scripts/run_cancer_risk_batch.py

#!/usr/bin/env python3
import argparse
import json
import sys
from pathlib import Path

import pandas as pd

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

from toxra_core.artifacts import make_run_dir, write_dataframe_csv, write_json
from toxra_core.calculation_client import run_batch_cancer_risk
from toxra_core.contracts import CANCER_RISK_TEMPLATE_COLUMNS


def main() -> None:
    parser = argparse.ArgumentParser(description="Run deterministic cancer risk batch using local MCP server")
    parser.add_argument("--input-csv", required=True, help="Path to cancer risk input CSV")
    parser.add_argument("--run-id", default="", help="Optional run ID")
    parser.add_argument("--runs-dir", default="runs", help="Runs base directory")
    args = parser.parse_args()

    inp = Path(args.input_csv)
    if not inp.exists():
        raise FileNotFoundError(f"Input CSV not found: {inp}")

    df = pd.read_csv(inp)
    missing = [c for c in CANCER_RISK_TEMPLATE_COLUMNS if c not in df.columns]
    if missing:
        raise ValueError(f"Missing required columns: {missing}")

    run_dir = make_run_dir(run_id=args.run_id or None, base_dir=args.runs_dir)
    rows = df.fillna("").to_dict("records")

    result = run_batch_cancer_risk(rows, run_dir=str(run_dir))
    res_rows = result.get("rows", []) if isinstance(result.get("rows", []), list) else []
    out_df = pd.DataFrame(res_rows)

    out_csv = run_dir / "cancer_risk_results.csv"
    out_json = run_dir / "cancer_risk_results.json"
    write_dataframe_csv(out_csv, out_df)
    write_json(out_json, result)

    print(json.dumps({
        "run_dir": str(run_dir),
        "results_csv": str(out_csv),
        "results_json": str(out_json),
        "log_jsonl": result.get("artifacts", {}).get("log_jsonl", ""),
        "report_md": result.get("artifacts", {}).get("report_md", ""),
        "summary": result.get("summary", {}),
    }, indent=2))


if __name__ == "__main__":
    main()