DOLPHIN/nautilus_dolphin/run_mc_leverage.py

import sys, time
from pathlib import Path
import numpy as np
import pandas as pd
import json

sys.path.insert(0, str(Path(__file__).parent))

from nautilus_dolphin.nautilus.alpha_orchestrator import NDAlphaEngine
from nautilus_dolphin.nautilus.adaptive_circuit_breaker import AdaptiveCircuitBreaker
from nautilus_dolphin.nautilus.ob_features import OBFeatureEngine
from nautilus_dolphin.nautilus.ob_provider import MockOBProvider

VBT_DIR = Path(r"C:\Users\Lenovo\Documents\- DOLPHIN NG HD HCM TSF Predict\vbt_cache")
META_COLS = {'timestamp', 'scan_number', 'v50_lambda_max_velocity', 'v150_lambda_max_velocity',
             'v300_lambda_max_velocity', 'v750_lambda_max_velocity', 'vel_div',
             'instability_50', 'instability_150'}

parquet_files = sorted(VBT_DIR.glob("*.parquet"))
parquet_files = [p for p in parquet_files if 'catalog' not in str(p)]

print("Loading data...")
all_vols = []
for pf in parquet_files[:2]:
    df = pd.read_parquet(pf)
    if 'BTCUSDT' not in df.columns: continue
    pr = df['BTCUSDT'].values
    for i in range(60, len(pr)):
        seg = pr[max(0,i-50):i]
        if len(seg)<10: continue
        v = float(np.std(np.diff(seg)/seg[:-1]))
        if v > 0: all_vols.append(v)
vol_p60 = float(np.percentile(all_vols, 60))

pq_data = {}
for pf in parquet_files:
    df = pd.read_parquet(pf)
    ac = [c for c in df.columns if c not in META_COLS]
    bp = df['BTCUSDT'].values if 'BTCUSDT' in df.columns else None
    dv = np.full(len(df), np.nan)
    if bp is not None:
        for i in range(50, len(bp)):
            seg = bp[max(0,i-50):i]
            if len(seg)<10: continue
            dv[i] = float(np.std(np.diff(seg)/seg[:-1]))
    pq_data[pf.stem] = (df, ac, dv)

# Initialize systems
acb = AdaptiveCircuitBreaker()
acb.preload_w750([pf.stem for pf in parquet_files])

mock = MockOBProvider(imbalance_bias=-0.09, depth_scale=1.0, 
                      assets=["BTCUSDT", "ETHUSDT", "BNBUSDT", "SOLUSDT"],
                      imbalance_biases={"BNBUSDT": 0.20, "SOLUSDT": 0.20})
ob_engine = OBFeatureEngine(mock)
ob_engine.preload_date("mock", mock.get_assets())

def run_base_backtest(lev_multiplier):
    ENGINE_KWARGS = dict(
        initial_capital=25000.0, vel_div_threshold=-0.02, vel_div_extreme=-0.05,
        min_leverage=0.5, max_leverage=5.0 * lev_multiplier, leverage_convexity=3.0,
        fraction=0.20, fixed_tp_pct=0.0099, stop_pct=1.0, max_hold_bars=120,
        use_direction_confirm=True, dc_lookback_bars=7, dc_min_magnitude_bps=0.75,
        dc_skip_contradicts=True, dc_leverage_boost=1.0, dc_leverage_reduce=0.5,
        use_asset_selection=True, min_irp_alignment=0.45,
        use_sp_fees=True, use_sp_slippage=True,
        use_ob_edge=True, ob_edge_bps=5.0, ob_confirm_rate=0.40,
        lookback=100, use_alpha_layers=True, use_dynamic_leverage=True, seed=42,
    )

    import gc
    gc.collect()
    
    engine = NDAlphaEngine(**ENGINE_KWARGS)
    engine.set_ob_engine(ob_engine)
        
    bar_idx = 0; peak_cap = engine.capital; max_dd = 0.0
    
    # Store daily returns for MC bootstrapping
    daily_returns = []
    
    for pf in parquet_files:
        ds = pf.stem
        cs = engine.capital
        # ACB logic
        acb_info = acb.get_dynamic_boost_for_date(ds, ob_engine=ob_engine)
        base_boost = acb_info['boost']
        beta = acb_info['beta']
        
        df, acols, dvol = pq_data[ds]
        ph = {}
        for ri in range(len(df)):
            row = df.iloc[ri]; vd = row.get("vel_div")
            if vd is None or not np.isfinite(vd): bar_idx+=1; continue
            prices = {}
            for ac in acols:
                p = row[ac]
                if p and p > 0 and np.isfinite(p):
                    prices[ac] = float(p)
                    if ac not in ph: ph[ac] = []
                    ph[ac].append(float(p))
                    if len(ph[ac]) > 500: ph[ac] = ph[ac][-200:]
            if not prices: bar_idx+=1; continue
            
            vrok = False if ri < 100 else (np.isfinite(dvol[ri]) and dvol[ri] > vol_p60)
            
            # Use beta strictly for meta-boost
            if beta > 0:
                ss = 0.0
                if vd < -0.02:
                    raw = (-0.02 - float(vd)) / (-0.02 - -0.05)
                    ss = min(1.0, max(0.0, raw)) ** 3.0
                engine.regime_size_mult = base_boost * (1.0 + beta * ss)
            else:
                engine.regime_size_mult = base_boost
                
            engine.process_bar(bar_idx=bar_idx, vel_div=float(vd), prices=prices, vol_regime_ok=vrok, price_histories=ph)
            bar_idx += 1
            
        peak_cap = max(peak_cap, engine.capital)
        dd = (peak_cap - engine.capital) / peak_cap
        max_dd = max(max_dd, dd)
        daily_returns.append((engine.capital - cs) / cs if cs > 0 else 0)
        
    trades = engine.trade_history
    w = [t for t in trades if t.pnl_absolute > 0]
    l = [t for t in trades if t.pnl_absolute <= 0]
    gw = sum(t.pnl_absolute for t in w) if w else 0
    gl = abs(sum(t.pnl_absolute for t in l)) if l else 0
    
    roi = (engine.capital - 25000) / 25000 * 100
    pf_val = gw / gl if gl > 0 else 999
    wr = len(w) / len(trades) * 100 if trades else 0
    
    return {
        'leverage': 5.0 * lev_multiplier,
        'roi': roi,
        'pf': pf_val,
        'wr': wr,
        'max_dd': max_dd * 100,
        'trades': len(trades),
        'daily_returns': np.array(daily_returns)
    }

def run_monte_carlo(base_results, n_simulations=1000, periods=365):
    """
    Run geometric Monte Carlo bootstrapping using historical daily returns.
    """
    np.random.seed(42)
    daily_returns = base_results['daily_returns']
    n_days = len(daily_returns)
    
    # Bootstrap sampling for n_simulations trajectories of length `periods`
    # Randomly sample historical daily returns with replacement to generate realistic synthetic years
    simulated_returns = np.random.choice(daily_returns, size=(n_simulations, periods), replace=True)
    
    # Calculate equity curves (geometric compounding)
    # Adding 1.0 to get multiplier for cumulative product
    equity_curves = np.cumprod(1.0 + simulated_returns, axis=1)
    
    # CAGR calculations
    final_multipliers = equity_curves[:, -1]
    # CAGR = (End/Start)^(1/Years) - 1. We simulate 1 year, so exponent is 1.
    cagrs = (final_multipliers - 1.0) * 100
    
    median_cagr = np.median(cagrs)
    p05_cagr = np.percentile(cagrs, 5)  # 5th percentile worst outcome
    
    # Calculate Max Drawdowns for each simulated trajectory
    max_dds = np.zeros(n_simulations)
    recovery_times = np.zeros(n_simulations)
    
    for i in range(n_simulations):
        curve = equity_curves[i]
        peaks = np.maximum.accumulate(curve)
        drawdowns = (peaks - curve) / peaks
        max_dd_idx = np.argmax(drawdowns)
        max_dds[i] = drawdowns[max_dd_idx]
        
        # Calculate time to recovery from max drawdown
        if drawdowns[max_dd_idx] > 0:
            peak_val = peaks[max_dd_idx]
            # Find first index after max drawdown where equity hits or exceeds the peak
            recovery_idx = -1
            for j in range(max_dd_idx, periods):
                if curve[j] >= peak_val:
                    recovery_idx = j
                    break
            
            if recovery_idx != -1:
                recovery_times[i] = recovery_idx - max_dd_idx
            else:
                recovery_times[i] = periods - max_dd_idx # Did not recover within period
    
    median_max_dd = np.median(max_dds) * 100
    median_recovery = np.median(recovery_times[recovery_times > 0]) if np.any(recovery_times > 0) else -1
    
    return {
        'median_cagr': median_cagr,
        'p05_cagr': p05_cagr,
        'median_max_dd': median_max_dd,
        'median_recovery_days': median_recovery,
        'prob_ruin_50': np.mean(max_dds >= 0.50) * 100 # Prob of 50% DD
    }

print("\n" + "="*80)
print("GEOMETRIC MONTE CARLO DRAG SIMULATION (1000 Trajectories / 1 Year)")
print("="*80)
print(f"{'Lev':<5} | {'Base ROI':<10} | {'Base DD':<10} | {'Base PF':<8} | {'Med CAGR':<10} | {'5th% CAGR':<10} | {'Med MC DD':<10} | {'Recovery':<10} | {'Risk > 50% DD'}")
print("-" * 80)

results = []
for mult in [1.0, 1.2, 1.4]: # 5x, 6x, 7x
    lev = 5.0 * mult
    
    # Get empirical sequence first
    base = run_base_backtest(mult)
    
    # Run MC on the empirical sequence
    mc = run_monte_carlo(base, n_simulations=1000, periods=365)
    
    print(f"{lev:<4.1f}x | {base['roi']:>+9.2f}% | {base['max_dd']:>9.2f}% | {base['pf']:>7.3f} | " + 
          f"{mc['median_cagr']:>+9.2f}% | {mc['p05_cagr']:>+9.2f}% | {mc['median_max_dd']:>9.2f}% | " +
          f"{mc['median_recovery_days']:>7.0f} d | {mc['prob_ruin_50']:>11.1f}%")