"""E7b: how do the smell features relate to the food-science measurements?

    python experiments/e7b_correlation.py data/demo_banana

Spearman correlation (rank based, fine for curved relationships) between every
odour feature and brown_pct, brix, ph, weight_loss_pct. Destructive measurements
(brix, pH) usually come from the sacrificed "companion" bananas; leave those cells
empty for the tracked bananas and pandas skips them automatically.
"""
from __future__ import annotations

import argparse
import sys
from pathlib import Path

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

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

QUALITY: tuple[str, ...] = ("brown_pct", "brix", "ph", "weight_loss_pct")


def main() -> None:
    parser = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
    parser.add_argument("folder", type=Path)
    arguments = parser.parse_args()
    table, _, _, names = load_table(arguments.folder / "features.csv")
    quality = [column for column in QUALITY if column in table]
    matrix = table[names + quality].corr(method="spearman").loc[names, quality]
    results = output_dir(arguments.folder / "results")
    matrix.to_csv(results / "e7b_correlation.csv")
    print(matrix.round(2).to_string())

    figure, axis = plt.subplots(figsize=(1.4 * len(quality) + 2, 0.45 * len(names) + 1.5))
    image = axis.imshow(matrix.to_numpy(), cmap="RdBu_r", vmin=-1, vmax=1)
    axis.set_xticks(range(len(quality)), quality, rotation=30)
    axis.set_yticks(range(len(names)), names)
    for row in range(len(names)):
        for column in range(len(quality)):
            axis.text(column, row, f"{matrix.iat[row, column]:.2f}", ha="center", va="center", fontsize=8)
    figure.colorbar(image, ax=axis, label="Spearman ρ")
    axis.set_title("氣味特徵 × 食品指標")
    save_figure(figure, results / "e7b_correlation.png")


if __name__ == "__main__":
    main()