"""
Single-factor scan: rank IC and long-only top-N backtests per period.

    PYTHONPATH=. uv run python -m research.lab.factor_scan --market us
    PYTHONPATH=. uv run python -m research.lab.factor_scan --market cn_hs300

Writes data/research/results/factor_scan_{market}.csv.
"""

import argparse
import os
import time
import warnings

import pandas as pd

from research.lab import panel as pnl
from research.lab.engine import simulate
from research.lab.factors import FACTORS
from research.lab.report import (forward_returns, ic_series, ic_summary, stats,
                                 top_minus_universe)

warnings.filterwarnings("ignore")

PERIODS = {
    "us": {"design": ("2006-01-01", "2016-09-26"), "holdout": ("2016-09-27", "2026-09-24")},
    "cn": {"design": ("2010-01-01", "2016-09-26"), "holdout": ("2016-09-27", "2026-09-24")},
}
RESULTS = os.path.join("data", "research", "results")


def load(market: str):
    if market == "us":
        return pnl.load_us(), PERIODS["us"]
    return pnl.load_cn(market.split("_", 1)[1]), PERIODS["cn"]


def phase_avg(p, score, start, end, top_n, every, **kw) -> dict:
    """Average stats over every rebalance phase (offset 0..every-1)."""
    w0 = p.dates.searchsorted(pd.Timestamp(start))
    sp = p.slice(p.dates[max(w0 - 5, 0)], end)
    rows = []
    for off in range(every):
        r = simulate(sp, score, top_n=top_n, every=every, offset=off, warmup=5, **kw)
        rows.append(stats(r.equity.loc[start:end], r.turnover))
    return pd.DataFrame(rows).mean().to_dict()


def main() -> None:
    ap = argparse.ArgumentParser()
    ap.add_argument("--market", default="us")
    ap.add_argument("--top-n", type=int, default=20)
    ap.add_argument("--every", type=int, default=5)
    ap.add_argument("--only", nargs="*")
    args = ap.parse_args()
    mk = "us" if args.market == "us" else "cn"
    p, periods = load(args.market)
    fwd5 = forward_returns(p, 5)
    fwd20 = forward_returns(p, 20)
    rows = []
    names = args.only or [n for n, f in FACTORS.items() if mk in f.markets]
    for name in names:
        t = time.time()
        try:
            s = FACTORS[name](p)
        except Exception as exc:  # noqa: BLE001
            print(f"{name}: failed {exc}")
            continue
        row = {"factor": name}
        for per, (a, b) in periods.items():
            sl = slice(a, b)
            ic5 = ic_summary(ic_series(s.loc[sl], fwd5.loc[sl], p.member.loc[sl], 5))
            ic20 = ic_summary(ic_series(s.loc[sl], fwd20.loc[sl], p.member.loc[sl], 20), 12)
            tmu = top_minus_universe(s.loc[sl], fwd5.loc[sl], p.member.loc[sl], args.top_n, 5)
            st = phase_avg(p, s, a, b, args.top_n, args.every)
            row.update({f"{per}_ic5": ic5["ic"], f"{per}_ic5_t": ic5["t"],
                        f"{per}_ic20": ic20["ic"], f"{per}_ic20_t": ic20["t"],
                        f"{per}_top_excess_ann": tmu.mean() * 52,
                        f"{per}_cagr": st["cagr"], f"{per}_sharpe": st["sharpe"],
                        f"{per}_mdd": st["mdd"], f"{per}_turn": st["turnover"]})
        rows.append(row)
        print(f"{name:16s} "
              f"D: ic5 {row['design_ic5']:+.3f} (t{row['design_ic5_t']:+.1f}) ic20 {row['design_ic20']:+.3f} "
              f"xs {row['design_top_excess_ann']*100:+5.1f}% cagr {row['design_cagr']*100:5.1f}% sh {row['design_sharpe']:.2f} | "
              f"H: ic5 {row['holdout_ic5']:+.3f} (t{row['holdout_ic5_t']:+.1f}) ic20 {row['holdout_ic20']:+.3f} "
              f"xs {row['holdout_top_excess_ann']*100:+5.1f}% cagr {row['holdout_cagr']*100:5.1f}% sh {row['holdout_sharpe']:.2f} "
              f"turn {row['holdout_turn']:.0f}x  [{time.time()-t:.0f}s]", flush=True)
    # equal-weight universe reference
    os.makedirs(RESULTS, exist_ok=True)
    out = pd.DataFrame(rows)
    out.to_csv(os.path.join(RESULTS, f"factor_scan_{args.market}.csv"), index=False)


if __name__ == "__main__":
    main()