k近邻算法之约会网站匹配和手写识别

机器学习 jinwei 711℃ 0评论
#kNN.py
# coding: utf-8
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]])
    lables = ['A','A','B','B']
    return group,labels
def classify0(inX,dataSet,labels,k):
    dataSetSize = dataSet.shape[0]
    diffMat=tile(inX,(dataSetSize,1))-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.items(),key = operator.itemgetter(1),reverse = True)
    return sortedClassCount[0][0]
#将文本记录转化为Numpy的解析程序 
def file2matrix(filename):
    fr = open(filename)
    array0Lines = fr.readlines()
    number0fLines = len(array0Lines)
    returnMat = zeros((number0fLines,3))
    classLabelVector = []
    index = 0
    for line in array0Lines:
        line = line.strip()
        listFromLine = line.split('\t')
        returnMat[index,:] = listFromLine[0:3]
        classLabelVector.append(int(listFromLine[-1]))
        index += 1
    return returnMat,classLabelVector
#归一化特征值
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
#分类器针对约会网站的测试代码
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 answer is: %d"\
             %(classifierResult,datingLabels[i]))
        if (classifierResult != datingLabels[i]): errorCount += 1.0
    print("the total error rate is: %f" % (errorCount/float(numTestVecs)))
#约会网站预测函数
def classifyPerson():
    resultList = ['not at all','in small doses','in large doses']
    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 years?"))
    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])
#图像转化为测试向量		  
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
#knn手写数字识别测试
def handwritingClassTest():
    hwLabels = []
    trainingFileList = listdir('trainingDigits')
    m = len(trainingFileList)
    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])
        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)))

转载请注明:沐雨语曦 » k近邻算法之约会网站匹配和手写识别

喜欢 (0)
发表我的评论
取消评论

表情

Hi,您需要填写昵称和邮箱!

  • 昵称 (必填)
  • 邮箱 (必填)
  • 网址