Enhance overall stats retrieval in app.py: add separate data frames for Draftkings and Fanduel to improve player ID mapping and streamline data handling during lineup processing.

app.py

@@ -113,6 +113,8 @@ def load_overall_stats():
     raw_display = raw_display.loc[raw_display['Median'] > 0]
     raw_display = raw_display.apply(pd.to_numeric, errors='ignore')
     sd_raw = raw_display.sort_values(by='Median', ascending=False)
+    dk_sd_raw = sd_raw[sd_raw['site'] == 'Draftkings']
+    fd_sd_raw = sd_raw[sd_raw['site'] == 'Fanduel']
 
     print(sd_raw.head(10))
 
@@ -128,7 +130,7 @@ def load_overall_stats():
 
     timestamp = raw_display['timestamp'].values[0]
     
-    return dk_raw, fd_raw, dk_raw_sec, fd_raw_sec, roo_raw, sd_raw, timestamp
+    return dk_raw, fd_raw, dk_raw_sec, fd_raw_sec, roo_raw, sd_raw, dk_sd_raw, fd_sd_raw, timestamp
 
 @st.cache_data(ttl = 60)
 def init_DK_lineups(slate_desig: str):  
@@ -248,11 +250,13 @@ def convert_df(array):
     array = pd.DataFrame(array, columns=column_names)
     return array.to_csv().encode('utf-8')
 
-dk_raw, fd_raw, dk_raw_sec, fd_raw_sec, roo_raw, sd_raw, timestamp = load_overall_stats()
+dk_raw, fd_raw, dk_raw_sec, fd_raw_sec, roo_raw, sd_raw, dk_sd_raw, fd_sd_raw, timestamp = load_overall_stats()
 salary_dict = dict(zip(roo_raw.Player, roo_raw.Salary))
 id_dict = dict(zip(roo_raw.Player, roo_raw.player_ID))
 salary_dict_sd = dict(zip(sd_raw.Player, sd_raw.Salary))
-id_dict_sd = dict(zip(sd_raw.Player, sd_raw.player_ID))
+dk_id_dict_sd = dict(zip(dk_sd_raw.Player, dk_sd_raw.player_ID))
+fd_id_dict_sd = dict(zip(fd_sd_raw.Player, fd_sd_raw.player_ID))
+
 dk_lineups = pd.DataFrame(columns=dk_columns)
 dk_sd_lineups = pd.DataFrame(columns=dk_sd_columns)
 fd_lineups = pd.DataFrame(columns=fd_columns)
@@ -274,11 +278,12 @@ with tab1:
             with col2:
                 if st.button("Load/Reset Data", key='reset1'):
                     st.cache_data.clear()
-                    dk_raw, fd_raw, dk_raw_sec, fd_raw_sec, roo_raw, sd_raw, timestamp = load_overall_stats()
+                    dk_raw, fd_raw, dk_raw_sec, fd_raw_sec, roo_raw, sd_raw, dk_sd_raw, fd_sd_raw, timestamp = load_overall_stats()
                     salary_dict = dict(zip(roo_raw.Player, roo_raw.Salary))
                     id_dict = dict(zip(roo_raw.Player, roo_raw.player_ID))
                     salary_dict_sd = dict(zip(sd_raw.Player, sd_raw.Salary))
-                    id_dict_sd = dict(zip(sd_raw.Player, sd_raw.player_ID))
+                    dk_id_dict_sd = dict(zip(dk_sd_raw.Player, dk_sd_raw.player_ID))
+                    fd_id_dict_sd = dict(zip(fd_sd_raw.Player, fd_sd_raw.player_ID))
                     dk_lineups = pd.DataFrame(columns=dk_columns)
                     dk_sd_lineups = pd.DataFrame(columns=dk_sd_columns)
                     fd_lineups = pd.DataFrame(columns=fd_columns)
@@ -371,11 +376,12 @@ with tab2:
     with st.expander("Info and Filters"):
         if st.button("Load/Reset Data", key='reset2'):
             st.cache_data.clear()
-            dk_raw, fd_raw, dk_raw_sec, fd_raw_sec, roo_raw, sd_raw, timestamp = load_overall_stats()
+            dk_raw, fd_raw, dk_raw_sec, fd_raw_sec, roo_raw, sd_raw, dk_sd_raw, fd_sd_raw, timestamp = load_overall_stats()
             salary_dict = dict(zip(roo_raw.Player, roo_raw.Salary))
             id_dict = dict(zip(roo_raw.Player, roo_raw.player_ID))
             salary_dict_sd = dict(zip(sd_raw.Player, sd_raw.Salary))
-            id_dict_sd = dict(zip(sd_raw.Player, sd_raw.player_ID))
+            dk_id_dict_sd = dict(zip(dk_sd_raw.Player, dk_sd_raw.player_ID))
+            fd_id_dict_sd = dict(zip(fd_sd_raw.Player, fd_sd_raw.player_ID))
             dk_lineups = pd.DataFrame(columns=dk_columns)
             dk_sd_lineups = pd.DataFrame(columns=dk_sd_columns)
             fd_lineups = pd.DataFrame(columns=fd_columns)
@@ -431,7 +437,7 @@ with tab2:
                     data_export = init_DK_SD_lineups(slate_var1)
                     data_export_names = data_export.copy()
                     for col_idx in range(6):
-                        data_export[:, col_idx] = np.array([id_dict_sd.get(player, player) for player in data_export[:, col_idx]])
+                        data_export[:, col_idx] = np.array([dk_id_dict_sd.get(player, player) for player in data_export[:, col_idx]])
                 
             elif site_var1 == 'Fanduel':
                 if slate_type_var1 == 'Regular':
@@ -443,7 +449,7 @@ with tab2:
                     data_export = init_FD_SD_lineups(slate_var1)
                     data_export_names = data_export.copy()
                     for col_idx in range(6):
-                        data_export[:, col_idx] = np.array([id_dict_sd.get(player, player) for player in data_export[:, col_idx]])
+                        data_export[:, col_idx] = np.array([fd_id_dict_sd.get(player, player) for player in data_export[:, col_idx]])
             st.download_button(
                 label="Export optimals (Names)",
                 data=convert_df(data_export_names),