QuantEngineByItz/tools/build_data_gated_progress_v1.py

"""build_data_gated_progress_v1.py — DATA_GATED_PROGRESS_V1

DATA_GATED 항목별 실측 데이터 기반 진척도를 추적한다.
모든 수치는 실측 artifact에서 직접 산출 — 추정/하드코딩 없음.

입력:
  GatherTradingData.json              (sector_flow_history)
  Temp/prediction_accuracy_harness_v2.json
  Temp/live_replay_separation_v3.json
  Temp/alpha_feedback_loop_v2.json
  Temp/imputed_data_exposure_gate_v2.json
  Temp/algorithm_guidance_proof_v1.json
  Temp/horizon_classification_v1.json

출력: Temp/data_gated_progress_v1.json
"""
from __future__ import annotations

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

ROOT = Path(__file__).resolve().parents[1]
TEMP = ROOT / "Temp"
FORMULA_ID = "DATA_GATED_PROGRESS_V1"


def _load(path: Path) -> Any:
    if not path.exists():
        return {}
    try:
        return json.loads(path.read_text(encoding="utf-8"))
    except Exception:
        return {}


def _f(v: Any, default: float = 0.0) -> float:
    try:
        return float(v)
    except Exception:
        return default


def _eta_trading_days(current: int, target: int, as_of: date) -> str:
    """남은 거래일 수를 근사 추정 (주말 제외, 공휴일 미반영)."""
    remaining = max(0, target - current)
    if remaining == 0:
        return "ACHIEVED"
    # 주 5일 기준 근사
    weeks, days = divmod(remaining, 5)
    delta = timedelta(weeks=weeks, days=days + (2 * weeks))
    eta = as_of + delta
    return eta.strftime("%Y-%m-%d")


def _count_sector_flow_dates(payload: dict) -> int:
    """GatherTradingData.json의 sector_flow_history 고유 날짜 수."""
    rows = (payload.get("data") or {}).get("sector_flow_history") or []
    dates: set[str] = set()
    for row in rows:
        if not isinstance(row, dict):
            continue
        snap = row.get("Snapshot_Date") or row.get("snapshot_date") or ""
        val = str(snap)[:10]
        if val and val != "None":
            dates.add(val)
    return len(dates)


def _count_live_samples(live_sep: dict) -> int:
    """live_replay_separation_v3.json의 실측(non-replay) 행 수."""
    rows = live_sep.get("performance_rows") or []
    return sum(
        1 for r in rows
        if isinstance(r, dict) and r.get("origin") in ("operational_live", "shadow_live")
    )


def main() -> int:
    today = date.today()
    today_str = today.isoformat()

    payload = _load(ROOT / "GatherTradingData.json")
    pred = _load(TEMP / "prediction_accuracy_harness_v2.json")
    live_sep = _load(TEMP / "live_replay_separation_v3.json")
    alpha = _load(TEMP / "alpha_feedback_loop_v2.json")
    imputed = _load(TEMP / "imputed_data_exposure_gate_v2.json")
    proof = _load(TEMP / "algorithm_guidance_proof_v1.json")
    horizon = _load(TEMP / "horizon_classification_v1.json")

    # ── WBS-2.5: sector_flow_history 30일 ────────────────────────────────────
    sfh_days = _count_sector_flow_dates(payload)
    sfh_target = 30
    sfh_done = sfh_days >= sfh_target
    wbs_2_5 = {
        "id": "WBS-2.5",
        "label": "sector_flow_history 30일 누적",
        "current": sfh_days,
        "target": sfh_target,
        "unit": "trading_days",
        "pct_complete": round(min(100.0, sfh_days / sfh_target * 100), 1),
        "status": "DONE" if sfh_done else "IN_PROGRESS",
        "eta": "ACHIEVED" if sfh_done else _eta_trading_days(sfh_days, sfh_target, today),
        "source": "GatherTradingData.json:data.sector_flow_history",
    }

    # ── WBS-4.1: T+20 레저 30건 ──────────────────────────────────────────────
    t20_sample = int(_f(pred.get("t20_sample") or 0))
    t20_op_rate = pred.get("t20_op_rate")
    live_sample_count = _count_live_samples(live_sep)
    t20_target = 30
    t20_done = t20_sample >= t20_target
    wbs_4_1 = {
        "id": "WBS-4.1",
        "label": "T+20 레저 30건 누적",
        "current": t20_sample,
        "target": t20_target,
        "unit": "trades",
        "live_sample_count": live_sample_count,
        "pct_complete": round(min(100.0, t20_sample / t20_target * 100), 1),
        "status": "DONE" if t20_done else "DATA_GATED",
        "eta": "ACHIEVED" if t20_done else "~2026-07-15",
        "source": "Temp/prediction_accuracy_harness_v2.json:t20_sample",
    }

    # ── WBS-4.2: 예측 정확도 (T+20 의존) ─────────────────────────────────────
    t20_rate_val = t20_op_rate if t20_op_rate is not None else "pending"
    wbs_4_2 = {
        "id": "WBS-4.2",
        "label": "예측 정확도 평가 (T+20 기준)",
        "current": t20_rate_val,
        "target": "t20_op_rate available",
        "status": "DATA_GATED" if t20_op_rate is None else "IN_PROGRESS",
        "depends_on": "WBS-4.1",
        "source": "Temp/prediction_accuracy_harness_v2.json:t20_op_rate",
    }

    # ── WBS-4.3: 알파 보정 (4.2 의존) ────────────────────────────────────────
    alpha_cases = int(_f(alpha.get("total_cases") or 0))
    wbs_4_3 = {
        "id": "WBS-4.3",
        "label": "알파 보정 (alpha_feedback_loop)",
        "current_cases": alpha_cases,
        "target_cases": 30,
        "status": "DATA_GATED" if alpha_cases < 30 else "IN_PROGRESS",
        "depends_on": "WBS-4.2",
        "source": "Temp/alpha_feedback_loop_v2.json:total_cases",
    }

    # ── RELEASE_GATE_TRUTH: honest_proof_score ─────────────────────────────
    honest_score = _f(proof.get("honest_proof_score") or 0)
    honest_gate = proof.get("honest_gate", "FAIL")
    fund_coverage = _f(imputed.get("fundamental_core_factor_coverage") or 0)
    truth_target = 70.0
    truth_done = honest_gate == "PASS" and honest_score >= truth_target
    rgt = {
        "id": "RELEASE_GATE_TRUTH",
        "label": "honest_proof_score >= 70 (RELEASE_GATE_TRUTH)",
        "current_honest_score": honest_score,
        "target": truth_target,
        "honest_gate": honest_gate,
        "gap": round(truth_target - honest_score, 2),
        "fundamental_core_factor_coverage": fund_coverage,
        "status": "PASS" if truth_done else "FAIL",
        "blockers": [
            b for b in [
                "REALIZED_OUTCOME_T20_ZERO: T+20 표본 0건 — WBS-4.1 달성 필요"
                if (t20_op_rate is None) else None,
                "FUNDAMENTAL_CORE_FACTORS_MISSING: ROE/OPM/OCF/FCF 미수집 — GAS fetchFundamentalsWithCache_ 실행 필요"
                if fund_coverage < 0.5 else None,
            ]
            if b is not None
        ],
        "source": "Temp/algorithm_guidance_proof_v1.json:honest_proof_score",
    }

    # ── imputed_data_exposure_gate ─────────────────────────────────────────
    imputed_gate = imputed.get("gate_status", "UNKNOWN")
    idge = {
        "id": "imputed_data_exposure_gate",
        "label": "펀더멘털 실측 데이터 커버리지",
        "gate_status": imputed_gate,
        "fundamental_core_factor_coverage": fund_coverage,
        "status": "USER_ACTION_REQUIRED" if fund_coverage < 0.5 else "IN_PROGRESS",
        "user_action": "GAS fetchFundamentalsWithCache_ 실행 → ROE/OPM/OCF/FCF 수집",
        "source": "Temp/imputed_data_exposure_gate_v2.json",
    }

    # ── routing_gate ───────────────────────────────────────────────────────
    alloc = horizon.get("allocation_pct") or {}
    short_pct = _f(alloc.get("SHORT") or 0)
    routing_status = "PASS" if short_pct <= 40.0 else "FAIL"
    rg = {
        "id": "routing_gate",
        "label": "SHORT 호라이즌 비중 <= 40%",
        "current_short_pct": short_pct,
        "cap_pct": 40.0,
        "status": routing_status,
        "note": (
            "horizon_classification_v1.json 기준 현재 SHORT 비중 측정값. "
            "strategy_routing_audit_v1.json 생성 후 공식 게이트 업데이트."
        ),
        "source": "Temp/horizon_classification_v1.json:allocation_pct.SHORT",
    }

    # ── 요약 ──────────────────────────────────────────────────────────────
    items = [wbs_2_5, wbs_4_1, wbs_4_2, wbs_4_3, rgt, idge, rg]
    done_count = sum(1 for i in items if i.get("status") in ("DONE", "PASS"))
    total_count = len(items)

    result = {
        "formula_id": FORMULA_ID,
        "as_of": today_str,
        "gate": "PASS" if done_count == total_count else "IN_PROGRESS",
        "done_count": done_count,
        "total_count": total_count,
        "items": items,
    }

    out = TEMP / "data_gated_progress_v1.json"
    out.write_text(json.dumps(result, ensure_ascii=False, indent=2) + "\n", encoding="utf-8")

    print(f"[{FORMULA_ID}] {done_count}/{total_count} DONE as_of={today_str}")
    for item in items:
        status = item.get("status", "?")
        label = item.get("label", item.get("id", ""))
        current = item.get("current", item.get("current_honest_score", item.get("gate_status", "")))
        target = item.get("target", "")
        print(f"  [{status}] {item['id']}: {current} / {target}")
    return 0


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