K-近邻算法改进约会网站的配对效果

from numpy import * '''numpy科学计算包，在抽象和处理矩阵运算上具有优势'''import operator'''导入数据，创建数据集和标签'''def createDataSet():    group = array([[1.0,1.1],[1.0,1.0],[0,0],[0,0.1]])    labels = ['A','A','B','B']    return group,labels'''实施kNN算法，构造分类器''''''inX:进行分类的数据；dataSet:训练样本集；labels：标签向量；k：KNN算法的参数k,用来选择最近邻居'''def classify0(inX, dataSet, labels, k):    dataSetSize = dataSet.shape[0] '''读取矩阵dataSet第一维度的长度即行数'''    diffMat = tile(inX, (dataSetSize,1)) - dataSet '''将待进行分类的数据复制dataSetSize份，diffMat得到了目标与训练数值之间的差值'''    sqDiffMat = diffMat**2 '''各个元素分别平方'''    sqDistances = sqDiffMat.sum(axis=1) '''每一行元素之和'''    distances = sqDistances**0.5'''开方求距离'''    sortedDistIndicies = distances.argsort() '''将distance进行排序:由小到大'''    classCount={}    '''选择距离最小的K个点'''    for i in range(k):        voteIlabel = labels[sortedDistIndicies[i]]         classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1 '''统计最后出现结果的不同标签值的数量，出现一次便加1，以此类推'''    sortedclassCount = sorted(classCount.iteritems(),key=operator.itemgetter(1),reverse=True)'''按照从大到小的次序排序，最后返回发生频率最高的元素标签'''return sortedclassCount[0][0]def file2matrix(filename):    fr = open(filename)    arrayOLines = fr.readlines() '''按行读取文件'''    numberOfLines = len(arrayOLines) '''文件的函数即为返回矩阵的行数'''    returnMat = zeros((numberOfLines,3)) '''创建行数为numberOfLines,列数为3的0矩阵'''    classLabelVector = []    index = 0    for line in arrayOLines:        line = line.strip()        listFromLine = line.split('\t')        returnMat[index,:] = [0:3]        classLabelVector.append(int (listFromLine[-1])) '''将列表的最后一列存储在classLabelVector中，此处明确的通知解释器列表所存储的元素值为整型，否则Python语言会将这些元素当做字符串来处理'''        index += 1    return returnMat,classLabelVector'''归一化特征值'''def autoNorm(dataSet):    minVals = dataSet.min(0)    maxVals = dataSet.max(0)    ranges = maxVals - minVals    normDataSet = zeros(shape(dataSet))    m = dataSet.shape[0]    normDataSet = dataSet - tile(minVals, (m,1))    normDataSet = normDataSet/tile(ranges, (m,1))   #element wise divide    return normDataSet, ranges, minVals'''分类器针对约会网站的测试代码''' def datingClassTest():    hoRatio = 0.50      #hold out 10%    datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')       #load data setfrom file    normMat, ranges, minVals = autoNorm(datingDataMat)    m = normMat.shape[0]    numTestVecs = int(m*hoRatio)    errorCount = 0.0    for i in range(numTestVecs):        classifierResult = classify0(normMat[i,:],normMat[numTestVecs:m,:],datingLabels[numTestVecs:m],3)        print "the classifier came back with: %d, the real answer is: %d" % (classifierResult, datingLabels[i])        if (classifierResult != datingLabels[i]): errorCount += 1.0    print "the total error rate is: %f" % (errorCount/float(numTestVecs))    print errorCount