"""E8 humidity: train at mid humidity, test at low and high humidity (1x concentration).

    python experiments/e8_humidity.py data/demo_calibration

Metal-oxide sensors react to water vapour, and bananas give off moisture, so this is the
main real-life disturbance besides concentration (E3). labels.csv needs rh_level
(low / mid / high). The "蕈狀體（無增益控制）" row is the ablation.
"""
from __future__ import annotations

import argparse
import sys
from pathlib import Path

import numpy as np
import pandas as pd
from sklearn.base import clone
from sklearn.metrics import accuracy_score

sys.path.insert(0, str(Path(__file__).resolve().parents[1]))

from enose.common import load_table, output_dir, plt, save_figure  # noqa: E402
from enose.methods import make_methods  # noqa: E402


def main() -> None:
    parser = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
    parser.add_argument("folder", type=Path)
    parser.add_argument("--concentration", type=float, default=1.0)
    arguments = parser.parse_args()
    table, features, labels, names = load_table(arguments.folder / "features.csv")
    at_concentration = (table["concentration"] == arguments.concentration).to_numpy()
    train = at_concentration & (table["rh_level"] == "mid").to_numpy()
    methods = make_methods(names, len(np.unique(labels)))

    rows = []
    for name, method in methods.items():
        model = clone(method).fit(features[train], labels[train])
        for rh_level in ("low", "high"):
            test = at_concentration & (table["rh_level"] == rh_level).to_numpy()
            if test.any():
                rows.append({"method": name, "rh_level": rh_level, "n": int(test.sum()),
                             "accuracy": accuracy_score(labels[test], model.predict(features[test]))})
    result = pd.DataFrame(rows)
    results = output_dir(arguments.folder / "results")
    result.to_csv(results / "e8_humidity.csv", index=False)
    pivot = result.pivot(index="method", columns="rh_level", values="accuracy").reindex(list(methods))
    print("用中濕度訓練，換濕度測試的準確率：")
    print(pivot.round(3).to_string())

    figure, axis = plt.subplots(figsize=(8, 4))
    pivot.plot.bar(ax=axis, rot=30)
    axis.set_ylabel("準確率")
    axis.set_ylim(0, 1.05)
    axis.set_title("濕度改變時的準確率（訓練：中濕度）")
    save_figure(figure, results / "e8_humidity.png")


if __name__ == "__main__":
    main()