find duplicates and delete script

nba_data/management/commands/remove_duplicates_playoff_advanced.py

@@ -0,0 +1,27 @@
+from django.core.management.base import BaseCommand
+from nba_data.models import PlayerPlayoffAdvancedData
+
+
+class Command(BaseCommand):
+    help = 'Remove duplicate records for DAL and BOS in season 2010'
+
+    def handle(self, *args, **options):
+        season = 2010
+        teams = ['DAL', 'BOS']
+
+        for team in teams:
+            duplicates = PlayerPlayoffAdvancedData.objects.filter(season=season, team=team).order_by('player_name')
+
+            # Group records by name
+            players_grouped = {}
+            for duplicate in duplicates:
+                if duplicate.player_name not in players_grouped:
+                    players_grouped[duplicate.player_name] = []
+                players_grouped[duplicate.player_name].append(duplicate)
+
+            # Delete duplicates while keeping one record per player
+            for player_name, player_records in players_grouped.items():
+                if len(player_records) > 1:
+                    for player_record in player_records[1:]:
+                        player_record.delete()
+                        self.stdout.write(self.style.SUCCESS(f"Deleted duplicate {player_name} for {team} in season {season}"))

nba_data/nba_scraper_playoffs_advanced.py

@@ -27,7 +27,9 @@ from nba_data.models import PlayerPlayoffAdvancedData
 # Change LAC to SDC for 1984 and prior.
 
 
-teams = ['HOU' ,'PHI', 'BOS', 'NYK', 'BRK', 'TOR', 'MEM', 'NOP', 'DAL', 'SAS', 'DEN', 'MIN', 'OKC', 'UTA', 'POR', 'MIL', 'CLE', 'CHI', 'IND', 'DET', 'SAC', 'PHO', 'GSW', 'LAC', 'LAL', 'MIA', 'ATL', 'WAS', 'ORL', 'CHA']
+teams = ['HOU' ,'PHI', 'BOS', 'NYK', 'NJN', 'TOR', 'MEM', 'NOH', 'DAL', 'SAS', 'DEN', 'MIN', 'OKC', 'UTA', 'POR', 'MIL', 'CLE', 'CHI', 'IND', 'DET', 'SAC', 'PHO', 'GSW', 'LAC', 'LAL', 'MIA', 'ATL', 'WAS', 'ORL', 'CHA']
+
+teams2 = ['HOU' ,'PHI', 'NYK', 'NJN', 'TOR', 'MEM', 'NOH', 'SAS', 'DEN', 'MIN', 'OKC', 'UTA', 'POR', 'MIL', 'CLE', 'CHI', 'IND', 'DET', 'SAC', 'PHO', 'GSW', 'LAC', 'LAL', 'MIA', 'ATL', 'WAS', 'ORL', 'CHA']
 
 team_abbreviations = ['ATL', 'BOS', 'BRK', 'CHI', 'CHO', 'CLE', 'DAL', 'DEN', 'DET', 'GSW', 'HOU', 'IND', 'LAC', 'LAL', 'MEM', 'MIA', 'MIL', 'MIN', 'NOP', 'NYK', 'OKC', 'ORL', 'PHI', 'PHO', 'POR', 'SAC', 'SAS', 'TOR', 'UTA', 'WAS']