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>
This commit is contained in:
Adriano Dal Pastro
2026-06-19 15:16:03 +00:00
parent 8401a280b9
commit 14522262e6
383 changed files with 1971 additions and 779 deletions
+148
View File
@@ -0,0 +1,148 @@
"""MR01 — Mean Reversion da estremi RSI.
Approccio opposto allo squeeze: quando il prezzo va troppo lontano troppo veloce,
scommetti che torni indietro. Autocorrelazione lag-1 negativa (-0.21 BTC, -0.35 ETH)
conferma che il mercato a 15m è mean-reverting.
IN:
- OHLCV DataFrame
- Parametri: rsi_period, rsi_oversold, rsi_overbought, hold_bars,
volume_filter (volume > N× media), atr_filter (move > N×ATR)
OUT:
- Signal: long quando RSI < oversold, short quando RSI > overbought
- BacktestResult con metriche
Logica:
1. RSI scende sotto soglia oversold → LONG (prezzo tornerà su)
2. RSI sale sopra soglia overbought → SHORT (prezzo tornerà giù)
3. Filtro opzionale: volume spike conferma l'eccesso
4. Filtro opzionale: move recente > N×ATR (eccesso di prezzo)
5. Hold fisso, poi chiudi
"""
from __future__ import annotations
import sys
sys.path.insert(0, ".")
import numpy as np
import pandas as pd
from src.strategies.base import Strategy, Signal
def rsi(close, period=14):
delta = np.diff(close)
gain = np.where(delta > 0, delta, 0)
loss = np.where(delta < 0, -delta, 0)
result = np.full(len(close), 50.0)
if len(gain) < period:
return result
ag = np.mean(gain[:period])
al = np.mean(loss[:period])
for i in range(period, len(delta)):
ag = (ag * (period - 1) + gain[i]) / period
al = (al * (period - 1) + loss[i]) / period
result[i + 1] = 100 if al == 0 else 100 - 100 / (1 + ag / al)
return result
class MeanReversionRSI(Strategy):
name = "MR01_mean_reversion_rsi"
description = "Mean reversion da estremi RSI — fade eccessi direzionali"
default_assets = ["BTC", "ETH"]
default_timeframes = ["15m", "1h"]
fee_rt = 0.002
def generate_signals(self, df, ts, **params):
c = df["close"].values
h = df["high"].values
l = df["low"].values
v = df["volume"].values
n = len(c)
rsi_period = params.get("rsi_period", 14)
oversold = params.get("rsi_oversold", 25)
overbought = params.get("rsi_overbought", 75)
use_vol_filter = params.get("vol_filter", False)
use_atr_filter = params.get("atr_filter", False)
cooldown = params.get("cooldown", 4)
rsi_vals = rsi(c, rsi_period)
# Volume media rolling
vol_ma = np.full(n, np.nan)
for i in range(20, n):
vol_ma[i] = np.mean(v[i - 20:i])
# ATR
tr = np.maximum(h[1:] - l[1:],
np.maximum(np.abs(h[1:] - c[:-1]), np.abs(l[1:] - c[:-1])))
atr_vals = np.full(n, np.nan)
for i in range(15, len(tr)):
atr_vals[i + 1] = np.mean(tr[i - 14:i])
signals = []
last_signal_idx = -cooldown
for i in range(20, n):
if i - last_signal_idx < cooldown:
continue
direction = 0
if rsi_vals[i] < oversold:
direction = 1 # oversold → long
elif rsi_vals[i] > overbought:
direction = -1 # overbought → short
if direction == 0:
continue
# Volume filter
if use_vol_filter and not np.isnan(vol_ma[i]):
if v[i] < vol_ma[i] * 1.5:
continue
# ATR filter: il move recente deve essere > 1.5× ATR
if use_atr_filter and not np.isnan(atr_vals[i]):
recent_move = abs(c[i] - c[max(0, i - 3)]) / c[max(0, i - 3)]
if recent_move < atr_vals[i] / c[i] * 1.5:
continue
signals.append(Signal(
idx=i, direction=direction, entry_price=c[i],
metadata={"rsi": float(rsi_vals[i])},
))
last_signal_idx = i
return signals
if __name__ == "__main__":
strategy = MeanReversionRSI()
configs = [
("RSI25/75", {}),
("RSI20/80", {"rsi_oversold": 20, "rsi_overbought": 80}),
("RSI25/75+vol", {"vol_filter": True}),
("RSI20/80+vol", {"rsi_oversold": 20, "rsi_overbought": 80, "vol_filter": True}),
("RSI25/75+atr", {"atr_filter": True}),
("RSI20/80+vol+atr", {"rsi_oversold": 20, "rsi_overbought": 80, "vol_filter": True, "atr_filter": True}),
]
all_results = []
for label, params in configs:
for asset in ["BTC", "ETH"]:
for tf in ["15m", "1h"]:
for hold in [3, 6]:
r = strategy.backtest(asset, tf, hold=hold, **params)
if r and r.trades >= 30:
r.strategy_name = f"MR01 {label} h={hold}"
all_results.append(r)
all_results.sort(key=lambda r: r.accuracy, reverse=True)
print(f"\n{'=' * 120}")
print(f" MR01 MEAN REVERSION RSI — TOP 20")
print(f"{'=' * 120}")
for r in all_results[:20]:
r.print_summary()
if all_results:
all_results[0].print_yearly()