01c19662cb
Includes core prod + GREEN/BLUE subsystems: - prod/ (BLUE harness, configs, scripts, docs) - nautilus_dolphin/ (GREEN Nautilus-native impl + dvae/ preserved) - adaptive_exit/ (AEM engine + models/bucket_assignments.pkl) - Observability/ (EsoF advisor, TUI, dashboards) - external_factors/ (EsoF producer) - mc_forewarning_qlabs_fork/ (MC regime/envelope) Excludes runtime caches, logs, backups, and reproducible artifacts per .gitignore.
261 lines
10 KiB
Python
Executable File
261 lines
10 KiB
Python
Executable File
import sys, time
|
|
from pathlib import Path
|
|
import numpy as np
|
|
import pandas as pd
|
|
|
|
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'}
|
|
|
|
# Load parquet files correctly
|
|
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])
|
|
|
|
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, 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,
|
|
)
|
|
|
|
def run_test(name, ob_engine=None):
|
|
engine = NDAlphaEngine(**ENGINE_KWARGS)
|
|
if ob_engine:
|
|
engine.set_ob_engine(ob_engine)
|
|
|
|
bar_idx = 0; peak_cap = engine.capital; max_dd = 0.0
|
|
for pf in parquet_files:
|
|
ds = pf.stem
|
|
# ACB logic
|
|
acb_info = acb.get_dynamic_boost_for_date(ds, ob_engine=ob_engine)
|
|
base_boost = acb_info['boost'] # This is now exactly (1.0 - cut)
|
|
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)
|
|
|
|
# 3-scale meta-boost: ACB boost * (1 + beta * strength^3)
|
|
if beta > 0 and base_boost > 1.0:
|
|
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)
|
|
|
|
# (no fraction reset needed)
|
|
bar_idx += 1
|
|
|
|
peak_cap = max(peak_cap, engine.capital)
|
|
dd = (peak_cap - engine.capital) / peak_cap * 100
|
|
max_dd = max(max_dd, dd)
|
|
|
|
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
|
|
|
|
returns = [(t.pnl_absolute / (25000+sum(x.pnl_absolute for x in trades[:i]))) for i, t in enumerate(trades)]
|
|
if not returns: returns = [0]
|
|
|
|
mc_med_cagr, mc_tail_cagr, mc_p40, mc_med_dd = compute_mc_cagr(returns)
|
|
|
|
print(f"\n{name}")
|
|
print(f" ROI: {roi:+.2f}%")
|
|
print(f" MaxDD (Emp): {max_dd:.2f}%")
|
|
print(f" Trades: {len(trades)}")
|
|
print(f" Win Rate: {wr:.1f}%")
|
|
print(f" Prof Factor: {pf_val:.3f}")
|
|
print(f" MC Med CAGR: {mc_med_cagr:+.1f}%")
|
|
print(f" MC Med DD: {mc_med_dd:.1f}%")
|
|
print(f" MC P(>40DD): {mc_p40:.1f}%")
|
|
|
|
# Helper for Monte Carlo
|
|
def compute_mc_cagr(returns, periods=252, n_simulations=1000):
|
|
np.random.seed(42)
|
|
dr = np.array(returns)
|
|
if len(dr) == 0: return 0,0,0,0
|
|
# Resample daily (simulated by block since returns are per trade, we approximate)
|
|
sr = np.random.choice(dr, size=(n_simulations, periods), replace=True)
|
|
eq = np.cumprod(1.0 + sr, axis=1)
|
|
cagrs = (eq[:, -1] - 1.0) * 100
|
|
med_cagr = np.median(cagrs)
|
|
tail_cagr = np.percentile(cagrs, 5)
|
|
|
|
max_dds = np.zeros(n_simulations)
|
|
for i in range(n_simulations):
|
|
curve = eq[i]
|
|
peaks = np.maximum.accumulate(curve)
|
|
dds = (peaks - curve) / peaks
|
|
max_dds[i] = np.max(dds)
|
|
p40 = np.mean(max_dds >= 0.40) * 100
|
|
mdd = np.median(max_dds) * 100
|
|
return med_cagr, tail_cagr, p40, mdd
|
|
|
|
# 1. Test Baseline
|
|
run_test("A. ACB v4 Baseline (No OB, Pure ACB)")
|
|
|
|
# 2. Test Full Production (ACB Cut + OB Engine Hard Skip)
|
|
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())
|
|
run_test("B. Production Stack (ACB + OB Hard-Skip, 5.0x)", ob_engine)
|
|
|
|
from nautilus_dolphin.nautilus.esf_alpha_orchestrator import NDAlphaEngine as ThrottledEngine
|
|
import json
|
|
|
|
def run_throttled_test(name, ob_engine=None):
|
|
engine = ThrottledEngine(**ENGINE_KWARGS)
|
|
if ob_engine:
|
|
engine.set_ob_engine(ob_engine)
|
|
|
|
bar_idx = 0; peak_cap = engine.capital; max_dd = 0.0
|
|
for pf in parquet_files:
|
|
ds = pf.stem
|
|
acb_info = acb.get_dynamic_boost_for_date(ds, ob_engine=ob_engine)
|
|
base_boost = acb_info['boost']
|
|
beta = acb_info['beta']
|
|
|
|
eso_path = VBT_DIR / f"ESOTERIC_data_{ds}.json"
|
|
eso = {}
|
|
if eso_path.exists():
|
|
with open(eso_path, 'r') as f:
|
|
eso = json.load(f)
|
|
|
|
hazard = 0.0
|
|
dow = eso.get('day_of_week', -1)
|
|
if dow == 1: hazard = 1.0
|
|
elif dow in [0, 2]: hazard = 0.5
|
|
if eso.get('moon_illumination', 0.5) <= 0.05: hazard = 1.0
|
|
|
|
engine.set_esoteric_hazard_multiplier(hazard)
|
|
# Enable 6.0x dynamic
|
|
engine.set_mc_forewarner_status(True)
|
|
|
|
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)
|
|
|
|
if beta > 0 and base_boost > 1.0:
|
|
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 * 100
|
|
max_dd = max(max_dd, dd)
|
|
|
|
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
|
|
|
|
returns = [(t.pnl_absolute / (25000+sum(x.pnl_absolute for x in trades[:i]))) for i, t in enumerate(trades)]
|
|
if not returns: returns = [0]
|
|
|
|
mc_med_cagr, mc_tail_cagr, mc_p40, mc_med_dd = compute_mc_cagr(returns)
|
|
|
|
print(f"\n{name}")
|
|
print(f" ROI: {roi:+.2f}%")
|
|
print(f" MaxDD (Emp): {max_dd:.2f}%")
|
|
print(f" Trades: {len(trades)}")
|
|
print(f" Win Rate: {wr:.1f}%")
|
|
print(f" Prof Factor: {pf_val:.3f}")
|
|
print(f" MC Med CAGR: {mc_med_cagr:+.1f}%")
|
|
print(f" MC Med DD: {mc_med_dd:.1f}%")
|
|
print(f" MC P(>40DD): {mc_p40:.1f}%")
|
|
|
|
run_throttled_test("C. Ultimate Stack (Production OB + Dynamic 5-6x + EsoF Taper)", ob_engine)
|