肘方法确定KMeans聚类的最佳K值

import numpy as np
import matplotlib.pyplot as plt
from matplotlib.font_manager import FontProperties
from sklearn.cluster import KMeans
from scipy.spatial.distance import cdist
# 1 数据可视化
cluster1 = np.random.uniform(0.5, 1.5, (2, 10))
cluster2 = np.random.uniform(3.5, 4.5, (2, 10))
X = np.hstack((cluster1, cluster2)).T
plt.figure()
plt.axis([0, 5, 0, 5])
plt.grid(True)
plt.plot(X[:, 0], X[:, 1], 'k.')
plt.show()

# 2 肘部法求最佳K值
K = range(1, 10)
mean_distortions = []
for k in K:
    kmeans = KMeans(n_clusters=k)
    kmeans.fit(X)
    mean_distortions.append(
        sum(
            np.min(
                cdist(X, kmeans.cluster_centers_, metric='euclidean'), axis=1))
        / X.shape[0])
plt.plot(K, mean_distortions, 'bx-')
plt.xlabel('k')
font = FontProperties(fname=r'c:\windows\fonts\msyh.ttc', size=20)
plt.ylabel(u'平均畸变程度', fontproperties=font)
plt.title(u'用肘部法确定最佳的K值', fontproperties=font)
plt.show()