Kmeans

from numpy import *
import matplotlib.pyplot as plt
import operator
inx=[1,3]
def createDataSet():
    '创建数据集'
    group=array([[1.0,1.1],[1.0,1.0],[0,0],[0,1.1]])
    labels=["A","A","B","B"]
    x=[1,1,0,0]
    y=[1.1,1.0,0,1.1]
    plt.figure()
    plt.plot(x[0:2],y[0:2],'ro') #A
    plt.plot(x[2:4],y[2:4],'bo') #B
    plt.plot(1,3,'y*')
    plt.show()
    return group,labels

def classify(inX,dataSet,labels,k):# dataSet是group inX是测试的点 labels是标签
    # 获取维度
    dataSetSize=dataSet.shape[0]   # 训练数据集数量
    #print (dataSetSize)
    #print (tile(inX,(dataSetSize,1)))
    diffMat=tile(inX,(dataSetSize,1))-dataSet  # 测试样本的各维度的差值
    #print (diffMat)
    sqDiffMat=diffMat**2  # 平方计算
    #print (sqDiffMat)
    sqDistance=sqDiffMat.sum(axis=1)  # 输出每行的值
    #print (sqDistance)
    distances=sqDistance**0.5   # 开方计算
    #print (distances)
    sortedDistances=distances.argsort()   # 排序 按距离从小到大 输出索引
    #print (sortedDistances)
    classCount={}
    for i in range(k):
        voteIlabel=labels[sortedDistances[i]]# voteIlabel是对应索引下的坐标的标签
        classCount[voteIlabel]=classCount.get(voteIlabel,0)+1.0 #在该标签的横坐标上加1 
    sortedClassCount=sorted(classCount.items(),key=operator.itemgetter(1),reverse=True)

    return sortedClassCount[0][0]

group,labels=createDataSet()
res=classify(inx,group,labels,3)
print (res)