"""Leave-one-out ablation of A' on all six corpora (APS, CHA, new corpus 1, Roots.jl, applied
+ GSL, fourth corpus), uniform success criterion (a sign change within 1e-6), for the paper's
label-honesty table.  Descriptive: every corpus has been seen by now.

    python -u sweep_ablation_all.py            run -> sweep_ablation_all.json, then the table
    python -u sweep_ablation_all.py --report
"""
from __future__ import annotations

import json
import sys
from multiprocessing import Pool

from sweep_fourth import corpus, evaluate as _eval_one
import sweep_fourth
from sweep_full import APRIME_ABLATIONS

SETS = ("APS", "CHA", "NEW", "RJL", "APP", "D")


def spec(pre, ext):
    return ("pure", "ratio", "derived3", "project", "x", pre, "recent", "distance", "none", ext)


for _name, (_pre, _ext) in APRIME_ABLATIONS.items():
    sweep_fourth.CONFIGS[f"abl{_name}"] = spec(_pre, _ext)


def evaluate(job):
    name, which = job
    return name, which, _eval_one((name, which))[1]


def cost(v):
    return v[0] if v[1] else 200


def main():
    names = [f"abl{n}" for n in APRIME_ABLATIONS]
    if "--report" not in sys.argv:
        jobs = [(n, w) for n in names for w in ("seen", "fourth")]
        with Pool(min(12, len(jobs))) as pool:
            out = pool.map(evaluate, jobs)
        R = {}
        for n, w, res in out:
            R.setdefault(n, {}).update(res)
        with open("sweep_ablation_all.json", "w", encoding="utf8") as fh:
            json.dump(R, fh)
    with open("sweep_ablation_all.json", encoding="utf8") as fh:
        R = json.load(fh)
    tot = {n: {s: sum(cost(v) for v in R[n][s].values()) for s in SETS} for n in R}
    base = tot["ablA'"]
    print("A' totals: " + "  ".join(f"{s} {base[s]}" for s in SETS))
    print("delta = (without) - (with);  + = the component earns its place")
    for n in names[1:]:
        d = {s: tot[n][s] - base[s] for s in SETS}
        earned = [s for s in SETS if d[s] > 0]
        print(f"  {n[3:]:<8} " + "  ".join(f"{s} {d[s]:+5d}" for s in SETS)
              + f"   sum {sum(d.values()):+6d}   earned on {len(earned)}/6")
    print("ablation done")


if __name__ == "__main__":
    main()