#!/usr/bin/env python3
"""Stress-test the one survivor: crypto cross-sectional momentum.

Three robustness probes on the broad-but-clean universe (funding-cov>0.90, >900d):
  1. LOOKBACK SWEEP — is the edge smooth across 5..120d (real factor) or a single spike (overfit)?
  2. COIN-BOOTSTRAP — resample WHICH coins are in the cross-section 200× (survivorship proxy):
     does momentum stay positive regardless of which coins survived?
  3. VOL-SCALED — does risk-adjusting the momentum signal (ret/vol) help?
Validation reused from the sweep (full/IS/OOS Sharpe, CPCV, Deflated Sharpe).
"""
import math
import os
import sys

import numpy as np

sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
import crypto_sweep as cs  # noqa: E402
from signal_sweep import xs_weights, pnl_w, validate, sharpe_t  # noqa: E402
import torch  # noqa: E402

DEV = "cuda" if torch.cuda.is_available() else "cpu"
cs.MIN_FUNDCOV, cs.MIN_DAYS = 0.90, 900


def trailing(lc, L):
    out = np.full_like(lc, np.nan); out[L:] = lc[L:] - lc[:-L]; return out


def main():
    syms, days, close, fund = cs.load_crypto()
    T, N = close.shape
    lc = np.log(close)
    R = np.zeros((T, N)); R[1:] = lc[1:] - lc[:-1]; R = np.where(np.isfinite(R), R, 0.0)
    Reff = R - np.where(np.isfinite(fund), fund, 0.0)
    vol30 = np.full_like(lc, np.nan)
    for t in range(30, T):
        vol30[t] = np.nanstd(R[t - 30:t], axis=0)

    print(f"\n===== MOMENTUM ROBUSTNESS — {N} clean coins, {T}d =====")
    print("\n[1] LOOKBACK SWEEP (XS momentum, ~10bp cost)")
    print(f"{'lookback':>9} {'full':>6} {'IS':>6} {'OOS':>6} {'CPCVmed':>8} {'DSR':>5}")
    for L in [5, 10, 20, 30, 45, 60, 90, 120]:
        pnl = pnl_w(xs_weights(trailing(lc, L)), Reff, cost_bp=10)
        v = validate(pnl, days, 8)
        print(f"{L:>9} {v['full']:>+6.2f} {v['is_']:>+6.2f} {v['oos']:>+6.2f} {v['med']:>+8.2f} {v['dsr']:>5.2f}")

    print("\n[2] VOL-SCALED vs RAW (30d)")
    for nm, sg in [("raw_mom30", trailing(lc, 30)), ("volscaled_mom30", trailing(lc, 30) / np.where(vol30 > 0, vol30, np.nan))]:
        v = validate(pnl_w(xs_weights(sg), Reff, cost_bp=10), days, 8)
        print(f"  {nm:>16}: full {v['full']:>+.2f}  OOS {v['oos']:>+.2f}  CPCVmed {v['med']:>+.2f}")

    print("\n[3] COIN-BOOTSTRAP — mom_30 on 200 random half-universes (survivorship proxy)")
    rng = np.random.default_rng(42)
    sig30 = trailing(lc, 30)
    sh = []
    for _ in range(200):
        cols = rng.choice(N, size=max(N // 2, 10), replace=False)
        sub = np.full((T, N), np.nan); sub[:, cols] = sig30[:, cols]
        pnl = pnl_w(xs_weights(sub), Reff[:, :], cost_bp=10)  # weights already zero outside cols
        s = sharpe_t(torch.tensor(pnl, device=DEV, dtype=torch.float64))
        if not math.isnan(s):
            sh.append(s)
    sh = np.array(sh)
    print(f"  draws={len(sh)}  mean Sharpe {sh.mean():+.2f}  median {np.median(sh):+.2f}  "
          f"5th-pct {np.percentile(sh,5):+.2f}  frac>0 {np.mean(sh>0):.2f}")
    print("\nVERDICT: smooth lookback curve + bootstrap frac>0 near 1.0 + 5th-pct>0 => robust real factor.")


if __name__ == "__main__":
    main()