Enhance lineup initialization functions by adding priority variable and mix options for Draftkings and Fanduel. Update UI to include controls for selecting priority variable and mix percentage, improving lineup customization capabilities.

app.py

@@ -3,6 +3,7 @@ import numpy as np
 import pandas as pd
 import pymongo
 import re
+import math
 
 st.set_page_config(layout="wide")
 
@@ -136,8 +137,11 @@ def init_baselines():
     return roo_data, sd_roo_data, scoring_percentages, dk_roo, fd_roo, dk_id_map, fd_id_map
 
 @st.cache_data(ttl = 60)
-def init_DK_lineups(type_var, slate_var):  
-    
+def init_DK_lineups(type_var, slate_var, prio_var, prio_mix):
+
+    if prio_var == 'Mix':
+        prio_var = None
+
     if type_var == 'Regular':
         if slate_var == 'Main':
             collection = db['DK_MLB_name_map']
@@ -146,9 +150,14 @@ def init_DK_lineups(type_var, slate_var):
             names_dict = dict(zip(raw_data['key'], raw_data['value']))
 
             collection = db['DK_MLB_seed_frame']
-            cursor = collection.find().limit(10000)
+            if prio_var == None:
+                cursor1 = collection.find().limit(math.ceil(10000 * (prio_mix / 100)))
+                cursor2 = collection.find().sort('Own', -1).limit(math.ceil(10000 * ((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(10000)
+                raw_display = pd.DataFrame(list(cursor))
 
-            raw_display = pd.DataFrame(list(cursor))
             raw_display = raw_display[['SP1', 'SP2', 'C', '1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
             dict_columns = ['SP1', 'SP2', 'C', '1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3']
             # Map names
@@ -160,9 +169,14 @@ def init_DK_lineups(type_var, slate_var):
             names_dict = dict(zip(raw_data['key'], raw_data['value']))
             
             collection = db['DK_MLB_Secondary_seed_frame']
-            cursor = collection.find().limit(10000)
+            if prio_var == None:
+                cursor1 = collection.find().limit(math.ceil(10000 * (prio_mix / 100)))
+                cursor2 = collection.find().sort('Own', -1).limit(math.ceil(10000 * ((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(10000)
+                raw_display = pd.DataFrame(list(cursor))
 
-            raw_display = pd.DataFrame(list(cursor))
             raw_display = raw_display[['SP1', 'SP2', 'C', '1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
             dict_columns = ['SP1', 'SP2', 'C', '1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3']
             # Map names
@@ -174,9 +188,14 @@ def init_DK_lineups(type_var, slate_var):
             names_dict = dict(zip(raw_data['key'], raw_data['value']))
             
             collection = db['DK_MLB_Turbo_seed_frame']
-            cursor = collection.find().limit(10000)
-
-            raw_display = pd.DataFrame(list(cursor))
+            if prio_var == None:
+                cursor1 = collection.find().limit(math.ceil(10000 * (prio_mix / 100)))
+                cursor2 = collection.find().sort('Own', -1).limit(math.ceil(10000 * ((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(10000)
+                raw_display = pd.DataFrame(list(cursor))
+            
             raw_display = raw_display[['SP1', 'SP2', 'C', '1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
             dict_columns = ['SP1', 'SP2', 'C', '1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3']
             # Map names
@@ -184,21 +203,36 @@ def init_DK_lineups(type_var, slate_var):
     elif type_var == 'Showdown':
         if slate_var == 'Main':
             collection = db['DK_MLB_SD1_seed_frame']
-            cursor = collection.find().limit(10000)
-
-            raw_display = pd.DataFrame(list(cursor))
+            if prio_var == None:
+                cursor1 = collection.find().limit(math.ceil(10000 * (prio_mix / 100)))
+                cursor2 = collection.find().sort('Own', -1).limit(math.ceil(10000 * ((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(10000)
+                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']]
         elif slate_var == 'Secondary':
             collection = db['DK_MLB_SD2_seed_frame']
-            cursor = collection.find().limit(10000)
-
-            raw_display = pd.DataFrame(list(cursor))
+            if prio_var == None:
+                cursor1 = collection.find().limit(math.ceil(10000 * (prio_mix / 100)))
+                cursor2 = collection.find().sort('Own', -1).limit(math.ceil(10000 * ((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(10000)
+                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']]
         elif slate_var == 'Auxiliary':
             collection = db['DK_MLB_SD3_seed_frame']
-            cursor = collection.find().limit(10000)
-
-            raw_display = pd.DataFrame(list(cursor))
+            if prio_var == None:
+                cursor1 = collection.find().limit(math.ceil(10000 * (prio_mix / 100)))
+                cursor2 = collection.find().sort('Own', -1).limit(math.ceil(10000 * ((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(10000)
+                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_seed = raw_display.to_numpy()
@@ -206,7 +240,7 @@ def init_DK_lineups(type_var, slate_var):
     return DK_seed
 
 @st.cache_data(ttl = 60)
-def init_FD_lineups(type_var,slate_var):  
+def init_FD_lineups(type_var,slate_var, prio_var, prio_mix):  
         
         if type_var == 'Regular':
             if slate_var == 'Main':
@@ -216,9 +250,14 @@ def init_FD_lineups(type_var,slate_var):
                 names_dict = dict(zip(raw_data['key'], raw_data['value']))
 
                 collection = db['FD_MLB_seed_frame']
-                cursor = collection.find().limit(10000)
-
-                raw_display = pd.DataFrame(list(cursor))
+                if prio_var == None:
+                    cursor1 = collection.find().limit(math.ceil(10000 * (prio_mix / 100)))
+                    cursor2 = collection.find().sort('Own', -1).limit(math.ceil(10000 * ((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(10000)
+                    raw_display = pd.DataFrame(list(cursor))
+                
                 raw_display = raw_display[['P', 'C_1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'UTIL', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
                 dict_columns = ['P', 'C_1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'UTIL']
                 # Map names
@@ -230,9 +269,14 @@ def init_FD_lineups(type_var,slate_var):
                 names_dict = dict(zip(raw_data['key'], raw_data['value']))
 
                 collection = db['FD_MLB_Secondary_seed_frame']
-                cursor = collection.find().limit(10000)
-
-                raw_display = pd.DataFrame(list(cursor))
+                if prio_var == None:
+                    cursor1 = collection.find().limit(math.ceil(10000 * (prio_mix / 100)))
+                    cursor2 = collection.find().sort('Own', -1).limit(math.ceil(10000 * ((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(10000)
+                    raw_display = pd.DataFrame(list(cursor))
+                
                 raw_display = raw_display[['P', 'C_1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'UTIL', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
                 dict_columns = ['P', 'C_1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'UTIL']
                 # Map names
@@ -244,9 +288,14 @@ def init_FD_lineups(type_var,slate_var):
                 names_dict = dict(zip(raw_data['key'], raw_data['value']))
 
                 collection = db['FD_MLB_Turbo_seed_frame']
-                cursor = collection.find().limit(10000)
-            
-                raw_display = pd.DataFrame(list(cursor))
+                if prio_var == None:
+                    cursor1 = collection.find().limit(math.ceil(10000 * (prio_mix / 100)))
+                    cursor2 = collection.find().sort('Own', -1).limit(math.ceil(10000 * ((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(10000)
+                    raw_display = pd.DataFrame(list(cursor))
+                
                 raw_display = raw_display[['P', 'C_1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'UTIL', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
                 dict_columns = ['P', 'C_1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'UTIL']
                 # Map names
@@ -255,21 +304,36 @@ def init_FD_lineups(type_var,slate_var):
         elif type_var == 'Showdown':
             if slate_var == 'Main':
                 collection = db['FD_MLB_SD1_seed_frame']
-                cursor = collection.find().limit(10000)
-
-                raw_display = pd.DataFrame(list(cursor))
+                if prio_var == None:
+                    cursor1 = collection.find().limit(math.ceil(10000 * (prio_mix / 100)))
+                    cursor2 = collection.find().sort('Own', -1).limit(math.ceil(10000 * ((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(10000)
+                    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']]
             elif slate_var == 'Secondary':
                 collection = db['FD_MLB_SD2_seed_frame']
-                cursor = collection.find().limit(10000)
-
-                raw_display = pd.DataFrame(list(cursor))
+                if prio_var == None:
+                    cursor1 = collection.find().limit(math.ceil(10000 * (prio_mix / 100)))
+                    cursor2 = collection.find().sort('Own', -1).limit(math.ceil(10000 * ((100 - prio_mix) / 100)))
+                    cursor = pd.concat([cursor1, cursor2])
+                else:
+                    cursor = collection.find().sort(prio_var, -1).limit(10000)
+                    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']]
             elif slate_var == 'Auxiliary':
                 collection = db['FD_MLB_SD3_seed_frame']
-                cursor = collection.find().limit(10000)
-            
-                raw_display = pd.DataFrame(list(cursor))
+                if prio_var == None:
+                    cursor1 = collection.find().limit(math.ceil(10000 * (prio_mix / 100)))
+                    cursor2 = collection.find().sort('Own', -1).limit(math.ceil(10000 * ((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(10000)
+                    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']]
     
         FD_seed = raw_display.to_numpy()
@@ -301,8 +365,8 @@ with col1:
         st.cache_data.clear()
         roo_data, sd_roo_data, scoring_percentages, dk_roo, fd_roo, dk_id_map, fd_id_map = init_baselines()
         hold_display = roo_data
-        dk_lineups = init_DK_lineups('Regular', 'Main')
-        fd_lineups = init_FD_lineups('Regular', 'Main')
+        dk_lineups = init_DK_lineups('Regular', 'Main', 'proj')
+        fd_lineups = init_FD_lineups('Regular', 'Main', 'proj')
         for key in st.session_state.keys():
             del st.session_state[key]
 with col2:
@@ -551,8 +615,11 @@ if selected_tab == "Optimals":
     st.header("Optimals")
     with st.expander("Info and Filters"):
         st.info("These filters will display various optimals in the table below to pick from. If you want to export the entire set of 10,000 optimals, hit the 'Prepare full data export' button. If you would like to apply the filters here to the 10,000 optimals before you export, use the 'Prepare full data export (Filter)' button.")
-        col1, col2, col3, col4 = st.columns(4)
+        col1, col2, col3, col4, col5 = st.columns(5)
         with col1:
+            prio_var = st.radio("Which priority variable do you want to use?", ('proj', 'Own', 'Mix'), key='prio_var')
+            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)
+        with col2:
             slate_type_var3 = st.radio("Which slate type are you loading?", ('Regular', 'Showdown'), key='slate_type_var3')
             if slate_type_var3 == 'Regular':
                 raw_baselines = roo_data
@@ -561,22 +628,22 @@ if selected_tab == "Optimals":
             slate_var3 = st.radio("Which slate data are you loading?", ('Main', 'Secondary', 'Auxiliary'), key='slate_var3')
             if slate_type_var3 == 'Regular':
                 if site_var == 'Draftkings':
-                    dk_lineups = init_DK_lineups(slate_type_var3, slate_var3)
+                    dk_lineups = init_DK_lineups(slate_type_var3, slate_var3, prio_var, prio_mix)
                 elif site_var == 'Fanduel':
-                    fd_lineups = init_FD_lineups(slate_type_var3, slate_var3)
+                    fd_lineups = init_FD_lineups(slate_type_var3, slate_var3, prio_var, prio_mix)
             elif slate_type_var3 == 'Showdown':
                 if site_var == 'Draftkings':
-                    dk_lineups = init_DK_lineups(slate_type_var3, slate_var3)
+                    dk_lineups = init_DK_lineups(slate_type_var3, slate_var3, prio_var, prio_mix)
                 elif site_var == 'Fanduel':
-                    fd_lineups = init_FD_lineups(slate_type_var3, slate_var3)
-        with col2:
+                    fd_lineups = init_FD_lineups(slate_type_var3, slate_var3, prio_var, prio_mix)
+        with col3:
             lineup_num_var = st.number_input("How many lineups do you want to display?", min_value=1, max_value=1000, value=150, step=1)
             player_var1 = st.radio("Do you want a frame with specific Players?", ('Full Slate', 'Specific Players'), key='player_var1')
             if player_var1 == 'Specific Players':
                 player_var2 = st.multiselect('Which players do you want?', options = raw_baselines['Player'].unique())
             elif player_var1 == 'Full Slate':
                     player_var2 = raw_baselines.Player.values.tolist()
-        with col3:
+        with col4:
             if site_var == 'Draftkings':
                 salary_min_var = st.number_input("Minimum salary used", min_value = 0, max_value = 50000, value = 49000, step = 100, key = 'salary_min_var')
                 salary_max_var = st.number_input("Maximum salary used", min_value = 0, max_value = 50000, value = 50000, step = 100, key = 'salary_max_var')
@@ -587,7 +654,7 @@ if selected_tab == "Optimals":
                 elif slate_type_var3 == 'Showdown':
                     salary_min_var = st.number_input("Minimum salary used", min_value = 0, max_value = 60000, value = 59000, step = 100, key = 'salary_min_var')
                     salary_max_var = st.number_input("Maximum salary used", min_value = 0, max_value = 60000, value = 60000, step = 100, key = 'salary_max_var')
-        with col4:
+        with col5:
             if site_var == 'Draftkings':
                 min_stacks_var = st.number_input("Minimum stacks used", min_value = 0, max_value = 5, value = 3, step = 1, key = 'min_stacks_var')
                 max_stacks_var = st.number_input("Maximum stacks used", min_value = 0, max_value = 5, value = 5, step = 1, key = 'max_stacks_var')