1 # coding=utf-8
 2 from numpy import * 
 3 import operator
 4 
 5 def createDataSet():
 6     group = array([[1.0,1.1],[1.0,1.0],[0,0],[0,0.1]])
 7     labels = [‘A‘,‘A‘,‘B‘,‘B‘]
 8     return group,labels
 9 
10 def classify(inX,dataSet,labels,k):
11     dataSetSize = dataSet.shape[0]
12     diffMat = tile(inX,(dataSetSize,1))-dataSet
13     sqDiffMat = diffMat**2
14     sqDistances = sqDiffMat.sum(axis=1)
15     distances = sqDistances**0.5
16     # 返回值所在的索引
17     sortedDistIndices = distances.argsort()
18     classCount={}
19     for i in range(k):
20         # 根据索引获取其对应的类别标签
21         voteIlabel = labels[sortedDistIndices[i]]
22         classCount[voteIlabel] = classCount.get(voteIlabel,0)+1
23     print classCount
24     sortedClassCount = sorted(classCount.iteritems(),key=operator.itemgetter(1),reverse=True)
25     return sortedClassCount[0][0]
26 
27 def main():
28     (group,labels)=createDataSet()
29     print classify([0.8,1.5],group,labels,3)
30 
31 if __name__=="__main__":
32     main()