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
email : [email protected] """ 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()