【読書ノート】機械学習実戦p 19-2.1.2(k-近隣アルゴリズム)
3250 ワード
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
def classify0(inX,dataSet,labels,k):
dataSetSize=dataSet.shape[0]
# shape :
diffMat=tile(inX,(dataSetSize,1))-dataSet
# :numpy.tile(A,reps) : A
# tile(A,[x,y])
# tile(A,x) tile(A,【1,x】)
sqDiffMat=diffMat**2
#**
sqDistances=sqDiffMat.sum(axis=1)
# sum(axis=0)
#sum(axis=1)
distances=sqDistances**0.5
sortedDistIndicies=distances.argsort()
#argsort() x , index( ), y
classCount={}
for i in range(k):
voteIlabel=labels[sortedDistIndicies[i]]
classCount[voteIlabel]=classCount.get(voteIlabel,0)+1
sortedClassCount=sorted(classCount.iteritems(),key=operator.itemgetter(1),reverse=True)
return sortedClassCount[0][0]
def file2matrix(filename):
fr=open(filename)
numberOfLines=len(fr.readlines())
#readlines([sizehit[,keepends]])
#Read all lines available on the input stream and return them as a list of lines
returnMat=zeros((numberOfLines,3))
#create a matrix with zero
classLabelVector=[]
fr=open(filename)
index=0
for line in fr.readlines():
line=line.strip()
#
listFromLine=line.split('\t')
# tab
returnMat[index,:]=listFromLine[0:3]
# 0、1、2 returnMat
classLabelVector.append(int(listFromLine[-1]))
# int classLabelVector
index += 1
return returnMat,classLabelVector
#
#newValue=(oldValue-min)/(max-min)
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))
return normDataSet,ranges,minVals
def datingClassTest():
hoRatio=0.50
#
datingDataMat,datingLabels=file2matrix('datingTestSet2.txt')
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 rate is :%f" %(errorCount/float(numTestVecs)))
print(errorCount)
python argsort()
python sum .sum(axis=1)
python NumPy—tile
python * **
python: numpy-- shape
Python sorted operator.itemgetter
Numpy