#!/usr/bin/env python3
"""Frontier (a) — cross-exchange funding dispersion: edge distinct from momentum?

Fetch funding from Bybit + OKX (free) to pair with Binance funding + prices (crypto_pit).
Build cross-sectional signals among multi-venue coins: multi-venue-avg funding (robust carry),
cross-venue dispersion (positioning stress), Binance-premium. Validate each + correlation to
the full crypto momentum book + marginal-alpha regression. Realistic: Reff = return - Binance
funding (traded venue), death-excl, 10bp. Honest prior: low (cross-venue spreads arbitraged).
"""
import json
import math
import os
import sys
import time
import urllib.request

import numpy as np

sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
import pit_sweep  # noqa: E402
from surfer_poc import compute_weights, CFG  # 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"
DAY_MS = 86_400_000
XF = "data/surfer/xfund"
COINS = ["BTC", "ETH", "SOL", "XRP", "DOGE", "ADA", "AVAX", "LINK", "LTC", "DOT",
         "NEAR", "ATOM", "FIL", "ETC", "XLM", "UNI", "AAVE", "BNB"]


def _get(u):
    try:
        return json.load(urllib.request.urlopen(urllib.request.Request(u, headers={"User-Agent": "curl/8"}), timeout=30))
    except Exception:
        return None


def bybit(coin):
    cache = f"{XF}/bybit_{coin}.json"
    if os.path.exists(cache):
        return {int(k): v for k, v in json.load(open(cache)).items()}
    out, end = {}, int(time.time() * 1000)
    for _ in range(40):
        r = _get(f"https://api.bybit.com/v5/market/funding/history?category=linear&symbol={coin}USDT&endTime={end}&limit=200")
        lst = (r or {}).get("result", {}).get("list", [])
        if not lst:
            break
        for x in lst:
            t = int(x["fundingRateTimestamp"]); out.setdefault(t // DAY_MS, 0.0)
            out[t // DAY_MS] += float(x["fundingRate"])
        end = min(int(x["fundingRateTimestamp"]) for x in lst) - 1
        if len(lst) < 200:
            break
        time.sleep(0.06)
    os.makedirs(XF, exist_ok=True); json.dump({str(k): v for k, v in out.items()}, open(cache, "w"))
    return out


def okx(coin):
    cache = f"{XF}/okx_{coin}.json"
    if os.path.exists(cache):
        return {int(k): v for k, v in json.load(open(cache)).items()}
    out, before = {}, ""
    for _ in range(60):
        u = f"https://www.okx.com/api/v5/public/funding-rate-history?instId={coin}-USDT-SWAP&limit=100"
        if before:
            u += f"&after={before}"
        r = _get(u); data = (r or {}).get("data", [])
        if not data:
            break
        for x in data:
            t = int(x["fundingTime"]); out.setdefault(t // DAY_MS, 0.0)
            out[t // DAY_MS] += float(x["fundingRate"])
        before = min(int(x["fundingTime"]) for x in data)
        if len(data) < 100:
            break
        time.sleep(0.06)
    os.makedirs(XF, exist_ok=True); json.dump({str(k): v for k, v in out.items()}, open(cache, "w"))
    return out


def main():
    syms, days, close, qv, fund = pit_sweep.load()
    idx = {s: j for j, s in enumerate(syms)}
    coins = [c for c in COINS if c + "USDT" in idx]
    print(f"fetching Bybit+OKX funding for {len(coins)} coins...")
    by = {c: bybit(c) for c in coins}
    ok = {c: okx(c) for c in coins}
    nby = sum(1 for c in coins if len(by[c]) > 100); nok = sum(1 for c in coins if len(ok[c]) > 100)
    print(f"  Bybit covered {nby}/{len(coins)}, OKX covered {nok}/{len(coins)}")

    N = len(coins); T = len(days)
    di = {int(days[t]): t for t in range(T)}
    bn_f = np.full((T, N), np.nan); by_f = np.full((T, N), np.nan); ok_f = np.full((T, N), np.nan)
    cl = np.full((T, N), np.nan)
    for j, c in enumerate(coins):
        col = idx[c + "USDT"]
        cl[:, j] = close[:, col]; bn_f[:, j] = fund[:, col]
        for d, v in by[c].items():
            if d in di:
                by_f[di[d], j] = v
        for d, v in ok[c].items():
            if d in di:
                ok_f[di[d], j] = v

    R = np.zeros((T, N)); R[1:] = np.log(cl)[1:] - np.log(cl)[:-1]; R = np.where(np.isfinite(R), R, 0.0)
    bnf = np.where(np.isfinite(bn_f), bn_f, 0.0)
    Reff = R - bnf                                                # trade on Binance -> pay Binance funding
    # cross-venue stack
    stack = np.stack([bn_f, by_f, ok_f])                          # [3,T,N]
    avg_f = np.nanmean(stack, axis=0)                             # multi-venue avg funding
    disp_f = np.nanstd(stack, axis=0)                             # cross-venue dispersion
    prem = bn_f - np.nanmean(np.stack([by_f, ok_f]), axis=0)      # Binance premium vs others

    def roll_mean(A, L):
        out = np.full_like(A, np.nan)
        for t in range(L, len(A)):
            out[t] = np.nanmean(A[t - L:t], axis=0)
        return out

    sigs = {
        "carry_BINANCE_only": -roll_mean(np.where(np.isfinite(bn_f), bn_f, np.nan), 7),  # control: is it just major-coin carry?
        "carry_multivenue": -roll_mean(avg_f, 7),                 # long low avg funding (robust carry)
        "venue_dispersion": -roll_mean(disp_f, 7),               # low disagreement? test
        "venue_dispersion+": roll_mean(disp_f, 7),               # high disagreement
        "binance_premium": -roll_mean(prem, 7),                  # fade Binance-crowded
    }
    valid = np.isfinite(cl) & np.isfinite(avg_f)
    year = (1970 + days / 365.25).astype(int)

    def book(sig):
        s = sig.copy(); s[~valid] = np.nan
        return pnl_w(xs_weights(s), Reff, cost_bp=10)

    # full-universe momentum book for correlation
    cw, _ = compute_weights(close, qv, days, CFG)
    cR = np.zeros_like(close); cR[1:] = np.log(close)[1:] - np.log(close)[:-1]; cR = np.where(np.isfinite(cR), cR, 0.0)
    cf = np.where(np.isfinite(fund), fund, 0.0)
    mom = np.sum(cw[:-1] * (cR - cf)[1:], axis=1)
    mom_by = {int(days[1:][i]): mom[i] for i in range(len(mom))}

    print(f"\n===== CROSS-EXCHANGE FUNDING — {len(coins)} multi-venue coins, death-excl, 10bp, deflate N=55 =====")
    print(f"{'signal':>18} {'full':>6} {'IS':>6} {'OOS':>6} {'CPCVmed':>8} {'DSR':>5} {'corr_mom':>8} {'marg_t':>7}")
    pdays = days[1:]
    for nm, sg in sigs.items():
        p = book(sg); v = validate(p, days, 55)
        pb = {int(pdays[i]): p[i] for i in range(len(p))}
        common = sorted(set(pb) & set(mom_by))
        a = np.array([mom_by[d] for d in common]); b = np.array([pb[d] for d in common])
        m = np.isfinite(a) & np.isfinite(b); a, b = a[m], b[m]
        corr = float(np.corrcoef(a, b)[0, 1]) if len(a) > 100 else float("nan")
        beta1 = np.cov(a, b)[0, 1] / (np.var(a) + 1e-12); res = b - beta1 * a
        mt = float(res.mean() / (res.std() / math.sqrt(len(res)) + 1e-12))
        print(f"{nm:>18} {v['full']:>+6.2f} {v['is_']:>+6.2f} {v['oos']:>+6.2f} {v['med']:>+8.2f} {v['dsr']:>5.2f} {corr:>+8.2f} {mt:>+7.2f}")
    print("\nVERDICT: any signal with full+OOS+CPCVmed>0, DSR>0.5, low |corr_mom|, AND marg_t>2 = real distinct edge.")
    print("(marg_t = t-stat of marginal alpha vs momentum book). Honest prior: cross-venue spreads arbitraged -> expect fail.")


if __name__ == "__main__":
    main()