def tests():
bayes.testingNB()
bayes.spamTest()
# -*- coding: utf-8 -*- import bayes from numpy import * #过滤垃圾邮件 bayes.spamTest()
print(flagLab)
#得到抽取特征后的文档，以及文档所属的类别
listOPosts,listClasses = bayes.loadDataSet()
#构建一个包含所有词的列表
myVocabList = bayes.createVocabList(listOPosts)
#词向量构成的列表
trainMat=[]
for postinDoc in listOPosts:
trainMat.append( bayes.setOfWords2Vec(myVocabList,postinDoc) )
#得到两个类别的概率向量，和侮辱性文档的概率
p0V,p1V,pAb = bayes.trainNB0(trainMat,listClasses)
print(pAb)
print(p0V)
print(p1V)
'''
#判断网站留言是否是恶意的
bayes.testingNB()
#过滤垃圾邮件
errRaiosum=0.0
for i in range(10):
errRaiosum += bayes.spamTest()
print('平均错误率为：' +str( errRaiosum/10))
import bayes print bayes.spamTest()
# myVocabList = bayes.createVocabList(listOPosts)
# print myVocabList
#
# print bayes.setOfWords2Vect(myVocabList, listOPosts[0])
# print bayes.setOfWords2Vect(myVocabList, listOPosts[3])
#
# trainMat = map(lambda postinDoc: bayes.setOfWords2Vect(myVocabList, postinDoc), listOPosts)
# print
# for item in trainMat:
# print item
#
# p0V, p1V, pAb = bayes.trainNB0(trainMat, listClasses)
#
# print p0V
# print p1V
# print pAb
#
# testEntry = ['love', 'my', 'dalmation']
# thisDoc = np.array(bayes.setOfWords2Vect(myVocabList, testEntry))
# # print thisDoc
# print testEntry, 'classified as:', bayes.classifyNB(thisDoc, p0V, p1V, pAb)
# testEntry = ['stupid', 'garbage']
# thisDoc = np.array(bayes.setOfWords2Vect(myVocabList, testEntry))
# # print thisDoc
# print testEntry, 'classified as:', bayes.classifyNB(thisDoc, p0V, p1V, pAb)
result = 0
N = 1.0
for i in range(int(N)):
result += bayes.spamTest()
print(result / N)
# myVocabList=bayes.createVocabList(listOPosts)
# print(myVocabList)
# # print(len(myVocabList))
# # print(bayes.setOfWords2Vec(myVocabList,listOPosts[0]))
# # print(bayes.setOfWords2Vec(myVocabList,['time']))
#
# trainMat=[]
# for postinDoc in listOPosts:
# trainMat.append(bayes.setOfWords2Vec(myVocabList,postinDoc))
#
# print(trainMat)
# p0V,p1V,pAb=bayes.trainNB0(trainMat,listClasses)
# # print(p0C,p1V,pAb)
# testEntry=['love','my','dalmation']
# thisDoc=np.array(bayes.setOfWords2Vec(myVocabList,testEntry))
# print(testEntry,'classified as:',bayes.classifyNB(thisDoc,p0V,p1V,pAb))
# testEntry=['stupid','garbage']
# thisDoc=np.array(bayes.setOfWords2Vec(myVocabList,testEntry))
# print(testEntry,'classified as:',bayes.classifyNB(thisDoc,p0V,p1V,pAb))
##----------------------------使用朴素贝叶斯过滤垃圾邮件----------------------------------------
filepath = '/Users/songhaiyue/Desktop/B01_python/Machine_Learning_in_Action/machinelearninginaction/Ch04/'
# filename=filepath+'email/ham/6.txt'
# emailText=open(filename,encoding ='unicode_escape').read()
# # print(emailText)
# listOfTokens=re.split('\s',emailText)
# print(listOfTokens)
bayes.spamTest(filepath)
import bayes
total=0.0
reload(bayes)
for i in range(1,20):
total+=bayes.spamTest()
print total/100
for docIndex in trainingSet:
trainMat.append(setOfWord2Vec(vocabList,docList[docIndex]))
trainClasses.append(classList[docIndex])
p0V,p1V,pSpam = trainNB0(array(trainMat),array(trainClasses))
errorCount = 0
#3.（以下四行）对测试集分类
for docIndex in testSet:
wordVector = sefOfWord2Vec(vocabList,docList[docIndex])
if classifyNB(array(wordVector),p0V,p1V,pSpam) != classList[docIndex]:
errorCount += 1
print('the error rate is: ',float(errorCount)/len(testSet))
#测试
print(bayes.spamTest())
print(bayes.spamTest())
import feedparser
ny = feedparser.parse('http://newyork.craiglist.org/stp/index.rss')
ny['entries']
len(ny['entries'])
#RSS源分类器及高频词去除函数
def calcMostFreq(vocabList,fullText):
import operator
freqDict = {}
for token in vocabList:
freqDict[token] = fullText.count(token)
sortedFreq = sorted(freqDict.iteritems(),key = operator.itemgetter(1),reveser)
import bayes
from numpy import *
import re
listOPosts, listClasses = bayes.loadDataSet()
# 4.5
# myVocabList = bayes.createVocabList(listOPosts)
# # print(myVocabList)
# word2vec = bayes.setOfWords2Vec(myVocabList,listOPosts[0])
# trainMat = []
# for postinDoc in listOPosts:
# trainMat.append(bayes.setOfWords2Vec(myVocabList,postinDoc))
# p0V,p1V,pAb = bayes.trainNB0(trainMat,listClasses)
# print(pAb)
# print(p0V)
# print(p1V)
# bayes.testingNB()
# 4.6
# mySent = ''
# mySent.split()
# regEx = re.compile('\\W*')
# listOfTokens = regEx.split(mySent)
error_rate = 0
for i in range(100):
error_rate += bayes.spamTest()
print("average error rate is:", float(error_rate / 100))
