《机器学习实战》第二章 Python3代码-（亲自修改测试可成功运行）

由于Peter Harrington所著的这本《机器学习实战》中的官方代码是Python2版本的且有一些勘误，使用Python3的朋友运行起来会有很多问题，所以我将自己在学习过程中修改好的Python3版本代码分享给大家，以供大家交流学习，共同进步！

官方源码文件下载地址：https://manning-content.s3.amazonaws.com/download/3/29c6e49-7df6-4909-ad1d-18640b3c8aa9/MLiA_SourceCode.zip

第二章-KNN

文件名：knn.py

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

#分类器
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]

#解析数据文件
def file2matrix(filename):
    fr = open(filename)
    numberOfLines = len(fr.readlines())         #get the number of lines in the file
    returnMat = zeros((numberOfLines,3))        #prepare matrix to return
    classLabelVector = []                       #prepare labels return   
    fr = open(filename)
    index = 0
    for line in fr.readlines():
        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))   #element wise divide
    return normDataSet, ranges, minVals

#约会网站数据测试代码
def datingClassTest():
    hoRatio = 0.50      #hold out 10%
    datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')       #load data setfrom file
    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 num is: %f" % errorCount)
    print ("the total num is: %f" % float(numTestVecs))
    print ("the total error rate is: %f" % (errorCount/float(numTestVecs)))

#约会网站预测函数
def classifyPerson():
    resultList = ['讨厌','一般喜欢','非常喜欢']
    percentTats = float(input("玩游戏所耗时间百分比?"))
    ffMiles = float(input("每年获得的飞行常客里程数?"))
    iceCream = float(input("每年消费的冰淇淋公升数?"))
    datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')
    normMat,ranges,minVals = autoNorm(datingDataMat)
    inArr = array([ffMiles,percentTats,iceCream])
    classifierResult = classify0((inArr-minVals)/ranges,normMat,datingLabels,3)
    print("你可能的喜爱程度:",resultList[classifierResult - 1])

#图像格式化为一个向量
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

#手写数字识别测试
def handwritingClassTest():
    hwLabels = []
    trainingFileList = listdir('trainingDigits')           #load the training set
    m = len(trainingFileList)
    trainingMat = zeros((m,1024))
    for i in range(m):
        fileNameStr = trainingFileList[i]
        fileStr = fileNameStr.split('.')[0]     #take off .txt
        classNumStr = int(fileStr.split('_')[0])
        hwLabels.append(classNumStr)
        trainingMat[i,:] = img2vector('trainingDigits/%s' % fileNameStr)
    testFileList = listdir('testDigits')        #iterate through the test set
    errorCount = 0.0
    mTest = len(testFileList)
    for i in range(mTest):
        fileNameStr = testFileList[i]
        fileStr = fileNameStr.split('.')[0]     #take off .txt
        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)))
        

PS:Python3使用中reload()函数需要先：

from importlib import reload

相关阅读推荐：

https://blog.csdn.net/y12345678904/article/details/5567089

https://lavi-liu.blog.csdn.net/article/details/78182412

https://blog.csdn.net/qq_41717584/article/details/83241243

https://blog.csdn.net/mlp750303040/article/details/79287177

https://blog.csdn.net/qq_41204464/article/details/88980654

https://blog.csdn.net/LaoYuanPython/article/details/100045507