round and handle negative values
+                portfolio['Dupes'] = np.where(
+                    np.round(portfolio['dupes_calc'], 0) <= 0,
+                    0, 
+                    np.round(portfolio['dupes_calc'], 0) - 1
+                )
+            elif sport_var != 'CS2':
+                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']
+                for i in range(1, num_players + 1):
+                    portfolio[f'player_{i}_percent_rank'] = portfolio.iloc[:,i-1].map(maps_dict['own_percent_rank'])
+                    portfolio[f'player_{i}_own'] = portfolio.iloc[:,i-1].map(maps_dict['own_map']) / 100
+                
+                portfolio['own_product'] = (portfolio[own_columns].product(axis=1))
+                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['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
+                # Round and handle negative values
+                portfolio['Dupes'] = np.where(
+                    np.round(portfolio['dupes_calc'], 0) <= 0,
+                    0, 
+                    np.round(portfolio['dupes_calc'], 0) - 1
+                )
 
     portfolio['Dupes'] = np.round(portfolio['Dupes'], 0)
     portfolio['own_ratio'] = np.where(