#!/usr/bin/env python3 """ Optimisation Massive Stratégie Hybride Teste 100+ configurations pour trouver les meilleurs paramètres """ import pandas as pd import numpy as np import json import random import time from datetime import datetime from pathlib import Path from hybrid_strategy import HybridStrategy from backtest_hybrid import HybridBacktest, get_btc_historical_data print("=" * 80) print("🚀 OPTIMISATION MASSIVE HYBRID STRATEGY") print("=" * 80) print(f"Démarrage: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}") print() # Charger données (1 jour = ~1440 bougies) print("📊 Chargement données...") df = get_btc_historical_data(days=1, interval='1m') print(f"✅ {len(df)} bougies chargées") print() results = [] TOTAL_TESTS = 100 output_file = 'hybrid_optimization_results.json' print(f"🔄 Lancement de {TOTAL_TESTS} tests...") print(f"💾 Sauvegarde progressive dans {output_file}") print() for i in range(TOTAL_TESTS): start_time = time.time() # Générer config aléatoire config = { # Bull params 'bull.min_trend_strength': random.randint(50, 80), 'bull.rsi_pullback_max': random.randint(35, 50), 'bull.rsi_breakout_min': random.randint(50, 65), 'bull.sl_atr_multiplier': round(random.uniform(1.0, 2.5), 2), 'bull.tp_atr_multiplier': round(random.uniform(2.0, 5.0), 2), 'bull.leverage': random.choice([50, 75, 100, 125, 150, 200]), # Bear params 'bear.min_trend_strength': random.randint(50, 80), 'bear.rsi_rally_min': random.randint(50, 65), 'bear.rsi_overbought': random.randint(65, 80), 'bear.sl_atr_multiplier': round(random.uniform(1.0, 2.5), 2), 'bear.tp_atr_multiplier': round(random.uniform(2.0, 5.0), 2), 'bear.leverage': random.choice([50, 75, 100, 125, 150, 200]), # Range params (V10) 'range.rsi_oversold': random.randint(25, 40), 'range.rsi_overbought': random.randint(60, 80), 'range.range_atr_threshold': round(random.uniform(0.20, 0.45), 2), 'range.sl_atr_multiplier': round(random.uniform(1.0, 2.5), 2), 'range.trailing_pct': round(random.uniform(0.03, 0.15), 2), 'range.leverage': random.choice([100, 150, 200, 250]), } # Créer stratégie avec ces params strategy = HybridStrategy(leverage=100) # Appliquer params bull strategy.bull_strategy.params['min_trend_strength'] = config['bull.min_trend_strength'] strategy.bull_strategy.params['rsi_pullback_max'] = config['bull.rsi_pullback_max'] strategy.bull_strategy.params['rsi_breakout_min'] = config['bull.rsi_breakout_min'] strategy.bull_strategy.params['sl_atr_multiplier'] = config['bull.sl_atr_multiplier'] strategy.bull_strategy.params['tp_atr_multiplier'] = config['bull.tp_atr_multiplier'] strategy.bull_strategy.leverage = config['bull.leverage'] # Appliquer params bear strategy.bear_strategy.params['min_trend_strength'] = config['bear.min_trend_strength'] strategy.bear_strategy.params['rsi_rally_min'] = config['bear.rsi_rally_min'] strategy.bear_strategy.params['rsi_overbought'] = config['bear.rsi_overbought'] strategy.bear_strategy.params['sl_atr_multiplier'] = config['bear.sl_atr_multiplier'] strategy.bear_strategy.params['tp_atr_multiplier'] = config['bear.tp_atr_multiplier'] strategy.bear_strategy.leverage = config['bear.leverage'] # Appliquer params range strategy.range_strategy.params['rsi_oversold'] = config['range.rsi_oversold'] strategy.range_strategy.params['rsi_overbought'] = config['range.rsi_overbought'] strategy.range_strategy.params['range_atr_threshold'] = config['range.range_atr_threshold'] strategy.range_strategy.params['sl_atr_multiplier'] = config['range.sl_atr_multiplier'] strategy.range_strategy.params['trailing_pct'] = config['range.trailing_pct'] strategy.range_strategy.leverage = config['range.leverage'] # Backtest try: backtest = HybridBacktest(df, initial_capital=500.0) result = backtest.run("Hybrid", strategy) elapsed = time.time() - start_time if result['total_trades'] > 0: results.append({ 'config': config, 'pnl_pct': result['total_pnl_pct'], 'trades': result['total_trades'], 'win_rate': result['win_rate'], 'profit_factor': result['profit_factor'], 'max_dd': result['max_drawdown'], 'trades_by_strategy': result['trades_by_strategy'], 'timestamp': datetime.now().isoformat() }) print(f"[{i+1}/{TOTAL_TESTS}] PnL {result['total_pnl_pct']:+.1f}% | Trades {result['total_trades']} | WR {result['win_rate']:.0f}% | PF {result['profit_factor']:.2f} | {elapsed:.1f}s") # Sauvegarder tous les 5 tests if (i + 1) % 5 == 0: with open(output_file, 'w') as f: json.dump(results, f, indent=2) print(f" 💾 Sauvegarde intermédiaire ({len(results)} résultats)") else: print(f"[{i+1}/{TOTAL_TESTS}] Aucun trade | {elapsed:.1f}s") except Exception as e: print(f"[{i+1}/{TOTAL_TESTS}] ERREUR: {e}") # Sauvegarde finale with open(output_file, 'w') as f: json.dump(results, f, indent=2) print() print("=" * 80) print("📊 RÉSULTATS FINAUX") print("=" * 80) print(f"Terminé: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}") print() if results: # Statistiques globales profitable = [r for r in results if r['pnl_pct'] > 0 and r['profit_factor'] > 1.0] print(f"Tests effectués: {len(results)}/{TOTAL_TESTS}") print(f"Configs profitables: {len(profitable)} ({len(profitable)/len(results)*100:.0f}%)") if profitable: profitable.sort(key=lambda x: x['pnl_pct'], reverse=True) print() print("🏆 TOP 5 PAR PnL:") for i, r in enumerate(profitable[:5], 1): print(f"\n{i}. PnL: {r['pnl_pct']:+.1f}% | PF: {r['profit_factor']:.2f} | WR: {r['win_rate']:.0f}% | Trades: {r['trades']}") print(f" Max DD: {r['max_dd']:.1f}%") print(f" Répartition: {r['trades_by_strategy']}") print() print("🏆 TOP 5 PAR PROFIT FACTOR:") profitable.sort(key=lambda x: x['profit_factor'], reverse=True) for i, r in enumerate(profitable[:5], 1): print(f"\n{i}. PF: {r['profit_factor']:.2f} | PnL: {r['pnl_pct']:+.1f}% | WR: {r['win_rate']:.0f}% | Trades: {r['trades']}") print(f" Max DD: {r['max_dd']:.1f}%") print(f" Répartition: {r['trades_by_strategy']}") else: print("\n❌ Aucune config profitable trouvée") else: print("\n❌ Aucun résultat") print() print(f"💾 Résultats sauvegardés: {output_file}") print("=" * 80)