Refactor baseline initialization to include player ID mappings for Draftkings and Fanduel. Update scoring percentage calculations to incorporate team ownership data for hitters, and enhance data export functionality to allow for exporting both player IDs and names.

app.py

@@ -26,7 +26,6 @@ player_roo_format = {'Top_finish': '{:.2%}','Top_5_finish': '{:.2%}', 'Top_10_fi
 dk_columns = ['SP1', 'SP2', 'C', '1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']
 fd_columns = ['P', 'C_1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'UTIL', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']
 
-
 @st.cache_resource(ttl = 60)
 def init_baselines():
     collection = db["Player_Range_Of_Outcomes"] 
@@ -37,7 +36,9 @@ def init_baselines():
     roo_data['Salary'] = roo_data['Salary'].astype(int)
     
     dk_roo = roo_data[roo_data['Site'] == 'Draftkings']
+    dk_id_map = dict(zip(dk_roo['Player'], dk_roo['player_ID']))
     fd_roo = roo_data[roo_data['Site'] == 'Fanduel']
+    fd_id_map = dict(zip(fd_roo['Player'], fd_roo['player_ID']))
 
     collection = db["Player_SD_Range_Of_Outcomes"] 
     cursor = collection.find()
@@ -55,22 +56,8 @@ def init_baselines():
     scoring_percentages['8+ runs'] = scoring_percentages['8+ runs'].replace('%', '', regex=True).astype(float)
     scoring_percentages['Win Percentage'] = scoring_percentages['Win Percentage'].replace('%', '', regex=True).astype(float)
     scoring_percentages['Top Score'] = scoring_percentages['Top Score'].replace('', np.nan).astype(float)
-    dk_hitters_only = dk_roo[dk_roo['pos_group'] != 'Pitchers']
-    dk_hitters_only = dk_hitters_only.replace('CWS', 'CHW')
-    dk_team_ownership = dk_hitters_only.groupby('Team')['Own%'].sum().reset_index()
-    fd_hitters_only = fd_roo[fd_roo['pos_group'] != 'Pitchers']
-    fd_hitters_only = fd_hitters_only.replace('CWS', 'CHW')
-    fd_team_ownership = fd_hitters_only.groupby('Team')['Own%'].sum().reset_index()
-    scoring_percentages = scoring_percentages.merge(dk_team_ownership, left_on='Names', right_on='Team', how='left')
-    scoring_percentages.rename(columns={'Own%': 'DK Own%'}, inplace=True)
-    scoring_percentages.drop('Team', axis=1, inplace=True)
-    scoring_percentages = scoring_percentages.merge(fd_team_ownership, left_on='Names', right_on='Team', how='left')
-    scoring_percentages.rename(columns={'Own%': 'FD Own%'}, inplace=True)
-    scoring_percentages.drop('Team', axis=1, inplace=True)
-    scoring_percentages['DK LevX'] = scoring_percentages['Top Score'].rank(pct=True).astype(float) - scoring_percentages['DK Own%'].rank(pct=True).astype(float)
-    scoring_percentages['FD LevX'] = scoring_percentages['Top Score'].rank(pct=True).astype(float) - scoring_percentages['FD Own%'].rank(pct=True).astype(float)
     
-    return roo_data, sd_roo_data, scoring_percentages, dk_roo, fd_roo
+    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):  
@@ -226,7 +213,7 @@ col1, col2 = st.columns([1, 9])
 with col1:
     if st.button("Load/Reset Data", key='reset'):
         st.cache_data.clear()
-        roo_data, sd_roo_data, scoring_percentages, dk_roo, fd_roo = init_baselines()
+        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')
@@ -243,7 +230,7 @@ with col2:
 
 tab1, tab2, tab3 = st.tabs(["Scoring Percentages", "Player ROO", "Optimals"])
 
-roo_data, sd_roo_data, scoring_percentages, dk_roo, fd_roo = init_baselines()
+roo_data, sd_roo_data, scoring_percentages, dk_roo, fd_roo, dk_id_map, fd_id_map = init_baselines()
 hold_display = roo_data
 
 with tab1:
@@ -258,6 +245,23 @@ with tab1:
     elif slate_var1 != 'Main Slate':
         pass
 
+    dk_hitters_only = dk_roo[dk_roo['pos_group'] != 'Pitchers']
+    dk_hitters_only = dk_hitters_only[dk_hitters_only['Slate'] == 'main_slate']
+    dk_hitters_only = dk_hitters_only.replace('CWS', 'CHW')
+    dk_team_ownership = dk_hitters_only.groupby('Team')['Own%'].sum().reset_index()
+    fd_hitters_only = fd_roo[fd_roo['pos_group'] != 'Pitchers']
+    fd_hitters_only = fd_hitters_only[fd_hitters_only['Slate'] == 'main_slate']
+    fd_hitters_only = fd_hitters_only.replace('CWS', 'CHW')
+    fd_team_ownership = fd_hitters_only.groupby('Team')['Own%'].sum().reset_index()
+    scoring_percentages = scoring_percentages.merge(dk_team_ownership, left_on='Names', right_on='Team', how='left')
+    scoring_percentages.rename(columns={'Own%': 'DK Own%'}, inplace=True)
+    scoring_percentages.drop('Team', axis=1, inplace=True)
+    scoring_percentages = scoring_percentages.merge(fd_team_ownership, left_on='Names', right_on='Team', how='left')
+    scoring_percentages.rename(columns={'Own%': 'FD Own%'}, inplace=True)
+    scoring_percentages.drop('Team', axis=1, inplace=True)
+    scoring_percentages['DK LevX'] = scoring_percentages['Top Score'].rank(pct=True).astype(float) - scoring_percentages['DK Own%'].rank(pct=True).astype(float)
+    scoring_percentages['FD LevX'] = scoring_percentages['Top Score'].rank(pct=True).astype(float) - scoring_percentages['FD Own%'].rank(pct=True).astype(float)
+
     scoring_percentages = scoring_percentages.sort_values(by='8+ runs', ascending=False)
     scoring_percentages = scoring_percentages.drop('Slate', axis=1)
     
@@ -407,19 +411,28 @@ with tab3:
                     player_var2 = raw_baselines.Player.values.tolist()
 
         if st.button("Prepare data export", key='data_export'):
-            data_export = st.session_state.working_seed.copy()
-            # if site_var == 'Draftkings':
-            #     for col_idx in range(6):
-            #         data_export[:, col_idx] = np.array([id_dict.get(player, player) for player in data_export[:, col_idx]])
-            # elif site_var == 'Fanduel':
-            #     for col_idx in range(6):
-            #         data_export[:, col_idx] = np.array([id_dict.get(player, player) for player in data_export[:, col_idx]])
+            name_export = pd.DataFrame(st.session_state.working_seed.copy(), columns=column_names)
+            data_export = pd.DataFrame(st.session_state.working_seed.copy(), columns=column_names)
+            if site_var == 'Draftkings':
+                map_columns = ['SP1', 'SP2', 'C', '1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3']
+                for col_idx in map_columns:
+                    data_export[col_idx] = data_export[col_idx].map(dk_id_map)
+            elif site_var == 'Fanduel':
+                map_columns = ['P', 'C_1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'UTIL']
+                for col_idx in map_columns:
+                    data_export[col_idx] = data_export[col_idx].map(fd_id_map)
             st.download_button(
-                label="Export optimals set",
+                label="Export optimals set (IDs)",
                 data=convert_df(data_export),
                 file_name='MLB_optimals_export.csv',
                 mime='text/csv',
             )
+            st.download_button(
+                label="Export optimals set (Names)",
+                data=convert_df(name_export),
+                file_name='MLB_optimals_export.csv',
+                mime='text/csv',
+            )
         
     if site_var == 'Draftkings':
         if 'working_seed' in st.session_state:
@@ -456,12 +469,15 @@ with tab3:
             st.session_state.data_export_display = pd.DataFrame(st.session_state.working_seed[0:lineup_num_var], columns=column_names)
 
     export_file = st.session_state.data_export_display.copy()
-    # if site_var == 'Draftkings':
-    #     for col_idx in range(6):
-    #         export_file.iloc[:, col_idx] = export_file.iloc[:, col_idx].map(id_dict)
-    # elif site_var == 'Fanduel':
-    #     for col_idx in range(6):
-    #         export_file.iloc[:, col_idx] = export_file.iloc[:, col_idx].map(id_dict)
+    name_export = st.session_state.data_export_display.copy()
+    if site_var == 'Draftkings':
+        map_columns = ['SP1', 'SP2', 'C', '1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3']
+        for col_idx in map_columns:
+            export_file[col_idx] = export_file[col_idx].map(dk_id_map)
+    elif site_var == 'Fanduel':
+        map_columns = ['P', 'C_1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'UTIL']
+        for col_idx in map_columns:
+            export_file[col_idx] = export_file[col_idx].map(fd_id_map)
             
     with st.container():
         if st.button("Reset Optimals", key='reset3'):
@@ -474,11 +490,17 @@ with tab3:
         if 'data_export_display' in st.session_state:
             st.dataframe(st.session_state.data_export_display.style.background_gradient(axis=0).background_gradient(cmap='RdYlGn').format(precision=2), height=500, use_container_width = True)
         st.download_button(
-            label="Export display optimals",
+            label="Export display optimals (IDs)",
             data=convert_df(export_file),
             file_name='MLB_display_optimals.csv',
             mime='text/csv',
         )
+        st.download_button(
+            label="Export display optimals (Names)",
+            data=convert_df(name_export),
+            file_name='MLB_display_optimals.csv',
+            mime='text/csv',
+        )
     
     with st.container():
         if 'working_seed' in st.session_state: