kNN算法

Posted 2020-07-15 大雄

import numpy as np
import operator
import os
def createDataset():
        group=np.array([[1.0,1.1],[1.0,1.0],[0,0],[0,0.1]])
        lables=[‘A‘,‘A‘,‘B‘,‘B‘]
        return  group,lables

def classify0(inX,dataSet,labels,k):
        dataSetSize=dataSet.shape[0]
        diffMat=np.tile(inX,(dataSetSize,1))-dataSet
        sqDiffMat=diffMat**2
        sqDistances=sqDiffMat.sum(axis=1)
        distances=sqDistances**0.5
        sortDistancesIndex=distances.argsort()
        classCount={}#TODO  toOrder dectionary
        for i in range(k):
                voteIlabel=labels[sortDistancesIndex[i]]
                classCount[voteIlabel]=classCount.get(voteIlabel,0)+1
        sortedClassCount=sorted(classCount.items(),key=operator.itemgetter(1),reverse=True)
        return sortedClassCount[0][0]
def filematrix(filename):
        fr=open(filename)
        arrayOfLines=fr.readlines()
        numberOfLines=len(arrayOfLines)
        returnMat=np.zeros((numberOfLines,3))
        classLableVector=[]
        index=0
        for line in arrayOfLines:
            line=line.strip()
            listFromLine=line.split(‘\t‘)
            returnMat[index,:]=listFromLine[0:3]
            classLableVector.append(int(listFromLine[-1]))
            index+=1
        return returnMat,classLableVector

def autoNorm(dataSet):
        minVals=dataSet.min(0)
        maxVals=dataSet.max(0)
        rangs=maxVals-minVals
        dtRow=dataSet.shape[0]
        normDataset=dataSet-np.tile(minVals,(dtRow,1))
        resultDataset=normDataset/np.tile(rangs,(dtRow,1))
        return resultDataset,rangs,minVals
def datingClassTest():
        hoRatio=0.10
        errorCount=0.0
        datingMat,datingLabels=filematrix(‘dts.txt‘);
        normMat,normRang,normMin=autoNorm(datingMat)
        dataRows=normMat.shape[0]
        testDataRows=int(dataRows*hoRatio)
        for i in range(testDataRows):
                classfileterResult=classfy0(normMat[i,:],normMat[testDataRows:dataRows,:],datingLabels[testDataRows:dataRows],3)
                print("这次分类结果是： %d,这个真实的结果为：%d"%(classfileterResult,datingLabels[i]))
                if(classfileterResult!= datingLabels[i]):errorCount+=1.0
                print("这次分类的总错误率为：%f"%(errorCount/float(testDataRows)))


def classifyPerson():
    resultList = [‘没有魅力‘, ‘魅力一般‘, ‘很有魅力‘]
    percentTats = float(input("每天所玩电子游戏的占比?"))
    ffMiles = float(input("每年的飞行里程数?"))
    iceCream = float(input("每周吃多少冰淇淋（升）?"))
    datingDataMat, datingLabels = filematrix(‘dts.txt‘)
    normMat, ranges, minVals = autoNorm(datingDataMat)
    inArr = np.array([ffMiles, percentTats, iceCream])
    classifierResult = classify0((inArr - minVals)/ranges, normMat, datingLabels,3)
    print (‘这个人让人感觉: ‘, resultList[classifierResult - 1])
    
# 2：手写识别系统
#将一个32*32的二进制图像矩阵转换成1*1024的向量

def img2vector(filename):
    returnVect = np.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


#手写识别系统测试代码
def handwritingClassTest():
    hwLabels = []
    trainingFileList = os.listdir(‘trainingDigits‘)   #获取目录内容
    m = len(trainingFileList)
    trainingMat = np.zeros((m, 1024))
    for i in range(m):
        fileNameStr = trainingFileList[i]              #分割得到标签  从文件名解析得到分类数据
        fileStr = fileNameStr.split(‘.‘)[0]
        classStr = int(fileStr.split(‘_‘)[0])
        hwLabels.append(classStr)                 #测试样例标签
        trainingMat[i,:] = img2vector(‘trainingDigits/%s‘ % fileNameStr)
    testFileList = os.listdir(‘testDigits‘)
    errorCount = 0.0
    mTest = len(testFileList)
    for i in range(mTest):
        fileNameStr = testFileList[i]
        fileStr = fileNameStr.split(‘.‘)[0]
        classStr = int(fileStr.split(‘_‘)[0])
        vectorUnderTest = img2vector(‘testDigits/%s‘ % fileNameStr)
        classifierResult = classify0(vectorUnderTest, trainingMat, hwLabels, 3)
        print (‘the classifier came back with: %d, the real answer is: %d‘ % (classifierResult, classStr))
        if(classifierResult != classStr): errorCount += 1.0
    print ("\nthe total numbers of errors is : %d" % errorCount)
    print ("\nthe total error rate is: %f" % (errorCount/float(mTest)))