KMeans

一、原理见Machine_Learning

from sklearn.datasets import make_blobs
X, y = make_blobs(n_samples=150, n_features=2, centers=3, cluster_std=0.5, shuffle=True, random_state=0)

from sklearn.cluster import KMeans
km = KMeans(n_clusters=3, init='random', n_init=10, max_iter=300, tol=0.0004, random_state=0)
#set n_init=10,该聚类算法按不同的随机中心跑10次，并选择最小的SSE作为最后的KMeans模型，这里SSE计算方法是属于某类的样本与该类中心点的欧式距离之和

y_km = km.fit_predict(X)
#y_km会保存X中每个样本属于哪个类别
'''
[1, 0, 0, 0, 1, 0, 0, 1, 2, 0, 1, 2, 2, 0, 0, 2, 2, 1, 2, 1, 0, 1,
       0, 0, 2, 1, 1, 0, 2, 1, 2, 2, 2, 2, 0, 1, 1, 1, 0, 0, 2, 2, 0, 1,
       1, 1, 2, 0, 2, 0, 1, 0, 0, 1, 1, 2, 0, 1, 2, 0, 2, 2, 2, 2, 0, 2,
       0, 1, 0, 0, 0, 1, 1, 0, 1, 0, 0, 2, 2, 0, 1, 1, 0, 0, 1, 1, 1, 2,
       2, 1, 1, 0, 1, 0, 1, 0, 2, 2, 1, 1, 1, 1, 2, 1, 1, 0, 2, 0, 0, 0,
       2, 0, 1, 2, 0, 2, 0, 0, 2, 2, 0, 1, 0, 0, 1, 1, 2, 1, 2, 2, 2, 2,
       1, 2, 2, 2, 0, 2, 1, 2, 0, 0, 1, 1, 2, 2, 2, 2, 1, 1]
'''

import matplotlib.pyplot as plt
plt.scatter(X[y_km==0, 0], X[y_km==0, 1], s=50, c='lightgreen', marker='s', label='cluster 1')

plt.scatter(X[y_km==1, 0], X[y_km==1, 1], s=50, c='orange', marker='o', label='cluster 2')

plt.scatter(X[y_km==2, 0], X[y_km==2, 1], s=50, c='lightblue', marker='v', label='cluster 3')

plt.scatter(km.cluster_centers_[:, 0], km.cluster_centers_[:, 1], s=250, marker='*', c='red', label='centroids')
plt.legend()
plt.grid()
plt.show()