机器学习实战-KNN

测试数据地址为：http://download.csdn.net/detail/u012005313/9190017

# encoding:utf-8from numpy import *import operatorimport matplotlibimport matplotlib.pyplot as pltdef createDataSet():    group = array([[1.0, 1.1], [1.0, 1.0], [0, 0], [0, 0.1]])    labels = ['A', 'A', 'B', 'B']    return group, labelsdef classify0(intX, dataSet, labels, k):    dataSetSize = dataSet.shape[0]    ds = tile(intX, (dataSetSize, 1))    diffMat = ds - dataSet    sqDiffMat = diffMat ** 2    sqDistances = sqDiffMat.sum(axis=1)    distances = sqDistances ** 0.5    sortedDistIndicies = distances.argsort()    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)    return sortedClassCount[0][0]def file2matrix(filename, dim2):    fr = open(filename)    arrayOLines = fr.readlines()    numberOfLines = len(arrayOLines)    returnMat = zeros((numberOfLines, dim2))    classLabelVector = []    index = 0    for line in arrayOLines:        line = line.strip()        listFromLine = line.split('\t')        returnMat[index, :] = listFromLine[0:dim2]        classLabelVector.append(int(listFromLine[-1]))        index += 1    return returnMat, classLabelVectordef 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))    return normDataSet, ranges, minValsdef datingClassTest():    hoRation = 0.10    datingDataMat, datingLabels = file2matrix('datingTestSet2.txt', 3)    normMat, ranges, minVals = autoNorm(datingDataMat)    m = normMat.shape[0]    numTestVecs = int(m * hoRation)    errCount = 0.0    for i in range(numTestVecs):        classifierResult = classify0(normMat[i, :], normMat[numTestVecs:m, :], datingLabels[numTestVecs:m], 3)        print "分类器结果：%d， 实际结果为：%d" % (classifierResult, datingLabels[i])        if classifierResult != datingLabels[i]:            errCount += 1.0    print "err rate：%f" % (errCount / float(numTestVecs))    numTestVecsdef classifyPerson():    resultList = ['not all', 'in small doses', 'in large doses']    percentTats = float(raw_input(u"在游戏上花费的时间占比( )%:"))    ffMiles = float(raw_input(u"每年航空的里程数:"))    iceCream = float(raw_input(u"每年吃的冰淇淋（升）"))    datingDataMat, datingLabels = file2matrix('datingTestSet2.txt', 3)    normMat, ranges, minVals = autoNorm(datingDataMat)    inArr = array([ffMiles, percentTats, iceCream])    classifiResult = classify0(inArr / ranges, normMat, datingLabels, 3)    print "你可能是属于以下这类人：", resultList[classifiResult - 1]if __name__ == '__main__':    classifyPerson()    # datingClassTest()    # fig = plt.figure()    # ax = fig.add_subplot(111)    # ax.scatter(datingDataMat[:, 1], datingDataMat[:, 2], 15.0 * array(datingLabels), array(datingLabels))    # plt.show()