Refactor lineup initialization functions for DraftKings and FanDuel to include lineup number parameter, enhancing flexibility in data retrieval and processing for various slate types.

src/streamlit_app.py

@@ -219,15 +219,7 @@ def init_baselines():
     return player_stats, dk_stacks_raw, fd_stacks_raw, dk_roo_raw, fd_roo_raw, dk_sd_roo_raw, fd_sd_roo_raw, dk_id_map, fd_id_map, dk_sd_id_map, fd_sd_id_map
 
 @st.cache_resource(ttl = 60)
-def init_DK_lineups(type_var, slate_var, prio_var, prio_mix, db_translation):  
-
-    if type_var == 'Showdown':
-        collection = db[db_translation[slate_var]]
-        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']]
-        for column in ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5']:
-            raw_display[column] = raw_display[column].map(dict(zip(wrong_team_names, right_name_teams)), na_action='ignore').fillna(raw_display[column])
+def init_DK_lineups(type_var, slate_var, prio_var, prio_mix, db_translation, lineup_num):  
 
     if prio_var == 'Mix':
         prio_var = None
@@ -242,11 +234,11 @@ def init_DK_lineups(type_var, slate_var, prio_var, prio_mix, db_translation):
 
             collection = db['DK_NFL_seed_frame']
             if prio_var == None:
-                cursor1 = collection.find().limit(math.ceil(50000 * (prio_mix / 100)))
-                cursor2 = collection.find().sort('Own', -1).limit(math.ceil(50000 * ((100 - prio_mix) / 100)))
+                cursor1 = collection.find().limit(math.ceil(lineup_num * (prio_mix / 100)))
+                cursor2 = collection.find().sort('Own', -1).limit(math.ceil(lineup_num * ((100 - prio_mix) / 100)))
                 raw_display = pd.concat([pd.DataFrame(list(cursor1)), pd.DataFrame(list(cursor2))])
             else:
-                cursor = collection.find().sort(prio_var, -1).limit(50000)
+                cursor = collection.find().sort(prio_var, -1).limit(lineup_num)
                 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']]
@@ -262,11 +254,11 @@ def init_DK_lineups(type_var, slate_var, prio_var, prio_mix, db_translation):
             
             collection = db['DK_NFL_Secondary_seed_frame']
             if prio_var == None:
-                cursor1 = collection.find().limit(math.ceil(50000 * (prio_mix / 100)))
-                cursor2 = collection.find().sort('Own', -1).limit(math.ceil(50000 * ((100 - prio_mix) / 100)))
+                cursor1 = collection.find().limit(math.ceil(lineup_num * (prio_mix / 100)))
+                cursor2 = collection.find().sort('Own', -1).limit(math.ceil(lineup_num * ((100 - prio_mix) / 100)))
                 raw_display = pd.concat([pd.DataFrame(list(cursor1)), pd.DataFrame(list(cursor2))])
             else:
-                cursor = collection.find().sort(prio_var, -1).limit(50000)
+                cursor = collection.find().sort(prio_var, -1).limit(lineup_num)
                 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']]
@@ -282,11 +274,11 @@ def init_DK_lineups(type_var, slate_var, prio_var, prio_mix, db_translation):
             
             collection = db['DK_NFL_Late_seed_frame']
             if prio_var == None:
-                cursor1 = collection.find().limit(math.ceil(50000 * (prio_mix / 100)))
-                cursor2 = collection.find().sort('Own', -1).limit(math.ceil(50000 * ((100 - prio_mix) / 100)))
+                cursor1 = collection.find().limit(math.ceil(lineup_num * (prio_mix / 100)))
+                cursor2 = collection.find().sort('Own', -1).limit(math.ceil(lineup_num * ((100 - prio_mix) / 100)))
                 raw_display = pd.concat([pd.DataFrame(list(cursor1)), pd.DataFrame(list(cursor2))])
             else:
-                cursor = collection.find().sort(prio_var, -1).limit(50000)
+                cursor = collection.find().sort(prio_var, -1).limit(lineup_num)
                 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']]
@@ -294,60 +286,25 @@ def init_DK_lineups(type_var, slate_var, prio_var, prio_mix, db_translation):
             # Map names
             raw_display[dict_columns] = raw_display[dict_columns].apply(lambda x: x.map(names_dict))
     elif type_var == 'Showdown':
-        if slate_var == 'Main':
-            collection = db['DK_NFL_SD_seed_frame']
-            if prio_var == None:
-                cursor1 = collection.find().limit(math.ceil(50000 * (prio_mix / 100)))
-                cursor2 = collection.find().sort('Own', -1).limit(math.ceil(50000 * ((100 - prio_mix) / 100)))
-                raw_display = pd.concat([pd.DataFrame(list(cursor1)), pd.DataFrame(list(cursor2))])
-            else:
-                cursor = collection.find().sort(prio_var, -1).limit(50000)
-                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']]
-            for column in ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5']:
-                raw_display[column] = raw_display[column].map(dict(zip(wrong_team_names, right_name_teams)), na_action='ignore').fillna(raw_display[column])
-        elif slate_var == 'Secondary':
-            collection = db['DK_NFL_Secondary_SD_seed_frame']
-            if prio_var == None:
-                cursor1 = collection.find().limit(math.ceil(50000 * (prio_mix / 100)))
-                cursor2 = collection.find().sort('Own', -1).limit(math.ceil(50000 * ((100 - prio_mix) / 100)))
-                raw_display = pd.concat([pd.DataFrame(list(cursor1)), pd.DataFrame(list(cursor2))])
-            else:
-                cursor = collection.find().sort(prio_var, -1).limit(50000)
-                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']]
-            for column in ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5']:
-                raw_display[column] = raw_display[column].map(dict(zip(wrong_team_names, right_name_teams)), na_action='ignore').fillna(raw_display[column])
-        elif slate_var == 'Auxiliary':
-            collection = db['DK_NFL_Auxiliary_SD_seed_frame']
-            if prio_var == None:
-                cursor1 = collection.find().limit(math.ceil(50000 * (prio_mix / 100)))
-                cursor2 = collection.find().sort('Own', -1).limit(math.ceil(50000 * ((100 - prio_mix) / 100)))
-                raw_display = pd.concat([pd.DataFrame(list(cursor1)), pd.DataFrame(list(cursor2))])
-            else:
-                cursor = collection.find().sort(prio_var, -1).limit(50000)
-                raw_display = pd.DataFrame(list(cursor))
+        collection = db[db_translation[slate_var]]
+        if prio_var == None:
+            cursor1 = collection.find().limit(math.ceil(lineup_num * (prio_mix / 100)))
+            cursor2 = collection.find().sort('Own', -1).limit(math.ceil(lineup_num * ((100 - prio_mix) / 100)))
+            raw_display = pd.concat([pd.DataFrame(list(cursor1)), pd.DataFrame(list(cursor2))])
+        else:
+            cursor = collection.find().sort(prio_var, -1).limit(lineup_num)
+            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']]
-            for column in ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5']:
-                raw_display[column] = raw_display[column].map(dict(zip(wrong_team_names, right_name_teams)), na_action='ignore').fillna(raw_display[column])
+        raw_display = raw_display[['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
+        for column in ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5']:
+            raw_display[column] = raw_display[column].map(dict(zip(wrong_team_names, right_name_teams)), na_action='ignore').fillna(raw_display[column])
 
     DK_seed = raw_display.to_numpy()
 
     return DK_seed
 
 @st.cache_resource(ttl = 60)
-def init_FD_lineups(type_var, slate_var, prio_var, prio_mix, db_translation):
-
-    if type_var == 'Showdown':
-        collection = db[db_translation[slate_var]]
-        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']]
-        for column in ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5']:
-            raw_display[column] = raw_display[column].map(dict(zip(wrong_team_names, right_name_teams)), na_action='ignore').fillna(raw_display[column])
+def init_FD_lineups(type_var, slate_var, prio_var, prio_mix, db_translation, lineup_num):
 
     if prio_var == 'Mix':
         prio_var = None
@@ -363,11 +320,11 @@ def init_FD_lineups(type_var, slate_var, prio_var, prio_mix, db_translation):
 
             collection = db['FD_NFL_seed_frame']
             if prio_var == None:
-                cursor1 = collection.find().limit(math.ceil(50000 * (prio_mix / 100)))
-                cursor2 = collection.find().sort('Own', -1).limit(math.ceil(50000 * ((100 - prio_mix) / 100)))
+                cursor1 = collection.find().limit(math.ceil(lineup_num * (prio_mix / 100)))
+                cursor2 = collection.find().sort('Own', -1).limit(math.ceil(lineup_num * ((100 - prio_mix) / 100)))
                 raw_display = pd.concat([pd.DataFrame(list(cursor1)), pd.DataFrame(list(cursor2))])
             else:
-                cursor = collection.find().sort(prio_var, -1).limit(50000)
+                cursor = collection.find().sort(prio_var, -1).limit(lineup_num)
                 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']]
@@ -383,11 +340,11 @@ def init_FD_lineups(type_var, slate_var, prio_var, prio_mix, db_translation):
 
             collection = db['FD_NFL_Secondary_seed_frame']
             if prio_var == None:
-                cursor1 = collection.find().limit(math.ceil(50000 * (prio_mix / 100)))
-                cursor2 = collection.find().sort('Own', -1).limit(math.ceil(50000 * ((100 - prio_mix) / 100)))
+                cursor1 = collection.find().limit(math.ceil(lineup_num * (prio_mix / 100)))
+                cursor2 = collection.find().sort('Own', -1).limit(math.ceil(lineup_num * ((100 - prio_mix) / 100)))
                 raw_display = pd.concat([pd.DataFrame(list(cursor1)), pd.DataFrame(list(cursor2))])
             else:
-                cursor = collection.find().sort(prio_var, -1).limit(50000)
+                cursor = collection.find().sort(prio_var, -1).limit(lineup_num)
                 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']]
@@ -403,11 +360,11 @@ def init_FD_lineups(type_var, slate_var, prio_var, prio_mix, db_translation):
 
             collection = db['FD_NFL_Late_seed_frame']
             if prio_var == None:
-                cursor1 = collection.find().limit(math.ceil(50000 * (prio_mix / 100)))
-                cursor2 = collection.find().sort('Own', -1).limit(math.ceil(50000 * ((100 - prio_mix) / 100)))
+                cursor1 = collection.find().limit(math.ceil(lineup_num * (prio_mix / 100)))
+                cursor2 = collection.find().sort('Own', -1).limit(math.ceil(lineup_num * ((100 - prio_mix) / 100)))
                 raw_display = pd.concat([pd.DataFrame(list(cursor1)), pd.DataFrame(list(cursor2))])
             else:
-                cursor = collection.find().sort(prio_var, -1).limit(50000)
+                cursor = collection.find().sort(prio_var, -1).limit(lineup_num)
                 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']]
@@ -416,45 +373,18 @@ def init_FD_lineups(type_var, slate_var, prio_var, prio_mix, db_translation):
             raw_display[dict_columns] = raw_display[dict_columns].apply(lambda x: x.map(names_dict))
 
     elif type_var == 'Showdown':
-        if slate_var == 'Main':
-            collection = db['FD_NFL_SD_seed_frame']
-            if prio_var == None:
-                cursor1 = collection.find().limit(math.ceil(50000 * (prio_mix / 100)))
-                cursor2 = collection.find().sort('Own', -1).limit(math.ceil(50000 * ((100 - prio_mix) / 100)))
-                raw_display = pd.concat([pd.DataFrame(list(cursor1)), pd.DataFrame(list(cursor2))])
-            else:
-                cursor = collection.find().sort(prio_var, -1).limit(50000)
-                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']]
-            for column in ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5']:
-                raw_display[column] = raw_display[column].map(dict(zip(wrong_team_names, right_name_teams)), na_action='ignore').fillna(raw_display[column])
-        elif slate_var == 'Secondary':
-            collection = db['FD_NFL_Secondary_SD_seed_frame']
-            if prio_var == None:
-                cursor1 = collection.find().limit(math.ceil(50000 * (prio_mix / 100)))
-                cursor2 = collection.find().sort('Own', -1).limit(math.ceil(50000 * ((100 - prio_mix) / 100)))
-                raw_display = pd.concat([pd.DataFrame(list(cursor1)), pd.DataFrame(list(cursor2))])
-            else:
-                cursor = collection.find().sort(prio_var, -1).limit(50000)
-                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']]
-            for column in ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5']:
-                raw_display[column] = raw_display[column].map(dict(zip(wrong_team_names, right_name_teams)), na_action='ignore').fillna(raw_display[column])
-        elif slate_var == 'Auxiliary':
-            collection = db['FD_NFL_Auxiliary_SD_seed_frame']
-            if prio_var == None:
-                cursor1 = collection.find().limit(math.ceil(50000 * (prio_mix / 100)))
-                cursor2 = collection.find().sort('Own', -1).limit(math.ceil(50000 * ((100 - prio_mix) / 100)))
-                raw_display = pd.concat([pd.DataFrame(list(cursor1)), pd.DataFrame(list(cursor2))])
-            else:
-                cursor = collection.find().sort(prio_var, -1).limit(50000)
-                raw_display = pd.DataFrame(list(cursor))
+        collection = db[db_translation[slate_var]]
+        if prio_var == None:
+            cursor1 = collection.find().limit(math.ceil(lineup_num * (prio_mix / 100)))
+            cursor2 = collection.find().sort('Own', -1).limit(math.ceil(lineup_num * ((100 - prio_mix) / 100)))
+            raw_display = pd.concat([pd.DataFrame(list(cursor1)), pd.DataFrame(list(cursor2))])
+        else:
+            cursor = collection.find().sort(prio_var, -1).limit(lineup_num)
+            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']]
-            for column in ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5']:
-                raw_display[column] = raw_display[column].map(dict(zip(wrong_team_names, right_name_teams)), na_action='ignore').fillna(raw_display[column])
+        raw_display = raw_display[['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
+        for column in ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5']:
+            raw_display[column] = raw_display[column].map(dict(zip(wrong_team_names, right_name_teams)), na_action='ignore').fillna(raw_display[column])
 
     FD_seed = raw_display.to_numpy()
 
@@ -487,8 +417,8 @@ with app_load_reset_column:
     if st.button("Load/Reset Data", key='reset_data_button'):
         st.cache_data.clear()
         player_stats, dk_stacks_raw, fd_stacks_raw, dk_roo_raw, fd_roo_raw, dk_sd_roo_raw, fd_sd_roo_raw, dk_id_map, fd_id_map, dk_sd_id_map, fd_sd_id_map = init_baselines()
-        dk_lineups = init_DK_lineups('Regular', slate_names_dk[0], 'proj', 50, dk_showdown_db_translation)
-        fd_lineups = init_FD_lineups('Regular', slate_names_fd[0], 'proj', 50, fd_showdown_db_translation)
+        dk_lineups = init_DK_lineups('Regular', slate_names_dk[0], 'proj', 50, dk_showdown_db_translation, 25000)
+        fd_lineups = init_FD_lineups('Regular', slate_names_fd[0], 'proj', 50, fd_showdown_db_translation, 25000)
         for key in st.session_state.keys():
             del st.session_state[key]
 with app_view_site_column:
@@ -1089,6 +1019,7 @@ if selected_tab == 'Optimals':
         with prio_col:
             prio_var = st.radio("Which priority variable do you want to use?", ('proj', 'Own', 'Mix'), key='prio_var_radio')
             prio_mix = st.number_input("If Mix, what split of Projection/Ownership to dedicate to Projection?", min_value=0, max_value=100, value=50, step=1)
+            lineup_num = st.number_input("How many lineups do you want to work with?", min_value=1000, max_value=50000, value=25000, step=100, key='lineup_num_var_input')
         with optimals_site_col:
             slate_type_var3 = st.radio("Which slate type are you loading?", ('Regular', 'Showdown'), key='slate_type_var3_radio')
             if slate_type_var3 == 'Regular':
@@ -1104,14 +1035,14 @@ if selected_tab == 'Optimals':
             slate_var3 = st.radio("Which slate data are you loading?", (slate_names_dk if slate_type_var3 == 'Showdown' else ['Main', 'Secondary', 'Auxiliary']), key='slate_var3_radio')
             if slate_type_var3 == 'Regular':
                 if site_var == 'Draftkings':
-                    dk_lineups = init_DK_lineups(slate_type_var3, slate_var3, prio_var, prio_mix, dk_showdown_db_translation)
+                    dk_lineups = init_DK_lineups(slate_type_var3, slate_var3, prio_var, prio_mix, dk_showdown_db_translation, lineup_num)
                 elif site_var == 'Fanduel':
-                    fd_lineups = init_FD_lineups(slate_type_var3, slate_var3, prio_var, prio_mix, fd_showdown_db_translation)
+                    fd_lineups = init_FD_lineups(slate_type_var3, slate_var3, prio_var, prio_mix, fd_showdown_db_translation, lineup_num)
             elif slate_type_var3 == 'Showdown':
                 if site_var == 'Draftkings':
-                    dk_lineups = init_DK_lineups(slate_type_var3, slate_name_lookup_dk[slate_var3], prio_var, prio_mix, dk_showdown_db_translation)
+                    dk_lineups = init_DK_lineups(slate_type_var3, slate_name_lookup_dk[slate_var3], prio_var, prio_mix, dk_showdown_db_translation, lineup_num)
                 elif site_var == 'Fanduel':
-                    fd_lineups = init_FD_lineups(slate_type_var3, slate_name_lookup_fd[slate_var3], prio_var, prio_mix, fd_showdown_db_translation)
+                    fd_lineups = init_FD_lineups(slate_type_var3, slate_name_lookup_fd[slate_var3], prio_var, prio_mix, fd_showdown_db_translation, lineup_num)
         with optimals_macro_col:
             lineup_num_var = st.number_input("How many lineups do you want to display?", min_value=1, max_value=1000, value=150, step=1, key='lineup_num_var_input')
             player_var1 = st.radio("Do you want a frame with specific Players?", ('Full Slate', 'Specific Players'), key='player_var1_radio')