‘‘‘
Created?on?Sep?16?2010
kNN:?k?Nearest?Neighbors

Input:??????inX:?vector?to?compare?to?existing?dataset?（1xN）
????????????dataSet:?size?m?data?set?of?known?vectors?（NxM）
????????????labels:?data?set?labels?（1xM?vector）
????????????k:?number?of?neighbors?to?use?for?comparison?（should?be?an?odd?number）
????????????
Output:?????the?most?popular?class?label

@author:?pbharrin
‘‘‘
from?numpy?import?*
import?operator
from?os?import?listdir


def?classify0（inX?dataSet?labels?k）:
????dataSetSize?=?dataSet.shape[0]
????diffMat?=?tile（inX?（dataSetSize1））?-?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（voteIlabel0）?+?1
????sortedClassCount?=?sorted（classCount.iteritems（）?key=operator.itemgetter（1）?reverse=True）
????return?sortedClassCount[0][0]

def?createDataSet（）:
????group?=?array（[[1.01.1][1.01.0][00][00.1]]）
????labels?=?[‘A‘‘A‘‘B‘‘B‘]
????return?group?labels

def?file2matrix（filename）:
????love_dictionary={‘largeDoses‘:3?‘smallDoses‘:2?‘didntLike‘:1}
????fr?=?open（filename）
????arrayOLines?=?fr.readlines（）
????numberOfLines?=?len（arrayOLines）????????????#get?the?number?of?lines?in?the?file
????returnMat?=?zeros（（numberOfLines3））????????#prepare?matrix?to?return
????classLabelVector?=?[]???????????????????????#prepare?labels?return???
????index?=?0
????for?line?in?arrayOLines:
????????line?=?line.strip（）
????????listFromLine?=?line.split（‘\t‘）
????????returnMat[index:]?=?listFromLine[0:3]
????????if（listFromLine[-1].isdigit（））:
????????????classLabelVector.append（int（listFromLine[-1]））
????????else:
????????????classLabelVector.append（love_dictionary.get（listFromLine[-1]））
????????index?+=?1
????return?returnMatclassLabelVector

????
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?（m1））
????normDataSet?=?normDataSet/tile（ranges?（m1））???#element?wise?divide
????return?normDataSet?ranges?minVals
???
def?datingClassTest（）:
????hoRatio?=?0.50??????#hold?out?10%
????datingDataMatdatingLabels?=?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?

?屬性????????????大小?????日期????時(shí)間???名稱
-----------?---------??----------?-----??----
?????目錄???????????0??2017-12-11?16:35??Ch02\
?????文件??????300040??2017-12-11?15:34??Ch02\testY
?????文件????30110934??2017-12-11?15:34??Ch02\testX
?????文件??????613237??2017-12-11?15:34??Ch02\trainY
?????文件????61541556??2017-12-11?15:34??Ch02\trainX
?????文件????????5353??2017-11-26?11:10??Ch02\kNN.pyc
?????文件????????5350??2017-11-26?09:46??Ch02\kNN.py
?????文件??????739988??2017-09-18?14:58??Ch02\digits.zip
?????文件???????27067??2017-09-18?14:58??Ch02\datingTestSet2.txt
?????文件???????35725??2017-09-18?14:58??Ch02\datingTestSet.txt
?????文件?????????242??2017-09-18?14:58??Ch02\README.txt
?????文件????????3937??2017-12-11?16:35??Ch02\tensorForDigits.py
?????目錄???????????0??2011-05-04?08:38??Ch02\trainingDigits\
?????文件????????1088??2010-10-06?11:32??Ch02\trainingDigits\1_139.txt
?????文件????????1088??2010-10-06?11:32??Ch02\trainingDigits\1_136.txt
?????文件????????1088??2010-10-06?11:32??Ch02\trainingDigits\1_135.txt
?????文件????????1088??2010-10-06?11:32??Ch02\trainingDigits\1_133.txt
?????文件????????1088??2010-10-06?11:32??Ch02\trainingDigits\1_132.txt
?????文件????????1088??2010-10-06?11:32??Ch02\trainingDigits\1_129.txt
?????文件????????1088??2010-10-06?11:32??Ch02\trainingDigits\1_128.txt
?????文件????????1088??2010-10-06?11:32??Ch02\trainingDigits\1_127.txt
?????文件????????1088??2010-10-06?11:32??Ch02\trainingDigits\1_126.txt
?????文件????????1088??2010-10-06?11:32??Ch02\trainingDigits\1_124.txt
?????文件????????1088??2010-10-06?11:32??Ch02\trainingDigits\1_122.txt
?????文件????????1088??2010-10-06?11:32??Ch02\trainingDigits\1_120.txt
?????文件????????1088??2010-10-06?11:32??Ch02\trainingDigits\1_12.txt
?????文件????????1088??2010-10-06?11:32??Ch02\trainingDigits\1_118.txt
?????文件????????1088??2010-10-06?11:32??Ch02\trainingDigits\1_116.txt
?????文件????????1088??2010-10-06?11:32??Ch02\trainingDigits\1_114.txt
?????文件????????1088??2010-10-06?11:32??Ch02\trainingDigits\1_111.txt
?????文件????????1088??2010-10-06?11:32??Ch02\trainingDigits\1_108.txt
............此處省略2875個(gè)文件信息