Refactor app.py to support NBA data integration and enhance functionality for both NFL and NBA sports. Added new functions for initializing seed frames and updated existing functions to handle sport-specific data. Improved data handling for ownership calculations and adjusted data structures for better performance. Updated user interface elements to allow sport selection and corresponding data loading.

app.py

@@ -38,68 +38,191 @@ def init_conn():
         
         uri = st.secrets['mongo_uri']
         client = pymongo.MongoClient(uri, retryWrites=True, serverSelectionTimeoutMS=500000)
-        db = client["testing_db"]
      
         NFL_Data = st.secrets['NFL_Data']
 
+        NBA_Data = st.secrets['NBA_Data']
+
         gc = gspread.service_account_from_dict(credentials)
         gc2 = gspread.service_account_from_dict(credentials2)
 
-        return gc, gc2, db, NFL_Data
+        return gc, gc2, client, NFL_Data, NBA_Data
     
-gcservice_account, gcservice_account2, db, NFL_Data = init_conn()
+gcservice_account, gcservice_account2, client, NFL_Data, NBA_Data = init_conn()
 
 percentages_format = {'Exposure': '{:.2%}'}
 freq_format = {'Exposure': '{:.2%}', 'Proj Own': '{:.2%}', 'Edge': '{:.2%}'}
-dk_columns = ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count']
-fd_columns = ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count']
+dk_columns = ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']
+fd_columns = ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']
 
 @st.cache_data(ttl = 599)
-def init_DK_seed_frames():  
-    
-        collection = db["DK_NFL_SD_seed_frame"] 
+def init_DK_seed_frames(sport): 
+        if sport == 'NFL':
+            db = client["NFL_Database"]
+        elif sport == 'NBA':
+            db = client["NBA_DFS"]
+        
+        collection = db[f"DK_{sport}_SD_seed_frame"] 
         cursor = collection.find()
     
         raw_display = pd.DataFrame(list(cursor))
-        raw_display = raw_display[['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count']]
+        raw_display = raw_display[['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
         DK_seed = raw_display.to_numpy()
 
         return DK_seed
+    
+@st.cache_data(ttl = 599)
+def init_DK_secondary_seed_frames(sport):  
+        
+        if sport == 'NFL':
+            db = client["NFL_Database"]
+        elif sport == 'NBA':
+            db = client["NBA_DFS"]
+    
+        collection = db[f"DK_{sport}_Secondary_SD_seed_frame"] 
+        cursor = collection.find()
+    
+        raw_display = pd.DataFrame(list(cursor))
+        raw_display = raw_display[['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
+        DK_second_seed = raw_display.to_numpy()
 
+        return DK_second_seed
+
+@st.cache_data(ttl = 599)
+def init_DK_auxiliary_seed_frames(sport):  
+        
+        if sport == 'NFL':
+            db = client["NFL_Database"]
+        elif sport == 'NBA':
+            db = client["NBA_DFS"]
+    
+        collection = db[f"DK_{sport}_Auxiliary_SD_seed_frame"] 
+        cursor = collection.find()
+    
+        raw_display = pd.DataFrame(list(cursor))
+        raw_display = raw_display[['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
+        DK_auxiliary_seed = raw_display.to_numpy()
+
+        return DK_auxiliary_seed
+    
 @st.cache_data(ttl = 599)
-def init_FD_seed_frames():  
+def init_FD_seed_frames(sport):  
+        
+        if sport == 'NFL':
+            db = client["NFL_Database"]
+        elif sport == 'NBA':
+            db = client["NBA_DFS"]
     
-        collection = db["FD_NFL_SD_seed_frame"] 
+        collection = db[f"FD_{sport}_SD_seed_frame"] 
         cursor = collection.find()
     
         raw_display = pd.DataFrame(list(cursor))
-        raw_display = raw_display[['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count']]
+        raw_display = raw_display[['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
         FD_seed = raw_display.to_numpy()
 
         return FD_seed
+    
+@st.cache_data(ttl = 599)
+def init_FD_secondary_seed_frames(sport):  
+        
+        if sport == 'NFL':
+            db = client["NFL_Database"]
+        elif sport == 'NBA':
+            db = client["NBA_DFS"]
+    
+        collection = db[f"FD_{sport}_Secondary_SD_seed_frame"] 
+        cursor = collection.find()
+    
+        raw_display = pd.DataFrame(list(cursor))
+        raw_display = raw_display[['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
+        FD_second_seed = raw_display.to_numpy()
+
+        return FD_second_seed
 
 @st.cache_data(ttl = 599)
-def init_baselines():
-    try:
-        sh = gcservice_account.open_by_url(NFL_Data)
-    except:
-        sh = gcservice_account2.open_by_url(NFL_Data)
+def init_FD_auxiliary_seed_frames(sport):  
+        
+        if sport == 'NFL':
+            db = client["NFL_Database"]
+        elif sport == 'NBA':
+            db = client["NBA_DFS"]
     
-    worksheet = sh.worksheet('DK_SD_ROO')
-    load_display = pd.DataFrame(worksheet.get_all_records())
-    load_display.replace('', np.nan, inplace=True)
-    load_display['STDev'] = load_display['Median'] / 4
-    load_display = load_display.drop_duplicates(subset=['Player'], keep='first')
+        collection = db[f"FD_{sport}_Auxiliary_SD_seed_frame"] 
+        cursor = collection.find()
     
-    dk_raw = load_display.dropna(subset=['Median'])
+        raw_display = pd.DataFrame(list(cursor))
+        raw_display = raw_display[['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
+        FD_auxiliary_seed = raw_display.to_numpy()
+
+        return FD_auxiliary_seed
+
+@st.cache_data(ttl = 599)
+def init_baselines(sport):
+    if sport == 'NFL':
+        db = client["NFL_Database"] 
+        collection = db['DK_SD_NFL_ROO'] 
+        cursor = collection.find()
     
-    worksheet = sh.worksheet('FD_SD_ROO')
-    load_display = pd.DataFrame(worksheet.get_all_records())
-    load_display.replace('', np.nan, inplace=True)
-    load_display['STDev'] = load_display['Median'] / 4
-    load_display = load_display.drop_duplicates(subset=['Player'], keep='first')
+        raw_display = pd.DataFrame(list(cursor))
+        raw_display = raw_display[['Player', 'Position', 'Team', 'Opp', 'Salary', 'Floor', 'Median', 'Ceiling', 'Top_finish', 'Top_5_finish', 'Top_10_finish', '20+%', '2x%', '3x%', '4x%',
+                                   'Own', 'Small_Field_Own', 'Large_Field_Own', 'Cash_Field_Own', 'CPT_Own', 'LevX', 'version', 'slate', 'timestamp', 'player_id', 'site']]
+        raw_display['Small_Field_Own'] = raw_display['Large_Field_Own']
+        raw_display['small_CPT_Own_raw'] = (raw_display['Small_Field_Own'] / 2) * ((100 - (100-raw_display['Small_Field_Own']))/100)
+        small_cpt_own_var = 300 / raw_display['small_CPT_Own_raw'].sum()
+        raw_display['small_CPT_Own'] = raw_display['small_CPT_Own_raw'] * small_cpt_own_var
+        raw_display['cpt_Median'] = raw_display['Median'] * 1.25
+        raw_display['STDev'] = raw_display['Median'] / 4
+        raw_display['CPT_STDev'] = raw_display['cpt_Median'] / 4
+        
+        dk_raw = raw_display.dropna(subset=['Median'])
+        
+        collection = db['FD_SD_NFL_ROO'] 
+        cursor = collection.find()
+    
+        raw_display = pd.DataFrame(list(cursor))
+        raw_display = raw_display[['Player', 'Position', 'Team', 'Opp', 'Salary', 'Floor', 'Median', 'Ceiling', 'Top_finish', 'Top_5_finish', 'Top_10_finish', '20+%', '2x%', '3x%', '4x%',
+                                   'Own', 'Small_Field_Own', 'Large_Field_Own', 'Cash_Field_Own', 'CPT_Own', 'LevX', 'version', 'slate', 'timestamp', 'player_id', 'site']]
+        raw_display['Small_Field_Own'] = raw_display['Large_Field_Own']
+        raw_display['small_CPT_Own'] = raw_display['CPT_Own']
+        raw_display['cpt_Median'] = raw_display['Median']
+        raw_display['STDev'] = raw_display['Median'] / 4
+        raw_display['CPT_STDev'] = raw_display['cpt_Median'] / 4
+        
+        fd_raw = raw_display.dropna(subset=['Median'])
+    
+    elif sport == 'NBA':
+        db = client["NBA_DFS"] 
+        collection = db['Player_SD_Range_Of_Outcomes'] 
+        cursor = collection.find()
     
-    fd_raw = load_display.dropna(subset=['Median'])
+        raw_display = pd.DataFrame(list(cursor))
+        raw_display = raw_display[['Player', 'Minutes Proj', 'Position', 'Team', 'Opp', 'Salary', 'Floor', 'Median', 'Ceiling', 'Top_finish', 'Top_5_finish', 'Top_10_finish', '20+%', '4x%', '5x%', '6x%', 'GPP%',
+                                   'Own', 'Small_Own', 'Large_Own', 'Cash_Own', 'CPT_Own', 'LevX', 'ValX', 'site', 'version', 'slate', 'timestamp', 'player_id']]
+        raw_display = raw_display[raw_display['site'] == 'Draftkings']
+        raw_display['Small_Field_Own'] = raw_display['Small_Own']
+        raw_display['small_CPT_Own_raw'] = (raw_display['Small_Field_Own'] / 2) * ((100 - (100-raw_display['Small_Field_Own']))/100)
+        small_cpt_own_var = 300 / raw_display['small_CPT_Own_raw'].sum()
+        raw_display['small_CPT_Own'] = raw_display['small_CPT_Own_raw'] * small_cpt_own_var
+        raw_display['cpt_Median'] = raw_display['Median'] * 1.25
+        raw_display['STDev'] = raw_display['Median'] / 4
+        raw_display['CPT_STDev'] = raw_display['cpt_Median'] / 4
+        
+        dk_raw = raw_display.dropna(subset=['Median'])
+        
+        collection = db['Player_SD_Range_Of_Outcomes'] 
+        cursor = collection.find()
+    
+        raw_display = pd.DataFrame(list(cursor))
+        raw_display = raw_display[['Player', 'Minutes Proj', 'Position', 'Team', 'Opp', 'Salary', 'Floor', 'Median', 'Ceiling', 'Top_finish', 'Top_5_finish', 'Top_10_finish', '20+%', '4x%', '5x%', '6x%', 'GPP%',
+                                   'Own', 'Small_Own', 'Large_Own', 'Cash_Own', 'CPT_Own', 'LevX', 'ValX', 'site', 'version', 'slate', 'timestamp', 'player_id']]
+        raw_display = raw_display[raw_display['site'] == 'Fanduel']
+        raw_display['Small_Field_Own'] = raw_display['Large_Own']
+        raw_display['small_CPT_Own'] = raw_display['CPT_Own']
+        raw_display['cpt_Median'] = raw_display['Median']
+        raw_display['STDev'] = raw_display['Median'] / 4
+        raw_display['CPT_STDev'] = raw_display['cpt_Median'] / 4
+        
+        fd_raw = raw_display.dropna(subset=['Median'])
 
     return dk_raw, fd_raw
 
@@ -130,7 +253,9 @@ def sim_contest(Sim_size, seed_frame, maps_dict, sharp_split, Contest_Size):
     
     # Pre-vectorize functions
     vec_projection_map = np.vectorize(maps_dict['Projection_map'].__getitem__)
+    vec_cpt_projection_map = np.vectorize(maps_dict['cpt_projection_map'].__getitem__)
     vec_stdev_map = np.vectorize(maps_dict['STDev_map'].__getitem__)
+    vec_cpt_stdev_map = np.vectorize(maps_dict['cpt_STDev_map'].__getitem__)
     
     st.write('Simulating contest on frames')
     
@@ -138,10 +263,16 @@ def sim_contest(Sim_size, seed_frame, maps_dict, sharp_split, Contest_Size):
         fp_random = fp_array[np.random.choice(fp_array.shape[0], Contest_Size)]
             
         sample_arrays1 = np.c_[
-            fp_random, 
+            fp_random,
             np.sum(np.random.normal(
-                loc=vec_projection_map(fp_random[:, :-6]),
-                scale=vec_stdev_map(fp_random[:, :-6])),
+                loc=np.concatenate([
+                    vec_cpt_projection_map(fp_random[:, 0:1]),  # Apply cpt_projection_map to first column
+                    vec_projection_map(fp_random[:, 1:-7])  # Apply original projection to remaining columns
+                ], axis=1),
+                scale=np.concatenate([
+                    vec_cpt_stdev_map(fp_random[:, 0:1]),  # Apply cpt_projection_map to first column
+                    vec_stdev_map(fp_random[:, 1:-7])  # Apply original projection to remaining columns
+                ], axis=1)),
             axis=1)
         ]
 
@@ -154,10 +285,6 @@ def sim_contest(Sim_size, seed_frame, maps_dict, sharp_split, Contest_Size):
         
     return Sim_Winners
 
-DK_seed = init_DK_seed_frames()
-FD_seed = init_FD_seed_frames()
-dk_raw, fd_raw = init_baselines()
-
 tab1, tab2 = st.tabs(['Contest Sims', 'Data Export'])
 with tab2:
     col1, col2 = st.columns([1, 7])
@@ -166,13 +293,32 @@ with tab2:
               st.cache_data.clear()
               for key in st.session_state.keys():
                   del st.session_state[key]
-              DK_seed = init_DK_seed_frames()
-              FD_seed = init_FD_seed_frames()
-              dk_raw, fd_raw = init_baselines()
-              
-        slate_var1 = st.radio("Which data are you loading?", ('Showdown', 'Other Showdown'))
-        site_var1 = st.radio("What site are you working with?", ('Draftkings', 'Fanduel'))
+              dk_raw, fd_raw = init_baselines('NFL')
+        
+        sport_var1 = st.radio("What sport are you working with?", ('NFL', 'NBA'), key='sport_var1')
+        dk_raw, fd_raw = init_baselines(sport_var1)
+        slate_var1 = st.radio("Which data are you loading?", ('Showdown', 'Secondary Showdown', 'Auxiliary Showdown'), key='slate_var1')
+            
+        site_var1 = st.radio("What site are you working with?", ('Draftkings', 'Fanduel'), key='site_var1')
         if site_var1 == 'Draftkings':
+            if slate_var1 == 'Showdown':
+                DK_seed = init_DK_seed_frames(sport_var1)
+                if sport_var1 == 'NFL':
+                    export_id_dict = dict(zip(dk_raw['Player'], dk_raw['player_id']))
+                elif sport_var1 == 'NBA':
+                    export_id_dict = dict(zip(dk_raw['Player'], dk_raw['player_id']))
+            elif slate_var1 == 'Secondary Showdown':
+                DK_seed = init_DK_secondary_seed_frames(sport_var1)
+                if sport_var1 == 'NFL':
+                    export_id_dict = dict(zip(dk_raw['Player'], dk_raw['player_id']))
+                elif sport_var1 == 'NBA':
+                    export_id_dict = dict(zip(dk_raw['Player'], dk_raw['player_id']))
+            elif slate_var1 == 'Auxiliary Showdown':
+                DK_seed = init_DK_auxiliary_seed_frames(sport_var1)
+                if sport_var1 == 'NFL':
+                    export_id_dict = dict(zip(dk_raw['Player'], dk_raw['player_id']))
+                elif sport_var1 == 'NBA':
+                    export_id_dict = dict(zip(dk_raw['Player'], dk_raw['player_id']))
             raw_baselines = dk_raw
             column_names = dk_columns
             
@@ -189,6 +335,24 @@ with tab2:
                     stack_var2 = [5, 4, 3, 2, 1, 0]
                     
         elif site_var1 == 'Fanduel':
+            if slate_var1 == 'Showdown':
+                FD_seed = init_FD_seed_frames(sport_var1)
+                if sport_var1 == 'NFL':
+                    export_id_dict = dict(zip(fd_raw['Player'], fd_raw['player_id']))
+                elif sport_var1 == 'NBA':
+                    export_id_dict = dict(zip(fd_raw['Player'], fd_raw['player_id']))
+            elif slate_var1 == 'Secondary Showdown':
+                FD_seed = init_FD_secondary_seed_frames(sport_var1)
+                if sport_var1 == 'NFL':
+                    export_id_dict = dict(zip(fd_raw['Player'], fd_raw['player_id']))
+                elif sport_var1 == 'NBA':
+                    export_id_dict = dict(zip(fd_raw['Player'], fd_raw['player_id']))
+            elif slate_var1 == 'Auxiliary Showdown':
+                FD_seed = init_FD_auxiliary_seed_frames(sport_var1)
+                if sport_var1 == 'NFL':
+                    export_id_dict = dict(zip(fd_raw['Player'], fd_raw['player_id']))
+                elif sport_var1 == 'NBA':
+                    export_id_dict = dict(zip(fd_raw['Player'], fd_raw['player_id']))
             raw_baselines = fd_raw
             column_names = fd_columns
             
@@ -207,6 +371,7 @@ with tab2:
 
         if st.button("Prepare data export", key='data_export'):
                 data_export = st.session_state.working_seed.copy()
+                data_export[0:6, 0] = [export_id_dict[x] for x in data_export[0:6, 0]]
                 st.download_button(
                     label="Export optimals set",
                     data=convert_df(data_export),
@@ -249,27 +414,68 @@ with tab1:
               st.cache_data.clear()
               for key in st.session_state.keys():
                   del st.session_state[key]
-              DK_seed = init_DK_seed_frames()
-              FD_seed = init_FD_seed_frames()
-              dk_raw, fd_raw = init_baselines()
-        sim_slate_var1 = st.radio("Which data are you loading?", ('Main Slate', 'Other Main Slate'), key='sim_slate_var1')
+              dk_raw, fd_raw = init_baselines('NFL')
+        sim_sport_var1 = st.radio("What sport are you working with?", ('NFL', 'NBA'), key='sim_sport_var1')
+        dk_raw, fd_raw = init_baselines(sim_sport_var1)
+        sim_slate_var1 = st.radio("Which data are you loading?", ('Showdown', 'Secondary Showdown', 'Auxiliary Showdown'), key='sim_slate_var1')
         sim_site_var1 = st.radio("What site are you working with?", ('Draftkings', 'Fanduel'), key='sim_site_var1')
         if sim_site_var1 == 'Draftkings':
+            if sim_slate_var1 == 'Showdown':
+                DK_seed = init_DK_seed_frames(sim_sport_var1)
+                if sport_var1 == 'NFL':
+                    export_id_dict = dict(zip(dk_raw['Player'], dk_raw['player_id']))
+                elif sport_var1 == 'NBA':
+                    export_id_dict = dict(zip(dk_raw['Player'], dk_raw['player_id']))
+            elif sim_slate_var1 == 'Secondary Showdown':
+                DK_seed = init_DK_secondary_seed_frames(sim_sport_var1)
+                if sport_var1 == 'NFL':
+                    export_id_dict = dict(zip(dk_raw['Player'], dk_raw['player_id']))
+                elif sport_var1 == 'NBA':
+                    export_id_dict = dict(zip(dk_raw['Player'], dk_raw['player_id']))
+            elif sim_slate_var1 == 'Auxiliary Showdown':
+                DK_seed = init_DK_auxiliary_seed_frames(sim_sport_var1)
+                if sport_var1 == 'NFL':
+                    export_id_dict = dict(zip(dk_raw['Player'], dk_raw['player_id']))
+                elif sport_var1 == 'NBA':
+                    export_id_dict = dict(zip(dk_raw['Player'], dk_raw['player_id']))
             raw_baselines = dk_raw
             column_names = dk_columns
         elif sim_site_var1 == 'Fanduel':
+            if sim_slate_var1 == 'Showdown':
+                FD_seed = init_FD_seed_frames(sim_sport_var1)
+                if sport_var1 == 'NFL':
+                    export_id_dict = dict(zip(fd_raw['Player'], fd_raw['player_id']))
+                elif sport_var1 == 'NBA':
+                    export_id_dict = dict(zip(fd_raw['Player'], fd_raw['player_id']))
+            elif sim_slate_var1 == 'Secondary Showdown':
+                FD_seed = init_FD_secondary_seed_frames(sim_sport_var1)
+                if sport_var1 == 'NFL':
+                    export_id_dict = dict(zip(fd_raw['Player'], fd_raw['player_id']))
+                elif sport_var1 == 'NBA':
+                    export_id_dict = dict(zip(fd_raw['Player'], fd_raw['player_id']))
+            elif sim_slate_var1 == 'Auxiliary Showdown':
+                FD_seed = init_FD_auxiliary_seed_frames(sim_sport_var1)
+                if sport_var1 == 'NFL':
+                    export_id_dict = dict(zip(fd_raw['Player'], fd_raw['player_id']))
+                elif sport_var1 == 'NBA':
+                    export_id_dict = dict(zip(fd_raw['Player'], fd_raw['player_id']))
             raw_baselines = fd_raw
             column_names = fd_columns
             
         contest_var1 = st.selectbox("What contest size are you simulating?", ('Small', 'Medium', 'Large', 'Custom'))
         if contest_var1 == 'Small':
             Contest_Size = 1000
+            st.write("Small field size is 1,000 entrants.")
+            raw_baselines['Own'] = raw_baselines['Small_Field_Own']
+            raw_baselines['CPT_Own'] = raw_baselines['small_CPT_Own']
         elif contest_var1 == 'Medium':
             Contest_Size = 5000
+            st.write("Medium field size is 5,000 entrants.")
         elif contest_var1 == 'Large':
             Contest_Size = 10000
+            st.write("Large field size is 10,000 entrants.")
         elif contest_var1 == 'Custom':
-            Contest_Size = st.number_input("Insert contest size", value=100, placeholder="Type a number under 10,000...")
+            Contest_Size = st.number_input("Insert contest size", value=100, min_value=1, max_value=100000)
         strength_var1 = st.selectbox("How sharp is the field in the contest?", ('Very', 'Above Average', 'Average', 'Below Average', 'Not Very'))
         if strength_var1 == 'Not Very':
             sharp_split = 500000
@@ -288,11 +494,14 @@ with tab1:
             if 'working_seed' in st.session_state:
                 maps_dict = {
                         'Projection_map':dict(zip(raw_baselines.Player,raw_baselines.Median)),
+                        'cpt_projection_map':dict(zip(raw_baselines.Player,raw_baselines.cpt_Median)),
                         'Salary_map':dict(zip(raw_baselines.Player,raw_baselines.Salary)),
                         'Pos_map':dict(zip(raw_baselines.Player,raw_baselines.Position)),
                         'Own_map':dict(zip(raw_baselines.Player,raw_baselines['Own'])),
+                        'cpt_Own_map':dict(zip(raw_baselines.Player,raw_baselines['CPT_Own'])),
                         'Team_map':dict(zip(raw_baselines.Player,raw_baselines.Team)),
-                        'STDev_map':dict(zip(raw_baselines.Player,raw_baselines.STDev))
+                        'STDev_map':dict(zip(raw_baselines.Player,raw_baselines.STDev)),
+                        'cpt_STDev_map':dict(zip(raw_baselines.Player,raw_baselines['CPT_STDev']))
                         }
                 Sim_Winners = sim_contest(1000, st.session_state.working_seed, maps_dict, sharp_split, Contest_Size)
                 Sim_Winner_Frame = pd.DataFrame(np.concatenate(Sim_Winners))
@@ -306,7 +515,7 @@ with tab1:
                 Sim_Winner_Frame = Sim_Winner_Frame.assign(win_count=Sim_Winner_Frame['unique_id'].map(Sim_Winner_Frame['unique_id'].value_counts()))
                 
                 # Type Casting
-                type_cast_dict = {'salary': int, 'proj': np.float16, 'Fantasy': np.float16, 'GPP_Proj': np.float32}
+                type_cast_dict = {'salary': int, 'proj': np.float16, 'Fantasy': np.float16, 'GPP_Proj': np.float32, 'Own': np.float32}
                 Sim_Winner_Frame = Sim_Winner_Frame.astype(type_cast_dict)
                 
                 # Sorting
@@ -326,11 +535,14 @@ with tab1:
                     st.session_state.working_seed = FD_seed.copy()
                 maps_dict = {
                         'Projection_map':dict(zip(raw_baselines.Player,raw_baselines.Median)),
+                        'cpt_projection_map':dict(zip(raw_baselines.Player,raw_baselines.cpt_Median)),
                         'Salary_map':dict(zip(raw_baselines.Player,raw_baselines.Salary)),
                         'Pos_map':dict(zip(raw_baselines.Player,raw_baselines.Position)),
                         'Own_map':dict(zip(raw_baselines.Player,raw_baselines['Own'])),
+                        'cpt_Own_map':dict(zip(raw_baselines.Player,raw_baselines['CPT_Own'])),
                         'Team_map':dict(zip(raw_baselines.Player,raw_baselines.Team)),
-                        'STDev_map':dict(zip(raw_baselines.Player,raw_baselines.STDev))
+                        'STDev_map':dict(zip(raw_baselines.Player,raw_baselines.STDev)),
+                        'cpt_STDev_map':dict(zip(raw_baselines.Player,raw_baselines['CPT_STDev']))
                         }
                 Sim_Winners = sim_contest(1000, st.session_state.working_seed, maps_dict, sharp_split, Contest_Size)
                 Sim_Winner_Frame = pd.DataFrame(np.concatenate(Sim_Winners))
@@ -341,10 +553,86 @@ with tab1:
                 Sim_Winner_Frame = pd.DataFrame(np.concatenate(Sim_Winners), columns=column_names + ['Fantasy'])
                 Sim_Winner_Frame['GPP_Proj'] = (Sim_Winner_Frame['proj'] + Sim_Winner_Frame['Fantasy']) / 2
                 Sim_Winner_Frame['unique_id'] = Sim_Winner_Frame['proj'].astype(str) + Sim_Winner_Frame['salary'].astype(str) + Sim_Winner_Frame['Team'].astype(str) + Sim_Winner_Frame['Secondary'].astype(str)
+                # Add percent rank columns for ownership at each roster position
+                # Calculate Dupes column for Fanduel
+                if sim_site_var1 == 'Fanduel':
+                    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', 'avg_own_rank', 'dupes_calc']
+                    Sim_Winner_Frame['CPT_Own_percent_rank'] = Sim_Winner_Frame.iloc[:,0].map(maps_dict['cpt_Own_map']).rank(pct=True)
+                    Sim_Winner_Frame['FLEX1_Own_percent_rank'] = Sim_Winner_Frame.iloc[:,1].map(maps_dict['Own_map']).rank(pct=True)
+                    Sim_Winner_Frame['FLEX2_Own_percent_rank'] = Sim_Winner_Frame.iloc[:,2].map(maps_dict['Own_map']).rank(pct=True)
+                    Sim_Winner_Frame['FLEX3_Own_percent_rank'] = Sim_Winner_Frame.iloc[:,3].map(maps_dict['Own_map']).rank(pct=True)
+                    Sim_Winner_Frame['FLEX4_Own_percent_rank'] = Sim_Winner_Frame.iloc[:,4].map(maps_dict['Own_map']).rank(pct=True)
+                    Sim_Winner_Frame['CPT_Own'] = Sim_Winner_Frame.iloc[:,0].map(maps_dict['cpt_Own_map']) / 100
+                    Sim_Winner_Frame['FLEX1_Own'] = Sim_Winner_Frame.iloc[:,1].map(maps_dict['Own_map']) / 100
+                    Sim_Winner_Frame['FLEX2_Own'] = Sim_Winner_Frame.iloc[:,2].map(maps_dict['Own_map']) / 100
+                    Sim_Winner_Frame['FLEX3_Own'] = Sim_Winner_Frame.iloc[:,3].map(maps_dict['Own_map']) / 100
+                    Sim_Winner_Frame['FLEX4_Own'] = Sim_Winner_Frame.iloc[:,4].map(maps_dict['Own_map']) / 100
+                    
+                    # Calculate ownership product and convert to probability
+                    Sim_Winner_Frame['own_product'] = (Sim_Winner_Frame[own_columns].product(axis=1)) + 0.0001
+                    
+                    # Calculate average of ownership percent rank columns
+                    Sim_Winner_Frame['avg_own_rank'] = Sim_Winner_Frame[dup_count_columns].mean(axis=1)
+                    
+                    # Calculate dupes formula
+                    Sim_Winner_Frame['dupes_calc'] = ((Sim_Winner_Frame['own_product'] * Sim_Winner_Frame['avg_own_rank']) * (Contest_Size * 1.5)) + ((Sim_Winner_Frame['salary'] - 59800) / 100)
+                    
+                    # Round and handle negative values
+                    Sim_Winner_Frame['Dupes'] = np.where(
+                        np.round(Sim_Winner_Frame['dupes_calc'], 0) <= 0,
+                        0, 
+                        np.round(Sim_Winner_Frame['dupes_calc'], 0) - 1
+                    )
+                    Sim_Winner_Frame['Dupes'] = (Sim_Winner_Frame['Dupes'] * (500000 / sharp_split)) / 2
+                elif sim_site_var1 == 'Draftkings':
+                    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', 'avg_own_rank', 'dupes_calc']
+                    Sim_Winner_Frame['CPT_Own_percent_rank'] = Sim_Winner_Frame.iloc[:,0].map(maps_dict['cpt_Own_map']).rank(pct=True)
+                    Sim_Winner_Frame['FLEX1_Own_percent_rank'] = Sim_Winner_Frame.iloc[:,1].map(maps_dict['Own_map']).rank(pct=True)
+                    Sim_Winner_Frame['FLEX2_Own_percent_rank'] = Sim_Winner_Frame.iloc[:,2].map(maps_dict['Own_map']).rank(pct=True)
+                    Sim_Winner_Frame['FLEX3_Own_percent_rank'] = Sim_Winner_Frame.iloc[:,3].map(maps_dict['Own_map']).rank(pct=True)
+                    Sim_Winner_Frame['FLEX4_Own_percent_rank'] = Sim_Winner_Frame.iloc[:,4].map(maps_dict['Own_map']).rank(pct=True)
+                    Sim_Winner_Frame['FLEX5_Own_percent_rank'] = Sim_Winner_Frame.iloc[:,5].map(maps_dict['Own_map']).rank(pct=True)
+                    Sim_Winner_Frame['CPT_Own'] = Sim_Winner_Frame.iloc[:,0].map(maps_dict['cpt_Own_map']) / 100
+                    Sim_Winner_Frame['FLEX1_Own'] = Sim_Winner_Frame.iloc[:,1].map(maps_dict['Own_map']) / 100
+                    Sim_Winner_Frame['FLEX2_Own'] = Sim_Winner_Frame.iloc[:,2].map(maps_dict['Own_map']) / 100
+                    Sim_Winner_Frame['FLEX3_Own'] = Sim_Winner_Frame.iloc[:,3].map(maps_dict['Own_map']) / 100
+                    Sim_Winner_Frame['FLEX4_Own'] = Sim_Winner_Frame.iloc[:,4].map(maps_dict['Own_map']) / 100
+                    Sim_Winner_Frame['FLEX5_Own'] = Sim_Winner_Frame.iloc[:,5].map(maps_dict['Own_map']) / 100
+
+                    # Calculate ownership product and convert to probability
+                    Sim_Winner_Frame['own_product'] = (Sim_Winner_Frame[own_columns].product(axis=1))
+                    
+                    # Calculate average of ownership percent rank columns
+                    Sim_Winner_Frame['avg_own_rank'] = Sim_Winner_Frame[dup_count_columns].mean(axis=1)
+                    
+                    # Calculate dupes formula
+                    Sim_Winner_Frame['dupes_calc'] = ((Sim_Winner_Frame['own_product'] * Sim_Winner_Frame['avg_own_rank']) * (Contest_Size * 1.5)) + ((Sim_Winner_Frame['salary'] - 49800) / 100)
+                    
+                    # Round and handle negative values
+                    Sim_Winner_Frame['Dupes'] = np.where(
+                        np.round(Sim_Winner_Frame['dupes_calc'], 0) <= 0,
+                        0, 
+                        np.round(Sim_Winner_Frame['dupes_calc'], 0) - 1
+                    )
+                    Sim_Winner_Frame['Dupes'] = (Sim_Winner_Frame['Dupes'] * (500000 / sharp_split)) / 2
+                Sim_Winner_Frame['Dupes'] = np.round(Sim_Winner_Frame['Dupes'], 0)
+                Sim_Winner_Frame['Dupes'] = np.where(
+                        np.round(Sim_Winner_Frame['dupes_calc'], 0) <= 0,
+                        0, 
+                        np.round(Sim_Winner_Frame['dupes_calc'], 0)
+                    )
+                Sim_Winner_Frame = Sim_Winner_Frame.drop(columns=dup_count_columns)
+                Sim_Winner_Frame = Sim_Winner_Frame.drop(columns=own_columns)
+                Sim_Winner_Frame = Sim_Winner_Frame.drop(columns=calc_columns)
+
                 Sim_Winner_Frame = Sim_Winner_Frame.assign(win_count=Sim_Winner_Frame['unique_id'].map(Sim_Winner_Frame['unique_id'].value_counts()))
                 
                 # Type Casting
-                type_cast_dict = {'salary': int, 'proj': np.float16, 'Fantasy': np.float16, 'GPP_Proj': np.float32}
+                type_cast_dict = {'salary': int, 'proj': np.float16, 'Fantasy': np.float16, 'GPP_Proj': np.float32, 'Own': np.float32, 'Dupes': int}
                 Sim_Winner_Frame = Sim_Winner_Frame.astype(type_cast_dict)
                 
                 # Sorting
@@ -353,6 +641,7 @@ with tab1:
                 
                # Data Copying
                 st.session_state.Sim_Winner_Export = Sim_Winner_Frame.copy()
+                st.session_state.Sim_Winner_Export.iloc[:, 0:6] = st.session_state.Sim_Winner_Export.iloc[:, 0:6].apply(lambda x: x.map(export_id_dict))
                 
                 # Data Copying
                 st.session_state.Sim_Winner_Display = Sim_Winner_Frame.copy()
@@ -366,7 +655,13 @@ with tab1:
                                                 columns=['Player','Freq']).sort_values('Freq', ascending=False).reset_index(drop=True)
             freq_working['Freq'] = freq_working['Freq'].astype(int)
             freq_working['Position'] = freq_working['Player'].map(maps_dict['Pos_map'])
-            freq_working['Salary'] = freq_working['Player'].map(maps_dict['Salary_map']) / 1.5
+            if sim_site_var1 == 'Draftkings':
+                if sim_sport_var1 == 'NFL':
+                    freq_working['Salary'] = freq_working['Player'].map(maps_dict['Salary_map']) / 1.5
+                elif sim_sport_var1 == 'NBA':
+                    freq_working['Salary'] = freq_working['Player'].map(maps_dict['Salary_map'])
+            elif sim_site_var1 == 'Fanduel':
+                freq_working['Salary'] = freq_working['Player'].map(maps_dict['Salary_map'])
             freq_working['Proj Own'] = freq_working['Player'].map(maps_dict['Own_map']) / 100
             freq_working['Exposure'] = freq_working['Freq']/(1000)
             freq_working['Edge'] = freq_working['Exposure'] - freq_working['Proj Own']
@@ -381,8 +676,11 @@ with tab1:
                                                 columns=['Player','Freq']).sort_values('Freq', ascending=False).reset_index(drop=True)
             cpt_working['Freq'] = cpt_working['Freq'].astype(int)
             cpt_working['Position'] = cpt_working['Player'].map(maps_dict['Pos_map'])
-            cpt_working['Salary'] = cpt_working['Player'].map(maps_dict['Salary_map'])
-            cpt_working['Proj Own'] = cpt_working['Player'].map(maps_dict['Own_map']) / 400
+            if sim_sport_var1 == 'NFL':
+                cpt_working['Salary'] = cpt_working['Player'].map(maps_dict['Salary_map'])
+            elif sim_sport_var1 == 'NBA':
+                cpt_working['Salary'] = cpt_working['Player'].map(maps_dict['Salary_map']) * 1.5
+            cpt_working['Proj Own'] = cpt_working['Player'].map(maps_dict['cpt_Own_map']) / 100
             cpt_working['Exposure'] = cpt_working['Freq']/(1000)
             cpt_working['Edge'] = cpt_working['Exposure'] - cpt_working['Proj Own']
             cpt_working['Team'] = cpt_working['Player'].map(maps_dict['Team_map'])
@@ -391,13 +689,21 @@ with tab1:
             if sim_site_var1 == 'Draftkings':
                 flex_working = pd.DataFrame(np.column_stack(np.unique(freq_copy.iloc[:,1:6].values, return_counts=True)),
                                                 columns=['Player','Freq']).sort_values('Freq', ascending=False).reset_index(drop=True)
+                cpt_own_div = 600
             elif sim_site_var1 == 'Fanduel':
                 flex_working = pd.DataFrame(np.column_stack(np.unique(freq_copy.iloc[:,1:5].values, return_counts=True)),
                                                 columns=['Player','Freq']).sort_values('Freq', ascending=False).reset_index(drop=True)
+                cpt_own_div = 500
             flex_working['Freq'] = flex_working['Freq'].astype(int)
             flex_working['Position'] = flex_working['Player'].map(maps_dict['Pos_map'])
-            flex_working['Salary'] = flex_working['Player'].map(maps_dict['Salary_map'])
-            flex_working['Proj Own'] = (flex_working['Player'].map(maps_dict['Own_map']) / 100) - (flex_working['Player'].map(maps_dict['Own_map']) / 400)
+            if sim_site_var1 == 'Draftkings':
+                if sim_sport_var1 == 'NFL':
+                    flex_working['Salary'] = flex_working['Player'].map(maps_dict['Salary_map']) / 1.5
+                elif sim_sport_var1 == 'NBA':
+                    flex_working['Salary'] = flex_working['Player'].map(maps_dict['Salary_map'])
+            elif sim_site_var1 == 'Fanduel':
+                flex_working['Salary'] = flex_working['Player'].map(maps_dict['Salary_map'])
+            flex_working['Proj Own'] = (flex_working['Player'].map(maps_dict['Own_map']) / 100) - (flex_working['Player'].map(maps_dict['cpt_Own_map']) / 100)
             flex_working['Exposure'] = flex_working['Freq']/(1000)
             flex_working['Edge'] = flex_working['Exposure'] - flex_working['Proj Own']
             flex_working['Team'] = flex_working['Player'].map(maps_dict['Team_map'])
@@ -412,16 +718,6 @@ with tab1:
             team_working['Freq'] = team_working['Freq'].astype(int)
             team_working['Exposure'] = team_working['Freq']/(1000)
             st.session_state.team_freq = team_working.copy()
-
-            if sim_site_var1 == 'Draftkings':
-                stack_working = pd.DataFrame(np.column_stack(np.unique(freq_copy.iloc[:,10:11].values, return_counts=True)),
-                                                columns=['Player','Freq']).sort_values('Freq', ascending=False).reset_index(drop=True)
-            elif sim_site_var1 == 'Fanduel':
-                stack_working = pd.DataFrame(np.column_stack(np.unique(freq_copy.iloc[:,9:10].values, return_counts=True)),
-                                                columns=['Player','Freq']).sort_values('Freq', ascending=False).reset_index(drop=True)
-            stack_working['Freq'] = stack_working['Freq'].astype(int)
-            stack_working['Exposure'] = stack_working['Freq']/(1000)
-            st.session_state.stack_freq = stack_working.copy()
             
         with st.container():
             if st.button("Reset Sim", key='reset_sim'):