def loading_dataSet():
file = open("res/dataset.txt", "r")
data = file.read()
file.close()
docs = data.split("\n")
types = []
train = []
for d in docs:
d = d.split()
if len(d) != 0:
types.append(d[0])
print('dataset Count = ' + str(len(types)))
normalized_corpus = Normalizer.normalize_corpus(docs)
normalized_corpus.remove('')
counter = 0
for x in normalized_corpus:
train.append((x, types[counter]))
counter = counter + 1
return train
def classify_btn_clicked():
def setClassification(type):
if type == '1':
classi_out.setPlainText('culture')
elif type == '2':
classi_out.setPlainText('sport')
elif type == '3':
classi_out.setPlainText('economy')
elif type == '4':
classi_out.setPlainText('international')
elif type == '5':
classi_out.setPlainText('local')
elif type == '6':
classi_out.setPlainText('religion')
tester_doc = file_.toPlainText().strip()
normalized_tester_doc = Normalizer.normalize_corpus([tester_doc])
featuresets_test = [features(words) for words in normalized_tester_doc]
predicted_label = classifier.classify_many(featuresets_test)
setClassification(predicted_label[0])
