源码部分:
from numpy import *
import operatordef createDataSet():
group=array([[1.0,1.1],[1.0,1.0],[0,0],[0,0.1]])
labels=['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
sortedDisIndicies=distances.argsort()
classCount={}
for i in range(k):
voteIlabel=labels[sortedDisIndicies[i]]
classCount[voteIlabel]=classCount.get(voteIlabel,0)+1
sortedClassCount=sorted(classCount.items(),key=operator.itemgetter(1),reverse=True)
return sortedClassCount[0][0]
def file2matrix(filename):
fr=open(filename)
arrayOLines=fr.readlines()
numberOfLines=len(arrayOLines)
returnMat=zeros((numberOfLines,3))
classLabelVector=[]
index=0
for line in arrayOLines:
line=line.strip()
listFromLine=line.split('\t')
returnMat[index,:]=listFromLine[0:3]
classLabelVector.append(int(listFromLine[-1]))
index +=1
return returnMat,classLabelVector
def autoNorm(dataSet):
minvals=dataSet.min(0)