def test_classify_by_bag_of_model(self):
listOPosts, listClasses = self.loadDataSet()
myVocabList = bayes.createVocabList(listOPosts)
trainMat=[]
for postinDoc in listOPosts:
trainMat.append(bayes.bagOfWords2VecMN(myVocabList, postinDoc))
pVectDict, pCateDict = bayes.train(array(trainMat), listClasses)
print pVectDict
print pCateDict
testEntry = ['love', 'my', 'dalmation']
thisDoc = array(bayes.bagOfWords2VecMN(myVocabList, testEntry))
print testEntry, 'classified as: ', bayes.classify(thisDoc, pVectDict, pCateDict)
testEntry = ['stupid', 'garbage']
thisDoc = array(bayes.bagOfWords2VecMN(myVocabList, testEntry))
print testEntry, 'classified as: ', bayes.classify(thisDoc, pVectDict, pCateDict)
def localWords(feed1, feed0):
docList=[]; classList = []; fullText =[]
minLen = min(len(feed1['entries']),len(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)
top30Words = calcMostFreq(vocabList, fullText)
for pairW in top30Words:
if pairW[0] in vocabList:
vocabList.remove(pairW[0])
trainingSet = range(2 * minLen); testSet=[]
# create test set
for i in range(20):
randIndex = int(random.uniform(0,len(trainingSet)))
testSet.append(trainingSet[randIndex])
del trainingSet[randIndex]
trainMat=[]; trainClasses = []
# train the classifier (get probs) train
for docIndex in trainingSet:
trainMat.append(bayes.bagOfWords2VecMN(vocabList, docList[docIndex]))
trainClasses.append(classList[docIndex])
pVectDict, pCateDict = bayes.train(array(trainMat), trainClasses)
errorCount = 0
# classify the remaining items
for docIndex in testSet:
wordVector = bayes.bagOfWords2VecMN(vocabList, docList[docIndex])
if bayes.classify(array(wordVector), pVectDict, pCateDict) != classList[docIndex]:
errorCount += 1
print 'the error rate is: ', float(errorCount) / len(testSet)
return vocabList, pVectDict
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).read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(0)
vocabList = bayes.createVocabList(docList)
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 = []
# train the classifier (get probs) train
for docIndex in trainingSet:
trainMat.append(bayes.bagOfWords2VecMN(vocabList, docList[docIndex]))
trainClasses.append(classList[docIndex])
pVectDict, pCateDict = bayes.train(array(trainMat), trainClasses)
errorCount = 0
# classify the remaining items
for docIndex in testSet:
wordVector = bayes.bagOfWords2VecMN(vocabList, docList[docIndex])
if bayes.classify(array(wordVector), pVectDict, pCateDict) != classList[docIndex]:
errorCount += 1
print "classification error:", docList[docIndex]
print 'the error rate is: ',float(errorCount) / len(testSet)
