K-means聚類

• 學(xué)習(xí)K-means原理
• 使用sklearn代碼實(shí)現(xiàn)

生成數(shù)據(jù)

import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
from sklearn.datasets.samples_generator import make_blobs
# X為樣本特征，Y為樣本簇類別， 共1000個(gè)樣本，每個(gè)樣本2個(gè)特征，共4個(gè)簇，簇中心在[-1,-1], [0,0],[1,1], [2,2]， 簇方差分別為[0.4, 0.2, 0.2]
X, y = make_blobs(n_samples=1000, n_features=2, centers=[[-1,-1], [0,0], [1,1], [2,2]], cluster_std=[0.4, 0.2, 0.2, 0.2], 
                  random_state =9)
plt.scatter(X[:, 0], X[:, 1], marker='o')
plt.show()

from sklearn.cluster import KMeans
y_pred = KMeans(n_clusters=3, random_state=9).fit_predict(X)
plt.scatter(X[:, 0], X[:, 1], c=y_pred)
plt.show()
metrics.calinski_harabasz_score(X, y_pred)  

download.png

最小簇聚類

from sklearn.cluster import MiniBatchKMeans
for index, k in enumerate((2,3,4,5)):
    plt.subplot(2,2,index+1)
    y_pred = MiniBatchKMeans(n_clusters=k, batch_size=200, random_state=9).fit_predict(X)
    score= metrics.calinski_harabasz_score(X, y_pred)  
    plt.scatter(X[:, 0], X[:, 1], c=y_pred)
    plt.text(.99, .01, ('k=%d, score: %.2f' % (k,score)),
                 transform=plt.gca().transAxes, size=10,
                 horizontalalignment='right')
plt.show()

download (1).png