"""Summarise rolling-origin harness output side by side.

Usage:
    uv run python scripts/summarize_eval.py models/eval_2026-09-12.json [more.json ...]

Aggregates each (station, variant) across folds: mean MAE, mean flood-regime
MAE, mean Brier, total false-alarm episodes, and every warning event with its
first-alert lead and the 24 h-ahead peak error -- the operational numbers that
decide whether a variant ships.
"""

import json
import statistics
import sys
from collections import OrderedDict


def summarize(paths):
    for path in paths:
        results = json.load(open(path, encoding="utf-8"))
        print(f"\n##### {path}")
        for station in results:
            print(f"\n=== {station['station']} (warn {station['warn_thr']:.2f} m) ===")
            agg = OrderedDict()
            for fold in station["folds"]:
                for name, m in fold["variants"].items():
                    a = agg.setdefault(
                        name, {"mae": [], "mae_hi": [], "brier": [], "fa": 0, "events": []}
                    )
                    a["mae"].append(m["mae"])
                    if m.get("mae_above_2p5") is not None:
                        a["mae_hi"].append(m["mae_above_2p5"])
                    if m.get("brier_warn") is not None:
                        a["brier"].append(m["brier_warn"])
                    a["fa"] += m["false_alarm_episodes"]
                    for e in m["events"]:
                        err = (
                            None
                            if e["peak_pred_24h_before"] is None
                            else e["peak_pred_24h_before"] - e["peak_level"]
                        )
                        a["events"].append((fold["year"], e["crossing"][:10], e["lead_h"], e["peak_level"], err))
            print(f"{'variant':22} {'MAE':>6} {'MAE_hi':>7} {'Brier':>7} {'FA':>3}  events: year crossing lead_h peak(err24h)")
            for name, a in agg.items():
                ev = "  ".join(
                    f"{y} {d} {'—' if l is None else format(l, '+.0f')}h {p:.2f}({'—' if err is None else format(err, '+.2f')})"
                    for y, d, l, p, err in a["events"]
                )
                leads = [l for *_, l, _, _ in a["events"] if l is not None]
                print(
                    f"{name:22} {statistics.mean(a['mae']):6.3f} "
                    f"{statistics.mean(a['mae_hi']) if a['mae_hi'] else float('nan'):7.3f} "
                    f"{statistics.mean(a['brier']) if a['brier'] else float('nan'):7.4f} "
                    f"{a['fa']:>3}  {ev}"
                )
                if leads:
                    print(f"{'':22} lead: mean {statistics.mean(leads):+.1f} h, min {min(leads):+.0f} h, "
                          f"missed {sum(1 for *_, l, _, _ in a['events'] if l is None)}/{len(a['events'])}")


if __name__ == "__main__":
    summarize(sys.argv[1:] or ["models/eval_variants.json"])