def main():
print "Creating Train File..."
Data.CreateDataFile("mails-train", "mails-train.txt")
print "Initializing Train File..."
trainingSet = Data.LoadFile("mails-train.txt")
print "Creating Test File..."
Data.CreateDataFile("mails-test", "mails-test.txt")
print "Initializing Test File..."
testSet = Data.LoadFile("mails-test.txt")
print "Extracting Classes.."
classes = Train.ExtractClasses(trainingSet)
print "Training NBC..."
vocabulary, prior, condprob = Train.TrainMultinomialNaiveBayes(
classes, trainingSet)
print "Testing Accuracy..."
percentage = Test.Accuracy(classes, vocabulary, prior, condprob,
testSet)
print "The percentage of correct predictions is ", 100 * percentage, "percent."
print "Get Random Document..."
testDocument = Data.GetDocument(testSet)
print "Do A Time Measurement of the Application of the NBC..."
print "The time is took to do a single application of the NBC on a document is", Test.TimeMeasure(
classes, vocabulary, prior, condprob, testDocument), "seconds."
print "Applying NBC on Document..."
topClass, score = Classify.ApplyMultinomialNaiveBayes(
classes, vocabulary, prior, condprob, testDocument['document'])
def TimeMeasure(classes, vocabulary, prior, condprob, document):
# Neemt een tijdmeting voor en na het uitvoeren van ApplyMultinomialNBC om te kijken
# hoelang het duurt om deze uit te voeren op het gegeven document.
start = time.time()
Classify.ApplyMultinomialNaiveBayes(classes, vocabulary, prior,
condprob, document)
end = time.time()
return end - start
def testSingleFile(self):
f = askopenfile(mode='r', defaultextension=".txt")
if f is None: # askopenfile return `None` if dialog closed with "cancel".
return
lines = f.read()
bagOfWords = re.split(' ',lines)
singleFile = Data.Normalize(bagOfWords)
print "Loaded."
print "Calculating..."
topClass, score = Classify.ApplyMultinomialNaiveBayes(self.classes, self.vocabulary, self.prior, self.condprob, singleFile)
print "This document belongs to", topClass
print "Done."
f.close() # `()` was missing.
def Accuracy(classes, vocabulary, prior, condprob, dataset):
# Voert ApplyMulitnomialNBC uit op een serie documenten, waarvan we de class kennen.
# Er wordt geteld hoevaak de voorspelling overeenkomt met de echte waarde.
# De teruggegeven waarde is een fractie tussen 0 en 1 die aangeeft welk deel van de keren de voorspelling correct was.
correct = 0
totaal = 0
count = 0
for c in dataset:
for d in dataset[c]:
topClass, score = Classify.ApplyMultinomialNaiveBayes(
classes, vocabulary, prior, condprob, dataset[c][d])
if topClass == c:
correct += 1
totaal += 1
print "The amount of total tested documents is", totaal
print "The amount of correct predictions are", correct
return correct / totaal