Files
PythagorasGoal/Old/scripts/analysis/validate_worker_pairs.py
Adriano Dal Pastro 14522262e6 chore(reset): v2.0.0 — storico certificato Deribit mainnet, ripartenza pulita
Reset del progetto su fondamenta verificate dopo la scoperta che l'intera
libreria "validata OOS" era artefatto di feed contaminato (print fantasma del
feed Cerbero TESTNET + storico Binance/USDT).

- Storico ricostruito da Deribit MAINNET (ccxt pubblico, tokenless) e
  CERTIFICATO (certify_feed.py): BTC/ETH puliti su TUTTA la storia
  (mediana 2-6 bps vs Coinbase USD), integrita' OHLC + coerenza resample
  (maxΔ 0.00) + cross-venue OK. Alt esclusi (illiquidi/divergenti: LTC/DOGE
  50-82% barre flat; XRP/BNB non certificabili).
- Verdetto sul feed pulito: FADE / PAIRS / XS01 / TSM01 morti (ogni
  portafoglio Sharpe -2.3..-3.0, DD ~40%); solo SH01 e frammenti HONEST
  con segnale residuo, da ri-validare in isolamento.
- Cleanup "restart pulito": strategie, stack live (src/live, src/portfolio,
  runner/executor, yml, docker), ~100 script ricerca/gate, waste/games/
  portfolios, dati non certificati + cache e 60+ diari -> archiviati in Old/
  (preservati, non cancellati). Diario consolidato in un unico documento.
- Skeleton ricerca tenuto: Strategy ABC + indicatori + src/fractal +
  src/backtest/engine + load_data; tool dati certificati (rebuild_history,
  certify_feed, audit_feed, multi_source_check).
- Universo dati ATTIVO: solo BTC/ETH (5m/15m/1h); guardrail fisico
  (load_data su alt -> FileNotFoundError). Esecuzione DISABILITATA, conto flat.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-19 15:20:59 +00:00

89 lines
3.8 KiB
Python

"""Valida il PairsWorker: replay bar-per-bar sui dati storici == backtest pairs_sim?
Come validate_worker_mr01 per MR01: alimenta il PairsWorker con finestre trailing
crescenti (simula il feed live) e confronta trade/capitale finale col backtest di
riferimento scripts/analysis/pairs_research.pairs_sim. Se combaciano, la semantica
live (z-score causale, exit |z|<=z_exit o max_bars, fee 2 gambe) e' fedele.
"""
from __future__ import annotations
import shutil
import sys
import tempfile
from pathlib import Path
import pandas as pd
PROJECT_ROOT = Path(__file__).resolve().parents[2]
sys.path.insert(0, str(PROJECT_ROOT))
from src.live.pairs_worker import PairsWorker
from scripts.analysis.pairs_research import aligned, aligned_ohlc, pairs_sim, pairs_sim_flat
from scripts.strategies.PR01_pairs_reversion import PAIRS
# Config 15m promossa dal gate (gioco Blind Traders + flat-skip): vedi
# docs/diary/2026-06-09-pairs15m-port06-gate.md
CFG_15M = dict(n=66, z_in=1.674, z_exit=1.0, max_bars=35, flat_skip=True)
def replay(a, b, params, data_dir, tf="1h", ohlc=False) -> PairsWorker:
if ohlc:
m = aligned_ohlc(a, b, tf)
df_a = pd.DataFrame({"timestamp": m["timestamp"], "open": m["open_a"],
"high": m["high_a"], "low": m["low_a"], "close": m["close_a"]})
df_b = pd.DataFrame({"timestamp": m["timestamp"], "open": m["open_b"],
"high": m["high_b"], "low": m["low_b"], "close": m["close_b"]})
else:
m = aligned(a, b, tf)
df_a = m[["timestamp"]].copy(); df_a["close"] = m["close_a"].values
df_b = m[["timestamp"]].copy(); df_b["close"] = m["close_b"].values
w = PairsWorker(a, b, tf, params=params, fee_rt=0.001, data_dir=data_dir)
w._save_state = lambda: None
w._log = lambda *a, **k: None
w._notify = lambda *a, **k: None
window = max(60, w.n + 6) # finestra trailing >= n+? : z[i] corretto
for k in range(w.n + 2, len(m) + 1):
lo = max(0, k - window)
w.tick(df_a.iloc[lo:k], df_b.iloc[lo:k])
return w
def _row(label, w, bt):
bt_cap = 1000.0 * (1 + bt["ret"] / 100)
cap_match = abs(w.capital - bt_cap) / bt_cap < 0.02 if bt_cap else False
trd_match = abs(w.total_trades - bt["trades"]) <= max(2, bt["trades"] * 0.02)
ok = "OK" if (cap_match and trd_match) else "DIFF"
ww = w.total_wins / w.total_trades * 100 if w.total_trades else 0
print(f" {label:<16s}{w.capital:>13.0f}{w.total_trades:>6d}{ww:>6.1f} | "
f"{bt_cap:>14.0f}{bt['trades']:>6d}{bt['win']:>6.1f} {ok}")
return ok == "OK"
def main():
print("=" * 100)
print(" VALIDAZIONE PairsWorker — replay live == backtest (fee 0.20% RT/coppia)")
print("=" * 100)
print(f" {'caso':<16s}{'WORKER cap':>13s}{'trd':>6s}{'win%':>6s} | "
f"{'BACKTEST cap':>14s}{'trd':>6s}{'win%':>6s} match?")
print(" " + "-" * 92)
tmp = Path(tempfile.mkdtemp(prefix="pairs_validate_"))
allok = True
try:
# [A] REGRESSIONE 1h (flat_skip=False, close-only) vs pairs_sim
for a, b, p in [pp for pp in PAIRS if (pp[0], pp[1]) in {("ETH", "BTC"), ("BTC", "LTC")}]:
w = replay(a, b, p, tmp, tf="1h", ohlc=False)
allok &= _row(f"{a}/{b} 1h", w, pairs_sim(a, b, **p))
# [B] NUOVO: 15m flat-skip (OHLC) vs pairs_sim_flat
w = replay("ETH", "BTC", CFG_15M, tmp, tf="15m", ohlc=True)
bt = pairs_sim_flat("ETH", "BTC", tf="15m", **CFG_15M)
allok &= _row("ETH/BTC 15m-flat", w, bt)
finally:
shutil.rmtree(tmp, ignore_errors=True)
print(" " + "-" * 92)
print(" match = capitale e trade entro 2% del backtest (diff minime = bar finale aperta).")
print(f" ESITO COMPLESSIVO: {'TUTTO OK' if allok else 'DIFFERENZE -> INDAGARE'}")
if __name__ == "__main__":
main()