# import the required libraries
import os
import numpy as np
from PIL import Image
from sklearn.cluster import KMeans
import matplotlib.pyplot as plt
from skimage.color import rgb2hsv
from skimage.color import rgb2lab
from skimage import transform, io

# define the folder that holds the jpg images
folder = "images"

# read the images and convert them to NumPy arrays
images = []
for filename in os.listdir(folder):
    # if filename.endswith(".jpg"):
        img = Image.open(os.path.join(folder, filename))
        img = np.array(img)
        images.append(img)

img.shape

# number of images
n = len(images)

plt.figure(figsize=(5, 3))
# loop over the images to display them
for j in range(n):
    # create a subplot for each image
    plt.subplot(3, n//3, j + 1)
    # remove the axes
    plt.axis("off")
    # display the image
    plt.imshow(images[j])
# display the figure
plt.show()

# compute the mean pixel intensity of each image
means = []
for img in images:
    # img = rgb2hsv(img)
    # img = rgb2lab(img)
    mean = np.mean(img, axis=(0, 1)) # mean over the height and width axes
    means.append(mean)

# convert the list of means to a NumPy array
X = np.array(means)
print(X.shape)
# cluster the mean vectors with the k-means algorithm
k = 3
kmeans = KMeans(n_clusters=k, random_state=42)
kmeans.fit(X)
labels = kmeans.labels_ # cluster labels

# display the images of each cluster
for i in range(k):
    # select the images that belong to cluster i
    cluster = [images[j] for j in range(n) if labels[j] == i]
    # number of images in cluster i
    m = len(cluster)
    # set the figure size used to display the images
    plt.figure(figsize=(6, 3))
    # loop over the images to display them
    for j in range(m):
        # create a subplot for each image
        plt.subplot(1, m, j + 1)
        # remove the axes
        plt.axis("off")
        # display the image
        plt.imshow(cluster[j])
    # display the figure title
    plt.suptitle(f"Cluster {i}")
    # display the figure
    plt.show()

mean.shape

print(img.shape)
resized_image = transform.resize(img, (100, 100))
print(resized_image.shape)
flatted_image = resized_image.reshape(100*100,3)
print(flatted_image.shape)
print(resized_image[0,0,:])
print(flatted_image[0])

flatted_image = resized_image.reshape(100*100*3)
print(flatted_image.shape)
print(resized_image[0,0,:])
print(flatted_image[:3])

# resize the images to 100 x 100 pixels
flatted_images = []
for img in images:
    img = rgb2hsv(img)
    # img = rgb2lab(img)
    resized_image = transform.resize(img, (100, 100))
    flatted_images.append(resized_image.reshape(100*100*3))

X = np.array(flatted_images)
print(X.shape)
# cluster the mean vectors with the k-means algorithm
k = 3
kmeans = KMeans(n_clusters=k, random_state=42)
kmeans.fit(X)
labels = kmeans.labels_ # cluster labels

# display the images of each cluster
for i in range(k):
    # select the images that belong to cluster i
    cluster = [images[j] for j in range(n) if labels[j] == i]
    # number of images in cluster i
    m = len(cluster)
    # set the figure size used to display the images
    plt.figure(figsize=(6, 3))
    # loop over the images to display them
    for j in range(m):
        # create a subplot for each image
        plt.subplot(1, m, j + 1)
        # remove the axes
        plt.axis("off")
        # display the image
        plt.imshow(cluster[j])
    # display the figure title
    plt.suptitle(f"Cluster {i}")
    # display the figure
    plt.show()