Refactor seed frame initialization in app.py to accept a 'sharp_split' parameter, allowing for dynamic data retrieval limits. Update related functions and session state handling to improve user input flexibility for DraftKings and FanDuel simulations.

app.py

@@ -55,52 +55,56 @@ dk_columns = ['QB', 'RB1', 'RB2', 'WR1', 'WR2', 'WR3', 'TE', 'FLEX', 'DST', 'sal
 fd_columns = ['QB', 'RB1', 'RB2', 'WR1', 'WR2', 'WR3', 'TE', 'FLEX', 'DST', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']
 
 @st.cache_data(ttl = 600)
-def init_DK_seed_frames():  
+def init_DK_seed_frames(sharp_split):  
     
     collection = db["DK_NFL_seed_frame"] 
-    cursor = collection.find()
+    cursor = collection.find().limit(sharp_split)
 
     raw_display = pd.DataFrame(list(cursor))
     raw_display = raw_display[['QB', 'RB1', 'RB2', 'WR1', 'WR2', 'WR3', 'TE', 'FLEX', 'DST', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
     DK_seed = raw_display.to_numpy()
+    fp_array = DK_seed[:sharp_split, :]
 
-    return DK_seed
+    return fp_array
 
 @st.cache_data(ttl = 600)
-def init_DK_Secondary_seed_frames():  
+def init_DK_Secondary_seed_frames(sharp_split):  
     
     collection = db["DK_NFL_Secondary_seed_frame"] 
-    cursor = collection.find()
+    cursor = collection.find().limit(sharp_split)
 
     raw_display = pd.DataFrame(list(cursor))
     raw_display = raw_display[['QB', 'RB1', 'RB2', 'WR1', 'WR2', 'WR3', 'TE', 'FLEX', 'DST', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
     DK_seed = raw_display.to_numpy()
+    fp_array = DK_seed[:sharp_split, :]
 
-    return DK_seed
+    return fp_array
 
 @st.cache_data(ttl = 599)
-def init_FD_seed_frames():  
+def init_FD_seed_frames(sharp_split):  
     
     collection = db["FD_NFL_seed_frame"] 
-    cursor = collection.find()
+    cursor = collection.find().limit(sharp_split)
 
     raw_display = pd.DataFrame(list(cursor))
     raw_display = raw_display[['QB', 'RB1', 'RB2', 'WR1', 'WR2', 'WR3', 'TE', 'FLEX', 'DST', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
     FD_seed = raw_display.to_numpy()
+    fp_array = FD_seed[:sharp_split, :]
 
-    return FD_seed
+    return fp_array
 
 @st.cache_data(ttl = 599)
-def init_FD_Secondary_seed_frames():  
+def init_FD_Secondary_seed_frames(sharp_split):  
     
     collection = db["FD_NFL_Secondary_seed_frame"] 
-    cursor = collection.find()
+    cursor = collection.find().limit(sharp_split)
 
     raw_display = pd.DataFrame(list(cursor))
     raw_display = raw_display[['QB', 'RB1', 'RB2', 'WR1', 'WR2', 'WR3', 'TE', 'FLEX', 'DST', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
     FD_seed = raw_display.to_numpy()
+    fp_array = FD_seed[:sharp_split, :]
 
-    return FD_seed
+    return fp_array
 
 @st.cache_data(ttl = 599)
 def init_baselines():
@@ -146,11 +150,10 @@ def calculate_FD_value_frequencies(np_array):
     return combined_array
 
 @st.cache_data
-def sim_contest(Sim_size, seed_frame, maps_dict, sharp_split, Contest_Size):
+def sim_contest(Sim_size, seed_frame, maps_dict, Contest_Size):
     SimVar = 1
     Sim_Winners = []
-    fp_array = seed_frame[:sharp_split, :]
-    
+    fp_array = seed_frame.copy()
     # Pre-vectorize functions
     vec_projection_map = np.vectorize(maps_dict['Projection_map'].__getitem__)
     vec_stdev_map = np.vectorize(maps_dict['STDev_map'].__getitem__)
@@ -189,22 +192,17 @@ 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_seed = init_DK_seed_frames(10000)
+              FD_seed = init_FD_seed_frames(10000)
               dk_raw, fd_raw = init_baselines()
               dk_id_dict = dict(zip(dk_raw.Player, dk_raw.player_id))
               fd_id_dict = dict(zip(fd_raw.Player, fd_raw.player_id))
               
         slate_var1 = st.radio("Which data are you loading?", ('Main Slate', 'Secondary Slate'))
         site_var1 = st.radio("What site are you working with?", ('Draftkings', 'Fanduel'))
+        sharp_split_var = st.number_input("How many lineups do you want?", value=10000, max_value=500000, min_value=10000, step=10000)
+        
         if site_var1 == 'Draftkings':
-            if slate_var1 == 'Main Slate':
-                DK_seed = init_DK_seed_frames()
-            elif slate_var1 == 'Secondary Slate':
-                DK_seed = init_DK_Secondary_seed_frames()
-                
-            raw_baselines = dk_raw
-            column_names = dk_columns
             
             team_var1 = st.radio("Do you want a frame with specific teams?", ('Full Slate', 'Specific Teams'), key='team_var1')
             if team_var1 == 'Specific Teams':
@@ -219,13 +217,6 @@ with tab2:
                     stack_var2 = [5, 4, 3, 2, 1, 0]
                     
         elif site_var1 == 'Fanduel':
-            if slate_var1 == 'Main Slate':
-                FD_seed = init_FD_seed_frames()
-            elif slate_var1 == 'Secondary Slate':
-                FD_seed = init_FD_Secondary_seed_frames()
-                
-            raw_baselines = fd_raw
-            column_names = fd_columns
             
             team_var1 = st.radio("Do you want a frame with specific teams?", ('Full Slate', 'Specific Teams'), key='team_var1')
             if team_var1 == 'Specific Teams':
@@ -245,7 +236,27 @@ with tab2:
                     st.session_state.working_seed = st.session_state.working_seed[np.isin(st.session_state.working_seed[:, 11], team_var2)]
                     st.session_state.working_seed = st.session_state.working_seed[np.isin(st.session_state.working_seed[:, 12], stack_var2)]
                 elif 'working_seed' not in st.session_state:
-                    st.session_state.working_seed = DK_seed.copy()
+                    if site_var1 == 'Draftkings':
+                        if slate_var1 == 'Main Slate':
+                            st.session_state.working_seed = init_DK_seed_frames(sharp_split_var)
+                            dk_id_dict = dict(zip(st.session_state.working_seed.Player, st.session_state.working_seed.player_id))
+                        elif slate_var1 == 'Secondary Slate':
+                            st.session_state.working_seed = init_DK_Secondary_seed_frames(sharp_split_var)
+                            dk_id_dict = dict(zip(st.session_state.working_seed.Player, st.session_state.working_seed.player_id))
+                            
+                        raw_baselines = dk_raw
+                        column_names = dk_columns
+                
+                    elif site_var1 == 'Fanduel':
+                        if slate_var1 == 'Main Slate':
+                            st.session_state.working_seed = init_FD_seed_frames(sharp_split_var)
+                            fd_id_dict = dict(zip(st.session_state.working_seed.Player, st.session_state.working_seed.player_id))
+                        elif slate_var1 == 'Secondary Slate':
+                            st.session_state.working_seed = init_FD_Secondary_seed_frames(sharp_split_var)
+                            fd_id_dict = dict(zip(st.session_state.working_seed.Player, st.session_state.working_seed.player_id))
+                            
+                        raw_baselines = fd_raw
+                        column_names = fd_columns
                     st.session_state.working_seed = st.session_state.working_seed[np.isin(st.session_state.working_seed[:, 11], team_var2)]
                     st.session_state.working_seed = st.session_state.working_seed[np.isin(st.session_state.working_seed[:, 12], stack_var2)]
                 data_export = st.session_state.working_seed.copy()
@@ -266,7 +277,16 @@ with tab2:
                     st.session_state.working_seed = st.session_state.working_seed[np.isin(st.session_state.working_seed[:, 12], stack_var2)]
                     st.session_state.data_export_display = pd.DataFrame(st.session_state.working_seed[0:1000], columns=column_names)
                 elif 'working_seed' not in st.session_state:
-                    st.session_state.working_seed = DK_seed.copy()
+                    if slate_var1 == 'Main Slate':
+                        st.session_state.working_seed = init_DK_seed_frames(sharp_split_var)
+                        dk_id_dict = dict(zip(st.session_state.working_seed.Player, st.session_state.working_seed.player_id))
+                    elif slate_var1 == 'Secondary Slate':
+                        st.session_state.working_seed = init_DK_Secondary_seed_frames(sharp_split_var)
+                        dk_id_dict = dict(zip(st.session_state.working_seed.Player, st.session_state.working_seed.player_id))
+                        
+                    raw_baselines = dk_raw
+                    column_names = dk_columns
+                
                     st.session_state.working_seed = st.session_state.working_seed[np.isin(st.session_state.working_seed[:, 11], team_var2)]
                     st.session_state.working_seed = st.session_state.working_seed[np.isin(st.session_state.working_seed[:, 12], stack_var2)]
                     st.session_state.data_export_display = pd.DataFrame(st.session_state.working_seed[0:1000], columns=column_names)
@@ -277,7 +297,15 @@ with tab2:
                     st.session_state.working_seed = st.session_state.working_seed[np.isin(st.session_state.working_seed[:, 12], stack_var2)]
                     st.session_state.data_export_display = pd.DataFrame(st.session_state.working_seed[0:1000], columns=column_names)
                 elif 'working_seed' not in st.session_state:
-                    st.session_state.working_seed = FD_seed.copy()
+                    if slate_var1 == 'Main Slate':
+                        st.session_state.working_seed = init_FD_seed_frames(sharp_split_var)
+                        fd_id_dict = dict(zip(st.session_state.working_seed.Player, st.session_state.working_seed.player_id))
+                    elif slate_var1 == 'Secondary Slate':
+                        st.session_state.working_seed = init_FD_Secondary_seed_frames(sharp_split_var)
+                        fd_id_dict = dict(zip(st.session_state.working_seed.Player, st.session_state.working_seed.player_id))
+                        
+                    raw_baselines = fd_raw
+                    column_names = fd_columns
                     st.session_state.working_seed = st.session_state.working_seed[np.isin(st.session_state.working_seed[:, 11], team_var2)]
                     st.session_state.working_seed = st.session_state.working_seed[np.isin(st.session_state.working_seed[:, 12], stack_var2)]
                     st.session_state.data_export_display = pd.DataFrame(st.session_state.working_seed[0:1000], columns=column_names)
@@ -293,30 +321,14 @@ 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_seed = init_DK_seed_frames(10000)
+              FD_seed = init_FD_seed_frames(10000)
               dk_raw, fd_raw = init_baselines()
               dk_id_dict = dict(zip(dk_raw.Player, dk_raw.player_id))
               fd_id_dict = dict(zip(fd_raw.Player, fd_raw.player_id))
 
         sim_slate_var1 = st.radio("Which data are you loading?", ('Main Slate', 'Secondary Slate'), 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 == 'Main Slate':
-                DK_seed = init_DK_seed_frames()
-            elif sim_slate_var1 == 'Secondary Slate':
-                DK_seed = init_DK_Secondary_seed_frames()
-                
-            raw_baselines = dk_raw
-            column_names = dk_columns
-        elif sim_site_var1 == 'Fanduel':
-            if sim_slate_var1 == 'Main Slate':
-                FD_seed = init_FD_seed_frames()
-            elif sim_slate_var1 == 'Secondary Slate':
-                FD_seed = init_FD_Secondary_seed_frames()
-                
-            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':
@@ -351,7 +363,7 @@ with tab1:
                         'Team_map':dict(zip(raw_baselines.Player,raw_baselines.Team)),
                         'STDev_map':dict(zip(raw_baselines.Player,raw_baselines.STDev))
                         }
-                Sim_Winners = sim_contest(1000, st.session_state.working_seed, st.session_state.maps_dict, sharp_split, Contest_Size)
+                Sim_Winners = sim_contest(1000, st.session_state.working_seed, st.session_state.maps_dict, Contest_Size)
                 Sim_Winner_Frame = pd.DataFrame(np.concatenate(Sim_Winners))
                 
                 #st.table(Sim_Winner_Frame)
@@ -378,9 +390,21 @@ with tab1:
                 
             else:
                 if sim_site_var1 == 'Draftkings':
-                    st.session_state.working_seed = DK_seed.copy()
+                    if sim_slate_var1 == 'Main Slate':
+                        st.session_state.working_seed = init_DK_seed_frames(sharp_split)
+                    elif sim_slate_var1 == 'Secondary Slate':
+                        st.session_state.working_seed = init_DK_Secondary_seed_frames(sharp_split)
+                        
+                    raw_baselines = dk_raw
+                    column_names = dk_columns
                 elif sim_site_var1 == 'Fanduel':
-                    st.session_state.working_seed = FD_seed.copy()
+                    if sim_slate_var1 == 'Main Slate':
+                        st.session_state.working_seed = init_FD_seed_frames(sharp_split)
+                    elif sim_slate_var1 == 'Secondary Slate':
+                        st.session_state.working_seed = init_FD_Secondary_seed_frames(sharp_split)
+                        
+                    raw_baselines = fd_raw
+                    column_names = fd_columns
                 st.session_state.maps_dict = {
                         'Projection_map':dict(zip(raw_baselines.Player,raw_baselines.Median)),
                         'Salary_map':dict(zip(raw_baselines.Player,raw_baselines.Salary)),
@@ -389,7 +413,7 @@ with tab1:
                         'Team_map':dict(zip(raw_baselines.Player,raw_baselines.Team)),
                         'STDev_map':dict(zip(raw_baselines.Player,raw_baselines.STDev))
                         }
-                Sim_Winners = sim_contest(1000, st.session_state.working_seed, st.session_state.maps_dict, sharp_split, Contest_Size)
+                Sim_Winners = sim_contest(1000, st.session_state.working_seed, st.session_state.maps_dict, Contest_Size)
                 Sim_Winner_Frame = pd.DataFrame(np.concatenate(Sim_Winners))
                 
                 #st.table(Sim_Winner_Frame)