#!/usr/bin/env python3
"""What can we DO with diversification: add more uncorrelated net-positive streams (the sqrt(N) lever).

Base 6 (SPY/IEF/GLD/PDBC/DBMF/BTC) + candidates: VNQ(REITs), TIP(infl-linked), HYG(HY credit),
EFA(intl eq), EEM(EM eq), PUTW(vol-risk-premium/buy-write). Same adaptive pipeline (edge-decay
trust auto-down-weights the bad ones). Does the expanded book beat the base-6? The trust layer
decides which candidates earn their place.
"""
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 book_series  # exact adaptive pipeline  # noqa: E402

BASE = [("SPY", "equity"), ("IEF", "bond"), ("GLD", "gold"), ("PDBC", "commod"), ("DBMF", "trend"), ("BTC-USD", "crypto")]
CAND = [("VNQ", "reit"), ("TIP", "tips"), ("HYG", "hycredit"), ("EFA", "intl"), ("EEM", "em"), ("PUTW", "volprem")]


def yhist(sym):
    res = json.loads(urllib.request.urlopen(urllib.request.Request(
        f"https://query1.finance.yahoo.com/v8/finance/chart/{sym}?interval=1d&range=10y",
        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 run(instr, data, label):
    dates = sorted(set.intersection(*[set(data[nm]) for _, nm in instr]))
    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
    book, w, L = book_series(R)
    a, v, sh, dd = stats(book)
    yr = np.array([int(d[:4]) for d in dates])
    py = " ".join(f"{y}:{stats(book[yr==y])[2]:+.1f}" for y in sorted(set(yr)) if (yr == y).sum() > 100)
    print(f"  {label:>16} ({len(instr)} streams, {len(dates)}d): Sharpe {sh:+.2f}  ann {100*a:+.1f}%  maxDD {100*dd:+.1f}%")
    print(f"       per-year: {py}")
    return w, [nm for _, nm in instr]


def main():
    allinstr = BASE + CAND
    data = {nm: yhist(sym) for sym, nm in allinstr}
    print(f"EXPANDED BOOK (diversification lever) — base 6 vs +candidates")
    run(BASE, data, "base-6")
    w, names = run(allinstr, data, "expanded-12")
    print(f"\n  trust-layer weights in expanded book (which candidates earned their place):")
    order = sorted(range(len(names)), key=lambda j: -w[j])
    for j in order:
        print(f"     {names[j]:>9}: {100*w[j]:>5.1f}%")
    print("\n  VERDICT: expanded Sharpe > base-6 = more uncorrelated streams lift the book (diversification works).")
    print("  If ~equal, the candidates are too correlated / not net-positive -> 6 streams already captures it.")


if __name__ == "__main__":
    main()