Python sklearn中的K-Means聚类使用方法浅析_python

import numpy as np
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans
from sklearn.datasets import make_blobs
X, y = make_blobs(1500)
fig = plt.figure()
for i in range(2):
    ax = fig.add_subplot(1,2,i+1)
    y = KMeans(i+2).fit_predict(X)
    plt.scatter(X[:, 0], X[:, 1], c=y)
plt.show()

from sklearn.cluster import k_means
cen, y, interia = k_means(X, 3)

from sklearn.cluster import MiniBatchKMeans
import time
ys, xs = np.indices([4,4])*6
cens = list(zip(xs.reshape(-1), ys.reshape(-1)))
X, y = make_blobs(100000,centers=cens)
km = KMeans(16)
mbk = MiniBatchKMeans(16)
def test(func, value):
    t = time.time()
    func(value)
    print("耗时", time.time()-t)
test(km.fit_predict, X)
# 耗时 3.2028110027313232
test(mbk.fit_predict, X)
# 耗时 0.2590029239654541

fig = plt.figure()
ax = fig.add_subplot(1,2,1)
ax.scatter(X[:,0], X[:,1], c=km.labels_, 
    marker='.', alpha=0.5)
ax = fig.add_subplot(1,2,2)
ax.scatter(X[:,0], X[:,1], c=mbk.labels_, 
    marker='.', alpha=0.5)
plt.show()