Refactor salary and ID dictionary handling in app.py: update variable names for clarity and ensure consistent mapping for Draftkings and Fanduel exports, enhancing data accuracy during player data processing.

app.py

@@ -369,9 +369,12 @@ def convert_pm_df(array):
     return array.to_csv(index=False).encode('utf-8')
 
 dk_raw, fd_raw, dk_raw_sec, fd_raw_sec, roo_raw, sd_raw, dk_sd_raw, fd_sd_raw, timestamp = load_overall_stats('NBA')
-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))
+dk_salary_dict = dict(zip(dk_raw.Player, dk_raw.Salary))
+fd_salary_dict = dict(zip(fd_raw.Player, fd_raw.Salary))
+dk_id_dict = dict(zip(dk_raw.Player, dk_raw.player_ID))
+fd_id_dict = dict(zip(fd_raw.Player, fd_raw.player_ID))
+dk_salary_dict_sd = dict(zip(dk_sd_raw.Player, dk_sd_raw.Salary))
+fd_salary_dict_sd = dict(zip(fd_sd_raw.Player, fd_sd_raw.Salary))
 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))
 
@@ -399,9 +402,12 @@ with reset_col:
         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, dk_sd_raw, fd_sd_raw, timestamp = load_overall_stats('NBA')
-            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))
+            dk_salary_dict = dict(zip(dk_raw.Player, dk_raw.Salary))
+            fd_salary_dict = dict(zip(fd_raw.Player, fd_raw.Salary))
+            dk_id_dict = dict(zip(dk_raw.Player, dk_raw.player_ID))
+            fd_id_dict = dict(zip(fd_raw.Player, fd_raw.player_ID))
+            dk_salary_dict_sd = dict(zip(dk_sd_raw.Player, dk_sd_raw.Salary))
+            fd_salary_dict_sd = dict(zip(fd_sd_raw.Player, fd_sd_raw.Salary))
             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_nba_lineups = pd.DataFrame(columns=dk_nba_columns)
@@ -527,9 +533,12 @@ with tab2:
         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, dk_sd_raw, fd_sd_raw, timestamp = load_overall_stats('NBA')
-            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))
+            dk_salary_dict = dict(zip(dk_raw.Player, dk_raw.Salary))
+            fd_salary_dict = dict(zip(fd_raw.Player, fd_raw.Salary))
+            dk_id_dict = dict(zip(dk_raw.Player, dk_raw.player_ID))
+            fd_id_dict = dict(zip(fd_raw.Player, fd_raw.player_ID))
+            dk_salary_dict_sd = dict(zip(dk_sd_raw.Player, dk_sd_raw.Salary))
+            fd_salary_dict_sd = dict(zip(fd_sd_raw.Player, fd_sd_raw.Salary))
             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_nba_lineups = pd.DataFrame(columns=dk_nba_columns)
@@ -611,7 +620,7 @@ with tab2:
                         map_columns = ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5']
                     for col_idx in map_columns:
                         if slate_type_var1 == 'Regular':
-                            data_export[col_idx] = data_export[col_idx].map(id_dict)
+                            data_export[col_idx] = data_export[col_idx].map(dk_id_dict)
                         elif slate_type_var1 == 'Showdown':
                             data_export[col_idx] = data_export[col_idx].map(dk_id_dict_sd)
                 elif site_var2 == 'Fanduel':
@@ -624,7 +633,7 @@ with tab2:
                         map_columns = ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4']
                     for col_idx in map_columns:
                         if slate_type_var1 == 'Regular':
-                            data_export[col_idx] = data_export[col_idx].map(id_dict)
+                            data_export[col_idx] = data_export[col_idx].map(fd_id_dict)
                         elif slate_type_var1 == 'Showdown':
                             data_export[col_idx] = data_export[col_idx].map(fd_id_dict_sd)
 
@@ -670,6 +679,11 @@ with tab2:
                             map_columns = ['G1', 'G2', 'F1', 'F2', 'F3', 'UTIL']
                     elif slate_type_var1 == 'Showdown':
                         map_columns = ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5']
+                    for col_idx in map_columns:
+                        if slate_type_var1 == 'Regular':
+                            data_export[col_idx] = data_export[col_idx].map(dk_id_dict)
+                        elif slate_type_var1 == 'Showdown':
+                            data_export[col_idx] = data_export[col_idx].map(dk_id_dict_sd)
                 elif site_var2 == 'Fanduel':
                     if slate_type_var1 == 'Regular':
                         if league_var == 'NBA':
@@ -678,11 +692,11 @@ with tab2:
                             map_columns = ['G1', 'G2', 'G3', 'F1', 'F2', 'F3', 'F4']
                     elif slate_type_var1 == 'Showdown':
                         map_columns = ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4']
-                for col_idx in map_columns:
-                    if slate_type_var1 == 'Regular':
-                        data_export[col_idx] = data_export[col_idx].map(id_dict)
-                    elif slate_type_var1 == 'Showdown':
-                        data_export[col_idx] = data_export[col_idx].map(fd_id_dict_sd)
+                    for col_idx in map_columns:
+                        if slate_type_var1 == 'Regular':
+                            data_export[col_idx] = data_export[col_idx].map(fd_id_dict)
+                        elif slate_type_var1 == 'Showdown':
+                            data_export[col_idx] = data_export[col_idx].map(fd_id_dict_sd)
                 data_export = data_export[data_export['salary'] >= salary_min_var]
                 data_export = data_export[data_export['salary'] <= salary_max_var]
 
@@ -756,14 +770,14 @@ with tab2:
     if site_var2 == 'Draftkings':
         if slate_type_var1 == 'Regular':
             for col_idx in range(8):
-                export_file.iloc[:, col_idx] = export_file.iloc[:, col_idx].map(id_dict)
+                export_file.iloc[:, col_idx] = export_file.iloc[:, col_idx].map(dk_id_dict)
         elif slate_type_var1 == 'Showdown':
             for col_idx in range(6):
                 export_file.iloc[:, col_idx] = export_file.iloc[:, col_idx].map(dk_id_dict_sd)
     elif site_var2 == 'Fanduel':
         if slate_type_var1 == 'Regular':
             for col_idx in range(9):
-                export_file.iloc[:, col_idx] = export_file.iloc[:, col_idx].map(id_dict)
+                export_file.iloc[:, col_idx] = export_file.iloc[:, col_idx].map(fd_id_dict)
         elif slate_type_var1 == 'Showdown':
             for col_idx in range(6):
                 export_file.iloc[:, col_idx] = export_file.iloc[:, col_idx].map(fd_id_dict_sd)
@@ -1036,12 +1050,20 @@ with tab2:
                 percentages = (value_counts / lineup_num_var * 100).round(2)
                 
                 # Create a DataFrame with the results
-                summary_df = pd.DataFrame({
-                    'Player': value_counts.index,
-                    'Salary': [salary_dict.get(player, player) for player in value_counts.index],
-                    'Frequency': value_counts.values,
-                    'Percentage': percentages.values                        
-                })
+                if site_var2 == 'Draftkings':
+                    summary_df = pd.DataFrame({
+                        'Player': value_counts.index,
+                        'Salary': [dk_salary_dict.get(player, player) for player in value_counts.index],
+                            'Frequency': value_counts.values,
+                            'Percentage': percentages.values                        
+                        })
+                elif site_var2 == 'Fanduel':
+                    summary_df = pd.DataFrame({
+                        'Player': value_counts.index,
+                        'Salary': [fd_salary_dict.get(player, player) for player in value_counts.index],
+                        'Frequency': value_counts.values,
+                        'Percentage': percentages.values                        
+                    })
                 
                 # Sort by frequency in descending order
                 summary_df = summary_df.sort_values('Frequency', ascending=False)
@@ -1087,13 +1109,20 @@ with tab2:
                 
                 percentages = (value_counts / len(st.session_state.working_seed) * 100).round(2)
                 # Create a DataFrame with the results
-                summary_df = pd.DataFrame({
-                    'Player': value_counts.index,
-                    'Salary': [salary_dict.get(player, player) for player in value_counts.index],
-                    'Frequency': value_counts.values,
-                    'Percentage': percentages.values                        
-                })
-                
+                if site_var2 == 'Draftkings':
+                    summary_df = pd.DataFrame({
+                        'Player': value_counts.index,
+                        'Salary': [dk_salary_dict.get(player, player) for player in value_counts.index],
+                        'Frequency': value_counts.values,
+                        'Percentage': percentages.values                        
+                    })
+                elif site_var2 == 'Fanduel':
+                    summary_df = pd.DataFrame({
+                        'Player': value_counts.index,
+                        'Salary': [fd_salary_dict.get(player, player) for player in value_counts.index],
+                        'Frequency': value_counts.values,
+                        'Percentage': percentages.values                        
+                    })
                 # Sort by frequency in descending order
                 summary_df = summary_df.sort_values('Frequency', ascending=False)