j简单的分类实现-K近邻

1 __author__ = 'worfzyq'
2 from numpy import *
3 import operator
4
5 def creatDataset() :
6 group=array([[1.0,1.1],[1.0,1.0],[0.0,0.0],[0,0.1]])
7 labels=['A','A','B','B']
8 return group,labels
9
def classify0(inX,dataSet,labels,k) :
dataSetSize=dataSet.shape[0] #返回数组得到维数
# print(dataSetSize)
diffMat=tile(inX,(dataSetSize,1))-dataSet #把inX扩展datasetSize-1维然后做减法
#print(diffMat)
sqDiffMat=diffMat**2 #乘方
#print(sqDiffMat)
sqDistances=sqDiffMat.sum(axis=1) #把每一列加起来
#print(sqDistances)
distances=sqDistances**0.5 # 得到距离
sortedDistIndicies=distances.argsort() #得到排好序得到下标
classCount={}
for i in range(k) :
voteIlabel=labels[sortedDistIndicies[i]]
classCount[voteIlabel]=classCount.get(voteIlabel,0)+1
sortedClassCount=sorted(classCount.iteritems(),key=operator.itemgetter(1),reverse=True)
#print(sortedClassCount)
return sortedClassCount[0][0]

group,labels=creatDataset()
# print(group)
print(classify0([0,0],group,labels,3))