main

ai-engine/models/v25_ensemble.py

@@ -20,6 +20,13 @@ from dataclasses import dataclass, field
 import xgboost as xgb
 import lightgbm as lgb
 
+import sys
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+try:
+    from config.config_loader import get_config as _get_cfg
+except ImportError:
+    _get_cfg = None  # type: ignore[assignment]
+
 # CatBoost is optional
 try:
     from catboost import CatBoostClassifier
@@ -228,7 +235,7 @@ class V25Predictor:
         print(f"[V25] Using fallback feature columns ({len(V25Predictor._FALLBACK_FEATURE_COLS)} features)")
         return V25Predictor._FALLBACK_FEATURE_COLS
 
-    # Model weights for ensemble
+    # Model weights for ensemble (overridden from config in __init__)
     DEFAULT_WEIGHTS = {
         'xgb': 0.50,
         'lgb': 0.50,
@@ -245,6 +252,16 @@ class V25Predictor:
         self.models = {}  # market -> {'xgb': model, 'lgb': model}
         self._loaded = False
         self.FEATURE_COLS = self._load_feature_cols()
+        # Load weights from config (falls back to class default 0.50/0.50)
+        if _get_cfg is not None:
+            try:
+                cfg = _get_cfg()
+                self.DEFAULT_WEIGHTS = {
+                    'xgb': float(cfg.get('model_ensemble.xgb_weight', 0.50)),
+                    'lgb': float(cfg.get('model_ensemble.lgb_weight', 0.50)),
+                }
+            except Exception:
+                pass  # keep class-level defaults
     
     # All trained market models available in V25
     ALL_MARKETS = [
@@ -275,21 +292,34 @@ class V25Predictor:
                         xgb_content = f.read()
                     booster = xgb.Booster()
                     booster.load_model(bytearray(xgb_content, 'utf-8'))
-                    self.models[market]['xgb'] = booster
-                    loaded_count += 1
-                
+                    # Corruption detection: verify model can run a dummy prediction
+                    try:
+                        _dummy = pd.DataFrame([{col: 0.0 for col in self.FEATURE_COLS}])
+                        booster.predict(xgb.DMatrix(_dummy))
+                        self.models[market]['xgb'] = booster
+                        loaded_count += 1
+                    except Exception as _ce:
+                        print(f"[V25] ⚠️ XGB model for {market} failed integrity check: {_ce} — skipping")
+
                 # Load LightGBM (read content in Python to avoid non-ASCII path issues)
                 lgb_path = os.path.join(self.models_dir, f'lgb_v25_{market}.txt')
                 if os.path.exists(lgb_path) and os.path.getsize(lgb_path) > 0:
                     with open(lgb_path, 'r', encoding='utf-8') as f:
                         model_str = f.read()
-                    self.models[market]['lgb'] = lgb.Booster(model_str=model_str)
-                    loaded_count += 1
-                
+                    lgb_model = lgb.Booster(model_str=model_str)
+                    # Corruption detection: verify model can run a dummy prediction
+                    try:
+                        _dummy = pd.DataFrame([{col: 0.0 for col in self.FEATURE_COLS}])
+                        lgb_model.predict(_dummy)
+                        self.models[market]['lgb'] = lgb_model
+                        loaded_count += 1
+                    except Exception as _ce:
+                        print(f"[V25] ⚠️ LGB model for {market} failed integrity check: {_ce} — skipping")
+
                 # Remove empty entries
                 if not self.models[market]:
                     del self.models[market]
-            
+
             print(f"[V25] Loaded {loaded_count} model files across {len(self.models)} markets: {list(self.models.keys())}")
             self._loaded = loaded_count > 0
             return self._loaded
@@ -305,7 +335,27 @@ class V25Predictor:
         if not self._loaded:
             if not self.load_models():
                 raise RuntimeError("Failed to load V25 models")
-    
+
+    def readiness_summary(self) -> Dict[str, Any]:
+        """Return per-market model status for health check endpoint."""
+        if not self._loaded:
+            self.load_models()
+        market_status = {}
+        for market in self.ALL_MARKETS:
+            m = self.models.get(market, {})
+            market_status[market] = {
+                "xgb": "xgb" in m,
+                "lgb": "lgb" in m,
+                "ready": bool(m),
+            }
+        loaded_markets = [k for k, v in market_status.items() if v["ready"]]
+        return {
+            "fully_loaded": len(loaded_markets) == len(self.ALL_MARKETS),
+            "loaded_markets": loaded_markets,
+            "missing_markets": [m for m in self.ALL_MARKETS if m not in loaded_markets],
+            "weights": self.DEFAULT_WEIGHTS,
+        }
+
     def _prepare_features(self, features: Dict[str, float]) -> pd.DataFrame:
         """Prepare feature vector for prediction."""
         X = pd.DataFrame([{col: features.get(col, 0.0) for col in self.FEATURE_COLS}])
@@ -563,13 +613,23 @@ class V25Predictor:
     ) -> List[ValueBet]:
         """Detect value bets based on model vs market odds."""
         value_bets = []
-        min_edge = 0.05  # 5% minimum edge
-        
+        # Market-specific minimum edge thresholds
+        # MS: higher variance → require more edge
+        # OU/BTTS: binary markets → tighter edge acceptable
+        EDGE_THRESHOLDS = {
+            'MS': 0.06,
+            'OU25': 0.04,
+            'BTTS': 0.04,
+        }
+        ms_edge = EDGE_THRESHOLDS['MS']
+        ou_edge = EDGE_THRESHOLDS['OU25']
+        btts_edge = EDGE_THRESHOLDS['BTTS']
+
         # MS value bets
         if 'ms_h' in odds and odds['ms_h'] > 0:
             implied = 1 / odds['ms_h']
             edge = home_prob - implied
-            if edge > min_edge:
+            if edge > ms_edge:
                 value_bets.append(ValueBet(
                     market_type='MS',
                     pick='1',
@@ -582,7 +642,7 @@ class V25Predictor:
         if 'ms_d' in odds and odds['ms_d'] > 0:
             implied = 1 / odds['ms_d']
             edge = draw_prob - implied
-            if edge > min_edge:
+            if edge > ms_edge:
                 value_bets.append(ValueBet(
                     market_type='MS',
                     pick='X',
@@ -595,7 +655,7 @@ class V25Predictor:
         if 'ms_a' in odds and odds['ms_a'] > 0:
             implied = 1 / odds['ms_a']
             edge = away_prob - implied
-            if edge > min_edge:
+            if edge > ms_edge:
                 value_bets.append(ValueBet(
                     market_type='MS',
                     pick='2',
@@ -609,7 +669,7 @@ class V25Predictor:
         if 'ou25_o' in odds and odds['ou25_o'] > 0:
             implied = 1 / odds['ou25_o']
             edge = over_prob - implied
-            if edge > min_edge:
+            if edge > ou_edge:
                 value_bets.append(ValueBet(
                     market_type='OU25',
                     pick='Over',
@@ -622,7 +682,7 @@ class V25Predictor:
         if 'ou25_u' in odds and odds['ou25_u'] > 0:
             implied = 1 / odds['ou25_u']
             edge = under_prob - implied
-            if edge > min_edge:
+            if edge > ou_edge:
                 value_bets.append(ValueBet(
                     market_type='OU25',
                     pick='Under',
@@ -636,7 +696,7 @@ class V25Predictor:
         if 'btts_y' in odds and odds['btts_y'] > 0:
             implied = 1 / odds['btts_y']
             edge = btts_yes_prob - implied
-            if edge > min_edge:
+            if edge > btts_edge:
                 value_bets.append(ValueBet(
                     market_type='BTTS',
                     pick='Yes',
@@ -649,7 +709,7 @@ class V25Predictor:
         if 'btts_n' in odds and odds['btts_n'] > 0:
             implied = 1 / odds['btts_n']
             edge = btts_no_prob - implied
-            if edge > min_edge:
+            if edge > btts_edge:
                 value_bets.append(ValueBet(
                     market_type='BTTS',
                     pick='No',