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]
# 函数shape 作为:查看矩阵或者数组的维数
diffMat=tile(inX,(dataSetSize,1))-dataSet
#函数原型:numpy.tile(A,reps) 作为:将A重复进行输出
# tile(A,[x,y])为二维输出
# tile(A,x)为一维输出等价于tile(A,【1,x】)
sqDiffMat=diffMat**2
#**为次方运算
sqDistances=sqDiffMat.sum(axis=1)
#默认sum(axis=0)简单相加运算
#sum(axis=1)将矩阵的每一行向量相加
distances=sqDistances**0.5
sortedDistIndicies=distances.argsort()
#argsort()函数是将x中的元素从小到大排列,提取其对应的index(索引),然后输出到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()
#去除换行符
listFromLine=line.split('\t')
#利用tab字符进行切分
returnMat[index,:]=listFromLine[0:3]
#将0、1、2加入returnMat矩阵中
classLabelVector.append(int(listFromLine[-1]))
#将每一行最后一个int值加入到classLabelVector中
index += 1
return returnMat,classLabelVector
#归一化数值计算
#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
#样本集和测试集比例
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)
浅述python中argsort()函数的用法
python中的sum函数.sum(axis=1)
python 科学计算库NumPy—tile函数
python *和**
python: numpy--函数 shape用法
Python中的sorted函数以及operator.itemgetter函数
Numpy数组操作