kNN算法改进约会网站的配对效果

#coding = 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]]) #生成一个数组labels = ['A', 'A', 'B', 'B']#标签向量return group, labelsdef classify0(inX, dataSet, labels, k): #分别为待分类向量，数据集，标签向量，kdataSetSize = dataSet.shape[0] #计算数据集行数diffMat = tile(inX, (dataSetSize, 1)) - dataSetsqDiffMat = diffMat ** 2sqDistances = sqDiffMat.sum(axis = 1)distances = sqDistances ** 0.5 #计算待分类向量和数据集每个向量的距离sortedDistIndicies = distances.argsort() #排序且返回的是升序元素的索引classCount = {} #创建空字典for i in range(k):voteIlabel = labels[sortedDistIndicies[i]]classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1 #记录不同类别的分别有几个sortedClassCount = sorted(classCount.iteritems(), key = operator.itemgetter(1), reverse = True) #按照键值对的第二维降序排return sortedClassCount[0][0] #分类结果def file2matrix(filename):fr = open(filename)arrayOLines = fr.readlines() #一次性读取文件所有行numberOfLines = len(arrayOLines) #共有多少行returnMat = zeros((numberOfLines, 3)) classLabelVector = []index = 0for line in arrayOLines:line = line.strip() #去除开头结尾的空格制表等listFromLine = line.split('\t') #按照制表分割returnMat[index,:] = listFromLine[0:3] #赋值classLabelVector.append(int(listFromLine[-1])) #赋值index += 1return returnMat, classLabelVectorgroup, labels = createDataset()sortedClassCount = classify0([0, 0], group, labels, 3)returnMat, classLabelVector = file2matrix('datingTestSet2.txt')fig = plt.figure()ax = fig.add_subplot(111)ax.scatter(returnMat[:,1], returnMat[:,2], 15.0*array(classLabelVector), 15.0*array(classLabelVector))def autoNorm(dataSet): #归一化特征值new = (old - min)/(max - min)minVals = dataSet.min(0) #求每一列的最小值maxVals = dataSet.max(0)ranges = maxVals - minValsnormDataSet = zeros(shape(dataSet))m = dataSet.shape[0]normDataSet = dataSet - tile(minVals, (m,1))normDataSet = normDataSet/tile(ranges, (m, 1))return normDataSet, ranges, minValsnormDataSet, ranges, minVals = autoNorm(returnMat)def datingClassTest(): #测试分类器错误率hoRatio = 0.10 #使用％10的数据进行测试即可datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')normMat, ranges, minVals = autoNorm(datingDataMat)m = normMat.shape[0]numTestVecs = int(m*hoRatio)errorCount = 0.0for 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 += 1.0print "the total error rate is: %f" % (errorCount/float(numTestVecs))datingClassTest()