iddaai-be/ai-engine/features/team_stats_engine.py

"""
Team Stats Engine
Takımların oyun tarzı istatistiklerini analiz eder.
football_team_stats tablosundaki kayıtlardan possession, şut, korner verilerini kullanır.
"""

import os
import sys
import psycopg2
from typing import Dict

sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from data.db import get_clean_dsn


class TeamStatsEngine:
    """
    Takım istatistikleri için feature engine.
    
    Analiz edilen metrikler:
    - Ortalama top hakimiyeti (possession)
    - Ortalama isabetli şut
    - Ortalama korner
    - Şut/Gol dönüşüm oranı (xG benzeri)
    - Savunma gücü
    """
    
    def __init__(self):
        self.conn = None
    
    def get_conn(self):
        if self.conn is None or self.conn.closed:
            self.conn = psycopg2.connect(get_clean_dsn())
        return self.conn
    
    def get_features(self, team_id: str, before_date: int,
                     limit: int = 10, max_days: int = 180) -> Dict[str, float]:
        """
        Takımın oyun tarzı feature'larını hesapla.
        
        Args:
            team_id: Takım ID
            before_date: Bu tarihten önceki maçlara bak (ms timestamp)
            limit: Kaç maç analiz edilecek
            max_days: Maksimum kaç gün geriye gidilecek
        
        Returns:
            Dict: Team stats feature'ları
        """
        if not team_id or len(team_id) < 5:
            return self._default_features()
        
        try:
            conn = self.get_conn()
            cur = conn.cursor()
            
            min_date = before_date - (max_days * 24 * 60 * 60 * 1000)
            
            # Bu takımın son N maçındaki istatistikleri çek
            cur.execute("""
                SELECT
                    mts.possession_percentage,
                    mts.shots_on_target,
                    mts.shots_off_target,
                    mts.total_shots,
                    mts.corners,
                    mts.fouls,
                    m.score_home,
                    m.score_away,
                    m.home_team_id
                FROM football_team_stats mts
                JOIN matches m ON mts.match_id = m.id
                WHERE mts.team_id = %s
                  AND m.mst_utc < %s
                  AND m.mst_utc > %s
                  AND m.score_home IS NOT NULL
                  AND m.sport = 'football'
                ORDER BY m.mst_utc DESC
                LIMIT %s
            """, (team_id, before_date, min_date, limit))
            
            stats = cur.fetchall()
            
            if not stats:
                return self._default_features()
            
            # İstatistikleri hesapla
            total_matches = len(stats)
            
            possession_sum = 0
            shots_on_target_sum = 0
            shots_total_sum = 0
            corners_sum = 0
            fouls_sum = 0
            goals_scored = 0
            valid_possession_count = 0
            
            for stat in stats:
                poss, sot, soff, total_shots, corners, fouls, sh, sa, home_id = stat
                
                if poss and poss > 0:
                    possession_sum += poss
                    valid_possession_count += 1
                
                if sot:
                    shots_on_target_sum += sot
                if total_shots:
                    shots_total_sum += total_shots
                if corners:
                    corners_sum += corners
                if fouls:
                    fouls_sum += fouls
                
                # Gol hesaplama
                is_home = (home_id == team_id)
                goals_scored += sh if is_home else sa
            
            avg_possession = possession_sum / valid_possession_count if valid_possession_count > 0 else 50.0
            avg_shots_on_target = shots_on_target_sum / total_matches if total_matches > 0 else 3.0
            avg_shots_total = shots_total_sum / total_matches if total_matches > 0 else 10.0
            avg_corners = corners_sum / total_matches if total_matches > 0 else 4.0
            avg_fouls = fouls_sum / total_matches if total_matches > 0 else 12.0
            
            # Shot conversion rate (xG benzeri)
            shot_conversion = goals_scored / shots_total_sum if shots_total_sum > 0 else 0.1
            
            # Shot accuracy
            shot_accuracy = shots_on_target_sum / shots_total_sum if shots_total_sum > 0 else 0.35
            
            return {
                'avg_possession': avg_possession / 100,  # Normalize to 0-1
                'avg_shots_on_target': avg_shots_on_target,
                'avg_shots_total': avg_shots_total,
                'avg_corners': avg_corners,
                'avg_fouls': avg_fouls,
                'shot_conversion_rate': shot_conversion,
                'shot_accuracy': shot_accuracy,
                'attacking_intensity': (avg_shots_total + avg_corners) / 2
            }
            
        except Exception as e:
            print(f"[TeamStatsEngine] Error: {e}")
            return self._default_features()
    
    def _default_features(self) -> Dict[str, float]:
        return {
            'avg_possession': 0.50,
            'avg_shots_on_target': 3.5,
            'avg_shots_total': 11.0,
            'avg_corners': 4.5,
            'avg_fouls': 12.0,
            'shot_conversion_rate': 0.10,
            'shot_accuracy': 0.35,
            'attacking_intensity': 7.5
        }


# Singleton
_engine = None

def get_team_stats_engine() -> TeamStatsEngine:
    global _engine
    if _engine is None:
        _engine = TeamStatsEngine()
    return _engine


if __name__ == "__main__":
    engine = get_team_stats_engine()
    
    print("\n🧪 Team Stats Engine Test")
    print("=" * 50)
    
    # Test için örnek takım ID'si al
    conn = engine.get_conn()
    cur = conn.cursor()
    cur.execute("""
        SELECT DISTINCT mts.team_id, t.name
        FROM match_team_stats mts
        JOIN teams t ON mts.team_id = t.id
        LIMIT 1
    """)
    result = cur.fetchone()
    
    if result:
        team_id, team_name = result
        print(f"Test Takımı: {team_name}")
        
        import time
        features = engine.get_features(team_id, int(time.time() * 1000))
        
        print(f"\n📊 Feature'lar:")
        for k, v in features.items():
            print(f"   {k}: {v:.3f}")