"""Backtest liquidation clusters: how often did the price reach the largest liquidation cluster near it within the
next hours? Python 3.9+, standard library only. Reads the heatmap history (GET /heatmap/{coin}) and the candles
(GET /candles/{coin}) of the same window and checks every hourly column.

    export BLOCKMETRIC_API_KEY=bm_live_...            # free key: every coin, the last 24 hours (DAYS=1); Pro: every coin, 1 year
    export BLOCKMETRIC_BASE_URL=https://<domain>/api/v1
    python backtest.py

Options: COIN (BTC), DAYS (14, at most 30 with tf=1h), MIN_USD (5000000), MAX_DISTANCE (0.03), HORIZON_HOURS (24),
CSV (file name for every test, optional). Descriptive statistics over a short window, not a trading signal.
"""
import csv
import json
import os
import urllib.error
import urllib.parse
import urllib.request
from datetime import datetime, timedelta, timezone

BASE = os.environ.get("BLOCKMETRIC_BASE_URL", "").rstrip("/")
KEY = os.environ.get("BLOCKMETRIC_API_KEY")
COIN = os.environ.get("COIN", "BTC")
DAYS = min(30, int(os.environ.get("DAYS", "14")))
MIN_USD = float(os.environ.get("MIN_USD", "5000000"))
MAX_DISTANCE = float(os.environ.get("MAX_DISTANCE", "0.03"))
HORIZON = int(os.environ.get("HORIZON_HOURS", "24"))


def api(path, **params):
    query = urllib.parse.urlencode({k: v for k, v in params.items() if v not in (None, "")})
    headers = {"Authorization": f"Bearer {KEY}"} if KEY else {"X-Blockmetric-Access": "public"}
    try:
        with urllib.request.urlopen(urllib.request.Request(f"{BASE}{path}?{query}", headers=headers), timeout=60) as res:
            return json.load(res)["data"]
    except urllib.error.HTTPError as e:
        err = json.load(e).get("error", {})
        raise SystemExit(f"{e.code} {err.get('code')}: {err.get('message')}")


def iso(dt):
    return dt.strftime("%Y-%m-%dT%H:%M:%S.000Z")


def nearest_big(h, col):
    """The largest cluster per side of one column within MAX_DISTANCE of the mark."""
    mark = h["mark"][col]
    best = {}
    for row, price in enumerate(h["prices"]):
        dist = (price - mark) / mark
        if abs(dist) > MAX_DISTANCE:
            continue
        side = "long" if price < mark else "short"  # longs liquidate below the mark, shorts above it
        usd = (h["longCells"] if side == "long" else h["shortCells"])[col][row]
        if usd >= MIN_USD and (side not in best or usd > best[side]["usd"]):
            best[side] = {"side": side, "price": price, "usd": usd, "distance": dist}
    return list(best.values())


def main():
    h = api(f"/heatmap/{urllib.parse.quote(COIN)}", tf="1h", hours=DAYS * 24)
    c = api(f"/candles/{urllib.parse.quote(COIN)}", tf="1h", limit=5000, **{"from": h["times"][0]})
    by_hour = {k["t"]: k for k in c["candles"]}
    now = datetime.now(timezone.utc)
    tests = []
    for col, t in enumerate(h["times"]):
        if (h.get("hasSnapshot") or [True] * len(h["times"]))[col] is False or not h["mark"][col]:
            continue
        start = datetime.fromisoformat(t.replace("Z", "+00:00"))
        if start + timedelta(hours=HORIZON + 1) > now:  # the horizon has not passed yet
            continue
        for cl in nearest_big(h, col):
            hit_after = None
            for i in range(1, HORIZON + 1):
                k = by_hour.get(iso(start + timedelta(hours=i)))
                if k and (k["low"] <= cl["price"] if cl["side"] == "long" else k["high"] >= cl["price"]):
                    hit_after = i
                    break
            tests.append({**cl, "time": t, "hit_after": hit_after})

    print(f"{COIN}: clusters of at least ${MIN_USD / 1e6:g}M within {MAX_DISTANCE * 100:g} % of the mark, {len(h['times'])} hourly columns since {h['times'][0][:10]}")
    print("side    tested   reached   hit rate   median hours to reach")
    for side in ("long", "short"):
        s = [x for x in tests if x["side"] == side]
        hits = sorted(x["hit_after"] for x in s if x["hit_after"] is not None)
        rate = f"{len(hits) / len(s) * 100:.0f} %" if s else "-"
        median = str(hits[len(hits) // 2]) if hits else "-"
        print(f"{side + 's':<7} {len(s):>6} {len(hits):>9} {rate:>10}   {median:>6}")
    print(f"Horizon {HORIZON} h. Longs = clusters of long liquidations below the mark, shorts = above it.")
    if os.environ.get("CSV"):
        with open(os.environ["CSV"], "w", newline="") as f:
            w = csv.writer(f)
            w.writerow(["time", "side", "price", "usd", "distance", "hit_after_hours"])
            for x in tests:
                w.writerow([x["time"], x["side"], x["price"], x["usd"], f"{x['distance']:.5f}", x["hit_after"] or ""])
        print(f"Wrote {len(tests)} tests to {os.environ['CSV']}")


if __name__ == "__main__":
    main()