数据分析与挖掘-Kmeans算法-1.聚类算法之Kmeans算法原理

import numpy as np
import pandas as pd
import matplotlib
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans
from sklearn.datasets import load_iris

matplotlib.use("TkAgg")

#导出数据
train,target = load_iris(return_X_y=True)

#样本集
train = train[:,:2]
print(train)
print(target)

#构建模型
kmean = KMeans(n_clusters=4)

#训练-得到结果
y_ = kmean.fit_predict(train)
print(y_)

#绘制图形，显示聚类结果
plt.figure(figsize=(14,5),dpi=80)

#绘制测试前的图形
plt.subplot(1,2,1)
plt.scatter(train[:,0],train[:,1],c = target)
plt.title("True")
#绘制测试后的图形
plt.subplot(1,2,2)
plt.scatter(train[:,0],train[:,1],c = y_)
plt.title("Train")

#获取聚类中心
centerts = kmean.cluster_centers_
print(centerts)
#绘制聚类中心
plt.scatter(centerts[:,0],centerts[:,1],c="red")
plt.show()