initial: import DOLPHIN baseline 2026-04-21 from dolphinng5_predict working tree

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.
2026-04-21 16:58:38 +02:00
commit 01c19662cb
643 changed files with 260241 additions and 0 deletions
--- a/prod/test_dliq_goldstyle.py
+++ b/prod/test_dliq_goldstyle.py
@@ -0,0 +1,132 @@
+"""
+test_dliq_goldstyle.py — Run D_LIQ using EXACTLY the same data setup as
+test_pf_dynamic_beta_validate.py (gold test), but with create_d_liq_engine()
+instead of NDAlphaEngine.
+
+This is the most faithful reproduction of certification conditions.
+"""
+import sys, time, math
+from pathlib import Path
+import numpy as np
+import pandas as pd
+
+ROOT = Path(r"C:\Users\Lenovo\Documents\- DOLPHIN NG HD HCM TSF Predict")
+sys.path.insert(0, str(ROOT / 'nautilus_dolphin'))
+sys.path.insert(0, str(ROOT / 'nautilus_dolphin' / 'dvae'))
+
+import exp_shared
+from nautilus_dolphin.nautilus.proxy_boost_engine import create_d_liq_engine
+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
+
+print("Ensuring JIT...", flush=True)
+exp_shared.ensure_jit()
+
+VBT_DIR = exp_shared.VBT_DIR
+parquet_files = sorted(VBT_DIR.glob("*.parquet"))
+parquet_files = [p for p in parquet_files if 'catalog' not in str(p)]
+date_strings = [p.stem for p in parquet_files]
+print(f"Found {len(parquet_files)} parquet files", flush=True)
+
+META_COLS = exp_shared.META_COLS
+
+# EXACT gold test vol_p60 computation: first 2 files, range(60), seg-based
+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)
+    del df
+vol_p60 = float(np.percentile(all_vols, 60))
+print(f"vol_p60 (gold test method, 2 files, offset 60): {vol_p60:.8f}", flush=True)
+
+# EXACT gold test pq_data loading: all 56 files, ALL assets, offset 50
+print("Loading all 56 parquet files (float64, gold test style)...", flush=True)
+pq_data = {}
+all_assets = set()
+for pf in parquet_files:
+    df = pd.read_parquet(pf)
+    ac = [c for c in df.columns if c not in META_COLS]
+    all_assets.update(ac)
+    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)
+
+# EXACT gold test OB setup: all assets
+OB_ASSETS = sorted(list(all_assets))
+print(f"OB_ASSETS count: {len(OB_ASSETS)}", flush=True)
+_mock_ob = MockOBProvider(
+    imbalance_bias=-0.09, depth_scale=1.0, assets=OB_ASSETS,
+    imbalance_biases={"BTCUSDT": -0.086, "ETHUSDT": -0.092,
+                      "BNBUSDT": +0.05, "SOLUSDT": +0.05},
+)
+ob_eng = OBFeatureEngine(_mock_ob)
+ob_eng.preload_date("mock", OB_ASSETS)
+
+print(f"All {len(pq_data)} days loaded. Starting D_LIQ run...", flush=True)
+
+# Create D_LIQ engine (SAME as gold certification)
+kw = exp_shared.ENGINE_KWARGS.copy()
+acb = AdaptiveCircuitBreaker()
+acb.preload_w750(date_strings)
+
+eng = create_d_liq_engine(**kw)
+eng.set_ob_engine(ob_eng)
+eng.set_acb(acb)
+eng.set_esoteric_hazard_multiplier(0.0)  # Current code: ceiling=10.0, sets base_max=10.0
+
+print(f"After hazard call: base_max={eng.base_max_leverage}  abs_max={eng.abs_max_leverage}", flush=True)
+
+daily_caps, daily_pnls = [], []
+t0 = time.time()
+
+for i, pf in enumerate(parquet_files):
+    ds = pf.stem
+    df, acols, dvol = pq_data[ds]
+    cap_before = eng.capital
+    vol_ok = np.where(np.isfinite(dvol), dvol > vol_p60, False)
+    eng.process_day(ds, df, acols, vol_regime_ok=vol_ok)
+    daily_caps.append(eng.capital)
+    daily_pnls.append(eng.capital - cap_before)
+    if (i+1) % 20 == 0 or i == len(parquet_files)-1:
+        print(f"  Day {i+1}/{len(parquet_files)}: cap=${eng.capital:,.0f} T={len(eng.trade_history)} ({time.time()-t0:.0f}s)", flush=True)
+
+tr = eng.trade_history
+n = len(tr)
+roi = (eng.capital - 25000.0) / 25000.0 * 100.0
+peak_cap, max_dd = 25000.0, 0.0
+for cap in daily_caps:
+    peak_cap = max(peak_cap, cap)
+    max_dd = max(max_dd, (peak_cap - cap) / peak_cap * 100.0)
+
+def _abs(t): return t.pnl_absolute if hasattr(t,'pnl_absolute') else t.pnl_pct*250.0
+wins = [t for t in tr if _abs(t) > 0]
+pf_val = sum(_abs(t) for t in wins) / max(abs(sum(_abs(t) for t in tr if _abs(t)<=0)), 1e-9) if n > 0 else 0
+dr = np.array([p/25000.*100. for p in daily_pnls])
+sharpe = float(dr.mean()/(dr.std()+1e-9)*math.sqrt(365)) if n > 0 else 0
+calmar = roi / max(max_dd, 0.01) if n > 0 else 0
+
+elapsed = time.time() - t0
+
+print(f"\n{'='*65}", flush=True)
+print(f"D_LIQ GOLD-STYLE RESULT:", flush=True)
+print(f"  ROI={roi:+.2f}%  T={n}  DD={max_dd:.2f}%  PF={pf_val:.3f}  Calmar={calmar:.2f}  ({elapsed:.0f}s)", flush=True)
+print(f"  liq_stops={eng.liquidation_stops}", flush=True)
+print(f"GOLD TARGET: ROI=+181.81%  T=2155  DD=17.65%", flush=True)
+print(f"T match: {'PASS' if abs(n-2155)<=10 else 'FAIL'} (diff={n-2155:+d})", flush=True)
+print(f"ROI match: {'PASS' if abs(roi-181.81)<=2.0 else 'FAIL'} (diff={roi-181.81:+.2f}pp)", flush=True)