import numpy as np

import matplotlib.pyplot as plt

from sklearn.cluster import KMeans

from sklearn.utils import shuffle

import mahotas as mh

original_img = np.array(mh.imread('Penguins.jpg'), dtype=np.float64) / 255

'''

>>> original_img

array([[[ 0.45490196, 0.68627451, 0.81960784],

[ 0.4627451 , 0.68235294, 0.81960784],

[ 0.4627451 , 0.68235294, 0.81960784],

...,

[ 0.34901961, 0.62352941, 0.81568627],

[ 0.35686275, 0.62352941, 0.81568627],

[ 0.35686275, 0.62352941, 0.81568627]],

[[ 0.45490196, 0.69019608, 0.82352941],

[ 0.45490196, 0.68235294, 0.82745098],

[ 0.45882353, 0.68627451, 0.83137255],

...,

[ 0.34117647, 0.63137255, 0.80784314],

[ 0.34117647, 0.63529412, 0.8 ],

[ 0.34117647, 0.63529412, 0.8 ]],

[[ 0.4627451 , 0.69411765, 0.82745098],

[ 0.45882353, 0.68627451, 0.83137255],

[ 0.45882353, 0.68627451, 0.83137255],

...,

[ 0.33333333, 0.63921569, 0.78823529],

[ 0.3372549 , 0.64313725, 0.78431373],

[ 0.3372549 , 0.64313725, 0.78431373]],

...,

[[ 0.34509804, 0.4745098 , 0.35294118],

[ 0.50588235, 0.54901961, 0.5254902 ],

[ 0.76078431, 0.79215686, 0.56078431],

...,

[ 0.43921569, 0.54117647, 0.5372549 ],

[ 0.39607843, 0.49803922, 0.50196078],

[ 0.34117647, 0.42352941, 0.42745098]],

[[ 0.31764706, 0.44705882, 0.40392157],

[ 0.37647059, 0.46666667, 0.49803922],

[ 0.30196078, 0.40392157, 0.29019608],

...,

[ 0.44313725, 0.52156863, 0.51372549],

[ 0.43921569, 0.50980392, 0.51764706],

[ 0.36078431, 0.45882353, 0.44705882]],

[[ 0.30588235, 0.40784314, 0.37254902],

[ 0.31372549, 0.42352941, 0.47058824],

[ 0.31372549, 0.39607843, 0.36862745],

...,

[ 0.40784314, 0.50588235, 0.48235294],

[ 0.41568627, 0.49803922, 0.50196078],

[ 0.33333333, 0.40392157, 0.40392157]]])

>>> original_img.shape[0] #宽度

434

>>> original_img.shape[1] #高度

1024

>>> original_img.shape[2]

3

'''


original_dimensions = tuple(original_img.shape)

'''

>>> original_dimensions

(434, 1024, 3)

'''


width, height, depth = tuple(original_img.shape)

#文档说，是高度，宽度，Must be of shape (h,w,3)

#http://mahotas.readthedocs.org/en/latest/api.html

image_flattened = np.reshape(original_img, (width * height, depth))

'''

>>> image_flattened.shape

(444416, 3)

'''

#随机选取1000个颜色点

image_array_sample = shuffle(image_flattened, random_state=0)[:1000]

'''

>>> image_array_sample

array([[ 0.2745098 , 0.37254902, 0.4 ],

[ 0.41568627, 0.6627451 , 0.82352941],

[ 0.64705882, 0.75686275, 0.94117647],

...,

[ 0.11764706, 0.25490196, 0.33333333],

[ 0.7372549 , 0.79607843, 0.96470588],

[ 0.7254902 , 0.78823529, 0.92156863]])

>>> image_array_sample.shape

(1000, 3)

'''

#1000个采样点，64个聚簇

estimator = KMeans(n_clusters=64, random_state=0)

estimator.fit(image_array_sample)

cluster_assignments = estimator.predict(image_flattened)

'''

>>> cluster_assignments

array([ 6, 6, 6, ..., 14, 14, 14])

>>> cluster_assignments.shape

(444416,)

>>>

这样就给每一个颜色值分配了一个颜色标签（这样的标签共有64个）

'''

compressed_palette = estimator.cluster_centers_

compressed_img = np.zeros((width, height, compressed_palette.shape[1]))

label_idx = 0

for i in range(width):

   for j in range(height):

      compressed_img[i][j] = compressed_palette[cluster_assignments[label_idx]]   #根据标签，获得颜色值

      label_idx += 1

plt.subplot(121) #一行两列第一个位置

plt.title('Original Image')

plt.imshow(original_img)

plt.axis('off')

plt.subplot(122) #很神奇的地方，一行两列，第二个位置

plt.title('Compressed Image')

plt.imshow(compressed_img)

plt.axis('off')

plt.show()