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 data(self):
print "Creating Train File..."
Data.CreateDataFile(self.trainDir, self.folder(self.trainDir) + ".txt")
print "Initializing Train File..."
self.trainingSet = Data.LoadFile(self.folder(self.trainDir) + ".txt")
print "Creating Test File..."
Data.CreateDataFile(self.testDir, self.folder(self.testDir) + ".txt")
print "Initializing Test File..."
self.testSet = Data.LoadFile(self.folder(self.testDir )+ ".txt")
print "Extracting Classes.."
self.classes = Train.ExtractClasses(self.trainingSet)
print "Done."
def accuracyOnTest(self):
print "Calculating Accuracy..."
print "Creating Test File..."
Data.CreateDataFile(self.testDir, self.folder(self.testDir) + ".txt")
print "Initializing Test File..."
self.testSet = Data.LoadFile(self.folder(self.testDir)+ ".txt")
percentage = Test.Accuracy(self.classes, self.vocabulary, self.prior, self.condprob, self.testSet)
print "The percentage of correct predictions is ",100*percentage,"percent."
print "Done."
def load(self):
f = askopenfile(mode='r', defaultextension=".train")
if f is None: # askopenfile return `None` if dialog closed with "cancel".
return
self.classes, self.vocabulary, self.prior, self.condprob = pickle.load(f)
datasets = [{"trainSet": "mails-train", "testSet": "mails-test"}, {"trainSet": "blogs-train", "testSet": "blogs-test"}]
if self.CheckVar1.get() == 1:
dataset = datasets[0]
if self.CheckVar2.get() == 1:
dataset = datasets[1]
self.testSet = Data.LoadFile(dataset['testSet'] + ".txt")
f.close() # `()` was missing.
print "Loaded."