"""DEEP-DIVE: crypto[sessione USA] -> indice EUROPEO[overnight successivo]. Reale o artefatto?

Lo sweep ha trovato un forte segnale: crypto[T-8h->T] (T~00:00 UTC, fine sessione USA) predice il
future europeo (ESTX50/DAX)[T->T+6h] con t_crypto incrementale ~8, Sharpe 2.5, 3/3 anni. Verifiche:
  (1) ROBUSTEZZA su T (ora entrata): un effetto vero non e' a coltello su una sola ora.
  (2) vs SEMPRE-LONG: l'overnight ha un drift? il crypto AGGIUNGE oltre il long incondizionato?
  (3) GAP 1-2h tra fine-segnale e inizio-cattura: se sopravvive, niente contaminazione di bordo.
  (4) vs FUTURE-OWN: il crypto batte il momentum proprio del future (gia' nel t incrementale).
Dati: cache (fut europei + crypto 1h). sqrt(252), net 2bps.
"""
import sys
from pathlib import Path
import numpy as np, pandas as pd

ROOT = Path(__file__).resolve().parents[2]; RAW = ROOT / "data" / "raw"
sys.path.insert(0, str(ROOT)); sys.path.insert(0, str(ROOT / "scripts" / "research"))
from crypto_lead_harness import crypto_hourly, at
COST = 0.0002


def fut_hourly(sym):
    d = pd.read_parquet(RAW / f"fut_{sym.lower()}_1h.parquet")
    return pd.Series(d["close"].astype(float).values, index=pd.to_datetime(d["timestamp"], unit="ms", utc=True)).sort_index()


def _sh(r):
    r = np.asarray(r, float); r = r[np.isfinite(r)]
    return float(np.mean(r) / np.std(r) * np.sqrt(252)) if len(r) > 5 and np.std(r) > 0 else 0.0


def series(fut, bc, T, S=8, H=6, gap=0):
    days = pd.date_range(fut.index[0].normalize(), fut.index[-1].normalize(), freq="D", tz="UTC")
    rows = []
    for D in days:
        te = D + pd.Timedelta(hours=T)
        f0, f1 = at(fut, te - pd.Timedelta(hours=S)), at(fut, te)
        fcs, fce = at(fut, te + pd.Timedelta(hours=gap)), at(fut, te + pd.Timedelta(hours=gap + H))
        c0, c1 = at(bc, te - pd.Timedelta(hours=S)), at(bc, te)
        if not all(np.isfinite(v) and v > 0 for v in (f0, f1, fcs, fce, c0, c1)):
            continue
        rows.append((D, c1/c0 - 1, f1/f0 - 1, fce/fcs - 1))
    Dd = pd.DataFrame(rows, columns=["d", "csig", "fctrl", "cap"]).set_index("d")
    return Dd[Dd["cap"].abs() > 1e-9]


def stats(Dd):
    x, ctrl, y = Dd["csig"].values, Dd["fctrl"].values, Dd["cap"].values
    def z(a):
        s = a.std(); return (a - a.mean()) / s if s > 0 else a * 0
    X = np.column_stack([np.ones(len(y)), z(x), z(ctrl)])
    beta, *_ = np.linalg.lstsq(X, z(y), rcond=None)
    resid = z(y) - X @ beta; dof = max(len(y) - 3, 1)
    se = np.sqrt(np.sum(resid**2)/dof * np.diag(np.linalg.inv(X.T@X)))
    t_c = float(beta[1]/se[1]) if se[1] > 0 else 0.0
    crypto = np.sign(x)*y - COST
    futown = np.sign(ctrl)*y - COST
    always = y - COST
    yrs = Dd.index.year.values
    py = {int(v): round(_sh(crypto[yrs==v]),2) for v in sorted(set(yrs)) if (yrs==v).sum()>=30}
    return dict(n=len(Dd), t_crypto=round(t_c,2), sh_crypto=round(_sh(crypto),2),
                sh_futown=round(_sh(futown),2), sh_always=round(_sh(always),2),
                ann_crypto=round(float(np.nanmean(crypto)*252*100),1), per_year=py)


def main():
    print("="*96); print("  DEEP-DIVE crypto -> indice EUROPEO overnight (reale o artefatto?)"); print("="*96)
    bcs = {l: crypto_hourly(l) for l in ("BTC","ETH")}
    for sym in ("ESTX50","DAX"):
        fut = fut_hourly(sym)
        print(f"\n  ===== {sym} =====")
        print(f"  (1) ROBUSTEZZA su T (lead=BTC, S=8h H=6h gap=0): t_crypto | Sh crypto vs futown vs always-long")
        for T in (20,21,22,23,0,1,2,3,4):
            s = stats(series(fut, bcs["BTC"], T))
            print(f"      T={T:>2}h: n={s['n']} t {s['t_crypto']:+.1f} | crypto {s['sh_crypto']:+.2f}  futown {s['sh_futown']:+.2f}  always {s['sh_always']:+.2f}  ann {s['ann_crypto']:+.1f}% {s['per_year']}")
        print(f"  (3) GAP test (T=0h, cattura inizia +1h e +2h dopo il segnale):")
        for g in (0,1,2):
            s = stats(series(fut, bcs["BTC"], 0, gap=g))
            print(f"      gap={g}h: t {s['t_crypto']:+.1f} | crypto {s['sh_crypto']:+.2f} always {s['sh_always']:+.2f}")
        print(f"  (lead ETH, T=0h): ", end="")
        s = stats(series(fut, bcs["ETH"], 0)); print(f"t {s['t_crypto']:+.1f} crypto {s['sh_crypto']:+.2f} always {s['sh_always']:+.2f} {s['per_year']}")
    print("\n  LETTURA: se 'crypto' >> 'always' E >> 'futown' E regge su T e col gap -> lead REALE (crypto")
    print("           anticipa il catch-up europeo). Se crypto ~ always -> e' solo overnight-drift europeo.")


if __name__ == "__main__":
    main()