# 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#fit-pca-from-rois

# region: setup
import os
from pathlib import Path

import joblib
import numpy as np
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
from sklearn.decomposition import PCA


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")
ROI_PCA_MODEL_PATH = Path(os.environ.get("HSI_EXAMPLE_ROI_PCA_MODEL", "roi_pca.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 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))
# end region

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

rng = np.random.default_rng(42)
max_pixels_per_roi = 1000

roi_pixels_list = []

for annot in ann_file.annotations:
    selected = reflectance.select_mask_from_descriptor(annot.descriptor)
    spectra = selected.to_numpy_with_interleave(hs.bip)[:, 0, :]
    if spectra.shape[0] > max_pixels_per_roi:
        selected = rng.choice(spectra.shape[0], size=max_pixels_per_roi, replace=False)
        spectra = spectra[selected]

    roi_pixels_list.append(spectra)

roi_pixels = np.concatenate(roi_pixels_list)
roi_pca = PCA(n_components=3, random_state=42)
roi_pca.fit(roi_pixels)

joblib.dump(roi_pca, ROI_PCA_MODEL_PATH)

print(f"ROI PCA explained variance: {roi_pca.explained_variance_ratio_}")
print(f"Saved ROI PCA model to {ROI_PCA_MODEL_PATH}")
# end region