#!/usr/bin/env python3 """ OPTIMISATION V10 RANGE STRATEGY Trouve le bon compromis entre sélectivité et fréquence """ import pandas as pd import numpy as np import random import json import logging from datetime import datetime from v10_range_strategy import V10RangeStrategy from backtest_adaptive import AdaptiveBacktest logging.basicConfig(level=logging.ERROR) logger = logging.getLogger(__name__) class V10RangeOptimizer: """Optimiseur pour stratégie V10 Range""" def __init__(self, df: pd.DataFrame, initial_capital: float = 500.0): self.df = df self.initial_capital = initial_capital self.results = [] def generate_random_params(self): """Génère des paramètres aléatoires pour V10""" return { 'leverage': random.choice([100, 110, 120, 125, 130, 140, 150]), 'rsi_oversold': random.randint(25, 40), 'rsi_overbought': random.randint(60, 75), 'range_atr_threshold': random.uniform(0.25, 0.45), 'min_confidence': random.randint(60, 80), 'sl_atr_mult': random.uniform(0.8, 2.0), 'tp_atr_mult': random.uniform(2.0, 5.0), 'bb_std': random.uniform(1.5, 2.5), } def test_params(self, params): """Teste une combinaison de paramètres""" try: # Créer stratégie avec params custom strategy = V10RangeStrategy(leverage=params['leverage']) # Appliquer les 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'] strategy.params['bb_std'] = params['bb_std'] # Créer adapteur from backtest_v10_range import V10StrategyAdapter, Signal class CustomV10Adapter: 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'], confidence=signal_dict['confidence'], strategy_used=signal_dict['strategy_used'], confluences=signal_dict['confluences'], leverage=self.leverage, timeframe='5m', timestamp=pd.Timestamp.now() ) adapter = CustomV10Adapter(strategy) # Backtest backtest = AdaptiveBacktest(adapter, initial_capital=self.initial_capital) results = backtest.run(self.df, "BTCUSD_DEGEN") if not results or results['total_trades'] == 0: return None return { 'params': params, '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"Error testing params: {e}") return None def optimize(self, n_iterations: int = 50): """Lance l'optimisation""" print(f"\n{'='*80}") print(f"🔬 OPTIMISATION V10 RANGE") print(f"{'='*80}") print(f"Itérations: {n_iterations}") print(f"Capital: ${self.initial_capital}") print(f"Données: {len(self.df)} bougies") print(f"{'='*80}\n") for i in range(n_iterations): # Générer params params = self.generate_random_params() # S'assurer TP > SL * 2 if params['tp_atr_mult'] < params['sl_atr_mult'] * 2.0: params['tp_atr_mult'] = params['sl_atr_mult'] * random.uniform(2.5, 3.5) # Tester result = self.test_params(params) if result: self.results.append(result) # Sauvegarder immédiatement with open('v10_optimization_results.json', 'w') as f: json.dump(self.results, f, indent=2) pnl = result['results']['total_pnl_pct'] pf = result['results']['profit_factor'] trades = result['results']['total_trades'] lev = result['params']['leverage'] if pnl > 0 and pf > 1.0: print(f"✅ Test {i+1}/{n_iterations} | " f"PnL: {pnl:+.2f}% | PF: {pf:.2f} | " f"Trades: {trades} | Lev: {lev}x") else: print(f"❌ Test {i+1}/{n_iterations} | " f"PnL: {pnl:+.2f}% | PF: {pf:.2f} | " f"Trades: {trades}") else: print(f"⚠️ Test {i+1}/{n_iterations} | Aucun trade") # Résumé self.print_summary() def print_summary(self): """Affiche le résumé""" if not self.results: print("\n❌ Aucun résultat") return print(f"\n\n{'='*80}") print(f"📊 RÉSUMÉ OPTIMISATION V10") 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 totaux: {len(self.results)}") print(f"Profitables: {len(profitable)} ({len(profitable)/len(self.results)*100:.1f}%)\n") if not profitable: print("❌ Aucune config profitable!") return # Trier par PnL profitable.sort(key=lambda x: x['results']['total_pnl_pct'], reverse=True) print(f"🏆 TOP 10 CONFIGS:\n") print(f"{'#':<4} {'PnL':<10} {'PF':<8} {'WR':<8} {'Trades':<8} {'Lev':<6} {'Params'}") print("-" * 80) for i, r in enumerate(profitable[:10], 1): res = r['results'] p = r['params'] param_str = (f"RSI:{p['rsi_oversold']}/{p['rsi_overbought']} " f"ATR:{p['range_atr_threshold']:.2f} " f"Conf:{p['min_confidence']} " f"SL/TP:{p['sl_atr_mult']:.1f}/{p['tp_atr_mult']:.1f}") print(f"{i:<4} {res['total_pnl_pct']:>+7.2f}% " f"{res['profit_factor']:>5.2f} " f"{res['win_rate']:>5.1f}% " f"{res['total_trades']:>5} " f"{p['leverage']:>4}x " f"{param_str}") print("\n" + "="*80) # Meilleur compromis (bon PnL + trades suffisants) good_volume = [r for r in profitable if r['results']['total_trades'] >= 5] if good_volume: print(f"\n💎 MEILLEUR COMPROMIS (5+ trades):\n") best = good_volume[0] res = best['results'] p = best['params'] print(f" PnL: {res['total_pnl_pct']:+.2f}% (${res['final_capital'] - self.initial_capital:+.2f})") print(f" Profit Factor: {res['profit_factor']:.3f}") print(f" Win Rate: {res['win_rate']:.1f}%") print(f" Trades: {res['total_trades']}") print(f" Leverage: {p['leverage']}x") print(f"\n Paramètres:") print(f" RSI oversold: {p['rsi_oversold']}") print(f" RSI overbought: {p['rsi_overbought']}") print(f" ATR threshold: {p['range_atr_threshold']:.3f}") print(f" Min confidence: {p['min_confidence']}%") print(f" SL ATR mult: {p['sl_atr_mult']:.2f}") print(f" TP ATR mult: {p['tp_atr_mult']:.2f}") print(f" BB std: {p['bb_std']:.2f}") print("\n" + "="*80 + "\n") if __name__ == '__main__': # Charger données df = pd.read_csv('historical_data/BTCUSDT_5m_2000candles.csv') df['timestamp'] = pd.to_datetime(df['timestamp']) # Optimiser optimizer = V10RangeOptimizer(df, initial_capital=500.0) optimizer.optimize(n_iterations=100)