机器学习sklearn（64）：算法实例（二十一）聚类（四）KMeans （三） 案例：聚类算法用于降维，KMeans的矢量量化应用

import numpy as np
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans
from sklearn.metrics import pairwise_distances_argmin
from sklearn.datasets import load_sample_image
from sklearn.utils import shuffle

china = load_sample_image("china.jpg")
china
china.dtype
china.shape
china[0][0] 
newimage = china.reshape((427 * 640,3))
import pandas as pd
pd.DataFrame(newimage).drop_duplicates().shape
plt.figure(figsize=(15,15))
plt.imshow(china)
flower = load_sample_image("flower.jpg")
plt.figure(figsize=(15,15))
plt.imshow(flower)

n_clusters = 64
china = np.array(china, dtype=np.float64) / china.max()
w, h, d = original_shape = tuple(china.shape)
assert d == 3
image_array = np.reshape(china, (w * h, d))

china = np.array(china, dtype=np.float64) / china.max()

w, h, d = original_shape = tuple(china.shape) 
w
h
d

assert d == 3
d_ = 5
assert d_ == 3, "一个格子中的特征数目不等于3种"
image_array = np.reshape(china, (w * h, d))
image_array

image_array.shape
a = np.random.random((2,4))
a
a.reshape((4,2))
np.reshape(a,(4,2))
np.reshape(a,(2,2,2))
np.reshape(a,(3,2))

image_array_sample = shuffle(image_array, random_state=0)[:1000]
kmeans = KMeans(n_clusters=n_clusters, random_state=0).fit(image_array_sample)
kmeans.cluster_centers_

labels = kmeans.predict(image_array)
labels.shape

image_kmeans = image_array.copy()
for i in range(w*h):
    image_kmeans[i] = kmeans.cluster_centers_[labels[i]]

image_kmeans
pd.DataFrame(image_kmeans).drop_duplicates().shape

image_kmeans = image_kmeans.reshape(w,h,d)
image_kmeans.shape

centroid_random = shuffle(image_array, random_state=0)[:n_clusters]
labels_random = pairwise_distances_argmin(centroid_random,image_array,axis=0)
labels_random.shape
len(set(labels_random))
image_random = image_array.copy()
for i in range(w*h):
    image_random[i] = centroid_random[labels_random[i]]
image_random = image_random.reshape(w,h,d)
image_random.shape

plt.figure(figsize=(10,10))
plt.axis(‘off‘)
plt.title(‘Original image (96,615 colors)‘)
plt.imshow(china)
plt.figure(figsize=(10,10))
plt.axis(‘off‘)
plt.title(‘Quantized image (64 colors, K-Means)‘)
plt.imshow(image_kmeans)
plt.figure(figsize=(10,10))
plt.axis(‘off‘)
plt.title(‘Quantized image (64 colors, Random)‘)
plt.imshow(image_random)
plt.show()