diff --git a/database/L1A/L1A.sqlite b/database/L1A/L1A.sqlite
index d94fcbd..0f441f4 100644
Binary files a/database/L1A/L1A.sqlite and b/database/L1A/L1A.sqlite differ
diff --git a/database/L2/L2_Main.sqlite b/database/L2/L2_Main.sqlite
index c488c63..bb8414f 100644
Binary files a/database/L2/L2_Main.sqlite and b/database/L2/L2_Main.sqlite differ
diff --git a/database/L3/L3_Features.sqlite b/database/L3/L3_Features.sqlite
index 7b9b1f3..4f65b92 100644
Binary files a/database/L3/L3_Features.sqlite and b/database/L3/L3_Features.sqlite differ
diff --git a/web/services/feature_service.py b/web/services/feature_service.py
index e971083..a5114b3 100644
--- a/web/services/feature_service.py
+++ b/web/services/feature_service.py
@@ -1001,7 +1001,6 @@ class FeatureService:
                 WHERE match_id IN ({match_id_ph}) AND match_team_id > 0
                 GROUP BY match_id, match_team_id
                 """
-                # Split match_ids into chunks if too many
                 chunk_size = 900
                 party_sizes_list = []
                 for i in range(0, len(match_ids), chunk_size):
@@ -1012,44 +1011,40 @@ class FeatureService:
                 
                 if party_sizes_list:
                     df_party_sizes = pd.concat(party_sizes_list)
-                    
-                    # Merge party size to base data
                     df_base_party = df_base.merge(df_party_sizes, on=['match_id', 'match_team_id'], how='left')
-                    
-                    # Calculate Stats per Party Size (1-5)
-                    # We want columns like party_1_win_rate, party_1_rating, party_1_adr
-                    party_stats = df_base_party.groupby(['steam_id_64', 'party_size']).agg({
-                        'is_win': 'mean',
-                        'rating': 'mean',
-                        'adr': 'mean'
-                    }).reset_index()
-                    
-                    # Pivot
-                    pivoted_party = party_stats.pivot(index='steam_id_64', columns='party_size').reset_index()
-                    
-                    # Flatten and rename
-                    new_party_cols = ['steam_id_64']
-                    for col in pivoted_party.columns:
-                        if col[0] == 'steam_id_64': continue
-                        metric, size = col
-                        if size in [1, 2, 3, 4, 5]:
-                            # metric is is_win, rating, adr
-                            metric_name = 'win_rate' if metric == 'is_win' else metric
-                            new_party_cols.append(f"party_{int(size)}_{metric_name}")
-                    
-                    # Handle MultiIndex column flattening properly
-                    # The pivot creates MultiIndex. We need to construct a flat DataFrame.
-                    flat_data = {'steam_id_64': pivoted_party['steam_id_64']}
-                    for size in [1, 2, 3, 4, 5]:
-                        if size in pivoted_party['is_win'].columns:
-                            flat_data[f"party_{size}_win_rate"] = pivoted_party['is_win'][size]
-                        if size in pivoted_party['rating'].columns:
-                            flat_data[f"party_{size}_rating"] = pivoted_party['rating'][size]
-                        if size in pivoted_party['adr'].columns:
-                            flat_data[f"party_{size}_adr"] = pivoted_party['adr'][size]
-                    
-                    df_party_flat = pd.DataFrame(flat_data)
-                    df = df.merge(df_party_flat, on='steam_id_64', how='left')
+                else:
+                    df_base_party = df_base.copy()
+                
+                df_base_party['party_size'] = df_base_party['party_size'].fillna(1)
+                df_base_party = df_base_party[df_base_party['party_size'].isin([1, 2, 3, 4, 5])]
+                
+                party_stats = df_base_party.groupby(['steam_id_64', 'party_size']).agg({
+                    'is_win': 'mean',
+                    'rating': 'mean',
+                    'adr': 'mean'
+                }).reset_index()
+                
+                pivoted_party = party_stats.pivot(index='steam_id_64', columns='party_size').reset_index()
+                
+                new_party_cols = ['steam_id_64']
+                for col in pivoted_party.columns:
+                    if col[0] == 'steam_id_64': continue
+                    metric, size = col
+                    if size in [1, 2, 3, 4, 5]:
+                        metric_name = 'win_rate' if metric == 'is_win' else metric
+                        new_party_cols.append(f"party_{int(size)}_{metric_name}")
+                
+                flat_data = {'steam_id_64': pivoted_party['steam_id_64']}
+                for size in [1, 2, 3, 4, 5]:
+                    if size in pivoted_party['is_win'].columns:
+                        flat_data[f"party_{size}_win_rate"] = pivoted_party['is_win'][size]
+                    if size in pivoted_party['rating'].columns:
+                        flat_data[f"party_{size}_rating"] = pivoted_party['rating'][size]
+                    if size in pivoted_party['adr'].columns:
+                        flat_data[f"party_{size}_adr"] = pivoted_party['adr'][size]
+                
+                df_party_flat = pd.DataFrame(flat_data)
+                df = df.merge(df_party_flat, on='steam_id_64', how='left')
 
             # 8.2 Rating Distribution
             # rating_dist_carry_rate (>1.5), normal (1.0-1.5), sacrifice (0.6-1.0), sleeping (<0.6)