first (part 2: other directories)

scripts/data_health_check.py

@@ -0,0 +1,69 @@
+
+import os
+import psycopg2
+from psycopg2.extras import RealDictCursor
+
+def check_health():
+    try:
+        db_url = os.environ.get('DATABASE_URL', 'postgresql://suggestbet:SuGGesT2026SecuRe@localhost:15432/boilerplate_db')
+        conn = psycopg2.connect(db_url)
+        cursor = conn.cursor(cursor_factory=RealDictCursor)
+        
+        print("📊 Data Health Check Starting...\n")
+
+        # 1. Total Football Matches (Finished)
+        cursor.execute("SELECT COUNT(*) as count FROM matches WHERE sport='football' AND state='postGame'")
+        total_matches = cursor.fetchone()['count']
+        print(f"Total Finished Football Matches: {total_matches:,}")
+
+        if total_matches == 0:
+            return
+
+        # 2. Matches with Team Stats (Possession, Shots)
+        cursor.execute("""
+            SELECT COUNT(DISTINCT m.id) as count 
+            FROM matches m
+            JOIN match_team_stats s ON m.id = s.match_id
+            WHERE m.sport='football' AND m.state='postGame'
+        """)
+        stats_count = cursor.fetchone()['count']
+        print(f"Matches with Team Stats:       {stats_count:,} ({stats_count/total_matches*100:.1f}%)")
+
+        # 3. Matches with Player Events (Goals/Cards)
+        cursor.execute("""
+            SELECT COUNT(DISTINCT m.id) as count 
+            FROM matches m
+            JOIN match_player_events e ON m.id = e.match_id
+            WHERE m.sport='football' AND m.state='postGame'
+        """)
+        events_count = cursor.fetchone()['count']
+        print(f"Matches with Player Events:    {events_count:,} ({events_count/total_matches*100:.1f}%)")
+
+        # 4. Matches with Odds (1X2)
+        cursor.execute("""
+            SELECT COUNT(DISTINCT m.id) as count 
+            FROM matches m
+            JOIN odd_categories oc ON m.id = oc.match_id
+            WHERE m.sport='football' AND m.state='postGame'
+        """)
+        odds_count = cursor.fetchone()['count']
+        print(f"Matches with Odds Data:        {odds_count:,} ({odds_count/total_matches*100:.1f}%)")
+        
+        # 5. Full Data Set (Intersection)
+        cursor.execute("""
+            SELECT COUNT(DISTINCT m.id) as count 
+            FROM matches m
+            JOIN match_team_stats s ON m.id = s.match_id
+            JOIN match_player_events e ON m.id = e.match_id
+            JOIN odd_categories oc ON m.id = oc.match_id
+            WHERE m.sport='football' AND m.state='postGame'
+        """)
+        full_data_count = cursor.fetchone()['count']
+        print(f"\n✅ GOLDEN DATASET (All 3 present): {full_data_count:,} ({full_data_count/total_matches*100:.1f}%)")
+
+        conn.close()
+    except Exception as e:
+        print(f"Error: {e}")
+
+if __name__ == "__main__":
+    check_health()