4.K均值算法--应用

from sklearn.datasets import load_sample_image
from sklearn.cluster import KMeans
import matplotlib.pyplot as plt
import numpy as np
import matplotlib.image as img
import sys

#读取一张图片,观察图片存放数据特点
china=load_sample_image(‘china.jpg‘)
plt.imshow(china)
plt.show()

#根据图片的分辨率，可适当降低分辨率
image=china[::3,::3]#降低分辨率
x=image.reshape(-1,3)#生成行数未知，列数为3
print(china.shape,image.shape,x.shape)
plt.imshow(image)
plt.show()

#再用k均值聚类算法，将图片中所有的颜色值做聚类。
n_colors=64 #(256,256,256)
model=KMeans(n_colors)
label=model.fit_predict(x)#每个点颜色分类，0-63
colors=model.cluster_centers_#二维（64，3）
new_image=colors[label].reshape(image.shape)#然后用聚类中心的颜色代替原来的颜色值。
new_image=new_image.astype(np.uint8)

plt.imshow(new_image)#形成新的图片
plt.show()

#观察原始图片与新图片所占用内存的大小。
sys.getsizeof(china)
sys.getsizeof(new_image)

#将原始图片与新图片保存成文件，观察文件的大小。
img.imsave(‘C:/Users/Administrator/Desktop/大三下学期/机器学习/4.16/china.jpg‘,china)
img.imsave(‘C:/Users/Administrator/Desktop/大三下学期/机器学习/4.16/new_china.jpg‘,new_image)

from sklearn.cluster import KMeans
import numpy as np
from sklearn.model_selection import train_test_split
X = np.array([[‘Sunny‘, ‘Hot‘, ‘High‘, ‘Weak‘],
               [‘Sunny‘, ‘Hot‘, ‘High‘, ‘Strong‘],
               [‘Overcast‘, ‘Hot‘, ‘High‘, ‘Weak‘],
               [‘Rain‘, ‘Mild‘, ‘High‘, ‘Weak‘],
               [‘Rain‘, ‘Cool‘, ‘Normal‘, ‘Weak‘],
               [‘Rain‘, ‘Cool‘, ‘Normal‘, ‘Strong‘],
               [‘Overcast‘, ‘Cool‘, ‘Normal‘, ‘Strong‘],
               [‘Sunny‘, ‘Mild‘, ‘High‘, ‘Weak‘],
               [‘Sunny‘, ‘Cool‘, ‘Normal‘, ‘Weak‘],
               [‘Rain‘, ‘Mild‘, ‘Normal‘, ‘Weak‘],
               [‘Sunny‘, ‘Mild‘, ‘Normal‘, ‘Strong‘],
               [‘Overcast‘, ‘Mild‘, ‘High‘, ‘Strong‘],
               [‘Overcast‘, ‘Hot‘, ‘Normal‘, ‘Weak‘],
               [‘Rain‘, ‘Mild‘, ‘High‘, ‘Strong‘]])
Y = np.array([‘No‘, ‘No‘, ‘Yes‘, ‘Yes‘, ‘Yes‘, ‘No‘, ‘Yes‘, ‘No‘, ‘Yes‘, ‘Yes‘, ‘Yes‘, ‘Yes‘, ‘Yes‘, ‘No‘])
x_ = np.array([[‘Sunny‘, ‘Cool‘, ‘High‘, ‘Strong‘]])
#对数据进行处理
X[X == ‘Sunny‘] = 1
X[X == ‘Overcast‘] = 2
X[X == ‘Rain‘] = 3
X[X == ‘Hot‘] = 1
X[X == ‘Mild‘] = 2
X[X == ‘Cool‘] = 3
X[X == ‘High‘] = 1
X[X == ‘Normal‘] = 2
X[X == ‘Weak‘] = 1
X[X == ‘Strong‘] = 2
Y[Y == ‘No‘] = 1
Y[Y == ‘Yes‘] = 2
x_ [x_ == ‘Sunny‘] = 1
x_ [x_ == ‘Overcast‘] = 2
x_ [x_ == ‘Rain‘] = 3
x_ [x_ == ‘Hot‘] = 1
x_ [x_ == ‘Mild‘] = 2
x_ [x_ == ‘Cool‘] = 3
x_ [x_ == ‘High‘] = 1
x_ [x_ == ‘Normal‘] = 2
x_ [x_ == ‘Weak‘] = 1
x_ [x_ == ‘Strong‘] = 2
X = [[int(x), int(y), int(z), int(v)] for x, y, z, v in X]
Y = list(map(int, Y))
x_ = [[int(x), int(y), int(z), int(v)] for x, y, z, v in x_]
x_tr,x_te,y_tr,y_te=train_test_split(X, Y, test_size=0.2)#切割

k_model=KMeans(n_clusters=3)
k_model.fit(x_tr,y_tr)
y_pre=k_model.predict(x_)
if y_pre==2:
    y_pre = ‘Yes‘
elif y_pre==1:
    y_pre = ‘No‘
print(‘k均值算法的预测值：‘, y_pre)