# 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-and-preview-components

# region: setup
import os
from pathlib import Path

import numpy as np
import qtec_hv_sdk as hs
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 contrast_stretch(image, percentiles=(1, 99)):
    low, high = np.percentile(image, percentiles)
    return np.clip((image - low) / (high - low + 1e-8), 0, 1)
# end region

# region: example
import joblib
import matplotlib.pyplot as plt
from qtec_hv_sdk.ml import pca_helper
from sklearn.decomposition import PCA


reflectance = open_reflectance_cube()

line_step = 50
sample_step = 20
n_components = 6

sample_stop = (reflectance.shape.samples // sample_step) * sample_step
sample_cube = reflectance[0:200:line_step, 0:sample_stop:sample_step, :].to_numpy_with_interleave(hs.bip)
sample_pixels = sample_cube.reshape(-1, sample_cube.shape[-1])

pca = PCA(n_components=n_components, random_state=42)
pca.fit(sample_pixels)

print(f"Explained variance: {pca.explained_variance_ratio_}")
print(f"Total explained variance: {pca.explained_variance_ratio_.sum():.3f}")

# Save the PCA model
joblib.dump(pca, PCA_MODEL_PATH)
print(f"Saved PCA model to {PCA_MODEL_PATH}")

hs_pca = pca_helper(pca)

preview_source = reflectance[0:250, 0:400, :]
pca_image = hs_pca(preview_source)
pca_preview = pca_image.to_numpy_with_interleave(hs.bip)

rgb_preview = pca_preview[:, :, :3].copy()
for channel in range(3):
    rgb_preview[:, :, channel] = contrast_stretch(rgb_preview[:, :, channel])

plt.imshow(rgb_preview)
plt.title("PCA RGB preview: PC1, PC2, PC3")
plt.axis("off")
plt.show()
# end region