"""Deterministic SYNTHETIC dataset for the M2 eval baseline.

There is no historical Hubei data in this repository yet (docs/12 §2 历史重放集
comes from the event log once the system runs; partner data is OPEN-QUESTION
D-class). Until real data lands, the eval harness needs *something* with
realistic structure — daily load shape, PV bell with cloud days, price with an
evening peak and occasional spikes — so metrics, calibration tests and the
reproducibility check exercise real code paths.

Every number here is invented for shape only. Baselines computed on it are
baselines of the *harness*, not of the business KPI (预测误差 ≤ 8% is judged
on real data, docs/12 §4). The dataset file says so in its ``meta``.
"""

from __future__ import annotations

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

import numpy as np

from .numeric import INTERVALS, SCALE_MW, SCALE_PRICE, quantize

GENERATOR = "vpp_skills.synthetic"
GENERATOR_VERSION = "0.1.0"


def _profiles() -> tuple[np.ndarray, np.ndarray, np.ndarray]:
    t = np.arange(INTERVALS) / 4.0  # hours
    load = 0.55 + 0.25 * np.exp(-((t - 11) ** 2) / 8) + 0.35 * np.exp(-((t - 19.5) ** 2) / 6) - 0.15 * np.exp(-((t - 3) ** 2) / 10)
    pv = np.clip(np.sin(np.pi * (t - 6.5) / 12.5), 0.0, None) ** 1.4
    pv[(t < 6.5) | (t > 19.0)] = 0.0
    price = 0.7 + 0.2 * np.exp(-((t - 11) ** 2) / 6) + 0.5 * np.exp(-((t - 19) ** 2) / 4) - 0.25 * np.exp(-((t - 3.5) ** 2) / 12)
    return load, pv, price


def generate_dataset(
    seed: int = 20260301,
    start: str = "2026-01-01",
    n_days: int = 120,
    peak_load_mw: float = 80.0,
    pv_capacity_mw: float = 30.0,
    adjustable_capacity_mw: float = 24.0,
    base_price: float = 400.0,
) -> dict:
    rng = np.random.default_rng(seed)
    load_p, pv_p, price_p = _profiles()
    d0 = date.fromisoformat(start)
    days = []
    load_ar = 0.0
    cloud = 0.8
    for i in range(n_days):
        d = d0 + timedelta(days=i)
        weekend = d.weekday() >= 5
        load_ar = 0.7 * load_ar + rng.normal(0, 0.04)
        day_factor = (0.85 if weekend else 1.0) * (1.0 + load_ar)
        load = peak_load_mw * load_p * day_factor * (1.0 + rng.normal(0, 0.02, INTERVALS))
        load = np.clip(load, 0.0, None)

        cloud = float(np.clip(0.6 * cloud + 0.4 * rng.beta(4, 1.5), 0.05, 1.0))
        pv = pv_capacity_mw * pv_p * cloud * (1.0 + rng.normal(0, 0.05, INTERVALS))
        pv = np.clip(pv, 0.0, None)
        pv[pv_p == 0.0] = 0.0

        net = (load - pv) / peak_load_mw
        price = base_price * (price_p + 0.35 * (net - net.mean())) * (1.0 + rng.normal(0, 0.03, INTERVALS))
        if rng.random() < 0.06:  # spike day: evening scarcity
            price[72:88] *= rng.uniform(1.6, 2.4)
        price = np.clip(price, 0.0, None)

        days.append(
            {
                "date": d.isoformat(),
                "weekend": weekend,
                "load_mw": [quantize(v, SCALE_MW) for v in load],
                "pv_mw": [quantize(v, SCALE_MW) for v in pv],
                "price_yuan_per_mwh": [quantize(v, SCALE_PRICE) for v in price],
                "adjustable_capacity_mw": [quantize(adjustable_capacity_mw, SCALE_MW)] * INTERVALS,
            }
        )
    return {
        "meta": {
            "name": f"synthetic-hubei-v0-{start}-{n_days}d",
            "synthetic": True,
            "note": "SYNTHETIC shape-only placeholder. Replace with historical Hubei replay data; "
            "baselines on this set measure the harness, not the business KPI.",
            "generator": GENERATOR,
            "generator_version": GENERATOR_VERSION,
            "seed": seed,
            "interval_minutes": 15,
            "peak_load_mw": quantize(peak_load_mw, SCALE_MW),
            "pv_capacity_mw": quantize(pv_capacity_mw, SCALE_MW),
            "adjustable_capacity_mw": quantize(adjustable_capacity_mw, SCALE_MW),
        },
        "days": days,
    }


def main() -> None:
    ap = argparse.ArgumentParser(description="write the synthetic eval dataset")
    ap.add_argument("--out", required=True, type=Path)
    ap.add_argument("--seed", type=int, default=20260301)
    ap.add_argument("--days", type=int, default=120)
    args = ap.parse_args()
    ds = generate_dataset(seed=args.seed, n_days=args.days)
    args.out.parent.mkdir(parents=True, exist_ok=True)
    args.out.write_text(json.dumps(ds, indent=1) + "\n")
    print(f"wrote {args.out} ({len(ds['days'])} days)")


if __name__ == "__main__":
    main()