Refactor app.py to enhance data handling and user input. Updated seed frame initialization to accept a dynamic lineup limit, improved data export functionality, and streamlined session state management for contest simulations. Removed unnecessary imports and optimized data retrieval processes.

app.py

@@ -2,9 +2,7 @@ import streamlit as st
 st.set_page_config(layout="wide")
 import numpy as np
 import pandas as pd
-import gspread
 import pymongo
-import time
 
 @st.cache_resource
 def init_conn():
@@ -23,10 +21,10 @@ dk_columns = ['C1', 'C2', 'W1', 'W2', 'W3', 'D1', 'D2', 'FLEX', 'G', 'salary', '
 fd_columns = ['C1', 'C2', 'W1', 'W2', 'D1', 'D2', 'FLEX1', 'FLEX2', 'G', '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_NHL_seed_frame"] 
-        cursor = collection.find()
+        cursor = collection.find().limit(sharp_split)
     
         raw_display = pd.DataFrame(list(cursor))
         raw_display = raw_display[['C1', 'C2', 'W1', 'W2', 'W3', 'D1', 'D2', 'FLEX', 'G', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
@@ -35,10 +33,10 @@ def init_DK_seed_frames():
         return DK_seed
 
 @st.cache_data(ttl = 599)
-def init_FD_seed_frames():  
+def init_FD_seed_frames(sharp_split):  
     
         collection = db["FD_NHL_seed_frame"] 
-        cursor = collection.find()
+        cursor = collection.find().limit(sharp_split)
     
         raw_display = pd.DataFrame(list(cursor))
         raw_display = raw_display[['C1', 'C2', 'W1', 'W2', 'D1', 'D2', 'FLEX1', 'FLEX2', 'G', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
@@ -87,11 +85,10 @@ 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__)
@@ -118,9 +115,9 @@ 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()
+dk_id_dict = dict(zip(dk_raw.Player, dk_raw.player_id))
+fd_id_dict = dict(zip(fd_raw.Player, fd_raw.player_id))
 
 tab1, tab2 = st.tabs(['Contest Sims', 'Data Export'])
 with tab2:
@@ -130,15 +127,17 @@ 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', 'Other Main 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':
-            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':
@@ -153,8 +152,6 @@ with tab2:
                     stack_var2 = [5, 4, 3, 2, 1, 0]
                     
         elif site_var1 == 'Fanduel':
-            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':
@@ -170,7 +167,30 @@ with tab2:
         
 
         if st.button("Prepare data export", key='data_export'):
+                if 'working_seed' in st.session_state:
+                    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:
+                    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))
+                            
+                        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))
+                            
+                        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()
+                for col in range(9):
+                    data_export[:, col] = np.array([dk_id_dict.get(x, x) for x in data_export[:, col]])
                 st.download_button(
                     label="Export optimals set",
                     data=convert_df(data_export),
@@ -186,7 +206,13 @@ 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))
+                        
+                    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)
@@ -197,7 +223,12 @@ 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))
+                        
+                    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)
@@ -213,17 +244,14 @@ 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', 'Other Main 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':
-            raw_baselines = dk_raw
-            column_names = dk_columns
-        elif sim_site_var1 == 'Fanduel':
-            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':
@@ -258,7 +286,7 @@ 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, 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)
@@ -285,10 +313,18 @@ 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)
+                        
+                    raw_baselines = dk_raw
+                    column_names = dk_columns
                 elif sim_site_var1 == 'Fanduel':
-                    st.session_state.working_seed = FD_seed.copy()
-                maps_dict = {
+                    if sim_slate_var1 == 'Main Slate':
+                        st.session_state.working_seed = init_FD_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)),
                         'Pos_map':dict(zip(raw_baselines.Player,raw_baselines.Position)),
@@ -296,7 +332,7 @@ 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, 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)
@@ -317,6 +353,8 @@ with tab1:
                 
                # Data Copying
                 st.session_state.Sim_Winner_Export = Sim_Winner_Frame.copy()
+                for col in st.session_state.Sim_Winner_Export.iloc[:, 0:9].columns:
+                    st.session_state.Sim_Winner_Export[col] = st.session_state.Sim_Winner_Export[col].map(dk_id_dict)
                 
                 # Data Copying
                 st.session_state.Sim_Winner_Display = Sim_Winner_Frame.copy()