"""Pre-vs-post Tiingo overlay factor check for the S&P panel.

Builds the panel twice in-process — Yahoo-only (pre, survivorship-biased)
and with the Tiingo overlay (post) — and runs the sleeve-relevant factors
through the standard top-N phase-averaged backtest on both. The delta is the
survivorship effect on the factors behind the live stock sleeves
(overnight_recovery: overnight_mom + rec_126; lowrisk: ivol + low_beta).

    PYTHONPATH=. uv run python -m research.factor_panel_check
"""
from __future__ import annotations

import os
import time
import warnings

import pandas as pd

import research.lab.panel as pnl
from research.lab.factor_scan import PERIODS, phase_avg
from research.lab.factors import FACTORS
from research.lab.report import forward_returns, ic_series, ic_summary

warnings.filterwarnings("ignore")

NAMES = ["overnight_mom", "rec_126", "mom_12_1", "low_vol",
         "ivol", "low_beta", "sharpe_mom", "amp_cut_mom"]
RESULTS = os.path.join("data", "research", "results")


def scan(p, label: str) -> pd.DataFrame:
    fwd5 = forward_returns(p, 5)
    rows = []
    for name in NAMES:
        t0 = time.time()
        s = FACTORS[name](p)
        row = {"panel": label, "factor": name}
        for per, (a, b) in PERIODS["us"].items():
            st = phase_avg(p, s, a, b, 20, 5)
            ic = ic_summary(ic_series(s.loc[a:b], fwd5.loc[a:b], p.member.loc[a:b], 5))
            row.update({f"{per}_cagr": st["cagr"], f"{per}_sharpe": st["sharpe"],
                        f"{per}_ic5": ic["ic"], f"{per}_ic5_t": ic["t"]})
        rows.append(row)
        print(f"[{label}] {name:14s} D {row['design_cagr']:6.1%}/{row['design_sharpe']:.2f}  "
              f"H {row['holdout_cagr']:6.1%}/{row['holdout_sharpe']:.2f}  [{time.time() - t0:.0f}s]",
              flush=True)
    return pd.DataFrame(rows)


def main() -> None:
    post = pnl.load_us()
    orig = pnl.apply_sp500
    pnl.apply_sp500 = lambda raw, **kw: raw
    try:
        pre = pnl._build_us()
    finally:
        pnl.apply_sp500 = orig
    a = scan(pre, "pre")
    b = scan(post, "post")
    df = pd.concat([a, b], ignore_index=True)
    os.makedirs(RESULTS, exist_ok=True)
    df.to_csv(os.path.join(RESULTS, "factor_panel_check.csv"), index=False)
    m = a.merge(b, on="factor", suffixes=("_pre", "_post"))
    print("\nfactor          D_cagr pre->post    D_sh pre->post   H_cagr pre->post    H_sh pre->post")
    for _, r in m.iterrows():
        print(f"{r['factor']:14s} {r['design_cagr_pre']:7.1%}->{r['design_cagr_post']:6.1%}   "
              f"{r['design_sharpe_pre']:5.2f}->{r['design_sharpe_post']:5.2f}   "
              f"{r['holdout_cagr_pre']:7.1%}->{r['holdout_cagr_post']:6.1%}   "
              f"{r['holdout_sharpe_pre']:5.2f}->{r['holdout_sharpe_post']:5.2f}")


if __name__ == "__main__":
    main()