分类

# -*- coding: utf-8 -*- """ Spyder Editor This is a temporary script file. """ from numpy import * #测试数据集 def creatdataset(): group=array([[1.0,1.1],[1.0,1.0],[0,0],[0,0.1]]) labels=['A','A','B','B'] return group,labels #K邻近算法 def classify0(inx,dataset,labels,k): datasetsize=dataset.shape[0]#求列数 diffmat=tile(inx,(datasetsize,1))-dataset#求测试数据与训练数据的差 sqdiffmat=diffmat**2#平方 sqdistance=sqdiffmat.sum(axis=1)#求和 distance=sqdistance**0.5#开方，这几步是计算欧氏距离 suoyinpm=distance.argsort()#对距离进行排序 biaoqiandict={}#新建一个字典用来存储标签 for i in range(k):#选取最近的K个数据 biaoqianweizhi=labels[suoyinpm[i]]#根据距离排序的索引得到相应位置的标签 biaoqiandict.setdefault(biaoqianweizhi,0)#如果不存在标签，默认0 biaoqiandict[biaoqianweizhi]+=1#存在就加1 zuidabiaoqian=sorted(biaoqiandict.items(),key=lambda x:x[1],reverse=True) #对字典进行反向排序 return zuidabiaoqian[0][0]#得到最近的标签 #读取文件，整理原始数据格式 def file2matrix(filename): fr=open(filename) arrayline=fr.readlines() n=len(arrayline) returnmat=zeros((n,3)) classlabel=[] index=0 for line in arrayline: line=line.strip() listline=line.split('\t') returnmat[index,:]=listline[0:3] classlabel.append(int(listline[-1])) index+=1 return returnmat,classlabel filename='D:/DATA/python/机器学习/machinelearninginaction/Ch02/datingTestSet2.txt' #dataset,label=file2matrix(filename) #最大最小数据规范化 def autonorm(dateset): datamin=dataset.min(0) datamax=dataset.max(0) data_max_min=datamax-datamin normmat=zeros((dataset.shape)) m=dataset.shape[0] normmat=dataset-tile(datamin,(m,1)) normmat=normmat/tile(data_max_min,(m,1)) return normmat,datamax,datamin #读取测试数据，运行K邻近算法，计算错误率 def datingclasstext(): dataset,label=file2matrix(filename) datanorm=autonorm(dataset) m=datanorm.shape[0] test=0.1 error=0.0 test_index=int(m*0.1) for i in range(test_index): test_label=classify0(datanorm[i,:],datanorm[test_index:,:],label[test_index:],3) print('测试标签: %d,预测标签: %d' % (label[i],test_label)) if label[i]!=test_label: error+=1 print ('错误率:%f'%(error/test_index)) #根据输入数据，运行K邻近算法，得到标签 def classifyperson(): resultlist=['一般','有一点魅力','很有魅力'] youxi=float(input('你的游戏时间')) feixing=float(input('你的飞行时间')) bingqilin=float(input('你的冰淇淋时间')) dataset,label=file2matrix(filename) datanorm,datamax,datamin=autonorm(dataset) innar=array([feixing,youxi,bingqilin]) classlabel=classify0((innar-datamin)/(datamax-datamin),datanorm,label,3) print ('你会喜欢这个人:%s'%resultlist[classlabel-1]) #读取原始数据，得到标签 def img2vector(filename): fr=open(filename) datamat=zeros((1,1024)) for i in range(32): line=fr.readline() for j in range(32): datamat[0,32*i+j]=int(line[j]) return datamat #手写数字识别系统 def handwritingclasstest(): hwlabel=[] trainmulu=listdir('D:/DATA/python/机器学习/machinelearninginaction/Ch02/digits/trainingDigits') m=len(trainmulu) train_data=zeros((m,1024)) for i in range(m): filenametxt=trainmulu[i] filenametxt=filenametxt.split('.')[0] filestr=filenametxt.split('_')[0] train_data[i,:]=img2vector('D:/DATA/python/机器学习/machinelearninginaction/Ch02/digits/trainingDigits/%s'%trainmulu[i]) hwlabel.append(filestr) testmulu=listdir('D:/DATA/python/机器学习/machinelearninginaction/Ch02/digits/testDigits') n=len(testmulu) error=0.0 for i in range(n): filenametxt1=testmulu[i] filenametxt1=filenametxt1.split('.')[0] filestr1=filenametxt1.split('_')[0] test_data=img2vector('D:/DATA/python/机器学习/machinelearninginaction/Ch02/digits/trainingDigits/%s'%testmulu[i]) classbiaoqian=classify0(test_data,train_data,hwlabel,3) print('预测标签:%s,实际标签:%s'%(classbiaoqian,filestr1)) if classbiaoqian!=filestr1:error+=1 print ('错误率:%f'%(error/n)) #错误率:0.015856

https://promotion.aliyun.com/ntms/act/enterprise-discount.html?userCode=1qylypgj

【助力企业上云】性能级主机2-5折

阿里云活动，服务器便宜卖哦，通过此链接注册购买，可联系作者协助部署搭建服务器环境。QQ（814341142）