#!/usr/bin/env python3
"""Backtest the EXACT deployable ETF book (the multistrat_paper live pipeline) on ~6y Yahoo history.

Real instruments (SPY/IEF/GLD/PDBC/DBMF + BTC-USD), same adaptive pipeline as the live harness
(vol-norm -> edge-decay trust -> trust-weighted combo -> adaptive risk layer, unlevered). Window is
limited by DBMF inception (~2019), so it spans COVID-2020, bear-2022, bulls-2021/2024 = multiple
regimes. Per-year Sharpe = the regime/robustness check; compared to plain 60/40 (SPY/IEF).
"""
import datetime
import json
import math
import os
import sys
import urllib.request

import numpy as np

sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
from multistrat_paper import INSTR, book_series  # exact live pipeline  # noqa: E402


def yhist(sym, rng="10y"):
    res = json.loads(urllib.request.urlopen(urllib.request.Request(
        f"https://query1.finance.yahoo.com/v8/finance/chart/{sym}?interval=1d&range={rng}",
        headers={"User-Agent": "Mozilla/5.0"}), timeout=30).read())["chart"]["result"][0]
    ts = res["timestamp"]; ind = res["indicators"]
    adj = ind.get("adjclose", [{}])[0].get("adjclose") or ind["quote"][0]["close"]
    return {datetime.datetime.utcfromtimestamp(t).strftime("%Y-%m-%d"): float(c) for t, c in zip(ts, adj) if c is not None}


def stats(r):
    r = r[np.isfinite(r) & (r != 0)]
    ann = r.mean() * 252; vol = r.std() * math.sqrt(252)
    eq = np.cumprod(1 + r); dd = float((eq / np.maximum.accumulate(eq) - 1).min())
    return ann, vol, (ann / vol if vol > 0 else float("nan")), dd


def main():
    data = {nm: yhist(sym) for sym, nm in INSTR}
    dates = sorted(set.intersection(*[set(d) for d in data.values()]))
    R = np.zeros((len(dates), len(INSTR)))
    for j, (_, nm) in enumerate(INSTR):
        s = np.array([data[nm][d] for d in dates]); R[1:, j] = s[1:] / s[:-1] - 1
    print(f"DEPLOYABLE ETF BOOK backtest — {len(dates)} days ({dates[0]}..{dates[-1]})")

    book, w, L = book_series(R)
    a, v, sh, dd = stats(book)
    print(f"  adaptive multi-strat (unlevered): Sharpe {sh:+.2f}  ann {100*a:+.1f}%  vol {100*v:.1f}%  maxDD {100*dd:+.1f}%")
    # 60/40 benchmark over same window
    j_eq = [nm for _, nm in INSTR].index("equity"); j_bd = [nm for _, nm in INSTR].index("bond")
    r6040 = np.zeros(len(dates)); r6040[1:] = 0.6 * R[1:, j_eq] + 0.4 * R[1:, j_bd]
    a2, v2, sh2, dd2 = stats(r6040)
    print(f"  60/40 (SPY/IEF) benchmark:        Sharpe {sh2:+.2f}  ann {100*a2:+.1f}%  vol {100*v2:.1f}%  maxDD {100*dd2:+.1f}%")
    # equity buy-hold
    aeq, veq, sheq, ddeq = stats(np.concatenate([[0], R[1:, j_eq]]))
    print(f"  equity buy-hold (SPY):            Sharpe {sheq:+.2f}  ann {100*aeq:+.1f}%  maxDD {100*ddeq:+.1f}%")
    yr = np.array([int(d[:4]) for d in dates])
    print("  per-year Sharpe (adaptive book): " + " ".join(f"{y}:{stats(book[yr == y])[2]:+.1f}" for y in sorted(set(yr)) if (yr == y).sum() > 100))
    print(f"  current target weights: " + " ".join(f"{nm}:{100*w[j]*L:.0f}%" for j, (_, nm) in enumerate(INSTR)))
    print("\n  VERDICT: adaptive book Sharpe >= 60/40 AND lower maxDD across most years = the deployable book")
    print("  delivers on real ETFs. If ~60/40, the diversification+adaptive layer earns its keep modestly.")


if __name__ == "__main__":
    main()