polyguard-rl/scripts/evaluate_all.py

#!/usr/bin/env python3
"""Run complete evaluation bundle."""

from __future__ import annotations

import json
from pathlib import Path

import sys

ROOT = Path(__file__).resolve().parents[1]
if str(ROOT) not in sys.path:
    sys.path.insert(0, str(ROOT))

from app.evaluation.benchmark_report import build_benchmark_report
from app.evaluation.plotting import generate_training_plots


def main() -> None:
    root = Path(__file__).resolve().parents[1]
    report = build_benchmark_report(root / "outputs" / "reports" / "benchmark_report.txt")
    (root / "outputs" / "reports" / "benchmark_report.json").write_text(
        json.dumps(report, ensure_ascii=True, indent=2), encoding="utf-8"
    )
    plot_paths = generate_training_plots(
        report_dir=root / "outputs" / "reports",
        plot_dir=root / "outputs" / "plots",
    )
    (root / "outputs" / "reports" / "plot_index.json").write_text(
        json.dumps({"plots": plot_paths}, ensure_ascii=True, indent=2),
        encoding="utf-8",
    )
    print("evaluation_done")


if __name__ == "__main__":
    main()