first (part 2: other directories)

2026-04-16 15:11:25 +03:00
parent 7814e0bc6b
commit 2f0b85a0c7
203 changed files with 59989 additions and 0 deletions
@@ -0,0 +1,137 @@
+"""
+VQWEN Model Training Script (Optimized)
+========================================
+Fast, efficient, uses all 180k+ matches with rich features.
+"""
+
+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():
+    print("🧠 VQWEN MODEL EĞİTİMİ (OPTIMIZED)")
+    print("="*60)
+
+    dsn = get_clean_dsn()
+    conn = psycopg2.connect(dsn)
+    cur = conn.cursor()
+
+    # ─── 1. HIZLI VERİ ÇEKME (Optimized Query) ───
+    query = """
+        SELECT 
+            m.id, m.home_team_id, m.away_team_id, m.score_home, m.score_away,
+            -- 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 odds_h,
+            (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 odds_d,
+            (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 odds_a,
+            -- Form (Last 5)
+            COALESCE((SELECT AVG(CASE WHEN m2.home_team_id = m.home_team_id AND m2.score_home > m2.score_away THEN 3 WHEN m2.home_team_id = m.home_team_id AND m2.score_home = m2.score_away THEN 1 ELSE 0 END) FROM matches m2 WHERE m2.home_team_id = m.home_team_id AND m2.status = 'FT' AND m2.mst_utc < m.mst_utc LIMIT 5), 0) as home_form,
+            COALESCE((SELECT AVG(CASE WHEN m2.away_team_id = m.away_team_id AND m2.score_away > m2.score_home THEN 3 WHEN m2.away_team_id = m.away_team_id AND m2.score_away = m2.score_home THEN 1 ELSE 0 END) FROM matches m2 WHERE m2.away_team_id = m.away_team_id AND m2.status = 'FT' AND m2.mst_utc < m.mst_utc LIMIT 5), 0) as away_form,
+            -- Goal Averages
+            COALESCE((SELECT AVG(m2.score_home) FROM matches m2 WHERE m2.home_team_id = m.home_team_id AND m2.status = 'FT' LIMIT 10), 1.2) as h_avg_scored,
+            COALESCE((SELECT AVG(m2.score_away) FROM matches m2 WHERE m2.away_team_id = m.home_team_id AND m2.status = 'FT' LIMIT 10), 1.2) as h_avg_conceded,
+            COALESCE((SELECT AVG(m2.score_away) FROM matches m2 WHERE m2.away_team_id = m.away_team_id AND m2.status = 'FT' LIMIT 10), 1.2) as a_avg_scored,
+            COALESCE((SELECT AVG(m2.score_home) FROM matches m2 WHERE m2.home_team_id = m.away_team_id AND m2.status = 'FT' LIMIT 10), 1.2) as a_avg_conceded,
+            -- Team Stats
+            COALESCE(ts_home.possession_percentage, 50) as h_poss,
+            COALESCE(ts_home.shots_on_target, 4) as h_sot,
+            COALESCE(ts_home.corners, 5) as h_corners,
+            COALESCE(ts_away.possession_percentage, 50) as a_poss,
+            COALESCE(ts_away.shots_on_target, 3) as a_sot,
+            COALESCE(ts_away.corners, 4) as a_corners
+        FROM matches m
+        LEFT JOIN football_team_stats ts_home ON ts_home.match_id = m.id AND ts_home.team_id = m.home_team_id
+        LEFT JOIN football_team_stats ts_away ON ts_away.match_id = m.id AND ts_away.team_id = m.away_team_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 200000
+    """
+    
+    print("📊 Veritabanından özellikler çekiliyor (Limit 200k)...")
+    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', 'oh', 'od', 'oa', 
+        'h_form', 'a_form', 'h_sc', 'h_co', 'a_sc', 'a_co',
+        'h_poss', 'h_sot', 'h_corn', 'a_poss', 'a_sot', 'a_corn'
+    ])
+
+    for col in df.columns[5:]:
+        df[col] = pd.to_numeric(df[col], errors='coerce')
+    df = df.fillna(df.median(numeric_only=True))
+
+    # ─── 2. ÖZELLİK MÜHENDİSLİĞİ ───
+    df['h_xg'] = (df['h_sc'] + df['a_co']) / 2
+    df['a_xg'] = (df['a_sc'] + df['h_co']) / 2
+    df['total_xg'] = df['h_xg'] + df['a_xg']
+    
+    df['h_pow'] = (df['h_form']*10) + (df['h_sc']*5) - (df['h_co']*5) + (df['h_sot']*2)
+    df['a_pow'] = (df['a_form']*10) + (df['a_sc']*5) - (df['a_co']*5) + (df['a_sot']*2)
+    df['pow_diff'] = df['h_pow'] - df['a_pow']
+    
+    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
+
+    # Targets
+    df['t_ms'] = df.apply(lambda r: 0 if r['sh']>r['sa'] else (2 if r['sh']<r['sa'] else 1), axis=1)
+    df['t_ou'] = ((df['sh'] + df['sa']) > 2.5).astype(int)
+    df['t_btts'] = ((df['sh'] > 0) & (df['sa'] > 0)).astype(int)
+
+    # ─── 3. MODELLER ───
+    feats_ms = ['h_form', 'a_form', 'h_xg', 'a_xg', 'pow_diff', 'imp_h', 'imp_d', 'imp_a', 'h_sot', 'a_sot']
+    X_ms, y_ms = df[feats_ms], 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)
+    print("🤖 MS Modeli eğitiliyor...")
+    model_ms = lgb.train({'objective': 'multiclass', 'num_class': 3, 'metric': 'multi_logloss', '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)])
+
+    feats_ou = ['h_xg', 'a_xg', 'total_xg', 'h_sot', 'a_sot']
+    print("🤖 OU2.5 Modeli...")
+    model_ou = lgb.train({'objective': 'binary', 'metric': 'binary_logloss', 'verbose': -1}, 
+                         lgb.Dataset(df[feats_ou], df['t_ou']), num_boost_round=500)
+
+    feats_btts = ['h_xg', 'a_xg', 'h_sc', 'a_sc']
+    print("🤖 BTTS Modeli...")
+    model_btts = lgb.train({'objective': 'binary', 'metric': 'binary_logloss', 'verbose': -1}, 
+                           lgb.Dataset(df[feats_btts], 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"✅ {p} kaydedildi.")
+
+    cur.close()
+    conn.close()
+    print("\n🎉 VQWEN EĞİTİMİ BİTTİ!")
+
+if __name__ == "__main__":
+    train_vqwen()