#!/usr/bin/env python3 """ OPTIMISATION V10 AVEC TRAILING STOP Compare TP fixe vs différents trailing stop % pour trouver la meilleure combinaison """ import pandas as pd import numpy as np import json import logging from datetime import datetime from v10_range_strategy import V10RangeStrategy from backtest_adaptive import AdaptiveBacktest from backtest_v10_range import V10StrategyAdapter, Signal logging.basicConfig(level=logging.ERROR) logger = logging.getLogger(__name__) class V10TrailingOptimizer: """Optimise V10 avec trailing stop""" def __init__(self, df: pd.DataFrame, initial_capital: float = 500.0): self.df = df self.initial_capital = initial_capital self.results = [] # MEILLEUR PARAM FIXE (baseline) self.best_fixed_params = { 'rsi_oversold': 30, 'rsi_overbought': 70, 'min_confidence': 75, 'range_atr_threshold': 0.30, 'sl_atr_mult': 1.0, # Meilleur de la grille précédente 'tp_atr_mult': 4.0, # Meilleur de la grille précédente 'leverage': 150, } def test_config(self, params, use_trailing: bool = False, trailing_pct: float = 0.15): """Teste une config avec ou sans trailing stop""" try: # Créer stratégie strategy = V10RangeStrategy(leverage=params['leverage']) # Appliquer params strategy.params['rsi_oversold'] = params['rsi_oversold'] strategy.params['rsi_overbought'] = params['rsi_overbought'] strategy.params['range_atr_threshold'] = params['range_atr_threshold'] strategy.params['min_confidence'] = params['min_confidence'] strategy.params['sl_atr_multiplier'] = params['sl_atr_mult'] strategy.params['tp_atr_multiplier'] = params['tp_atr_mult'] # Adapter class CustomAdapter: def __init__(self, strat): self.strategy = strat self.leverage = strat.leverage self.params = { 'ranging': { 'sl_atr_multiplier': strat.params['sl_atr_multiplier'], 'tp_atr_multiplier': strat.params['tp_atr_multiplier'], 'min_confidence': strat.params['min_confidence'], } } def analyze(self, symbol, df): signal_dict = self.strategy.analyze(symbol, df) if not signal_dict: return None return Signal( symbol=signal_dict['symbol'], side=signal_dict['side'], entry_price=signal_dict['entry_price'], stop_loss=signal_dict['stop_loss'], take_profit=signal_dict['take_profit'], leverage=signal_dict['leverage'], risk_pct=signal_dict['risk_pct'], score=signal_dict['confidence'], confluences=signal_dict['confluences'], strategy_used='v10_range_reversal', confidence=signal_dict['confidence'] ) adapter = CustomAdapter(strategy) # Backtest avec ou sans trailing backtest = AdaptiveBacktest( adapter, initial_capital=self.initial_capital, use_trailing_stop=use_trailing, trailing_pct=trailing_pct if use_trailing else 0.15 ) results = backtest.run(self.df, 'BTCUSDT') if not results or results['total_trades'] == 0: return None return { 'params': params.copy(), 'trailing': use_trailing, 'trailing_pct': trailing_pct if use_trailing else None, 'results': { 'total_trades': results['total_trades'], 'win_rate': results['win_rate'], 'total_pnl_pct': results['total_pnl_pct'], 'final_capital': results['final_capital'], 'profit_factor': results['profit_factor'], 'avg_win': results['avg_win'], 'avg_loss': results['avg_loss'] }, 'timestamp': datetime.now().isoformat() } except Exception as e: logger.error(f"Erreur test config: {e}") return None def optimize(self): """Lance l'optimisation""" print("="*80) print("🚀 OPTIMISATION V10 - TP FIXE vs TRAILING STOP") print("="*80) print(f"Capital: ${self.initial_capital}") print(f"Données: {len(self.df)} bougies") print(f"Période: {self.df['timestamp'].iloc[0]} → {self.df['timestamp'].iloc[-1]}") print(f"{'='*80}\n") # 1. BASELINE: TP/SL fixe avec meilleurs params print("📊 Test 1/11: TP Fixe (baseline)...") result = self.test_config(self.best_fixed_params, use_trailing=False) if result: result['is_baseline'] = True self.results.append(result) print(f" ✅ PnL: {result['results']['total_pnl_pct']:+.2f}% | " f"PF: {result['results']['profit_factor']:.2f} | " f"Trades: {result['results']['total_trades']}") # 2. TRAILING STOPS: différents % trailing_pcts = [0.05, 0.10, 0.12, 0.15, 0.18, 0.20, 0.22, 0.25, 0.30, 0.35] for i, trail_pct in enumerate(trailing_pcts, 2): print(f"📊 Test {i}/11: Trailing Stop {int(trail_pct*100)}%...") result = self.test_config(self.best_fixed_params, use_trailing=True, trailing_pct=trail_pct) if result: self.results.append(result) print(f" ✅ PnL: {result['results']['total_pnl_pct']:+.2f}% | " f"PF: {result['results']['profit_factor']:.2f} | " f"Trades: {result['results']['total_trades']}") # Sauvegarder with open('v10_trailing_results.json', 'w') as f: json.dump(self.results, f, indent=2) self.print_summary() def print_summary(self): """Affiche résumé""" if not self.results: print("\n❌ Aucun résultat") return print(f"\n\n{'='*80}") print(f"📊 RÉSUMÉ: TP FIXE vs TRAILING STOP") print(f"{'='*80}\n") # Filtrer profitables profitable = [r for r in self.results if r['results']['total_pnl_pct'] > 0 and r['results']['profit_factor'] > 1.0] print(f"Tests effectués: {len(self.results)}") print(f"Profitables: {len(profitable)} ({len(profitable)/len(self.results)*100:.1f}%)\n") if not profitable: print("❌ Aucune config profitable!") return # Baseline baseline = [r for r in profitable if r.get('is_baseline')] if baseline: b = baseline[0] print(f"⭐ BASELINE (TP Fixe - SL/TP: {b['params']['sl_atr_mult']}/{b['params']['tp_atr_mult']}):") print(f" PnL: {b['results']['total_pnl_pct']:+.2f}%") print(f" PF: {b['results']['profit_factor']:.2f}") print(f" Trades: {b['results']['total_trades']}\n") # Trier par PnL profitable.sort(key=lambda x: x['results']['total_pnl_pct'], reverse=True) print(f"🏆 TOP 10 CONFIGS (tous systèmes):\n") print(f"{'#':<4} {'Type':<20} {'PnL':<12} {'PF':<8} {'Trades':<8} {'Params'}") print("-" * 90) for i, r in enumerate(profitable[:10], 1): res = r['results'] if r.get('trailing'): type_str = f"Trailing {int(r['trailing_pct']*100)}%" else: type_str = "TP Fixe" baseline_mark = "⭐" if r.get('is_baseline') else " " print(f"{baseline_mark}{i:<2} {type_str:<20} {res['total_pnl_pct']:>+9.2f}% " f"{res['profit_factor']:>5.2f} " f"{res['total_trades']:>5}") # Comparaison best = profitable[0] if baseline: improvement = best['results']['total_pnl_pct'] - baseline[0]['results']['total_pnl_pct'] print("\n" + "="*80) print(f"🎯 MEILLEUR SYSTÈME:") if best.get('trailing'): print(f" Type: Trailing Stop {int(best['trailing_pct']*100)}%") else: print(f" Type: TP Fixe") print(f" PnL: {best['results']['total_pnl_pct']:+.2f}%") print(f" PF: {best['results']['profit_factor']:.2f}") print(f" Trades: {best['results']['total_trades']}") if improvement > 0: print(f"\n💰 AMÉLIORATION vs TP Fixe: {improvement:+.2f}%") print(f" Gain supplémentaire: ${self.initial_capital * improvement / 100:.2f}") elif improvement < 0: print(f"\n⚠️ TP Fixe reste meilleur de {abs(improvement):.2f}%") else: print(f"\n➡️ Performance identique") print("="*80) # Sauvegarder with open('v10_trailing_results.json', 'w') as f: json.dump(self.results, f, indent=2) print(f"\n💾 Résultats sauvegardés: v10_trailing_results.json") if __name__ == '__main__': # Charger données df = pd.read_csv('historical_data/BTCUSDT_5m_9000candles.csv') df['timestamp'] = pd.to_datetime(df['timestamp']) print("📊 Chargement données...") print(f" Période: {df['timestamp'].iloc[0]} → {df['timestamp'].iloc[-1]}") print(f" Bougies: {len(df):,}\n") optimizer = V10TrailingOptimizer(df, initial_capital=500.0) optimizer.optimize()