""" VQWEN Deep Model Training Script (Final Version) ================================================ Includes: ELO, Contextual Goals, Rest Days, Player Participation. """ import os import sys import json import time import pickle import psycopg2 import pandas as pd import numpy as np from sklearn.model_selection import train_test_split import lightgbm as lgb AI_DIR = os.path.dirname(os.path.abspath(__file__)) ROOT_DIR = os.path.dirname(AI_DIR) sys.path.insert(0, ROOT_DIR) def get_clean_dsn() -> str: return "postgresql://suggestbet:SuGGesT2026SecuRe@localhost:15432/boilerplate_db" def train_vqwen_deep(): print("🧠 VQWEN DEEP MODEL EĞİTİMİ (ELO + REST + CONTEXT)") print("="*60) dsn = get_clean_dsn() conn = psycopg2.connect(dsn) cur = conn.cursor() # ─── 1. GELİŞMİŞ VERİ SORGUSU ─── # ELO, Dinlenme Süresi, İç Saha/Deplasman Performansı query = """ SELECT m.id, m.home_team_id, m.away_team_id, m.score_home, m.score_away, m.mst_utc, -- ELO Ratings COALESCE(maf.home_elo, 1500) as home_elo, COALESCE(maf.away_elo, 1500) as away_elo, -- Contextual Goals (Home Team at Home, Away Team Away) COALESCE((SELECT AVG(m2.score_home) FROM matches m2 WHERE m2.home_team_id = m.home_team_id AND m2.status = 'FT' AND m2.mst_utc < m.mst_utc), 1.2) as h_home_goals, COALESCE((SELECT AVG(m2.score_away) FROM matches m2 WHERE m2.away_team_id = m.away_team_id AND m2.status = 'FT' AND m2.mst_utc < m.mst_utc), 1.2) as a_away_goals, -- Rest Days (Yorgunluk) COALESCE(EXTRACT(EPOCH FROM (to_timestamp(m.mst_utc/1000) - (SELECT MAX(to_timestamp(m2.mst_utc/1000)) FROM matches m2 WHERE m2.home_team_id = m.home_team_id AND m2.status = 'FT' AND m2.mst_utc < m.mst_utc)) / 86400), 7) as h_rest, COALESCE(EXTRACT(EPOCH FROM (to_timestamp(m.mst_utc/1000) - (SELECT MAX(to_timestamp(m2.mst_utc/1000)) FROM matches m2 WHERE m2.away_team_id = m.away_team_id AND m2.status = 'FT' AND m2.mst_utc < m.mst_utc)) / 86400), 7) as a_rest, -- Squad Participation COALESCE((SELECT COUNT(*) FROM match_player_participation mp WHERE mp.match_id = m.id AND mp.team_id = m.home_team_id AND mp.is_starting = true), 11) as h_xi, COALESCE((SELECT COUNT(*) FROM match_player_participation mp WHERE mp.match_id = m.id AND mp.team_id = m.away_team_id AND mp.is_starting = true), 11) as a_xi, -- Cards COALESCE((SELECT COUNT(*) FROM match_player_events mpe WHERE mpe.match_id = m.id AND mpe.event_type = 'card'), 4) as cards, -- Odds (SELECT os.odd_value FROM odd_categories oc JOIN odd_selections os ON os.odd_category_db_id = oc.db_id WHERE oc.match_id = m.id AND oc.name ILIKE 'Maç Sonucu' AND os.name = '1' LIMIT 1) as oh, (SELECT os.odd_value FROM odd_categories oc JOIN odd_selections os ON os.odd_category_db_id = oc.db_id WHERE oc.match_id = m.id AND oc.name ILIKE 'Maç Sonucu' AND os.name = 'X' LIMIT 1) as od, (SELECT os.odd_value FROM odd_categories oc JOIN odd_selections os ON os.odd_category_db_id = oc.db_id WHERE oc.match_id = m.id AND oc.name ILIKE 'Maç Sonucu' AND os.name = '2' LIMIT 1) as oa FROM matches m LEFT JOIN football_ai_features maf ON maf.match_id = m.id WHERE m.status = 'FT' AND m.score_home IS NOT NULL AND m.sport = 'football' AND EXISTS (SELECT 1 FROM odd_categories oc WHERE oc.match_id = m.id) ORDER BY m.mst_utc DESC LIMIT 150000 """ print("📊 Veri çekiliyor...") start = time.time() cur.execute(query) rows = cur.fetchall() print(f"✅ {len(rows)} maç çekildi ({time.time()-start:.1f}s)") df = pd.DataFrame(rows, columns=[ 'id', 'h_id', 'a_id', 'sh', 'sa', 'utc', 'h_elo', 'a_elo', 'h_home_goals', 'a_away_goals', 'h_rest', 'a_rest', 'h_xi', 'a_xi', 'cards', 'oh', 'od', 'oa' ]) # Temizlik for col in df.columns[2:]: df[col] = pd.to_numeric(df[col], errors='coerce') df = df.fillna(df.median(numeric_only=True)) df = df[(df['oh'] > 1.0) & (df['oa'] > 1.0)] # ─── 2. ÖZELLİK MÜHENDİSLİĞİ ─── # 1. ELO Farkı df['elo_diff'] = df['h_elo'] - df['a_elo'] # 2. Yorgunluk Faktörü (Dinlenme < 3 günse performans düşer) # xG hesaplamasında kullanacağız def fatigue_factor(rest): if rest < 3: return 0.85 if rest < 5: return 0.95 return 1.0 df['h_fatigue'] = df['h_rest'].apply(fatigue_factor) df['a_fatigue'] = df['a_rest'].apply(fatigue_factor) # 3. xG (Contextual Goals * Fatigue) df['h_xg'] = df['h_home_goals'] * df['h_fatigue'] df['a_xg'] = df['a_away_goals'] * df['a_fatigue'] df['total_xg'] = df['h_xg'] + df['a_xg'] df['rest_diff'] = df['h_rest'] - df['a_rest'] # 4. Form (ELO bazlı power rating) df['h_pow'] = (df['h_elo'] / 100) * df['h_fatigue'] df['a_pow'] = (df['a_elo'] / 100) * df['a_fatigue'] df['pow_diff'] = df['h_pow'] - df['a_pow'] # Oranlar margin = (1/df['oh']) + (1/df['od']) + (1/df['oa']) df['imp_h'] = (1/df['oh']) / margin df['imp_d'] = (1/df['od']) / margin df['imp_a'] = (1/df['oa']) / margin # Hedefler df['t_ms'] = df.apply(lambda r: 0 if r['sh']>r['sa'] else (2 if r['sh'] 2.5).astype(int) df['t_btts'] = ((df['sh'] > 0) & (df['sa'] > 0)).astype(int) # ─── 3. MODEL EĞİTİMİ ─── # Yeni Özellik Seti feats = ['elo_diff', 'h_xg', 'a_xg', 'total_xg', 'pow_diff', 'rest_diff', 'h_fatigue', 'a_fatigue', 'imp_h', 'imp_d', 'imp_a', 'h_xi', 'a_xi', 'cards'] # MS print("🤖 MS...") X_ms, y_ms = df[feats], df['t_ms'] X_tr, X_te, y_tr, y_te = train_test_split(X_ms, y_ms, test_size=0.15, random_state=42) model_ms = lgb.train({'objective': 'multiclass', 'num_class': 3, 'verbose': -1, 'num_leaves': 63}, lgb.Dataset(X_tr, y_tr), num_boost_round=1000, valid_sets=[lgb.Dataset(X_te, y_te)], callbacks=[lgb.early_stopping(50)]) # OU2.5 print("🤖 OU2.5...") model_ou = lgb.train({'objective': 'binary', 'verbose': -1}, lgb.Dataset(df[feats], df['t_ou']), num_boost_round=500) # BTTS print("🤖 BTTS...") model_btts = lgb.train({'objective': 'binary', 'verbose': -1}, lgb.Dataset(df[feats], df['t_btts']), num_boost_round=500) # ─── 4. KAYDET ─── mdir = os.path.join(ROOT_DIR, 'models', 'vqwen') os.makedirs(mdir, exist_ok=True) for nm, md in [('ms', model_ms), ('ou25', model_ou), ('btts', model_btts)]: p = os.path.join(mdir, f'vqwen_{nm}.pkl') with open(p, 'wb') as f: pickle.dump(md, f) print(f"✅ vqwen_{nm}.pkl") print("\n🎉 VQWEN DEEP EĞİTİMİ BİTTİ!") cur.close() conn.close() if __name__ == "__main__": train_vqwen_deep()