from sklearn.datasets import load_iris data,target=load_iris(return_X_y=True) print('feature_value:',data.shape) print('target:',target) from sklearn.cluster import KMeans import numpy as np for i in range(0,30): kmeans=KMeans(n_clusters=3,max_iter=30,tol=0.0001, random_state=i).fit(data) label=kmeans.labels_ #print('label:',label) center=kmeans.cluster_centers_ #print('center:',center) predict=kmeans.predict(data) print('i=',i) print('predict:',predict) accuracy=np.mean(predict==target)*100 print('accuracy',accuracy) #模型预测 predict=kmeans.predict(data) print('predict:',predict) import numpy as np accurancy=np.mean(predict==target)*100 print('i=',i) print('accurancy',accurancy) import matplotlib.pyplot as plt import mglearn plt.figure(figsize=(10,8)) plt.subplot(221) mglearn.discrete_scatter(data[:,0],data[:,1],target,markers='^') plt.xlabel('data') plt.ylabel('origin') plt.subplot(222) mglearn.discrete_scatter(data[:,0],data[:,1],y_predict,markers='^') mglearn.discrete_scatter(kmeans.cluster_centers_[:,0],kmeans.cluster_centers_[:,1],[0,1,2],markers='o',markeredgewidth=2) plt.xlabel('data') plt.ylabel('y_predict') plt.show()写一下注释

代码功能：使用KMeans算法对鸢尾花数据集进行聚类，并绘制聚类结果的散点图。

1. 导入所需的库和数据集：

from sklearn.datasets import load_iris 
data,target=load_iris(return_X_y=True)

2. 输出特征值和目标值的形状：

print('feature_value:',data.shape) 
print('target:',target)

3. 导入KMeans算法，对数据进行聚类：

from sklearn.cluster import KMeans 
for i in range(0,30):     
    kmeans=KMeans(n_clusters=3,max_iter=30,tol=0.0001, random_state=i).fit(data)     
    label=kmeans.labels_ #print('label:',label)     
    center=kmeans.cluster_centers_ #print('center:',center)     
    predict=kmeans.predict(data)     
    print('i=',i)     
    print('predict:',predict)     
    accuracy=np.mean(predict==target)*100      
    print('accuracy',accuracy)

4. 输出聚类的预测结果，并计算准确率：

predict=kmeans.predict(data) 
print('predict:',predict) 
import numpy as np 
accurancy=np.mean(predict==target)*100 
print('i=',i) 
print('accurancy',accurancy)

5. 绘制散点图：

import matplotlib.pyplot as plt 
import mglearn 
plt.figure(figsize=(10,8)) 
plt.subplot(221) 
mglearn.discrete_scatter(data[:,0],data[:,1],target,markers='^') 
plt.xlabel('data') 
plt.ylabel('origin') 
plt.subplot(222) 
mglearn.discrete_scatter(data[:,0],data[:,1],y_predict,markers='^') 
mglearn.discrete_scatter(kmeans.cluster_centers_[:,0],kmeans.cluster_centers_[:,1],[0,1,2],markers='o',markeredgewidth=2) 
plt.xlabel('data') 
plt.ylabel('y_predict') 
plt.show()

其中，第一个子图是原始数据的散点图，第二个子图是聚类结果的散点图，红色、黄色和紫色分别代表三个不同的簇。