# WashData - Home Assistant integration for appliance cycle monitoring via smart plugs.
# Copyright (C) 2026 Lukas Bandura
# SPDX-License-Identifier: AGPL-3.0-or-later
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as published
# by the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with this program. If not, see <https://www.gnu.org/licenses/>.
"""Auto-generated by ml_washdata/wash_ml/promotion.py. Do not edit by hand.

Embedded WashData model: 'live_match_commit' (target: 'match_top1_correct').
Kind: standardized logistic regression. Runtime dependency: NumPy only.

Regenerate with ``./ml.sh experiment`` in the ml_washdata lab and copy the new
file. Determinism check at generation time: max_abs_score_diff=1.6467e-08
over 2392 rows.

Usage in the integration::

    from .live_match_commit_model import score, predict, FEATURE_COLUMNS
    features = build_runtime_features(...)  # must populate FEATURE_COLUMNS
    is_positive = predict(features)
"""

from __future__ import annotations

import base64
import gzip
import json
from typing import Mapping

import numpy as np

MODEL_NAME = 'live_match_commit'
MODEL_TARGET = 'match_top1_correct'
MODEL_KIND = 'standardized_logistic'
TARGET_UNITS = ''
THRESHOLD = 0.371786

FEATURE_COLUMNS = [
    'match_progress_top1',
    'top1_distance',
    'margin',
    'distance_ratio',
    'candidate_count_log',
    'prefix_active_fraction',
    'duration_ratio_top1',
    'elapsed_log',
]

# Provenance (metrics at training time):
MODEL_METRICS = json.loads("""{
    "owner_holdout": {
        "accuracy": 0.771789,
        "balanced_accuracy": 0.741539,
        "f1": 0.836751,
        "fn": 120,
        "fp": 79,
        "positive_rate": 0.675459,
        "precision": 0.865874,
        "problem_recall": 0.809524,
        "rows": 872,
        "specificity": 0.673554,
        "tn": 163,
        "tp": 510
    }
}""")

_MODEL_BLOB = (
    'H4sIAAAAAAACA1VU246kNhD9FYunRKGJDb7BKpGi0UaKtJONktmn1Qq5wXRbAxgZdzqb1fx7jmG6NXmiqMupOnXxt+zozJo1tNCM'
    'aVELnWednaMNWfOZFoJyJcqS57Rglaoha4gVo5UQsoQoGOe6ZiJnRc2kkoolX64oE7pi+RsEVWheUa7FF2TwdtjwS0UlFzo5Ms2o'
    'oila8lJQIWV+YEXJeF1zKfIDUJlAjUwmWai6qsSW7I6R1JwBRaqUI1gTbd+amDVZSUt5oPJQ1k8lbXjdUPEDpQ2lWZ4N8LsE23Z+'
    'vEwzevE5m0zszu0S/CnYdW2jXxgc06ft3RrN3Fn8Tyac3AzhpmuDic5D0Zm5dz3SA/Qyx3b0J2iXYAf3T2u66P627RCS4Lf4yxY4'
    '7/G3dHY0ywoCKRh8Ti4CbZpc4iOpMFqW8Hp2cw9FKqA3oXf/7hGoyHWpRhuD60DqW+avsw3t2Y+9v8SkMF2HxN3XNH2lmNJ1nh3N'
    'mJigbW+N6HwF48C2RamkEgx/c9awkkJYskbBvPjVbdRAwyZP+HFRb8Q7tyauKVwKrXhS+uNopxY2M46bhdYCi5IFf0XBWpV5ti6I'
    'HFzn4tcdEHsHj5hSywoCUgtGX17ybDYTkmZjKmCf32u3YPLRbnP9AONhM5LdeOj8PLjegnJD/vgOnT8wcp8ecSuJZwvfgCoj2RbC'
    'TN8XwHzY4kn0xJCU82YkO/z1bGeyItCSn38CCPYodf4d8QAMV7da8mztsnu7+USQk6xXd481pHfDYANu8U1BR4u67UpuZcdUylMw'
    'brY98TO5WvNMzCX6w2iOdlzfkYD9c5Ml02WNifRyAczDx8fH357aX9//8vTpz/ftw8cPnx5//4sMwU8b4Y3QTiSYGSt2KtIKYm8Q'
    '3t7eB1rQu27FENF+llSvcjpvXWnNucCVUq1Lzfj2JJSqqvFspJeE0ppj99KbwSvFZbVdNB4UhcD8fwh4B7A5FfuSMpztZDDtq1nP'
    'aIwp0P3Jp3OffG/HH7dzxXnadCz7NmzX+zrJu7W9zC5iNbKkuQ0pMavSPciX/wDk5KXIHwUAAA=='
)

_MODEL_CACHE: dict | None = None


def _load() -> dict:
    global _MODEL_CACHE
    if _MODEL_CACHE is None:
        payload = gzip.decompress(base64.b64decode(_MODEL_BLOB.encode("ascii")))
        spec = json.loads(payload.decode("utf-8"))
        _MODEL_CACHE = {
            "center": np.asarray(spec["center"], dtype=float),
            "scale": np.asarray(spec["scale"], dtype=float),
            "coef": np.asarray(spec["coef"], dtype=float),
            "bias": float(spec["bias"]),
            "threshold": float(spec["threshold"]),
            "output_center": float(spec.get("output_center") or 0.0),
            "output_scale": float(spec.get("output_scale") if spec.get("output_scale") is not None else 1.0),
            "feature_columns": list(spec["feature_columns"]),
        }
    return _MODEL_CACHE


def score(features: Mapping[str, float]) -> float:
    """Return the model probability in [0, 1] for one feature mapping."""
    model = _load()
    vector = np.array(
        [float(features.get(column) or 0.0) for column in model["feature_columns"]],
        dtype=float,
    )
    scaled = (vector - model["center"]) / model["scale"]
    logit = float(scaled @ model["coef"] + model["bias"])
    logit = max(-60.0, min(60.0, logit))
    return 1.0 / (1.0 + np.exp(-logit))


def predict(features: Mapping[str, float]) -> bool:
    """True when the example crosses the embedded decision threshold."""
    return score(features) >= _load()["threshold"]