PythagorasGoal/scripts/analysis/pairs_research.py

"""Verifica indipendente + ricerca PAIRS / SPREAD MEAN-REVERSION fra cripto.

Famiglia nuova market-neutral (distinta da tutto l'esistente, single-asset).
Idea: il log-ratio di due cripto oscilla attorno alla media; z-score estremo -> rientra.

Engine ONESTO (no look-ahead, verificato):
  - r[i] = log(closeA[i]/closeB[i]); ma/sd = rolling(n) su r -> usano solo r[<=i].
  - z[i] = (r[i]-ma[i])/sd[i]. ENTRY a close[i] (eseguibile):
      z<=-z_in -> LONG ratio (long A / short B);  z>=+z_in -> SHORT ratio.
  - EXIT quando |z[j]| <= z_exit (rientro) o time-limit max_bars, a close[j].
  - pairs = 2 GAMBE -> fee = 2*fee_rt*lev (0.20% RT/coppia a fee_rt=0.001), il doppio
    del single-asset. Rendimento neutral = retA*d - retB*d (notional uguale per gamba).
  - non-overlap, capitale composto. Filtro candele sporche: salta salti |dr|>jump_max.
  - Ritorno riportato come CAGR e Sharpe ANNUALIZZATO sul tempo reale (no sqrt(n_trade)).
"""
from __future__ import annotations

import sys
from pathlib import Path

import numpy as np
import pandas as pd

PROJECT_ROOT = Path(__file__).resolve().parents[2]
sys.path.insert(0, str(PROJECT_ROOT))

from src.data.downloader import load_data

FEE_RT, LEV, POS, OOS_FRAC = 0.001, 3.0, 0.15, 0.30
BARS_YEAR = 8760  # 1h


def aligned(a: str, b: str, tf: str = "1h"):
    da = load_data(a, tf)[["timestamp", "open", "high", "low", "close"]].rename(columns=lambda x: x + "_a" if x != "timestamp" else x)
    db = load_data(b, tf)[["timestamp", "close"]].rename(columns={"close": "close_b"})
    m = da.merge(db, on="timestamp", how="inner").reset_index(drop=True)
    m["dt"] = pd.to_datetime(m["timestamp"], unit="ms", utc=True)
    return m


def pairs_sim(a, b, tf="1h", n=50, z_in=2.0, z_exit=0.5, max_bars=72,
              jump_max=0.08, fee_rt=FEE_RT, lev=LEV, pos=POS, split_frac=0.0):
    m = aligned(a, b, tf)
    ca, cb = m["close_a"].values, m["close_b"].values
    r = np.log(ca / cb)
    dr = np.abs(np.diff(r, prepend=r[0]))               # salto 1-bar del log-ratio
    ma = pd.Series(r).rolling(n).mean().values
    sd = pd.Series(r).rolling(n).std().values
    z = (r - ma) / np.where(sd == 0, np.nan, sd)        # causale: usa r[<=i]
    ts = m["dt"]; N = len(r)
    split = int(N * split_frac)
    fee = 2 * fee_rt * lev                               # 2 gambe
    cap = peak = 1000.0; dd = 0.0; last = -1
    trades = wins = 0; rets = []; yearly = {}; yearly_n = {}
    eq_ts: list = []; eq_v: list = []
    for i in range(n + 1, N - 1):
        if i < split or np.isnan(z[i]) or dr[i] > jump_max:
            continue
        if i <= last:
            continue
        if z[i] <= -z_in:
            d = 1
        elif z[i] >= z_in:
            d = -1
        else:
            continue
        # exit: |z|<=z_exit o max_bars
        j = min(i + max_bars, N - 1)
        for k in range(1, max_bars + 1):
            jj = i + k
            if jj >= N:
                j = N - 1; break
            if abs(z[jj]) <= z_exit:
                j = jj; break
            j = jj
        retA = (ca[j] - ca[i]) / ca[i]
        retB = (cb[j] - cb[i]) / cb[i]
        ret = (retA - retB) * d * lev - fee             # long A / short B (o viceversa)
        cap = max(cap + cap * pos * ret, 10.0)
        peak = max(peak, cap); dd = max(dd, (peak - cap) / peak)
        trades += 1; wins += ret > 0; rets.append(ret * pos); last = j
        eq_ts.append(ts.iloc[j]); eq_v.append(cap)
        yearly[ts.iloc[i].year] = yearly.get(ts.iloc[i].year, 0.0) + ret * 100
        yearly_n[ts.iloc[i].year] = yearly_n.get(ts.iloc[i].year, 0) + 1
    yrs_span = (ts.iloc[-1] - ts.iloc[max(split, 0)]).days / 365.25 or 1
    sharpe = float(np.mean(rets) / np.std(rets) * np.sqrt(BARS_YEAR / np.mean([max_bars])) ) if len(rets) > 1 and np.std(rets) > 0 else 0.0
    # Sharpe annualizzato sul tempo reale: usa rendimenti per-trade scalati alla frequenza media
    if len(rets) > 1 and np.std(rets) > 0:
        trades_per_year = trades / yrs_span
        sharpe = float(np.mean(rets) / np.std(rets) * np.sqrt(trades_per_year))
    ret_tot = (cap / 1000 - 1) * 100
    cagr = ((cap / 1000) ** (1 / yrs_span) - 1) * 100 if cap > 0 else -100
    return dict(trades=trades, win=wins / trades * 100 if trades else 0, ret=ret_tot, cagr=cagr,
                dd=dd * 100, sharpe=sharpe, yearly=yearly, yearly_n=yearly_n,
                eq_ts=eq_ts, eq_v=eq_v)


def check_no_lookahead():
    """Perturba il FUTURO del ratio e verifica che z[i] non cambi (causalita')."""
    m = aligned("ETH", "BTC")
    r = np.log(m["close_a"].values / m["close_b"].values)
    n = 50; i = 1000
    z_i = (r[i] - pd.Series(r).rolling(n).mean().values[i]) / pd.Series(r).rolling(n).std().values[i]
    r2 = r.copy(); r2[i + 1:] += 0.5      # stravolge il futuro
    z_i2 = (r2[i] - pd.Series(r2).rolling(n).mean().values[i]) / pd.Series(r2).rolling(n).std().values[i]
    print(f"  no-look-ahead: z[i]={z_i:.6f} vs z[i] con futuro perturbato={z_i2:.6f} -> "
          f"{'OK (identico)' if abs(z_i - z_i2) < 1e-9 else 'VIOLAZIONE!'}")


def main():
    print("=" * 104)
    print(f"  PAIRS spread reversion — NETTO fee 0.20% RT/coppia (2 gambe), leva {LEV:.0f}x, OOS ultimo {int(OOS_FRAC*100)}%")
    print("=" * 104)
    check_no_lookahead()
    pairs = [("ETH", "BTC"), ("LTC", "ETH"), ("ADA", "ETH"), ("SOL", "ETH"),
             ("BNB", "BTC"), ("XRP", "BTC"), ("SOL", "BTC"), ("DOGE", "BTC")]
    print(f"\n  {'coppia':<10s}{'trd':>5s}{'win%':>6s}{'FULL%':>8s}{'OOS%':>8s}{'CAGR%':>7s}"
          f"{'DD%':>6s}{'oDD%':>6s}{'Shrp':>6s}{'anni+':>7s}{'fee0.4%RT':>11s}")
    print("  " + "-" * 96)
    for a, b in pairs:
        f = pairs_sim(a, b, n=50, z_in=2.0, z_exit=0.5, max_bars=72)
        o = pairs_sim(a, b, n=50, z_in=2.0, z_exit=0.5, max_bars=72, split_frac=1 - OOS_FRAC)
        hi = pairs_sim(a, b, n=50, z_in=2.0, z_exit=0.5, max_bars=72, fee_rt=0.002)  # 0.4% RT/coppia
        yrs = f["yearly"]; pos_y = sum(1 for v in yrs.values() if v > 0)
        print(f"  {a+'/'+b:<10s}{f['trades']:>5d}{f['win']:>6.1f}{f['ret']:>+8.0f}{o['ret']:>+8.0f}"
              f"{f['cagr']:>7.0f}{f['dd']:>6.0f}{o['dd']:>6.0f}{f['sharpe']:>6.2f}{f'{pos_y}/{len(yrs)}':>7s}"
              f"{hi['ret']:>+11.0f}")
    # correlazione con BTC daily (market-neutrality) sulla coppia migliore
    print("\n  Verifica market-neutrality ETH/BTC: per-anno")
    f = pairs_sim("ETH", "BTC", n=50, z_in=2.0, z_exit=0.5, max_bars=72)
    print("  " + "  ".join(f"{y}:{v:+.0f}%" for y, v in sorted(f["yearly"].items())))


if __name__ == "__main__":
    main()