def process_training_xml(weibo_emotion, weibo_content, weibo_content_emotion):
bow = []
map(
lambda weibo: map(
lambda sentence: map(lambda each: bow.append(each), sentence),
weibo), weibo_content)
bow = list(set(bow))
# word to vec
train_mat, train_cat = convert_to_mat_and_cat(bow, weibo_content,
weibo_content_emotion)
# first_level_mat , first_level_cat : 有无感情色彩(1,-1有，0无)
first_level_mat = train_mat
first_level_cat = map(lambda each: _turn_to_same(each, -1, 1), train_cat)
l1_p0_vect, l1_p1_vect, p_emotion = bayes.trainNB0(first_level_mat,
first_level_cat)
# second_level_mat , second_level_cat : 感情色彩积极消极(1积极-1消极，归为1积极，0消极)
train_combile = zip(train_mat, train_cat)
second_level_tmp = filter(lambda each: each[1] != 0, train_combile)
second_level_mat = map(lambda each: each[0], second_level_tmp)
second_level_cat = map(lambda each: each[1], second_level_tmp)
second_level_cat = map(lambda each: _turn_to_same(each, -1, 0),
second_level_cat)
l2_p0_vect, l2_p1_vect, p_positive = bayes.trainNB0(
second_level_mat, second_level_cat)
return bow, l1_p0_vect, l1_p1_vect, p_emotion, l2_p0_vect, l2_p1_vect, p_positive
def main():
postingList, classVec = bayes.loadDataSet()
vlist = bayes.create_vacabulary_list(postingList)
tranmat = []
for row in postingList:
tranmat.append(bayes.setOfWords2Vec(vlist, row))
print bayes.trainNB0(tranmat, classVec)
def spamTest():
docList = []
classList = []
fullText = []
for i in range(1, 26):
# 导入并解析文本
wordList = textParse(open('email/spam/%d.txt' % i).read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(1)
wordList = textParse(open('email/ham/%d.txt' % i).read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(0)
vocabList = bayes.createVocabList(docList)
trainingSet = range(50)
testSet = []
# 随机构建训练集
for i in range(10):
randIndex = int(random.uniform(0, len(trainingSet)))
testSet.append(trainingSet[randIndex])
del (trainingSet[randIndex])
trainMat = []
trainClasses = []
for docIndex in trainingSet:
trainMat.append(bayes.setOfWords2Vec(vocabList, docList[docIndex]))
trainClasses.append(classList[docIndex])
p0V, p1V, pSpam = bayes.trainNB0(array(trainMat), array(trainClasses))
errorCount = 0
# 对测试集分类
for docIndex in testSet:
wordVector = bayes.setOfWords2Vec(vocabList, docList[docIndex])
if bayes.classifyNB(array(wordVector), p0V, p1V, pSpam) != classList[docIndex]:
errorCount += 1
print 'the error rate is:', float(errorCount) / len(testSet)
def spamTest():
docList = []
classList = []
fullText = []
for i in range(1, 26):
wordList = textParse(open('xxx/%d.txt' % i).read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(1)
wordList = textParse(open('xxx/%d,txt' % i).read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(0)
vocabList = bayes.createVocabList(docList)
trainingSet = range(50)
testSet = []
for i in range(10):
randIndex = int(random.uniform(0, len(trainingSet)))
testSet.append(trainingSet[randIndex])
del(trainingSet[randIndex])
trainMat = []
trainClasses = []
for docIndex in trainingSet:
trainMat.append(bayes.setOfWords2Vec(vocabList, docList[docIndex]))
trainClasses.append(classList[docIndex])
p0V, p1V, pSpam = bayes.trainNB0(array(trainMat), array(trainClasses))
errorCount = 0
for docIndex in testSet:
wordVector = bayes.setOfWord2Vec(vocabList, docList[docIndex])
if bayes.classifyNB(array(wordVector), p0V, p1V, pSpam) != classList[docIndex]:
errorCount += 1
print 'the error rate is: ', float(errorCount) / len(testSet)
def spamTest():
docList = []
classList =[]
fullText = []
for i in range(1, 26):
wordList = bayes.textParse(open('email/spam/%d.txt' % i).read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(1)
wordList = bayes.textParse(open('email/ham/%d.txt' % i,errors='ignore').read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(0)
vocabList = bayes.createVocabList(docList)
dataSet = list(range(50))
testSet = []
for i in range(10):
randIndex = int(np.random.uniform(0, len(dataSet)))
testSet.append(dataSet[randIndex])
del(dataSet[randIndex])
trainMat = []
trainClasses = []
for doc in dataSet:
trainMat.append(bayes.bagOfWord2Vec(vocabList, docList[doc]))
trainClasses.append(classList[doc])
pAbusive, p1Vect, p0Vect = bayes.trainNB0(trainMat, trainClasses)
errorCount = 0.0
for i in testSet:
vec2Classify = bayes.bagOfWord2Vec(vocabList, docList[i])
if bayes.classifyNB(vec2Classify, p1Vect, p0Vect, pAbusive) != classList[i]:
errorCount += 1
return errorCount/10
def spamTest():
docList = []
classList = []
fullText = []
for i in range(1, 26):
wordList = textParse(open('./email/spam/%d.txt' % i).read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(1)
wordList = textParse(open('./email/ham/%d.txt' % i).read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(0)
vocalList = bayes.createVocabList(docList)
trainingSet = range(50)
testSet = []
for i in range(10):
randIndex = int(random.uniform(0, len(trainingSet)))
testSet.append(trainingSet[randIndex])
del (trainingSet[randIndex])
trainMat = []
trainClass = []
for docIndex in trainingSet:
trainMat.append(bayes.addWordInList(vocalList, docList[docIndex]))
trainClass.append(classList[docIndex])
p0V, p1V, ps = bayes.trainNB0(array(trainMat), array(trainClass))
errorCount = 0
for doc in testSet:
wordV = bayes.addWordInList(vocalList, docList[doc])
if bayes.classifyNB(array(wordV), p0V, p1V, ps) != classList[doc]:
errorCount += 1
print 'err count is %d' % errorCount
def spamTest():
docList = []; classList=[]; fullText=[]
for i in range(1, 26):
wordList = textParse(open('./email/spam/%d.txt' % i).read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(1)
wordList = textParse(open('./email/ham/%d.txt' % i).read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(0)
vocalList = bayes.createVocabList(docList)
trainingSet = range(50); testSet=[]
for i in range(10):
randIndex = int(random.uniform(0, len(trainingSet)))
testSet.append(trainingSet[randIndex])
del(trainingSet[randIndex])
trainMat=[];trainClass=[];
for docIndex in trainingSet:
trainMat.append(bayes.addWordInList(vocalList, docList[docIndex]))
trainClass.append(classList[docIndex])
p0V,p1V,ps = bayes.trainNB0(array(trainMat), array(trainClass))
errorCount = 0
for doc in testSet:
wordV = bayes.addWordInList(vocalList, docList[doc])
if bayes.classifyNB(array(wordV), p0V, p1V, ps) != classList[doc]:
errorCount+=1
print 'err count is %d' % errorCount
def test_train():
listOposts,listClasses=bayes.loadDataSet()
myVocabList=bayes.createVocabList(listOposts)
trainMat=[]
for postinDoc in listOposts:
trainMat.append(bayes.setOfWords2Vec(myVocabList,postinDoc))
p0v,p1v,pab=bayes.trainNB0(trainMat,listClasses)
print p1v
def test_train_nb(self):
data_set, listClasses = bayes.loadDataSet()
vocab_list = bayes.createVocabList(data_set)
print("\n vocab_list == %s" % (vocab_list))
trainMat = []
for postinDoc in data_set:
trainMat.append(bayes.setOfWords2Vec(vocab_list, postinDoc))
p0Vect, p1Vect, pAbusive = bayes.trainNB0(trainMat, listClasses)
print("\n p0Vect == %s\n p1Vect == %s\n pAbusive == %s\n" %
(p0Vect, p1Vect, pAbusive))
def localWords(feed1, feed0):
import feedparser
docList = []
classList = []
fullText = []
minLen = min(len(feed1['entries']), len(feed0['entries']))
# print('minlen=%d'%minLen)
for i in range(minLen):
# visit one rss source every time
wordList = bayes.textParse(feed1['entries'][i]['summary'])
docList.append(wordList)
fullText.extend(wordList)
classList.append(1)
# visit rss 0
wordList = bayes.textParse(feed0['entries'][i]['summary'])
docList.append(wordList)
fullText.extend(wordList)
classList.append(0)
# remove most frequent words
vocabList = bayes.createVocabList(docList)
top30words = calcMostFreq(vocabList, fullText)
for pairW in top30words:
if pairW[0] in vocabList:
vocabList.remove(pairW[0])
trainingSet = list(range(2 * minLen))
testSet = []
for i in range(20):
randIdx = int(random.uniform(0, len(trainingSet)))
testSet.append(trainingSet[randIdx])
del (trainingSet[randIdx])
trainMat = []
trainClasses = []
for docIdx in trainingSet:
# print("doc idx:%d, len=%d" %( docIdx, len(docList)))
trainMat.append(bayes.bagOfWords2VecMN(vocabList, docList[docIdx]))
trainClasses.append(classList[docIdx])
p0V, p1V, pSpam = bayes.trainNB0(numpy.array(trainMat),
numpy.array(trainClasses))
errorCount = 0
for docIdx in testSet:
wordVector = bayes.bagOfWords2VecMN(vocabList, docList[docIdx])
if bayes.classifyNB(numpy.array(wordVector), p0V, p1V,
pSpam) != classList[docIdx]:
errorCount += 1
print('the error rate is: %.2f' % (float(errorCount) / len(testSet)))
return vocabList, p0V, p1V
def testingNB():
listOPosts,listClasses = bayes.loadDataSet()
myVocabList = bayes.createVocabList(listOPosts)
trainMat=[]
for postinDoc in listOPosts:
trainMat.append(bayes.setOfWords2Vec(myVocabList, postinDoc))
p0V,p1V,pAb = bayes.trainNB0(array(trainMat),array(listClasses))
testEntry = ['love', 'my', 'dalmation']
thisDoc = array(bayes.setOfWords2Vec(myVocabList, testEntry))
print testEntry,'classified as: ',bayes.classifyNB(thisDoc,p0V,p1V,pAb)
testEntry = ['stupid', 'garbage']
thisDoc = array(bayes.setOfWords2Vec(myVocabList, testEntry))
print testEntry,'classified as: ',bayes.classifyNB(thisDoc,p0V,p1V,pAb)
def testSimpTrain():
listOPosts, listClasses = bayes.loadDataSet()
myVocabList = bayes.createVocabList(listOPosts)
trainMat = []
for postinDoc in listOPosts:
trainMat.append(bayes.setOfWords2Vec(myVocabList, postinDoc))
print "trainMat:", trainMat
print "listClasses:", listClasses
p0V,p1V,pAb = bayes.trainNB0(trainMat, listClasses)
print "pAb:",pAb
print "p0V:",p0V
print "p1V:",p1V
def testingNB():
listOPosts, listClasses = bayes.loadDataSet()
myVocabList = bayes.createVocabList(listOPosts)
trainMat = []
for postinDoc in listOPosts:
trainMat.append(bayes.setOfWords2Vec(myVocabList, postinDoc))
p0V,p1V,pAb = bayes.trainNB0(trainMat, listClasses)
testEntry = ['love', 'my', 'dalmation', 'stupid']
thisDoc = array(bayes.setOfWords2Vec(myVocabList, testEntry))
print testEntry,'classified as: ', bayes.classifyNB(thisDoc, p0V, p1V, pAb)
testEntry = ['quit', 'stupid']
thisDoc = array(bayes.setOfWords2Vec(myVocabList, testEntry))
print testEntry,'classified as: ', bayes.classifyNB(thisDoc, p0V, p1V, pAb)
def localWords(feed1, feed0):
docList = []
classList = []
fullText = []
minLen = min(len(feed1['entries']), len(feed0['entries']))
for i in range(minLen):
wordList = st.textParse(feed1['entries'][i]['summary'])
docList.append(wordList)
fullText.extend(wordList)
classList.append(1)
wordList = st.textParse(feed0['entries'][i]['summary'])
docList.append(wordList)
fullText.extend(wordList)
classList.append(0)
vocabList = bayes.createVocabList(docList)
#remove top frequent words
top30Words = calcMostFreq(vocabList, fullText)
for pairW in top30Words:
if pairW[0] in vocabList: vocabList.remove(pairW[0])
#build training and testing set
trainingSet = range(2*minLen)
testSet = []
for i in range(20):
randIndex = int(random.uniform(0, len(trainingSet)))
testSet.append(trainingSet[randIndex])
del(trainingSet[randIndex])
trainMat = []
trainClasses = []
for docIndex in trainingSet:
trainMat.append(bayes.bagOfWords2VecMN(vocabList, docList[docIndex]))
trainClasses.append(classList[docIndex])
#training
p0V, p1V, pLocal = bayes.trainNB0(array(trainMat), array(trainClasses))
#testing
errorCount = 0
for docIndex in testSet:
wordVector = bayes.bagOfWords2VecMN(vocabList, docList[docIndex])
if bayes.classifyNB(array(wordVector), p0V, p1V, pLocal) != classList[docIndex]:
errorCount+=1
print 'the error rate is: ', float(errorCount)/len(testSet)
return vocabList, p0V, p1V
def testingNB():
postList, classList = bayes.loadDataSet()
myVocabList = bayes.createVocabList(postList)
trainMat = []
for post in postList:
trainMat.append(bayes.setOfWords2Vec(myVocabList, post))
p0V, p1V, pAb = bayes.trainNB0(trainMat, classList)
testEntry = ['love', 'my', 'dalmation']
thisDoc = bayes.setOfWords2Vec(myVocabList, testEntry)
print testEntry, 'classified as: ', bayes.classifyNB(
thisDoc, p0V, p1V, pAb)
testEntry = ['stupid', 'garbage']
thisDoc = bayes.setOfWords2Vec(myVocabList, testEntry)
print testEntry, 'classified as: ', bayes.classifyNB(
thisDoc, p0V, p1V, pAb)
def spamTest():
'''
对贝叶斯垃圾邮件分类器进行自动化处理
对测试集中的每封邮件进行分类，若邮件分类错误，测错误数加1，最后返回总的错误百分比
'''
docList = []
classList = []
fullText = []
for i in range(1, 26):
#切分，解析数据，并归类为1的类别
wordList = textParse(open('email/spam/%d.txt' % i).read())
docList.append(wordList)
classList.append(1)
wordList = textParse(open('email/ham/%d.txt' % i).read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(0)
#创建词汇表
vocabList = bayes.createVocabList(docList)
trainingSet = list(range(50))
testSet = []
#随机取10个邮件测试
for i in range(10):
#random.uniform(x,y)随机产生一个范围为x-y的实数
randIndex = int(random.uniform(0, len(trainingSet)))
testSet.append(trainingSet[randIndex])
del (trainingSet[randIndex])
trainMat = []
trainClasses = []
for docIndex in trainingSet:
trainMat.append(bayes.setWords2Vec(vocabList, docList[docIndex]))
trainClasses.append(classList[docIndex])
p0V, p1V, pSpam = bayes.trainNB0(array(trainMat), array(trainClasses))
errorCount = 0
errorDoc = []
for docIndex in testSet:
wordVector = bayes.setWords2Vec(vocabList, docList[docIndex])
if bayes.classifyNB(array(wordVector), p0V, p1V,
pSpam) != classList[docIndex]:
errorCount += 1
errorDoc.append(docList[docIndex])
print(vocabList)
print(trainMat)
print('the errorCount is: ', errorCount)
print('the testSet length is: ', len(testSet))
print('the error rate is； ', float(errorCount) / len(testSet))
print(errorDoc)
def localWord(feed1, feed0):
docList = []
classList = []
fullText = []
minLength = min(len(feed1['entries']), len(feed0['entries']))
for i in range(minLength):
wordList = bayes.textParse(feed1['entries'][i]['summary'])
docList.append(wordList)
fullText.extend(wordList)
classList.append(1)
wordList = bayes.textParse(feed0['entries'][i]['summary'])
docList.append(wordList)
fullText.extend(wordList)
classList.append(0)
vocabList = bayes.createVocabList(docList)
top30words = calMostFeq(vocabList, fullText)
for pairW in top30words:
if (pairW[0] in vocabList):
vocabList.remove(pairW[0])
trainingSet = range(2 * minLength)
testSet = []
for i in range(20):
randIndex = int(random.uniform(0, len(trainingSet)))
testSet.append(trainingSet[randIndex])
del (trainingSet[randIndex])
trainMatrix = []
trainClass = []
for docIndex in trainingSet:
trainMatrix.append(bayes.bagOfWordsToVec(vocabList, docList[docIndex]))
trainClass.append(classList[docIndex])
p0V, p1V, pSapm = bayes.trainNB0(trainMatrix, trainClass)
errorCount = 0
for docIndex in testSet:
calculatedClass = bayes.classifyNB(
bayes.bagOfWordsToVec(vocabList, docList[docIndex]), p0V, p1V,
pSapm)
if (calculatedClass != classList[docIndex]):
errorCount += 1
print "error rate is: ", float(errorCount) / len(testSet)
return vocabList, p0V, p1V
def localWords(feed1, feed0):
import feedparser
docList = []
classList = []
fullText = []
minLen = min(len(feed1['entries']), len(feed0['entries']))
for i in range(minLen):
# 每次访问一条RSS源
wordList = bayes.textParse(feed1['entries'][i]['summary'])
docList.append(wordList)
fullText.extend(wordList)
classList.append(1)
wordList = bayes.textParse(feed0['entries'][i]['summary'])
docList.append(wordList)
fullText.extend(wordList)
classList.append(0)
vocabList = bayes.createVocabList(docList)
top30Words = calcMostFreq(vocabList, fullText)
# 去掉出现频数最高的词
for pairW in top30Words:
if pairW[0] in vocabList:
vocabList.remove(pairW[0])
trainingSet = list(range(2 * minLen))
testSet = []
for i in range(20):
randIndex = int(random.uniform(0, len(trainingSet)))
testSet.append(trainingSet[randIndex])
del (trainingSet[randIndex])
trainMat = []
trainClasses = []
for docIndex in trainingSet:
trainMat.append(bayes.bagOfWords2VecMN(vocabList, docList[docIndex]))
trainClasses.append(classList[docIndex])
p0V, p1V, pSpam = bayes.trainNB0(array(trainMat), array(trainClasses))
errorCount = 0
for docIndex in testSet:
wordVector = bayes.bagOfWords2VecMN(vocabList, docList[docIndex])
if bayes.classifyNB(array(wordVector), p0V, p1V,
pSpam) != classList[docIndex]:
errorCount += 1
print('the error rate is:', float(errorCount) / len(testSet))
return vocabList, p0V, p1V
def spamTest():
docList = []
classList = []
fullText = []
# read the mail
for i in range(1, 26):
wordlist1 = textParse(open('./email/spam/%d.txt' % i).read())
docList.append(wordlist1)
fullText.extend(docList)
classList.append(1)
wordlist0 = textParse(open('./email/ham/%d.txt' % i).read())
docList.append(wordlist0)
fullText.extend(docList)
classList.append(0)
# get the dictionary
vablist = bayes.createVocablist(docList)
# Random Test dateset
trainingSet = range(50)
testSet = []
for i in range(10):
randIndex = int(random.uniform(0, len(trainingSet)))
testSet.append(trainingSet[randIndex])
del (trainingSet[randIndex])
trainMat = []
trainClasses = []
# Get the train dateset
for docIndex in trainingSet:
trainMat.append(bayes.setOfwords2Vec(vablist, docList[docIndex]))
trainClasses.append(classList[docIndex])
pa, p1Vec, p0Vec = bayes.trainNB0(trainMat, trainClasses)
# test the bayes
errorCount = 0
for docIndex in testSet:
testVec = bayes.setOfwords2Vec(vablist, docList[docIndex])
result = bayes.classifyNB(testVec, p1Vec, p0Vec, pa)
if result != classList[docIndex]:
errorCount += 1
errorrate = float(errorCount) / len(testSet)
print "the filter spam mail error rate is %f" % errorrate
def spamTest():
docList = []
classList = []
fullText = []
# read the mail
for i in range(1,26):
wordlist1 = textParse(open('./email/spam/%d.txt' %i).read())
docList.append(wordlist1)
fullText.extend(docList)
classList.append(1)
wordlist0 = textParse(open('./email/ham/%d.txt' %i).read())
docList.append(wordlist0)
fullText.extend(docList)
classList.append(0)
# get the dictionary
vablist = bayes.createVocablist(docList)
# Random Test dateset
trainingSet = range(50)
testSet = []
for i in range(10):
randIndex = int(random.uniform(0, len(trainingSet)))
testSet.append(trainingSet[randIndex])
del (trainingSet[randIndex])
trainMat = []
trainClasses = []
# Get the train dateset
for docIndex in trainingSet:
trainMat.append(bayes.setOfwords2Vec(vablist, docList[docIndex]))
trainClasses.append(classList[docIndex])
pa, p1Vec, p0Vec = bayes.trainNB0(trainMat, trainClasses)
# test the bayes
errorCount = 0
for docIndex in testSet:
testVec = bayes.setOfwords2Vec(vablist, docList[docIndex])
result = bayes.classifyNB(testVec, p1Vec, p0Vec, pa)
if result != classList[docIndex]:
errorCount += 1
errorrate = float(errorCount) / len(testSet)
print "the filter spam mail error rate is %f" %errorrate
def spamTest():
docList = []
classList = []
fullText = []
for i in range(1, 26):
wordList = textParse(open('email/spam/%d.txt' % i).read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(1)
wordList = textParse(open('email/ham/%d.txt' % i).read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(0)
vocabList = docTool.createVocabList(docList)
trainingSet = range(50)
testSet = []
for i in range(10):
randIndex = int(np.random.uniform(0, len(trainingSet)))
testSet.append(trainingSet[randIndex])
del(trainingSet[randIndex])
trainMat = []
trainClasses = []
for docIndex in trainingSet:
trainMat.append(docTool.setOfWords2Vec(vocabList, docList[docIndex]))
trainClasses.append(classList[docIndex])
p0V, p1V, pSpam = bayes.trainNB0(trainMat, trainClasses)
errorCount = 0
for docIndex in testSet:
wordVector = docTool.setOfWords2Vec(vocabList, docList[docIndex])
if bayes.classifyNB(wordVector, p0V, p1V, pSpam) != classList[docIndex]:
errorCount += 1
print '错误率: ', float(errorCount) / len(testSet)
def spamTest():
docList = []
classList = []
fullText = []
for i in range(1, 26):
wordList = textParse(open('email/spam/%d.txt' % i).read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(1)
wordList = textParse(open('email/ham/%d.txt' % i).read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(0)
vocabList = docTool.createVocabList(docList)
trainingSet = range(50)
testSet = []
for i in range(10):
randIndex = int(np.random.uniform(0, len(trainingSet)))
testSet.append(trainingSet[randIndex])
del (trainingSet[randIndex])
trainMat = []
trainClasses = []
for docIndex in trainingSet:
trainMat.append(docTool.setOfWords2Vec(vocabList, docList[docIndex]))
trainClasses.append(classList[docIndex])
p0V, p1V, pSpam = bayes.trainNB0(trainMat, trainClasses)
errorCount = 0
for docIndex in testSet:
wordVector = docTool.setOfWords2Vec(vocabList, docList[docIndex])
if bayes.classifyNB(wordVector, p0V, p1V,
pSpam) != classList[docIndex]:
errorCount += 1
print '错误率: ', float(errorCount) / len(testSet)
def testNB():
listOPosts, listClasses = bayes.loadDataSet() #加载数据
myVocabList = bayes.createVocabList(listOPosts)
trainMat = []
for postinDoc in listOPosts:
trainMat.append(bayes.setOfWords2Vec(myVocabList, postinDoc))
p0V, p1V, pAb = bayes.trainNB0(trainMat, listClasses)
resultLabel = {0: 'Not garbage', 1: 'Garbage'}
testEntry = ['love', 'my', 'dalmation']
thisDoc = array(bayes.setOfWords2Vec(myVocabList, testEntry))
print(testEntry, 'classified as:',
resultLabel[bayes.classifyNB(thisDoc, p0V, p1V, pAb)])
testEntry = ['stupid', 'garbage']
thisDoc = array(bayes.setOfWords2Vec(myVocabList, testEntry))
print(testEntry, 'classified as:',
resultLabel[bayes.classifyNB(thisDoc, p0V, p1V, pAb)])
def localWords(feed1, feed0): # 两份RSS文件分别经feedparser解析，得到2个字典
docList = [] # 一条条帖子组成的List, 帖子拆成了单词
classList = [] # 标签列表
fullText = [] # 所有帖子的所有单词组成的List
# entries条目包含多个帖子，miNLen记录帖子数少的数目，怕越界
minLen = min(len(feed1['entries']), len(feed0['entries']))
for i in range(minLen):
wordList = bayes.textParse(feed1['entries'][i]['summary']) # 取出帖子内容，并拆成词
docList.append(wordList) # ['12','34'].append(['56','78']) ==> [ ['12','34'], ['56','78'] ]
fullText.extend(wordList) # ['12','34'].extend(['56','78']) ==> ['12','34','56','78']
classList.append(1) # 纽约的标签是1
wordList = bayes.textParse(feed0['entries'][i]['summary'])
docList.append(wordList)
fullText.extend(wordList)
classList.append(0) # 旧金山的标签是0
vocabList = bayes.createVocabList(docList) # 创建词汇表
# 从fulltext中找出最高频的30个单词，并从vocabList中去除它们
top30Words = calcMostFreq(vocabList, fullText)
for (word, count) in top30Words:
if word in vocabList:
vocabList.remove(word)
trainingSet = range(2 * minLen);
testSet = [] # 创建训练集、测试集
for i in range(minLen / 10): # 随机选取10%的数据，建立测试集
randIndex = int(random.uniform(0, len(trainingSet)))
testSet.append(trainingSet[randIndex])
del (trainingSet[randIndex])
trainMat = [];
trainClasses = []
for docIndex in trainingSet:
trainMat.append(bayes.bagOfWords2VecMN(vocabList, docList[docIndex])) # 将训练集中的每一条数据，转化为词向量
trainClasses.append(classList[docIndex])
p0V, p1V, pSpam = bayes.trainNB0(np.array(trainMat), np.array(trainClasses)) # 开始训练
# 用测试数据，测试分类器的准确性
errorCount = 0
for docIndex in testSet:
wordVector = bayes.bagOfWords2VecMN(vocabList, docList[docIndex])
if bayes.classifyNB(np.array(wordVector), p0V, p1V, pSpam) != classList[docIndex]:
errorCount += 1
print 'the error rate is: ', float(errorCount) / len(testSet)
return vocabList, p0V, p1V
def spamTest():
"""
将文件夹spam和ham中分别的25篇右键导入解析为词列表，再构建一个测试集与训练集,
50篇中再随机选10篇作为测试集，其余20篇作为测试集（留存交叉验证）
:return:
"""
docList = []
classList = []
fullText = []
for i in range(1, 26):
wordList = bayes.textParse(open('email/spam/%d.txt' % i).read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(1)
wordList = bayes.textParse(open('email/ham/%d.txt' % i).read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(0)
vocabList = bayes.createVocabList(docList)
trainingSet = list(range(50))
testSet = []
for i in range(10): #随机选出10篇
randIndex = int(random.uniform(
0,
len(trainingSet))) #random.uniform(x, y) 方法将随机生成一个实数，它在 [x,y] 范围内。
testSet.append(trainingSet[randIndex])
del (trainingSet[randIndex])
trainMat = []
trainClasses = []
for docIndex in trainingSet: #遍历训练集中所有的文档
trainMat.append(bayes.bagOfWords2VecMN(vocabList,
docList[docIndex])) #构建词向量
trainClasses.append(classList[docIndex])
p0V, p1V, pSpam = bayes.trainNB0(array(trainMat),
array(trainClasses)) #计算分类所需的概率
errorCount = 0
for docIndex in testSet: #遍历测试集
wordVector = bayes.setOfWords2Vec(vocabList, docList[docIndex])
if bayes.classifyNB(array(wordVector), p0V, p1V,
pSpam) != classList[docIndex]:
errorCount += 1
print('the error rate is :', float(errorCount) / len(testSet))
return vocabList, p0V, p1V
def spamTest():
docList = []
classList = []
fullText = []
for i in range(1, 26):
# assume we have 25 emails for normal email and spam
wordList = textParse(
codecs.open(baseURI + 'email/spam/%d.txt' % i,
encoding='ANSI').read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(1)
wordList = textParse(
open(baseURI + 'email/ham/%d.txt' % i, encoding='ANSI').read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(0)
vocabList = bayes.create_vocab_list(docList) #create vocabulary
trainingSet = list(range(50))
testSet = [] #create test set
# this will pop out 10 emails of traning set for testing algorithm randomly
for i in range(10):
# np.random.uniform(low, high) draw samples from a uniform distribution
# The probability density function of the uniform distribution is p(x)=1/(high-low)
randIndex = int(np.random.uniform(0, len(trainingSet)))
testSet.append(trainingSet[randIndex])
del (trainingSet[randIndex])
trainMat = []
trainClasses = []
for docIndex in trainingSet: # train the classifier (get probs) trainNB0
trainMat.append(bagOfwords2Vec(vocabList, docList[docIndex]))
trainClasses.append(classList[docIndex])
p0V, p1V, pSpam = bayes.trainNB0(np.array(trainMat),
np.array(trainClasses))
errorCount = 0
for docIndex in testSet: #classify the remaining items
wordVector = bagOfwords2Vec(vocabList, docList[docIndex])
if bayes.classifyNB(np.array(wordVector), p0V, p1V,
pSpam) != classList[docIndex]:
errorCount += 1
print("classification error", docList[docIndex])
print('the error rate is: ', float(errorCount) / len(testSet))
def spamTest():
docList=[]; classList = []; fullText =[]
for i in range(1,26):
str=open('email/spam/%d.txt' % i).read()
print "str"
print str
wordList = bayes.textParse(str)
print "wordlist"
print wordList
docList.append(wordList)
fullText.extend(wordList)
classList.append(1)
wordList = bayes.textParse(open('email/ham/%d.txt' % i).read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(0)
print "doclist"
print len(docList)
print docList
print "fulllist"
print len(fullText)
print fullText
print classList
vocabList = bayes.createVocabList(docList)#create vocabulary
trainingSet = range(50); testSet=[] #create test set
for i in range(10):
randIndex = int(random.uniform(0,len(trainingSet)))
testSet.append(trainingSet[randIndex])
del(trainingSet[randIndex])
trainMat=[]; trainClasses = []
for docIndex in trainingSet:#train the classifier (get probs) trainNB0
trainMat.append(bayes.bagOfWords2VecMN(vocabList, docList[docIndex]))
trainClasses.append(classList[docIndex])
p0V,p1V,pSpam = bayes.trainNB0(array(trainMat),array(trainClasses))
errorCount = 0
for docIndex in testSet: #classify the remaining items
wordVector = bayes.bagOfWords2VecMN(vocabList, docList[docIndex])
if bayes.classifyNB(array(wordVector),p0V,p1V,pSpam) != classList[docIndex]:
errorCount += 1
print "classification error",docList[docIndex]
print 'the error rate is: ',float(errorCount)/len(testSet)
def localWords(feed1, feed0):
import feedparser
docList = []
classList = []
fullText = []
minLen = min(len(feed1['entries']), len(feed0['entries']))
print feed1['entries']
print feed0['entries']
for i in range(minLen):
wordList = bayes.textParse(feed1['entries'][i]['summary'])
docList.append(wordList)
fullText.extend(wordList)
classList.append(1) #NY is class 1
wordList = bayes.textParse(feed0['entries'][i]['summary'])
docList.append(wordList)
fullText.extend(wordList)
classList.append(0)
vocabList = bayes.createVocabList(docList) #create vocabulary
top30Words = calcMostFreq(vocabList, fullText) #remove top 30 words
for pairW in top30Words:
if pairW[0] in vocabList: vocabList.remove(pairW[0])
trainingSet = list(range(2 * minLen))
testSet = [] #create test set
for i in range(10):
randIndex = int(random.uniform(0, len(trainingSet)))
testSet.append(trainingSet[randIndex])
del (trainingSet[randIndex])
trainMat = []
trainClasses = []
for docIndex in trainingSet: #train the classifier (get probs) trainNB0
trainMat.append(bayes.bagOfWord2VecMN(vocabList, docList[docIndex]))
trainClasses.append(classList[docIndex])
p0V, p1V, pSpam = bayes.trainNB0(array(trainMat), array(trainClasses))
errorCount = 0
for docIndex in testSet: #classify the remaining items
wordVector = bayes.bagOfWord2VecMN(vocabList, docList[docIndex])
if bayes.classifyNB(array(wordVector), p0V, p1V,
pSpam) != classList[docIndex]:
errorCount += 1
print('the error rate is: ', float(errorCount) / len(testSet))
return vocabList, p0V, p1V
def spamTest():
docList = []
classList = []
fullText = []
# parse text from email
for i in range(1, 26):
wordList = textParse(open('email/spam/%d.txt' % i).read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(1)
#parse text
wordList = textParse(open('email/ham/%d.txt' % i).read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(0)
vocabList = bayes.createVocabList(docList)
#build training set and test set
trainingSet = range(50)
testSet = []
for i in range(10):
randIndex = int(random.uniform(0, len(trainingSet)))
#select testset and remove the testset from all dataset
testSet.append(trainingSet[randIndex])
del (trainingSet[randIndex])
trainMat = []
trainClasses = []
for docIndex in trainingSet:
trainMat.append(bayes.setOfWords2Vec(vocabList, docList[docIndex]))
trainClasses.append(classList[docIndex])
p0V, p1V, pSpam = bayes.trainNB0(array(trainMat), array(trainClasses))
#classify and test precision
errorCount = 0
for docIndex in testSet:
wordVector = bayes.setOfWords2Vec(vocabList, docList[docIndex])
if bayes.classifyNB(array(wordVector), p0V, p1V,
pSpam) != classList[docIndex]:
errorCount += 1
print 'the error rate is: ', float(errorCount) / len(testSet)
def spamTest():
docList = []
classList = []
fullText = []
for i in range(1, 26):
wordList = textParse(open('email/spam/%d.txt' % i).read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(1)
wordList = textParse(open('email/ham/%d.txt' % i).read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(0)
vocabList = bayes.createVocabList(docList)
trainingSet = range(50)
testSet = []
# randomly split data set into 2 sets: test set, and training set
for i in range(10):
randIndex = int(random.uniform(0, len(trainingSet))) # random int 0~len
testSet.append(trainingSet[randIndex])
del(trainingSet[randIndex]) # split
trainMat = [];
trainClasses = [];
for docIndex in trainingSet:
trainMat.append(bayes.setOfWords2Vec(vocabList, docList[docIndex]))
trainClasses.append(classList[docIndex])
p0V, p1V, pSpam = bayes.trainNB0(array(trainMat), array(trainClasses))
errorCount = 0
for docIndex in testSet:
wordVector = bayes.setOfWords2Vec(vocabList, docList[docIndex])
if bayes.classifyNB(array(wordVector), p0V, p1V, pSpam) != classList[docIndex]:
errorCount += 1
print "error word: %s" % (docList[docIndex])
print "error rate is: %f", float(errorCount) / len(testSet)
def spamTest():
docList = []
classList = []
fullText = []
# parse text from email
for i in range(1,26):
wordList = textParse(open('email/spam/%d.txt' %i).read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(1)
#parse text
wordList = textParse(open('email/ham/%d.txt' %i).read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(0)
vocabList = bayes.createVocabList(docList)
#build training set and test set
trainingSet = range(50);
testSet =[]
for i in range(10):
randIndex = int(random.uniform(0, len(trainingSet)))
#select testset and remove the testset from all dataset
testSet.append(trainingSet[randIndex])
del(trainingSet[randIndex])
trainMat = []
trainClasses = []
for docIndex in trainingSet:
trainMat.append(bayes.setOfWords2Vec(vocabList, docList[docIndex]))
trainClasses.append(classList[docIndex])
p0V, p1V, pSpam = bayes.trainNB0(array(trainMat), array(trainClasses))
#classify and test precision
errorCount = 0
for docIndex in testSet:
wordVector = bayes.setOfWords2Vec(vocabList, docList[docIndex])
if bayes.classifyNB(array(wordVector), p0V, p1V, pSpam) != classList[docIndex]:
errorCount += 1
print 'the error rate is: ', float(errorCount)/len(testSet)
def spamTest():
"""
对贝叶斯垃圾邮件分类器进行自动化处理
:return:
"""
docList = []
classList = []
fullText = []
for i in range(1, 26):
# 1. 导入并解析文本文件
wordList = textParse(open('email/spam/%d.txt' % i).read())
docList.append(wordList)
fullText.append(wordList)
classList.append(1)
wordList = textParse(open('email/ham/%d.txt' % i).read())
docList.append(wordList)
fullText.append(wordList)
classList.append(0)
vocabList = bayes.createVocabList(docList)
trainingSet = range(50)
testSet = []
for i in range(10):
# 2. 随机构建训练集
randIndex = int(random.uniform(0, len(trainingSet)))
testSet.append(trainingSet[randIndex])
del (trainingSet[randIndex])
trainMat = []
trainClasses = []
for docIndex in trainingSet: # train the classifier (get probs) trainNB0
trainMat.append(bagOfWords2VecMN(vocabList, docList[docIndex]))
trainClasses.append(classList[docIndex])
p0V, p1V, pSpam = bayes.trainNB0(array(trainMat), array(trainClasses))
errorCount = 0
# 3. 对测试集分类
for docIndex in testSet:
wordVector = bayes.setOfWords2Vec(vocabList, docList[docIndex])
if bayes.classifyNB(array(wordVector), p0V, p1V,
pSpam) != classList[docIndex]:
errorCount += 1
print 'the error rate is: ', float(errorCount) / len(testSet)
def main():
print '开始测试...'
listOPosts, listClasses = loadDataSet()
myVocabList = docTool.createVocabList(listOPosts)
print '词汇表:\n', myVocabList
wordsVec = docTool.setOfWords2Vec(myVocabList, listOPosts[0])
print '将第一句话转换成向量,存在的单词为1,不存在的单词为0\n', wordsVec
trainMat = []
for postinDoc in listOPosts:
trainMat.append(docTool.setOfWords2Vec(myVocabList, postinDoc))
p0V, p1V, pAb = bayes.trainNB0(trainMat, listClasses)
testEntry = ['love', 'my', 'dalmation']
# 将testEntry转化成特征量的组合,也就是一个要求的样本
thisDoc = np.array(docTool.setOfWords2Vec(myVocabList, testEntry))
label = bayes.classifyNB(thisDoc, p0V, p1V, pAb)
print testEntry, '分类是:', label
testEntry = ['stupid', 'garbage']
# 将testEntry转化成特征量的组合,也就是一个要求的样本
thisDoc = np.array(docTool.setOfWords2Vec(myVocabList, testEntry))
label = bayes.classifyNB(thisDoc, p0V, p1V, pAb)
print testEntry, '分类是:', label
print '测试结束...'
def main():
print '开始测试...'
listOPosts, listClasses = loadDataSet()
myVocabList = docTool.createVocabList(listOPosts)
print '词汇表:\n', myVocabList
wordsVec = docTool.setOfWords2Vec(myVocabList, listOPosts[0])
print '将第一句话转换成向量,存在的单词为1,不存在的单词为0\n', wordsVec
trainMat = []
for postinDoc in listOPosts:
trainMat.append(docTool.setOfWords2Vec(myVocabList, postinDoc))
p0V, p1V, pAb = bayes.trainNB0(trainMat, listClasses)
testEntry = ['love', 'my', 'dalmation']
# 将testEntry转化成特征量的组合,也就是一个要求的样本
thisDoc = np.array(docTool.setOfWords2Vec(myVocabList, testEntry))
label = bayes.classifyNB(thisDoc, p0V, p1V, pAb)
print testEntry, '分类是:',label
testEntry = ['stupid', 'garbage']
# 将testEntry转化成特征量的组合,也就是一个要求的样本
thisDoc = np.array(docTool.setOfWords2Vec(myVocabList, testEntry))
label = bayes.classifyNB(thisDoc, p0V, p1V, pAb)
print testEntry, '分类是:',label
print '测试结束...'
def spamTest():
docList = []
classList = []
#fullText = [] #没起作用
for i in range(1,26): #此案例中样本集名为1.txt~25.txt
wordList = textParse(open('email/spam/%d.txt' % i).read()) #解析邮件，分隔成一个个词汇
docList.append(wordList) #将样本内容存储到docList中
#fullText.extend(wordList)
classList.append(1) #spam下对应的类别标签设置为1
wordList = textParse(open('email/ham/%d.txt' % i).read())
docList.append(wordList)
#fullText.extend(wordList)
classList.append(0) #ham下对应的类别标签设置为0
vocabList = bayes.createVocabList(docList) #通过docList获取全部的词汇表
trainingSet = list(range(50)) #此处共50个案例，与classList长度对应
testSet = [] #存储测试样本集
for i in list(range(10)):
randIndex = int(random.uniform(0,len(trainingSet))) #随机提取样本作为测试样本
testSet.append(trainingSet[randIndex])
del(trainingSet[randIndex]) #把测试样本从训练样本中剔除
trainMat = []
trainClasses = []
for docIndex in trainingSet:#遍历训练样本集
trainMat.append(bayes.setOfWords2Vec(vocabList, docList[docIndex])) #获取样本中使用词汇情况向量
trainClasses.append(classList[docIndex]) #获取当前样本的类别标签
p0V,p1V,pSpam = bayes.trainNB0(array(trainMat), array(trainClasses)) #训练算法，得到概率
errorCount = 0
for docIndex in testSet: #遍历测试样本集
wordVector=bayes.setOfWords2Vec(vocabList, docList[docIndex])
resultFlag = bayes.classifyNB(array(wordVector), p0V, p1V, pSpam) #使用分类函数进行分类
if(resultFlag != classList[docIndex]): #如果得到结果不正确，则错误数加上1
errorCount += 1
print('the error rate is: ', float(errorCount)/len(testSet))
# coding=utf-8 import bayes listOPosts, listClasses = bayes.loadDataSet() myVobList = bayes.createVocabList(listOPosts) trainMat = [] for postinDoc in listOPosts: trainMat.append(bayes.setOfWords2Vec(myVobList, postinDoc)) p0v, p1v, pAb = bayes.trainNB0(trainMat, listClasses)
import bayes
from numpy import *
listOposts, listClasses = bayes.loadDataSet()
myVocabList = bayes.createVocabList(listOposts)
trainMat = []
print("-----start for about trainMat----- ")
for postinDoc in listOposts:
print("postinDoc = ", postinDoc)
trainMat.append(bayes.setOfWords2Vec(myVocabList, postinDoc))
print("trainMat = ", trainMat)
p0V, p1V, pAb = bayes.trainNB0(trainMat, listClasses)
print("p0V = ", p0V)
print("p1V = ", p1V)
print("pAb = ", pAb)
#coding:utf-8
import bayes
#文档集，标签集
listOPosts, listClasses = bayes.loadDataSet()
#包含所有词的列表
myList = bayes.createVocabList(listOPosts)
#print myList
trainMat = [] #文档矩阵
for i in listOPosts:
trainMat.append(bayes.setOfWords2Vec(myList, i))
p0Vect, p1Vect, pAbusive = bayes.trainNB0(trainMat, listClasses)
print p0Vect
print p1Vect
print pAbusive # 侮辱性文档占总文档数目的概率
#print len(trainMat)
#myVec = bayes.setOfWords2Vec(myList,listOPosts[0]) #得到第0篇文档的向量
#print myVec
# vo = [1,2,3]
# print vo.index(2)
# print vo.index(3)
# print vo.index(1)
__author__ = 'jack'
import bayes
listOPosts,listClasses = bayes.loadDataSet()
myVocabList = bayes.createVocabList(listOPosts)
print myVocabList
#print bayes.setOfWords2Vec(myVocabList, listOPosts[0])
trainMat = []
for post in listOPosts:
trainMat.append(bayes.setOfWords2Vec(myVocabList, post))
p0V, p1V, pAb = bayes.trainNB0(array(trainMat), array(listClasses))
print pAb
print p0V
print p1V
testEntry = ['love', 'my', 'dalmation']
thisDoc = array(bayes.setOfWords2Vec(myVocabList, testEntry))
print thisDoc
print testEntry, 'classsified as: ', bayes.classifyNB(thisDoc, p0V, p1V, pAb)
testEntry = ['stupid', 'garbage']
thisDoc = array(bayes.setOfWords2Vec(myVocabList, testEntry))
print thisDoc
print testEntry, 'classsified as: ', bayes.classifyNB(thisDoc, p0V, p1V, pAb)
#!/usr/bin/python
#encoding:utf-8
import bayes
from numpy import *
postingList , classList = bayes.loadDataSet()
myVocabList = bayes.createVocabList(postingList)
trainMat = []
for a in postingList:
trainMat.append( bayes.setOfWords( myVocabList, a ) )
pc, p0, p1 = bayes.trainNB0(trainMat, classList)
test = ['stupid', 'garbage']
thisDoc = array( bayes.setOfWords( myVocabList, test ) )
print bayes.classifyNB(thisDoc, p0, p1, pc)
from numpy import *
import bayes
import FilterMail
postingList, classVec = bayes.loadDataSet()
# get the vablist
vablist = bayes.createVocablist(postingList)
print "Show my vablist\n", vablist
print "-------------------------------"
# get the returnVec
returnVec = bayes.setOfwords2Vec(vablist, ["my", "love", "dog", "happy", "daddy"])
print "the word vec is ", returnVec
print "-------------------------------"
# get the prior probability
trainMat = []
for one in postingList:
trainMat.append(bayes.setOfwords2Vec(vablist, one))
pa, p1Vec, p0Vec = bayes.trainNB0(trainMat, classVec)
print "the 1 probability is %f, " % pa
print "the each class , each element probability\n", p1Vec, '\n', p0Vec
print "--------------------------------"
bayes.testNB()
print "--------------------------------"
FilterMail.spamTest()
import bayes
import feedparser
listOPosts, listClasses = bayes.loadDataSet()
myVocabList = bayes.createVocabList(listOPosts)
print myVocabList
print bayes.setOfWords2Vec(myVocabList, listOPosts[0])
print bayes.setOfWords2Vec(myVocabList, listOPosts[3])
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()
print '==email classify=='
bayes.spamTest()
print '==email classify=='
bayes.spamTest()
print '==email classify=='
bayes.spamTest()
print '==feedparser classify=='
ny = feedparser.parse('http://newyork.craigslist.org/stp/index.rss')
sf = feedparser.parse('http://sfbay.craigslist.org/stp/index.rss')
vocabList, pSF, pNY = bayes.localWords(ny, sf)
vocabList, pSF, pNY = bayes.localWords(ny, sf)
def local_words(feed1, feed0):
"""
feed1: rss源1
feed0: rss源0
"""
import feedparser
# 文档列表
doc_list = []
# 文档类别列表
class_list = []
full_text = []
# 计算两个源中用于训练的数据的数量
min_len = min(len(feed1['entries']), len(feed0['entries']))
# 遍历每个训练数据（文档）
for i in range(min_len):
# 分词，去掉标点符号
word_list = text_parse(feed1['entries'][i]['summary'])
doc_list.append(word_list)
full_text.extend(word_list)
class_list.append(1)
# 分词，去掉标点符号
word_list = text_parse(feed0['entries'][i]['summary'])
doc_list.append(word_list)
full_text.extend(word_list)
class_list.append(0)
# 构造单词列表
vocab_list = create_vocab_list(doc_list)
# 统计出出现频率前30的单词
top30_words = calc_most_freq(vocab_list, full_text)
# 从单词中去掉高频词汇
for pair_w in top30_words:
if pair_w[0] in vocab_list:
vocab_list.remove(pair_w[0])
# 因为是两个源的数据所以*2
training_set = range(2 * min_len)
#print(training_set)
# 接下来构造测试数据集
test_set = []
for i in range(20):
# 随机从训练数据集中获得20个数据，同时在训练数据集中将其删除
rand_index = int(random.uniform(0, len(training_set)))
test_set.append(training_set[rand_index])
del (training_set[rand_index])
train_mat = []
train_classes = []
# 下面遍历training_set构造出最终用于训练的文档向量和标签
for doc_index in training_set:
# 用词袋模型构造每个文档的向量
train_mat.append(bag_of_word2vec(vocab_list, doc_list[doc_index]))
train_classes.append(class_list[doc_index])
# 训练贝叶斯分类器，这里由于使用两源同样数量的数据，所以p_spam为0.5
p0_v, p1_v, p_spam = trainNB0(np.array(train_mat), np.array(train_classes))
error_count = 0
# 测试数据
for doc_index in test_set:
# 构造测试文档的向量
word_vec = bag_of_word2vec(vocab_list, doc_list[doc_index])
if classifyNB(np.array(word_vec), p0_v, p1_v,
p_spam) != class_list[doc_index]:
error_count += 1
print('the error rate is: ', float(error_count) / len(test_set))
return vocab_list, p0_v, p1_v
# coding=utf-8
# http://blog.csdn.net/lu597203933/article/details/38445315
from numpy import *
import bayes
if __name__ == "__main__" :
listOPosts,listClasses = bayes.loadDataSet()
myVocabList = bayes.createVocabList(listOPosts)
print myVocabList
print bayes.setOfWords2Vec(myVocabList,listOPosts[0])
print bayes.setOfWords2Vec(myVocabList,listOPosts[3])
trainMatrix,trainCategory = bayes.getTrainMatrix()
p0V,p1V,pAb = bayes.trainNB0(trainMatrix,trainCategory)
print p0V
print p1V
print pAb