from numpy import *
def createDataSet():group=array([[1.1,1.1],[1.0,1.0],[0,0],[0,0.1]])labels=['A','A','B','B']return group,labels

from numpy import *
import operator
def classify0(inX,dataSet,labels,k):dataSetSize=dataSet.shape[0]    #shape[0]表示dataSet的行数diffMat=tile(inX,(dataSetSize,1))-dataSetsqDiffMat=diffMat**2sqDistances=sqDiffMat.sum(axis=1)distances=sqDistances**0.5sortedDistIndicies=distances.argsort()classCount={}for i in range(k):voteIlabel=labels[sortedDistIndicies[i]]classCount[voteIlabel]=classCount.get(voteIlabel,0)+1sortedClassCount=sorted(classCount.items(),key=operator.itemgetter(1),reverse=True)return sortedClassCount[0][0]

import kNN
from classify_kNN import *
g,l=kNN.createDataSet()
result=classify0([0,0],g,l,3)
print(result)

dic={'a':1,'b':2,'c':3}
print(dic.items())
print(dic.get('c','no'))
输出：
dict_items([('b', 2), ('c', 3), ('a', 1)])
3

from numpy import *
c=array([[1,1],[2,3,],[5,6]])
print(c)
print(c.shape)
print(c.shape[0])
print(c.shape[1])
输出：
[[1 1][2 3][5 6]]
(3, 2)
3
2

import operator
students=[['刚田武',20,'gangtw'],['朱二娃',25,'zhuerw'],['咪咪two',30,'miomitwo']]
print(sorted(students,key=operator.itemgetter(1),reverse=True))
输出：
[['咪咪two', 30, 'miomitwo'], ['朱二娃', 25, 'zhuerw'], ['刚田武', 20, 'gangtw']]

from numpy import *
def autoNorm(dataset):minVals=dataset.min(0)  #取每列的最小值，返回数组print(minVals)maxVals=dataset.max(0)print(maxVals)ranges=maxVals-minVals  #ranges是每列的最大值与最小值之差组成的数组print(ranges)normDataset=zeros(shape(dataset))print(normDataset)m=dataset.shape[0]  #取dataset的行数normDataset=dataset-tile(minVals,(m,1))print(normDataset)normDataset=normDataset/tile(ranges,(m,1))print(ranges)return normDataset

from numpy import *
dataset=array(([6,5],[3,1000],[10,300]))
print(dataset.min())    #返回所有元素中的最小值
print(dataset.min(0))   #返回每列的最小值组成的数组
print(dataset.min(1))   #返回每行的最小值组成的数组
输出：
3
[3 5]
[ 5  3 10]

from numpy import *
dataset=array(([6,5],[3,1000],[10,300]))
print(dataset.shape)    #返回数据集的“形状”，行数和列数
print(dataset.shape[0])     #返回行数
print(dataset.shape[1])     #返回列数
输出：
(3, 2)
3
2

def datingClassTest():hoRatio=0.1datingDataMat,datingLabels=file2matrix('datingTestSet2.txt')normMat,ranges,minVals=autoNorm(datingDataMat)m=normMat.shape[0]numTestVecs=int(m*hoRatio)errorCount=0for i in range(numTestVecs):classifyerResult=classify0(normMat[i,:],normMat[numTestVecs:m,:],datingLabels[numTestVecs:m],3)print('classify result is %s ,the real answer is %s'%(classifyerResult,datingLabels[i]))if classifyerResult!=datingLabels[i]:errorCount+=1print('the total error rate is %f'%(errorCount/float(numTestVecs)))

def classifyPerson():resultList=['not at all','in small doses','in largr doses']timeOnGames=float(input('请输入游戏时间百分比：'))flyMiles=float(input('请输入每年飞行里程数：'))iceCream=float(input('请输入每周消耗的冰淇淋升数：'))datingDataMat,datingLabels=file2matrix('datingTestSet2.txt')normMat,ranges,minVals=autoNorm(datingDataMat)person2test=array([flyMiles,timeOnGames,iceCream])classifierResult=classify0((person2test-minVals)/ranges,normMat,datingLabels,5)print('you may like thie one:',resultList[classifierResult-1])

def handwritingClassTest():hwLabels=[]trainingFileList=listdir('digits/trainingDigits')m=len(trainingFileList)trainingMat=zeros((m,1024))for i in range(m):fileNameStr=trainingFileList[i]fileStr=fileNameStr.split('.')[0]classNumStr=int(fileStr.split('_')[0])hwLabels.append(classNumStr)trainingMat[i,:]=img2vector('digits/trainingDigits/%s'%fileNameStr)testFileList=listdir('digits/testDigits')errorCount=0mTest=len(testFileList)for i in range(mTest):fileNameStr=testFileList[i]fileStr=fileNameStr.split('.')[0]classNumStr=int(fileStr.split('_')[0])vectorUnderTest=img2vector('digits/testDigits/%s'%fileNameStr)classifierResult=classify0(vectorUnderTest,trainingMat,hwLabels,3)#print('分类结果：%s,实际结果：%s'%(classifierResult,classNumStr))if(classifierResult!=classNumStr):errorCount+=1print('分类错误总计：',errorCount)print('分类错误率：',errorCount/float(mTest))