from __future__ import annotations

import argparse
import json
from datetime import datetime, timezone
from statistics import mean

from v7_hardening_common import ROOT, TEMP, load_json, save_json


DEFAULT_OUT = TEMP / "confidence_calibration_v2.json"


def _label_rank(label: str) -> int:
    order = {
        "BEARISH": 0,
        "NEUTRAL": 1,
        "BULLISH": 2,
        "STRONG_BULLISH": 3,
    }
    return order.get(str(label).upper(), 1)


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

    exposure = load_json(TEMP / "imputed_data_exposure_gate_v2.json")
    pred = load_json(TEMP / "prediction_accuracy_harness_v2.json")
    conf = load_json(TEMP / "portfolio_alpha_confidence_per_ticker_v1.json")
    rows = [r for r in conf.get("rows", []) if isinstance(r, dict)]

    monotonic = True
    if rows:
        ordered = sorted(rows, key=lambda r: float(r.get("pac_score") or 0.0))
        label_scores = [_label_rank(r.get("pac_label") or "") for r in ordered]
        monotonic = all(a <= b for a, b in zip(label_scores, label_scores[1:]))

    high_conf_low_evidence = sum(
        1 for r in rows
        if float(r.get("pac_score") or 0.0) >= 80.0 and str(r.get("fundamental_grade") or "").upper() in {"D", "F", "E"}
    )

    result = {
        "formula_id": "CONFIDENCE_CALIBRATION_V2",
        "generated_at": datetime.now(timezone.utc).isoformat(),
        "confidence_cap_basis_score": float(exposure.get("raw_confidence_cap_basis") or exposure.get("effective_confidence_honest") or 0.0),
        "effective_confidence_honest": float(exposure.get("effective_confidence_honest") or 0.0),
        "confidence_cap_gap_pct": round(float(exposure.get("confidence_cap_inflation_gap") or 0.0), 1),
        "calibration_brier_score_improving": str(pred.get("calibration_state") or "").upper() == "CALIBRATED",
        "confidence_bucket_monotonicity": "PASS" if monotonic else "FAIL",
        "high_confidence_low_evidence_count": high_conf_low_evidence,
        "calibration_state": pred.get("calibration_state"),
        "portfolio_label_diversity": int(conf.get("label_diversity") or 0),
        "portfolio_score_mean": round(mean(float(r.get("pac_score") or 0.0) for r in rows), 2) if rows else 0.0,
        "source_paths": [
            "Temp/imputed_data_exposure_gate_v2.json",
            "Temp/prediction_accuracy_harness_v2.json",
            "Temp/portfolio_alpha_confidence_per_ticker_v1.json",
        ],
    }
    save_json(args.out, result)
    print(json.dumps(result, ensure_ascii=False, indent=2))
    return 0


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