机器学习实战第二章记录

第二章讲的是K-邻近算法

from numpy import*
import operator


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

group,labels = createDataSet()

K-邻近算法报错 还没有解决 好像是python2和3的版本问题，百度了一圈没有解决方法。

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]

2.2中代码有错误，报错原因 invalid literal for int() with base 10: 'largeDoses' 详情请见https://blog.****.net/michaelhan3/article/details/74017111，更正方法：重新处理txt文件中的内容，将浮点数改为整数，

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

datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')

数据分析：使用Matplotlib创建散点图

import matplotlib

import matplotlib.pyplot as plt
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(datingDataMat[:,1],datingDataMat[:,2])

plt.show()

ax.scatter(datingDataMat[:,1],datingDataMat[:,2],15.0 * array(datingLabels),15.0 * array(datingLabels))

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

normMat,ranges,minVals = autoNorm(datingDataMat)

分类器针对约会网站的测试代码

def datingClassTest():
    hoRatio = 0.10      #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 "%d, %d" % (classifierResult, datingLabels[i])
        if (classifierResult != datingLabels[i]): errorCount += 1.0
    print "the total error rate is: %f" % (errorCount/float(numTestVecs))
    print errorCount

测试算法：使用K-邻近算法识别手写数字

import os                                            #第一二句一定要写，否则会报错
from os import listdir
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 ("\n the total number of errors is: %d" % errorCount)

    print ("\n the total error rate is: %f" % (errorCount/float(mTest)))

这一章是我第一次实现代码，以前都是只看书学习理论知识不实践，书中内容上代码最大的错误是书本是Python2版本的，但是目前大家普遍使用python3版本，所以代码输入输出引号之类的需要修改。