"""Generate paper/results_macros.tex from saved machine-readable outputs.

Every numerical claim in the manuscript resolves to a macro defined here
(CLAUDE.md §26.5). Rerun after any estimation stage; compile refuses stale
numbers by construction because macros are the only path into the text.
"""

from __future__ import annotations

import json
from pathlib import Path

import polars as pl

ROOT = Path(__file__).resolve().parents[1]
OUTE = ROOT / "outputs"
M = []


def macro(name: str, value: str) -> None:
    M.append(f"\\newcommand{{\\{name}}}{{{value}}}")


def num(x, nd=0):
    return f"{x:,.{nd}f}"


def main() -> None:
    # ---- data scale (stage C summary)
    sc = json.loads((OUTE / "diagnostics/stage_c/stage_c_summary.json").read_text())
    macro("DataRows", num(sc["total_rows"]))
    macro("DataRowsBn", f"{sc['total_rows']/1e9:.2f}")
    macro("DataTickers", num(sc["tickers_total"]))
    macro("DataSpells", num(sc["spells_total"]))
    macro("DataOHLCViol", num(sc["total_ohlc_violations"]))
    macro("DataDupKeys", num(sc["total_duplicate_keys"]))
    macro("DataMultiSpellTickers", num(sc["multi_spell_tickers"]))

    # ---- splits (stage D)
    ev = pl.read_parquet(OUTE / "diagnostics/stage_d/split_events.parquet")
    fwd = int(ev["event"].str.starts_with("split").sum())
    macro("NSplitEvents", num(ev.height))
    macro("NSplitFwd", num(fwd))
    macro("NSplitRev", num(ev.height - fwd))

    # ---- extreme minute returns (fig E5 source)
    e5 = pl.read_csv(OUTE / "figures/data/figE5_extreme_minutes.csv")
    g1_90s = e5.filter(pl.col("year").is_between(1992, 1999))["gt1"].mean() * 1e4
    g1_10s = e5.filter(pl.col("year").is_between(2010, 2019))["gt1"].mean() * 1e4
    g5_1719 = e5.filter(pl.col("year").is_between(2017, 2019))["gt5"].mean() * 1e4
    g5_20 = e5.filter(pl.col("year") == 2020)["gt5"].mean() * 1e4
    macro("ExtremeGtOneNineties", num(g1_90s, 0))
    macro("ExtremeGtOneTens", num(g1_10s, 1))
    macro("ExtremeDropFactor", num(g1_90s / g1_10s, 0))
    macro("ExtremeGtFivePreCovid", f"{g5_1719:.3f}")
    macro("ExtremeGtFiveCovid", num(g5_20, 1))
    macro("ExtremeCovidFactor", num(g5_20 / g5_1719, 0))

    # ---- Epps (fig E8 source)
    ep = pl.read_csv(OUTE / "diagnostics/stage_e/epps_curves.csv")
    def epv(y, k):
        return ep.filter((pl.col("year") == y) & (pl.col("agg_minutes") == k)
                         )["mean_pairwise_corr"][0]
    macro("EppsNinetySixOne", f"{epv(1996,1):.3f}")
    macro("EppsNinetySixThirty", f"{epv(1996,30):.2f}")
    macro("EppsFifteenOne", f"{epv(2015,1):.2f}")
    macro("EppsFifteenThirty", f"{epv(2015,30):.2f}")
    macro("EppsTwentyFourOne", f"{epv(2024,1):.2f}")
    macro("EppsTwentyFourThirty", f"{epv(2024,30):.2f}")

    # ---- stage F baseline
    f1 = json.loads((OUTE / "estimates/stage_f_baseline.json").read_text())
    macro("NEventsReal", num(f1["n_events_real"]))
    macro("NEventsRealMM", f"{f1['n_events_real']/1e6:.2f}")
    macro("NEventsPlacebo", num(f1["n_events_placebo"]))
    for r in f1["baseline"]:
        if r["h"] in (5, 30):
            tag = "Five" if r["h"] == 5 else "Thirty"
            macro(f"DDBreadth{tag}", f"{r['dd_breadth']*1e4:.2f}")
            macro(f"DDBreadth{tag}SE", f"{r['se_breadth']*1e4:.2f}")
    grad = {g["group"]: g for g in f1["gradient_state"]}
    macro("DDGradLargest", f"{grad['12–20']['dd']*1e4:.2f}")
    macro("DDGradLargestSE", f"{grad['12–20']['se']*1e4:.2f}")

    # ---- stage F2 (if available)
    f2p = OUTE / "estimates/stage_f2.json"
    if f2p.exists():
        f2 = json.loads(f2p.read_text())
        nw = {(r["scope"], r["h"]): r for r in f2["network"]}
        for h, tag in [(5, "Five"), (15, "Fifteen"), (30, "Thirty")]:
            macro(f"NetDiff{tag}", f"{nw[('all',h)]['dd']*1e4:.1f}")
            macro(f"NetDiff{tag}SE", f"{nw[('all',h)]['se']*1e4:.1f}")
        macro("NetDiffFiveNineties", f"{nw[('1992–1999',5)]['dd']*1e4:.0f}")
        macro("NetDiffFiveOughts", f"{nw[('2000–2009',5)]['dd']*1e4:.0f}")
        macro("NetDiffFiveTens", f"{nw[('2010–2019',5)]['dd']*1e4:.0f}")
        macro("NetDiffFiveTwenties", f"{nw[('2020–2026',5)]['dd']*1e4:.0f}")
        cm = {(r["scope"], r["h"]): r for r in f2["cumulative"]}
        macro("CumThirty", f"{cm[('all',30)]['dd']*1e4:.1f}")
        macro("CumThirtySE", f"{cm[('all',30)]['se']*1e4:.1f}")
        cj = pl.DataFrame(f2["cojumps_yearly"])
        def sev(y):
            return cj.filter(pl.col("year") == y)["mean_share4"][0] * 100
        macro("CoJumpSevCalm",
              f"{cj.filter(pl.col('year').is_in([2015,2017,2019]))['mean_share4'].mean()*100:.1f}")
        macro("CoJumpSevGFC", f"{sev(2008):.1f}")
        macro("CoJumpSevCovid", f"{sev(2020):.1f}")
        sv = cj.filter(pl.col("year") >= 2013)
        macro("SevereCovid",
              f"{cj.filter(pl.col('year')==2020)['severe_per1000'][0]:.1f}")
        macro("SeverePreCovid",
              f"{cj.filter(pl.col('year').is_in([2017,2018,2019]))['severe_per1000'].mean():.2f}")

    tex = "% Auto-generated by scripts/15_build_results_macros.py — DO NOT EDIT.\n"
    tex += "\n".join(M) + "\n"
    (ROOT / "paper" / "results_macros.tex").write_text(tex)
    print(f"{len(M)} macros written")


if __name__ == "__main__":
    main()