QuantEngineByItz/tools/build_operational_t20_outcome_ledger_v1.py

from __future__ import annotations

import argparse
import json
from datetime import date, timedelta
from pathlib import Path
from typing import Any

ROOT = Path(__file__).resolve().parents[1]
DEFAULT_HISTORY = ROOT / "Temp" / "proposal_evaluation_history.json"
DEFAULT_OUT = ROOT / "Temp" / "operational_t20_outcome_ledger_v1.json"

# T+20 성숙 판정: 20 영업일 ≈ 28 캘린더일 (보수적 기준)
T20_CALENDAR_DAYS = 28


def _load(path: Path) -> dict[str, Any]:
    if not path.exists():
        return {}
    try:
        obj = json.loads(path.read_text(encoding="utf-8"))
    except Exception:
        return {}
    return obj if isinstance(obj, dict) else {}


def _is_matured(r: dict) -> bool:
    """proposal_date + 28 캘린더일 <= today 이면 T+20 성숙 판정."""
    pd = r.get("proposal_date") or r.get("entry_date") or ""
    if not pd:
        return False
    try:
        entry = date.fromisoformat(str(pd)[:10])
        return (date.today() - entry).days >= T20_CALENDAR_DAYS
    except Exception:
        return False


def main() -> int:
    ap = argparse.ArgumentParser()
    ap.add_argument("--history", default=str(DEFAULT_HISTORY))
    ap.add_argument("--out", default=str(DEFAULT_OUT))
    args = ap.parse_args()

    hist_path = Path(args.history) if Path(args.history).is_absolute() else ROOT / args.history
    hist = _load(hist_path)
    records = hist.get("records") if isinstance(hist.get("records"), list) else []

    # [T3/SG1] 운영(비-REPLAY) 레코드만 추출, T+20 성숙 확인
    operational = [
        r for r in records
        if isinstance(r, dict)
        and str(r.get("validation_status") or "").upper() != "REPLAY_BACKFILL"
    ]
    # T+20 평가 완료 OR 20 캘린더일 이상 경과한 행 → matured
    t20 = [
        r for r in operational
        if str(r.get("t20_evaluation_status") or "").startswith("EVALUATED_")
        or _is_matured(r)
    ]
    # INCONCLUSIVE는 통계에서 제외 (match_rate 분자/분모 모두)
    decisive = [r for r in t20 if r.get("t20_outcome") in ("MATCHED", "MISMATCHED")]
    matched = sum(1 for r in decisive if r.get("t20_outcome") == "MATCHED")
    mismatched = sum(1 for r in decisive if r.get("t20_outcome") == "MISMATCHED")
    rate = round((matched / len(decisive)) * 100.0, 2) if decisive else 0.0

    result = {
        "formula_id": "OPERATIONAL_T20_OUTCOME_LEDGER_V1",
        "evaluated_count": len(t20),
        "decisive_count": len(decisive),
        "matched_count": matched,
        "mismatched_count": mismatched,
        "pass_rate_pct": rate,
        # [SG1] n<30 → WATCH_PENDING_SAMPLE (공허PASS 금지)
        "gate": (
            "PASS" if len(decisive) >= 30 and rate >= 60.0
            else "WATCH_PENDING_SAMPLE"
        ),
        "operational_total": len(operational),
        "maturity_threshold_days": T20_CALENDAR_DAYS,
        "rows": [
            {
                "proposal_id": r.get("proposal_id"),
                "ticker": r.get("ticker"),
                "name": r.get("name"),
                "proposal_date": r.get("proposal_date"),
                "t20_evaluation_status": r.get("t20_evaluation_status"),
                "t20_outcome": r.get("t20_outcome"),
                "t20_return_pct": r.get("t20_return_pct"),
                "validation_status": r.get("validation_status"),
                "matured": _is_matured(r),
            }
            for r in t20[:500]
        ],
    }
    out = Path(args.out)
    if not out.is_absolute():
        out = ROOT / out
    out.parent.mkdir(parents=True, exist_ok=True)
    out.write_text(json.dumps(result, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(result, ensure_ascii=False, indent=2))
    return 0


if __name__ == "__main__":
    raise SystemExit(main())