# This file was extracted from the HV SDK Docusaurus examples.
# It is intended as a downloadable, runnable companion to the documentation.
# Set HSI_EXAMPLE_BASE_DIR and related env vars to use your own data.
# Source page: /hsi/hv_sdk/examples/pca#pca-scatter-plot-with-rois

# region: setup
import os
from pathlib import Path

import joblib
import matplotlib.pyplot as plt
import qtec_hv_sdk as hs
import qtec_hv_sdk.annotations
from qtec_hv_sdk.preprocessing import make_reference
from qtec_hv_sdk.preprocessing import reflectance_calibration


BASE_DIR = Path(os.environ.get("HSI_EXAMPLE_BASE_DIR", "/path/to/HSI_data/nuts"))
if not BASE_DIR.exists():
    raise SystemExit(
        "Run: 'export HSI_EXAMPLE_BASE_DIR=/path/to/HSI_data/' to setup the "
        "folder containing the example datacubes."
    )
TRAIN_CUBE = os.environ.get("HSI_EXAMPLE_TRAIN_CUBE", "mix1.pam")
DARK_REF = os.environ.get("HSI_EXAMPLE_DARK_REF", "dark_ref.pam")
WHITE_REF = os.environ.get("HSI_EXAMPLE_WHITE_REF", "white_ref.pam")
PCA_MODEL_PATH = Path(os.environ.get("HSI_EXAMPLE_PCA_MODEL", "pca_model.joblib"))


def make_references():
    dark = hs.open(str(BASE_DIR / DARK_REF))
    white = hs.open(str(BASE_DIR / WHITE_REF))
    return make_reference(dark), make_reference(white)


def open_reflectance_cube(cube_name=TRAIN_CUBE):
    dark_ref, white_ref = make_references()
    img = hs.open(str(BASE_DIR / cube_name))
    return reflectance_calibration(img, white_ref, dark_ref, clip=True)


def annotation_value(value):
    return value[0] if value is not None else None


def load_annotations():
    annotations_path = Path(os.environ.get("HSI_EXAMPLE_ANNOTATIONS", "mix1_roi.json"))
    if not annotations_path.is_absolute():
        annotations_path = BASE_DIR / annotations_path
    if not annotations_path.exists():
        raise SystemExit("Set HSI_EXAMPLE_ANNOTATIONS to the annotations JSON file.")
    return hs.annotations.open(str(annotations_path))


def load_pca_model():
    if not PCA_MODEL_PATH.exists():
        raise SystemExit(
            f"PCA model not found at {PCA_MODEL_PATH}. "
            "Run 01_principal_component_analysis.py first, or set HSI_EXAMPLE_PCA_MODEL."
        )
    return joblib.load(PCA_MODEL_PATH)
# end region


# region: example
reflectance = open_reflectance_cube()
pca = load_pca_model()
ann_file = load_annotations()

class_colors = {annotation_value(annot.properties["type"]): annot.color for annot in ann_file.annotations}
component_x = 0
component_y = 1

plt.figure(figsize=(8, 6))

for annot in ann_file.annotations:
    class_name = annotation_value(annot.properties["type"])
    selected = reflectance.select_mask_from_descriptor(annot.descriptor)
    spectra = selected.to_numpy_with_interleave(hs.bip)[:, 0, :]
    scores = pca.transform(spectra)

    plt.scatter(
        scores[:, component_x],
        scores[:, component_y],
        s=8,
        alpha=0.25,
        color=class_colors[class_name],
        edgecolors="none",
        label=class_name,
    )

handles, labels = plt.gca().get_legend_handles_labels()
unique = dict(zip(labels, handles))
plt.legend(unique.values(), unique.keys())
plt.xlabel(f"PC{component_x + 1}")
plt.ylabel(f"PC{component_y + 1}")
plt.title("ROI pixels in PCA space")
plt.grid(True, alpha=0.3)
plt.show()
# end region