aiming to fix missing players in mappings

app.py

@@ -666,6 +666,175 @@ def create_memory_efficient_mappings(projections_df, site_var, type_var, sport_v
     
     return base_mappings
 
+def create_comprehensive_mappings(projections_df, portfolio_df, csv_file, site_var, type_var, sport_var):
+    """Create mappings that include all portfolio players, using projections first and csv_file as fallback"""
+    
+    # Get all unique players from portfolio
+    portfolio_players = get_portfolio_names(portfolio_df)
+    
+    # Optimize projections data types first (existing logic)
+    projections_df = projections_df.copy()
+    if 'position' in projections_df.columns:
+        projections_df['position'] = projections_df['position'].astype('category')
+    if 'team' in projections_df.columns:
+        projections_df['team'] = projections_df['team'].astype('category')
+    if 'salary' in projections_df.columns:
+        projections_df['salary'] = projections_df['salary'].astype('int32')
+    if 'median' in projections_df.columns:
+        projections_df['median'] = projections_df['median'].astype('float32')
+    if 'ownership' in projections_df.columns:
+        projections_df['ownership'] = projections_df['ownership'].astype('float32')
+    if 'captain ownership' in projections_df.columns:
+        projections_df['captain ownership'] = projections_df['captain ownership'].astype('float32')
+    
+    # Create sets for efficient lookup
+    projection_players = set(projections_df['player_names'].tolist())
+    missing_players = set(portfolio_players) - projection_players
+    
+    # Prepare csv_file fallback data
+    csv_fallback = {}
+    if not missing_players:
+        # No missing players, use existing logic
+        return create_memory_efficient_mappings(projections_df, site_var, type_var, sport_var)
+    
+    # Create fallback mappings from csv_file for missing players
+    try:
+        csv_name_col = 'Name' if 'Name' in csv_file.columns else 'Nickname'
+        csv_salary_col = 'Salary'
+        csv_position_col = 'Position' if 'Position' in csv_file.columns else 'Roster Position'
+        csv_team_col = 'Team' if 'Team' in csv_file.columns else None
+        
+        # Create efficient lookup dictionaries from csv_file
+        csv_salary_map = dict(zip(csv_file[csv_name_col], csv_file[csv_salary_col]))
+        csv_position_map = dict(zip(csv_file[csv_name_col], csv_file[csv_position_col]))
+        csv_team_map = dict(zip(csv_file[csv_name_col], csv_file.get(csv_team_col, 'Unknown'))) if csv_team_col else {}
+        
+    except Exception as e:
+        st.warning(f"Could not create csv fallback mappings: {e}")
+        # Fall back to original function if csv_file structure is unexpected
+        return create_memory_efficient_mappings(projections_df, site_var, type_var, sport_var)
+    
+    # Start with projections-based mappings
+    base_mappings = {
+        'pos_map': dict(zip(projections_df['player_names'], projections_df['position'])),
+        'team_map': dict(zip(projections_df['player_names'], projections_df['team'])),
+        'salary_map': dict(zip(projections_df['player_names'], projections_df['salary'])),
+        'proj_map': dict(zip(projections_df['player_names'], projections_df['median'])),
+        'own_map': dict(zip(projections_df['player_names'], projections_df['ownership'])),
+        'own_percent_rank': dict(zip(projections_df['player_names'], projections_df['ownership'].rank(pct=True).astype('float32')))
+    }
+    
+    # Add missing players with csv_file data and 0 projections/ownership
+    for player in missing_players:
+        if player in csv_salary_map:
+            base_mappings['pos_map'][player] = csv_position_map.get(player, 'FLEX')
+            base_mappings['team_map'][player] = csv_team_map.get(player, 'Unknown') if csv_team_map else 'Unknown'
+            base_mappings['salary_map'][player] = csv_salary_map[player]
+            base_mappings['proj_map'][player] = 0.0  # No projection available
+            base_mappings['own_map'][player] = 0.0   # No ownership available
+            base_mappings['own_percent_rank'][player] = 0.0  # Lowest rank for missing players
+        else:
+            st.warning(f"Player '{player}' not found in projections or csv_file")
+            # Add with default values to prevent KeyError
+            base_mappings['pos_map'][player] = 'FLEX'
+            base_mappings['team_map'][player] = 'Unknown'
+            base_mappings['salary_map'][player] = 0
+            base_mappings['proj_map'][player] = 0.0
+            base_mappings['own_map'][player] = 0.0
+            base_mappings['own_percent_rank'][player] = 0.0
+    
+    # Add site/type specific mappings (existing logic)
+    if site_var == 'Draftkings':
+        if type_var == 'Classic':
+            if sport_var == 'CS2' or sport_var == 'LOL':
+                cpt_salary_map = dict(zip(projections_df['player_names'], projections_df['salary'] * 1.5))
+                cpt_proj_map = dict(zip(projections_df['player_names'], projections_df['median'] * 1.5))
+                cpt_own_map = dict(zip(projections_df['player_names'], projections_df['captain ownership']))
+                
+                # Add missing players to captain mappings
+                for player in missing_players:
+                    if player in csv_salary_map:
+                        cpt_salary_map[player] = csv_salary_map[player] * 1.5
+                        cpt_proj_map[player] = 0.0  # No captain projection
+                        cpt_own_map[player] = 0.0   # No captain ownership
+                
+                base_mappings.update({
+                    'cpt_salary_map': cpt_salary_map,
+                    'cpt_proj_map': cpt_proj_map,
+                    'cpt_own_map': cpt_own_map
+                })
+            else:
+                cpt_salary_map = dict(zip(projections_df['player_names'], projections_df['salary']))
+                cpt_proj_map = dict(zip(projections_df['player_names'], projections_df['median'] * 1.5))
+                cpt_own_map = dict(zip(projections_df['player_names'], projections_df['captain ownership']))
+                
+                # Add missing players to captain mappings
+                for player in missing_players:
+                    if player in csv_salary_map:
+                        cpt_salary_map[player] = csv_salary_map[player]
+                        cpt_proj_map[player] = 0.0
+                        cpt_own_map[player] = 0.0
+                
+                base_mappings.update({
+                    'cpt_salary_map': cpt_salary_map,
+                    'cpt_proj_map': cpt_proj_map,
+                    'cpt_own_map': cpt_own_map
+                })
+        elif type_var == 'Showdown':
+            if sport_var == 'GOLF':
+                cpt_salary_map = dict(zip(projections_df['player_names'], projections_df['salary']))
+                cpt_proj_map = dict(zip(projections_df['player_names'], projections_df['median']))
+                cpt_own_map = dict(zip(projections_df['player_names'], projections_df['ownership']))
+                
+                # Add missing players
+                for player in missing_players:
+                    if player in csv_salary_map:
+                        cpt_salary_map[player] = csv_salary_map[player]
+                        cpt_proj_map[player] = 0.0
+                        cpt_own_map[player] = 0.0
+                
+                base_mappings.update({
+                    'cpt_salary_map': cpt_salary_map,
+                    'cpt_proj_map': cpt_proj_map,
+                    'cpt_own_map': cpt_own_map
+                })
+            else:
+                cpt_salary_map = dict(zip(projections_df['player_names'], projections_df['salary'] * 1.5))
+                cpt_proj_map = dict(zip(projections_df['player_names'], projections_df['median'] * 1.5))
+                cpt_own_map = dict(zip(projections_df['player_names'], projections_df['captain ownership']))
+                
+                # Add missing players
+                for player in missing_players:
+                    if player in csv_salary_map:
+                        cpt_salary_map[player] = csv_salary_map[player] * 1.5
+                        cpt_proj_map[player] = 0.0
+                        cpt_own_map[player] = 0.0
+                
+                base_mappings.update({
+                    'cpt_salary_map': cpt_salary_map,
+                    'cpt_proj_map': cpt_proj_map,
+                    'cpt_own_map': cpt_own_map
+                })
+    elif site_var == 'Fanduel':
+        cpt_salary_map = dict(zip(projections_df['player_names'], projections_df['salary'] * 1.5))
+        cpt_proj_map = dict(zip(projections_df['player_names'], projections_df['median'] * 1.5))
+        cpt_own_map = dict(zip(projections_df['player_names'], projections_df['captain ownership']))
+        
+        # Add missing players
+        for player in missing_players:
+            if player in csv_salary_map:
+                cpt_salary_map[player] = csv_salary_map[player] * 1.5
+                cpt_proj_map[player] = 0.0
+                cpt_own_map[player] = 0.0
+        
+        base_mappings.update({
+            'cpt_salary_map': cpt_salary_map,
+            'cpt_proj_map': cpt_proj_map,
+            'cpt_own_map': cpt_own_map
+        })
+    
+    return base_mappings
+
 def calculate_salary_vectorized(df, player_columns, map_dict, type_var, sport_var):
     """Vectorized salary calculation to replace expensive apply operations"""
     def safe_map_and_fill(series, mapping, fill_value=0):
@@ -1471,7 +1640,14 @@ if selected_tab == 'Data Load':
             
             # Create memory-efficient mappings
             if 'map_dict' not in st.session_state:
-                st.session_state['map_dict'] = create_memory_efficient_mappings(st.session_state['projections_df'], site_var, type_var, sport_var)
+                st.session_state['map_dict'] = create_comprehensive_mappings(
+                    projections,
+                    st.session_state['portfolio'],
+                    st.session_state['csv_file'],
+                    site_var,
+                    type_var,
+                    sport_var
+                )
             
             # Store portfolio in compressed format and clean up
             st.session_state['portfolio'] = st.session_state['portfolio'].astype(str)