kNN算法代码实现（k-近邻）

 

从《机器学习实战》当中学到的第一个算法： 

from numpy import *
from os import listdir
import operator
#创建训练样本集
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
#返回预测结果
def classify0(inX,dataSet,labels,k):
    #dataSetSize : dateSet有多少行数据
    dataSetSize = dataSet.shape[0]
    #diffMat : tile函数得到dataSetSize行1*(inX的列数)列-dataSet的数据
    diffMat = tile(inX,(dataSetSize,1)) - dataSet
    #欧式距离公式 ； d = sqrt((xA0-xB0)^2+(xA1-xB1)^2)
    sqlDiffMat = diffMat**2
    #按行累加
    sqDistances = sqlDiffMat.sum(axis=1)
    distances = sqDistances**0.5
    #按distances从小到大的顺序将索引录入到sortedDistIndicies
    sortedDistIndicies = distances.argsort()
    classCount = {}
    #取k个欧氏距离最小的数据统计出现次数最多的分类
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1
    #按照第二个元素的次序进行降序排序
    max = 0
    for key,value in classCount.items():
        if value > max :
            max = value
            flag = key
    #sortedClassCount = sorted(classCount.iteritems(),
    #key=operator.itemgetter(1), reverse=True)
    return flag
#返回x样本和y样本
def file2matrix(filename):
    fr = open(filename)
    arrayOLines = fr.readlines()
    numberOfLines = len(arrayOLines)
    #生成numberOfLines行3列值为零的数组
    returnMat = zeros((numberOfLines,3))
    classLabelVector = []
    index = 0
    for line in arrayOLines:
        line = line.strip()
        listFromLine = line.split('\t')
        returnMat[index,:] = listFromLine[0:3]
        classLabelVector.append(int(listFromLine[-1]))
        index += 1
    return returnMat,classLabelVector
#将各个变量取值变为[0,1]
def autoNorm(dataSet):
    minVals = dataSet.min(0)
    mmaxVals = dataSet.max(0)
    ranges = mmaxVals - minVals
    #值为零的dataSet数组
    normDataSet = zeros(shape(dataSet))
    #dataSet的行数
    m = dataSet.shape[0]
    normDataSet = dataSet - tile(minVals,(m,1))
    normDataSet = normDataSet/tile(ranges,(m,1))
    #normDataSet值域[0,1]
    return normDataSet,ranges,minVals

def datingClassTest():
    hoRatio = 0.10
    datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')
    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 ans wer is: %d"\
        % (classifierResult,datingLabels[i]))
        if(classifierResult != datingLabels[i]):
            errorCount += 1.0
    print("the total error rate is : %f " % (errorCount/float(numTestVecs)))

def classifyPerson():
    resultList = ['not at all','in small doses','in large doses']
    #输入文本行命令并返回用户所输入的命令
    percentTats = float(input(\
                  "percentage of time spent playing video games?"))
    ffMiles = float(input("frequent flier miles earned per year?"))
    iceCream = float(input("liters of ice cream consumed per year?"))
    datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')
    normMat,ranges,minVals = autoNorm(datingDataMat)
    inArr = array([ffMiles,percentTats,iceCream])
    classifierResult = classify0((inArr-minVals)/ranges,normMat,datingLabels,3)
    print("You will probably like this person: ",\
            resultList[classifierResult - 1])
#将文件的32*32的数据转为1*1024并返回returnVect数组
def img2vector(filename):
    returnVect = zeros((1,1024))
    fr = open(filename)
    for i in range(32):
        lineStr = fr.readline()
        for j in range(32):
            returnVect[0,32*i+j] = int(lineStr[j])
    return returnVect
#对数字进行识别
def handwritingClassTest():
    #结果集
    hwLabels = []
    #获得指定文件名下的列表
    trainingFileList = listdir('trainingDigits')
    m = len(trainingFileList)
    #训练集
    trainingMat = zeros((m,1024))
    for i in range(m):
        fileNameStr = trainingFileList[i]
        fileStr = fileNameStr.split('.')[0]
        classNumStr = int(fileStr.split('_')[0])
        hwLabels.append(classNumStr)
        trainingMat[i,:] = img2vector('trainingDigits/%s' % fileNameStr)

    testFileList = listdir('testDigits')
    errorCount = 0.0
    mTest = len(testFileList)

    for i in range(mTest):
        fileNameStr = testFileList[i]
        fileStr = fileNameStr.split('.')[0]
        classNumStr = int(fileStr.split('_')[0])
        #测试
        vectorUnderTest = img2vector('testDigits/%s' % fileNameStr)
        classifierResult = classify0(vectorUnderTest,\
        trainingMat,hwLabels,3)
        print("the classifier came back with: %d,the real answer is: %d"\
        % (classifierResult,classNumStr))
        if(classifierResult != classNumStr): errorCount += 1.0

    print("\nthe total number of errors is: %d" % errorCount)
    print("\nthe total error rate is : %f"% (errorCount/float(mTest)))