def classify0(inX, dataSet, labels, k):dataSetSize = dataSet.shape[0]  diffMat = tile(inX, (dataSetSize,1)) - dataSetsqDiffMat = diffMat**2sqDistances = sqDiffMat.sum(axis=1)distances = sqDistances**0.5sortedDistIndicies = distances.argsort()     classCount={}          for i in range(k):voteIlabel = labels[sortedDistIndicies[i]]classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(1), reverse=True)return sortedClassCount[0][0]

 1 def file2matrix(filename):
 2     fr = open(filename)
 3     numberOfLines = len(fr.readlines())         #get the number of lines in the file
 4     returnMat = zeros((numberOfLines,3))        #prepare matrix to return
 5     classLabelVector = []                       #prepare labels return
 6     fr = open(filename)
 7     index = 0
 8     for line in fr.readlines():
 9         line = line.strip()
10         listFromLine = line.split('\t')
11         returnMat[index,:] = listFromLine[0:3]
12         classLabelVector.append(int(listFromLine[-1]))
13         index += 1
14     return returnMat,classLabelVector

1 def autoNorm(dataSet):
2     minVals = dataSet.min(0)
3     maxVals = dataSet.max(0)
4     ranges = maxVals - minVals
5     normDataSet = zeros(shape(dataSet))
6     m = dataSet.shape[0]
7     normDataSet = dataSet - tile(minVals, (m,1))
8     normDataSet = normDataSet/tile(ranges, (m,1))   #element wise divide
9     return normDataSet, ranges, minVals

 1 def datingClassTest():
 2     hoRatio = 0.10      #hold out 10%
 3     datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')       #load data setfrom file
 4     normMat, ranges, minVals = autoNorm(datingDataMat)
 5     m = normMat.shape[0]
 6     numTestVecs = int(m*hoRatio)
 7     errorCount = 0.0
 8     for i in range(numTestVecs):
 9         classifierResult = classify0(normMat[i,:],normMat[numTestVecs:m,:],datingLabels[numTestVecs:m],3)
10         print "the classifier came back with: %d, the real answer is: %d" % (classifierResult, datingLabels[i])
11         if (classifierResult != datingLabels[i]): errorCount += 1.0
12     print "the total error rate is: %f" % (errorCount/float(numTestVecs))
13     print errorCount

 1 def classifierPerson():
 2    resultList = [u'不喜欢',u'比较喜欢',u'很喜欢']
 3    percentTats = float(raw_input(u"玩视频游戏所耗时间百分百："))
 4    ffmiles = float(raw_input(u"每年获得的飞行常客里程数："))
 5    iceCream = float(raw_input(u"每周消耗的冰淇淋公升数："))
 6    datingDataMat, datingLables = kNN.file2matrix('datingTestSet2.txt')
 7    normMat,ranges,minVals = kNN.autoNorm(datingDataMat )
 8    inArr = array([ffmiles ,percentTats ,iceCream ])
 9    classifierResult = kNN.classify0((inArr-minVals )/ranges,normMat ,datingLables ,3)
10    print u"你对这个人喜欢度: %s" % resultList [classifierResult -1]

1 def show_data():
2    dataSet,lables = kNN .file2matrix('datingTestSet2.txt')
3    jieguo = kNN .classify0([2674,8.54,8.0],dataSet ,lables ,10)
4    fig= plt.figure()
5    ax = fig.add_subplot(111)
6    ax.scatter(dataSet [:, 1], dataSet [:, 2],
7               15.0*array(lables ),15.0*array(lables))
8    fig.show()
9    raw_input()