第二章講的是K-鄰近演算法

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-鄰近演算法報錯 還沒有解決 好像是python2和3的版本問題，百度了一圈沒有解決方法。

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中程式碼有錯誤，報錯原因 invalid literal for int() with base 10: 'largeDoses' 詳情請見https://blog.csdn.net/michaelhan3/article/details/74017111，更正方法：重新處理txt檔案中的內容，將浮點數改為整數，

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')

資料分析：使用Matplotlib建立散點圖

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))

歸一化特徵值

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)

分類器針對約會網站的測試程式碼

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

測試演算法：使用K-鄰近演算法識別手寫數字

import os                                            #第一二句一定要寫，否則會報錯
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)))

這一章是我第一次實現程式碼，以前都是隻看書學習理論知識不實踐，書中內容上程式碼最大的錯誤是書本是Python2版本的，但是目前大家普遍使用python3版本，所以程式碼輸入輸出引號之類的需要修改。