k-近邻算法

from numpy import *
import operator
from os import listdir

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

#   用于分类的输入向量inX
#   输入的训练样本集为dataset
#   标签向量为labels
#   参数k用于选择最近邻居的数目

def classify0(inX,dataset,labels,k):
    dataSetSize = dataset.shape[0]
    diffMat=tile(inX,(dataSetSize,1))-dataset
    sqDiffMat=diffMat**2
    sqDistance=sqDiffMat.sum(axis=1)
    distances=sqDistance**0.5

    #   argsort函数返回的是数组值从小到大的索引值
    sortedDistIndicies=distances.argsort()

    classCount={}
    for i in range(k):
        voteIlabel=labels[sortedDistIndicies[i]]
        classCount[voteIlabel]=classCount.get(voteIlabel,0)+1
    sortedClassCount=sorted(classCount.items(),key=operator.itemgetter(1),reverse=True)
    return sortedClassCount[0][0]


def file2Matrix(filename):
    fr=open(filename)
    arrayOfLines = fr.readlines()
    numberOfLines=len(arrayOfLines)
    returnMat=zeros((numberOfLines,3))
    classLabelVector=[]
    index = 0
    for line in arrayOfLines:
        line = line.strip()
        listFromLine=line.split('\t')
        returnMat[index,:]=listFromLine[0:3]
        classLabelVector.append(int(listFromLine[-1]))
        index=index+1

    return returnMat,classLabelVector


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))
    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: '+str(classifierResult)+'the real answer is : '+str(datingLabels[i]))
        if(classifierResult!=datingLabels[i]):errorCount=errorCount+1
    print('The total error rate is : '+str(errorCount/float(numTestVecs)))

def calssifyPerson():
    resultList=['无感','有点感觉','非常喜欢']

    percentTats = float(input("每天多大比例的时间用来打游戏：\t"))
    ffMiles = float(input("每年获得的飞行常客里程数：\t"))
    iceCream = float(input("每周消耗多少公升冰淇淋：\t"))
    datingDataMat,datingLabels=file2Matrix('datingTestSet2.txt')
    normMat,ranges,minVals = autoNorm(datingDataMat)
    inArr = array([ffMiles,percentTats,iceCream])
    classifierResult=classify0((inArr-minVals)/ranges,normMat,datingLabels,3)

    print('预测你喜欢这个人的程度为：'+resultList[classifierResult-1])


def img2Vector(filename):
    fr = open(filename)
    returnVect = zeros((1,1024))
    for i in range(32):
        linestr = fr.readline()
        for j in range(32):
            returnVect[0,32*i+j]=int(linestr[j])
    return returnVect


def handwritingClassTest():
    hwLabels = []
    trainingFileList = listdir('./digits/trainingDigits')
    m = len(trainingFileList)
    trainingMat = zeros((m,1024))
    for i in range(m):
        fileNameStr = trainingFileList[i]
        fileStr = fileNameStr.split('.')[0]
        classNumStr = fileStr.split('_')[0]
        hwLabels.append(classNumStr)
        trainingMat[i,:] = img2Vector('./digits/trainingDigits/%s'%fileNameStr)

    testFileList = listdir('./digits/testDigits')
    errorCount = 0
    mTest = len(testFileList)
    for i in range(mTest):
        fileNameStr = testFileList[i]
        fileStr = fileNameStr.split('.')[0]
        classNumStr = int(fileStr.split('_')[0])
        vectorUnderTest = img2Vector('./digits/testDigits/%s'%fileNameStr)
        classifierResult = classify0(vectorUnderTest,trainingMat,hwLabels,3)
        print("the classifier came back with : "+str(classifierResult)+"\nthe real answer is : "+ str(classNumStr))
        if(int(classifierResult) != int(classNumStr)):errorCount=errorCount+1

    print("\nThe total number of errors is : "+str(errorCount))
    print("\nThe total right rate is : %f"%(1-errorCount/float(mTest)))