Update ml_engine/monte_carlo.py

ml_engine/monte_carlo.py

@@ -1,4 +1,4 @@
-# ml_engine/monte_carlo.py
+# ml_engine/monte_carlo.py (Updated to V6.2 - Stablecoin Guard)
 import numpy as np
 import pandas as pd
 from arch import arch_model
@@ -12,7 +12,6 @@ except ImportError:
     print("⚠️ مكتبة pandas_ta غير موجودة، سيتم استخدام حسابات يدوية للمؤشرات.")
     ta = None
 
-# 🔴 --- START OF CHANGE (FIX NumPy 2.0 Crash) --- 🔴
 def _sanitize_results_for_json(results_dict):
     """
     Recursively converts numpy types (ndarray, np.float64, etc.)
@@ -33,7 +32,6 @@ def _sanitize_results_for_json(results_dict):
         return int(results_dict)
     else:
         return results_dict
-# 🔴 --- END OF CHANGE --- 🔴
 
 
 class MonteCarloAnalyzer:
@@ -76,6 +74,14 @@ class MonteCarloAnalyzer:
             mean_return = np.mean(log_returns)
             std_return = np.std(log_returns)
             
+            # 🔴 --- START OF CHANGE (V6.2 - STABLECOIN GUARD) --- 🔴
+            # واقي العملة المستقرة: إذا كان الانحراف المعياري (التقلب) شبه صفري، أوقف التحليل
+            if std_return < 1e-5: # (1e-5 هو 0.00001)
+                print(f"   [MC Guard] {ohlcv_data.get('symbol', 'Symbol')} - Zero volatility detected. Stopping MC.")
+                self.simulation_results = {'error': 'Zero volatility detected (Stablecoin?)'}
+                return None
+            # 🔴 --- END OF CHANGE --- 🔴
+
             num_simulations = 5000
             t_df = 10
             jump_lambda = 0.05
@@ -155,9 +161,18 @@ class MonteCarloAnalyzer:
             df['log_returns'] = np.log(df['close'] / df['close'].shift(1)).fillna(0)
             log_returns_series = df['log_returns'].replace([np.inf, -np.inf], 0)
 
+            # 🔴 --- START OF CHANGE (V6.2 - STABLECOIN GUARD) --- 🔴
+            # واقي العملة المستقرة: التحقق من التقلب قبل بدء التحليل
+            std_return_check = np.std(log_returns_series.iloc[-30:])
+            if std_return_check < 1e-5: # (1e-5 هو 0.00001)
+                print(f"   [MC Guard Adv] {ohlcv_data.get('symbol', 'Symbol')} - Zero volatility detected. Stopping GARCH/LGBM.")
+                self.simulation_results = {'error': 'Zero volatility detected (Stablecoin?)'}
+                # العودة إلى المرحلة 1 (التي ستمسك بها أيضاً وترجع None)
+                return await self.generate_1h_price_distribution(ohlcv_data, target_profit_percent)
+            # 🔴 --- END OF CHANGE --- 🔴
+
             # 3. (Phase 2) توقع التقلب باستخدام GARCH(1,1)
             try:
-                # 🔴 --- START OF CHANGE (FIX GARCH Warning) --- 🔴
                 # (Rescale by 100, and set rescale=False to stop GARCH from auto-scaling)
                 garch_model = arch_model(log_returns_series * 100, vol='Garch', p=1, q=1, dist='t', rescale=False)
                 res = garch_model.fit(update_freq=0, disp='off') 
@@ -165,9 +180,8 @@ class MonteCarloAnalyzer:
                 # (Divide by 100^2 = 10000)
                 forecasted_var = forecast.variance.iloc[-1, 0] / (100**2)
                 forecasted_std_return = np.sqrt(forecasted_var)
-                # 🔴 --- END OF CHANGE --- 🔴
             except Exception as garch_err:
-                forecasted_std_return = np.std(log_returns_series.iloc[-30:])
+                forecasted_std_return = std_return_check # (استخدام القيمة التي تم التحقق منها)
                 print(f"⚠️ GARCH failed, using std: {garch_err}")