"""Realized-Vol Gated Crossover — 5y Klines ========================================== Critical fee-viability test. EV per trade on ungated crossover: +0.0002% (UNGATED) EV per trade on BEST3 hour gate: +0.0014% After 4bps maker fee: -0.039% ← NEGATIVE Hypothesis: Q4 realized_vol days (volatile) have +23pp edge on the old directional strategy. In the crossover framing, volatile days should generate LARGER per-trade moves → higher EV per trade → potentially fee-viable. This script: 1. Computes per-day realized_vol 2. Classifies days into quartiles (Q1=calm, Q4=volatile) 3. Runs crossover (vel_div <= -0.020 → LONG, exit vel_div >= +0.020) per quartile 4. Reports per-trade stats (avg_win%, avg_loss%, EV%) and PF per quartile 5. Also tests SHORT direction (vel_div >= +0.020 → SHORT, exit vel_div <= -0.020) in Q4 volatile days (should benefit from +23pp historical edge) Fee thresholds: Maker RT: 4bps = 0.04% ← minimum viable EV per trade Taker RT: 10bps = 0.10% ← typical market order Output: run_logs/rvol_gated_crossover_YYYYMMDD_HHMMSS.csv Runtime: ~15s """ import sys, time, csv, gc sys.stdout.reconfigure(encoding='utf-8', errors='replace') from pathlib import Path from datetime import datetime from collections import defaultdict import numpy as np import pandas as pd VBT_DIR = Path(r"C:\Users\Lenovo\Documents\- DOLPHIN NG HD HCM TSF Predict\vbt_cache_klines") LOG_DIR = Path(r"C:\Users\Lenovo\Documents\- DOLPHIN NG HD HCM TSF Predict\nautilus_dolphin\run_logs") ENTRY_T = 0.020 MAX_HOLD = 20 # bars safety cap YEARS = ['2021', '2022', '2023', '2024', '2025', '2026'] parquet_files = sorted(VBT_DIR.glob("*.parquet")) parquet_files = [p for p in parquet_files if 'catalog' not in str(p)] total = len(parquet_files) print(f"Files: {total}") # Pass 1: compute realized_vol per day daily_rvol = {} daily_n = {} t0 = time.time() for pf in parquet_files: ds = pf.stem try: df = pd.read_parquet(pf, columns=['BTCUSDT']) except Exception: continue btc = df['BTCUSDT'].values.astype(np.float64) btc = btc[np.isfinite(btc) & (btc > 0)] if len(btc) < 2: continue log_r = np.diff(np.log(btc)) daily_rvol[ds] = float(np.std(log_r)) daily_n[ds] = len(btc) # Quartile breakpoints rvols = np.array(list(daily_rvol.values())) q25, q50, q75 = np.percentile(rvols, [25, 50, 75]) print(f"Realized-vol quartiles: Q1<{q25:.6f} Q2<{q50:.6f} Q3<{q75:.6f} Q4>={q75:.6f}") def rvol_quartile(rv): if rv < q25: return 'Q1_calm' if rv < q50: return 'Q2' if rv < q75: return 'Q3' return 'Q4_volatile' # stats[(rvol_q, direction)] = {wins, losses, gw, gl, n, total_hold} stats = defaultdict(lambda: {'wins': 0, 'losses': 0, 'gw': 0.0, 'gl': 0.0, 'n': 0, 'total_hold': 0}) # Also per year breakdown stats_yr = defaultdict(lambda: {'wins': 0, 'losses': 0, 'gw': 0.0, 'gl': 0.0, 'n': 0, 'total_hold': 0}) daily_rows = [] print(f"\nPass 2: running crossover per rvol quartile...") for i, pf in enumerate(parquet_files): ds = pf.stem year = ds[:4] rv = daily_rvol.get(ds) if rv is None: continue rvq = rvol_quartile(rv) try: df = pd.read_parquet(pf) except Exception: continue if 'vel_div' not in df.columns or 'BTCUSDT' not in df.columns: continue vd = df['vel_div'].values.astype(np.float64) btc = df['BTCUSDT'].values.astype(np.float64) vd = np.where(np.isfinite(vd), vd, 0.0) btc = np.where(np.isfinite(btc) & (btc > 0), btc, np.nan) n = len(btc) del df if n < MAX_HOLD + 5: del vd, btc continue # LONG crossover: enter vel_div <= -ENTRY_T, exit vel_div >= +ENTRY_T long_entry = (vd <= -ENTRY_T) & np.isfinite(btc) long_cross = (vd >= ENTRY_T) # SHORT crossover: enter vel_div >= +ENTRY_T, exit vel_div <= -ENTRY_T short_entry = (vd >= ENTRY_T) & np.isfinite(btc) short_cross = (vd <= -ENTRY_T) day_stats = {'L': {}, 'S': {}} for direction, entry_mask, cross_back in [ ('L', long_entry, long_cross), ('S', short_entry, short_cross)]: d_wins = d_losses = 0 d_gw = d_gl = 0.0 d_n = d_hold = 0 for t in range(n - MAX_HOLD): if not entry_mask[t]: continue ep = btc[t] if not np.isfinite(ep) or ep <= 0: continue # Find exit exit_bar = MAX_HOLD for k in range(1, MAX_HOLD + 1): tb = t + k if tb >= n: exit_bar = k break if cross_back[tb]: exit_bar = k break tb = t + exit_bar if tb >= n: continue xp = btc[tb] if not np.isfinite(xp) or xp <= 0: continue if direction == 'L': ret = (xp - ep) / ep else: ret = (ep - xp) / ep # SHORT return if ret >= 0: d_wins += 1; d_gw += ret else: d_losses += 1; d_gl += abs(ret) d_n += 1; d_hold += exit_bar key = (rvq, direction) key_yr = (rvq, direction, year) for k in [key]: s = stats[k] s['wins'] += d_wins; s['losses'] += d_losses s['gw'] += d_gw; s['gl'] += d_gl s['n'] += d_n; s['total_hold'] += d_hold s = stats_yr[key_yr] s['wins'] += d_wins; s['losses'] += d_losses s['gw'] += d_gw; s['gl'] += d_gl s['n'] += d_n; s['total_hold'] += d_hold day_stats[direction] = { 'n': d_n, 'wr': d_wins/d_n*100 if d_n > 0 else 0, 'avg_win': d_gw/d_wins*100 if d_wins > 0 else 0, 'avg_loss': d_gl/d_losses*100 if d_losses > 0 else 0, } daily_rows.append({ 'date': ds, 'year': year, 'rvol_q': rvq, 'rvol': round(rv, 8), 'n_long': day_stats['L'].get('n', 0), 'wr_long': round(day_stats['L'].get('wr', 0), 2), 'n_short': day_stats['S'].get('n', 0), 'wr_short': round(day_stats['S'].get('wr', 0), 2), }) del vd, btc, long_entry, long_cross, short_entry, short_cross if (i + 1) % 200 == 0: gc.collect() print(f" [{i+1}/{total}] {ds} {time.time()-t0:.0f}s") elapsed = time.time() - t0 print(f"\nPass complete: {elapsed:.0f}s\n") # ─── Results ────────────────────────────────────────────────────────────────── RVOL_BINS = ['Q1_calm', 'Q2', 'Q3', 'Q4_volatile'] DIRS = ['L', 'S'] rows = [] print(f"{'RVolQ':<14} {'Dir'} {'N':>8} {'PF':>7} {'WR%':>6} {'AvgH':>5} " f"{'AvgW%':>8} {'AvgL%':>8} {'EV%':>9} {'EV-4bp':>9} {'EV-10bp':>10}") print("-" * 110) for rvq in RVOL_BINS: for direction in DIRS: key = (rvq, direction) s = stats.get(key, {'wins': 0, 'losses': 0, 'gw': 0.0, 'gl': 0.0, 'n': 0, 'total_hold': 0}) n = s['n'] if n == 0: continue wr = s['wins'] / n * 100 pf = s['gw'] / s['gl'] if s['gl'] > 0 else 999.0 avg_hold = s['total_hold'] / n avg_win = s['gw'] / s['wins'] * 100 if s['wins'] > 0 else 0.0 avg_loss = s['gl'] / s['losses'] * 100 if s['losses'] > 0 else 0.0 ev = (s['gw'] - s['gl']) / n * 100 # EV per trade in % ev_4bp = ev - 0.04 # after maker RT fee ev_10bp = ev - 0.10 # after taker RT fee marker = " ◄◄ FEE-VIABLE (maker)" if ev_4bp > 0 else (" ◄ BORDERLINE" if ev > 0.03 else "") print(f"{rvq:<14} {direction} {n:>8,} {pf:>7.4f} {wr:>6.2f}% {avg_hold:>5.2f} " f"{avg_win:>8.4f}% {avg_loss:>8.4f}% {ev:>+9.4f}% {ev_4bp:>+9.4f}% {ev_10bp:>+10.4f}%{marker}") # Per-year PF yr_pfs = {} for yr in YEARS: ky = (rvq, direction, yr) sy = stats_yr.get(ky) if sy and sy['n'] > 0: pfy = sy['gw'] / sy['gl'] if sy['gl'] > 0 else 999.0 yr_pfs[yr] = round(pfy, 3) else: yr_pfs[yr] = float('nan') rows.append({ 'rvol_q': rvq, 'direction': direction, 'n_trades': n, 'pf': round(pf, 4), 'wr': round(wr, 3), 'avg_hold_bars': round(avg_hold, 2), 'avg_win_pct': round(avg_win, 5), 'avg_loss_pct': round(avg_loss, 5), 'ev_pct': round(ev, 5), 'ev_minus_4bp': round(ev_4bp, 5), 'ev_minus_10bp': round(ev_10bp, 5), **{f'pf_{yr}': yr_pfs[yr] for yr in YEARS}, }) print() # Per-year breakdown for Q4 only print(f"\n{'='*80}") print(f" Q4 VOLATILE — Per-Year PF (LONG and SHORT crossover)") print(f"{'='*80}") print(f" {'Year':<6} {'L_PF':>7} {'L_N':>8} {'L_EV%':>9} | {'S_PF':>7} {'S_N':>8} {'S_EV%':>9}") print(f" {'-'*70}") for yr in YEARS: for direction, label in [('L', 'L'), ('S', 'S')]: key = ('Q4_volatile', direction, yr) s = stats_yr.get(key) if s and s['n'] > 0: pfy = s['gw'] / s['gl'] if s['gl'] > 0 else 999.0 evy = (s['gw'] - s['gl']) / s['n'] * 100 else: pfy = evy = float('nan') globals()[f'{label}_{yr}_pf'] = pfy globals()[f'{label}_{yr}_ev'] = evy globals()[f'{label}_{yr}_n'] = s['n'] if s else 0 print(f" {yr:<6} {globals()[f'L_{yr}_pf']:>7.3f} {globals()[f'L_{yr}_n']:>8,} " f"{globals()[f'L_{yr}_ev']:>+9.4f}% | " f"{globals()[f'S_{yr}_pf']:>7.3f} {globals()[f'S_{yr}_n']:>8,} " f"{globals()[f'S_{yr}_ev']:>+9.4f}%") # ─── Save ────────────────────────────────────────────────────────────────────── LOG_DIR.mkdir(exist_ok=True) ts_str = datetime.now().strftime("%Y%m%d_%H%M%S") out_csv = LOG_DIR / f"rvol_gated_crossover_{ts_str}.csv" if rows: with open(out_csv, 'w', newline='') as f: w = csv.DictWriter(f, fieldnames=rows[0].keys()) w.writeheader(); w.writerows(rows) print(f"\n → {out_csv}") daily_csv = LOG_DIR / f"rvol_gated_daily_{ts_str}.csv" if daily_rows: with open(daily_csv, 'w', newline='') as f: w = csv.DictWriter(f, fieldnames=daily_rows[0].keys()) w.writeheader(); w.writerows(daily_rows) print(f" → {daily_csv}") print(f"\n Runtime: {elapsed:.0f}s") print(f"\n KEY:") print(f" EV-4bp > 0 = fee-viable with maker orders") print(f" EV-10bp > 0 = fee-viable with market orders") print(f" Q4_volatile = top 25% most volatile days — target regime")