用K均值算法（K-means）做聚类分析

1.导入模块

import numpy as np
import pandas as pd
from pandas import Series,DataFrame

import matplotlib.pyplot as plt
%matplotlib inline

#k-means学习模型
from sklearn.cluster import KMeans

#聚类数据生成器
from sklearn.datasets import make_blobs

2.生成训练数据

#生成聚类数据，作为训练数据
X_train,Y_train = make_blobs(n_samples=100,n_features=2,centers=2,cluster_std=1)

#展示生成的聚类数据
plt.scatter(X_train[:,0],X_train[:,1],c=Y_train)

3.创建kmeans机器学习对象

kmean = KMeans(n_clusters=2)

4.训练数据

kmean.fit(X_train)

5.预测数据

y_pre = kmean.predict(X_train)

6.绘图

plt.scatter(X_train[:,0],X_train[:,1],c=y_pre)