# -*- coding: utf-8 -*-
import pandas as pd
from sklearn.cluster import KMeans
import matplotlib.pyplot as plt
'''
k-means最优K的选取
'''
data_Path = 'dataset/first_round_training_data.csv'
df_features = pd.read_csv(data_Path) # 读入数据
'针对对特征Parameter1,利用SSE选择最优k'
SSE = [] # 存放每次结果的误差平方和
for k in range(1, 9): # K的范围 : 1-9
estimator = KMeans(n_clusters=k) # 构造聚类器
estimator.fit(df_features[['Parameter1']])
SSE.append(estimator.inertia_)
X = range(1, 9)
plt.xlabel('k')
plt.ylabel('SSE')
plt.plot(X, SSE, 'o-')
plt.show()
运行截图:
选择折线坡度骤减的点作为最优K,如上图K为2时最优
参考博客: https://blog.csdn.net/qq_15738501/article/details/79036255