def test_sentiment_1(self):
text = "Không tin tưởng vào ngân hàng BIDV "
actual = sentiment(text)
expected = "TRADEMARK#NEGATIVE"
self.assertEquals(actual[0], expected)
def test_sentiment_2(self):
text = "Bạn ra ngân hàng hỏi luôn cho nhanh giải đáp qua đây ko ăn thua lắm."
actual = sentiment(text)
expected = "CUSTOMER SUPPORT#NEGATIVE"
self.assertEquals(actual[0], expected)
nineties_score = nineties['Lyrics']
nineties_score = nineties_score.to_string()
nineties_score = ''.join(nineties_score)
thousands_score = thousands['Lyrics']
thousands_score = thousands_score.to_string()
thousands_score = ''.join(thousands_score)
tens_score = tens['Lyrics']
tens_score = tens_score.to_string()
tens_score = ''.join(tens_score)
#print(file)
from model import sentiment
func = sentiment()
six_data = func.tokener(sixties_score)
seven_data = func.tokener(seventies_score)
eight_data = func.tokener(eighties_score)
nine_data = func.tokener(nineties_score)
thousand_data = func.tokener(thousands_score)
ten_data = func.tokener(tens_score)
data = {'Year': ['1960s', '1970s', '1980s', '1990s', '2000s', '2010s'],
'Sentiment Score': [six_data, seven_data, eight_data, nine_data, thousand_data, ten_data]
}
from os.path import join, dirname import sys from languageflow.board import Board from languageflow.log import MultilabelLogger from languageflow.log.tfidf import TfidfLogger from load_data import load_dataset from model import sentiment data_file = join(dirname(dirname(dirname(dirname(__file__)))), "data", "fb_bank", "corpus", "test.xlsx") X_test, y_test = load_dataset(data_file) y_test = [tuple(item) for item in y_test] y_pred = sentiment(X_test) log_folder = join(dirname(__file__), "analyze") model_folder = join(dirname(__file__), "model") board = Board(log_folder=log_folder) MultilabelLogger.log(X_test, y_test, y_pred, log_folder=log_folder) TfidfLogger.log(model_folder=model_folder, log_folder=log_folder) board.serve(port=62010)
def test_sentiment(self):
sentence = "Thật tuyệt vời"
tags = "POSITIVE"
actual = sentiment(sentence)
self.assertEquals(tags, actual[0])
import model as s
print(s.sentiment("This movie was awesome! The acting was great, plot was wonderful"))
print(s.sentiment("This movie was utter junk. I don't see what the point was at all. Horrible movie, 0/10"))
def test_sentiment_5(self):
sentence = "Vietcombank là lũ lừa đảo"
tags = "NEGATIVE"
actual = sentiment(sentence)
self.assertEquals(tags, actual[0])
def test_sentiment_3(self):
text = "Tháng này tiền banking bị thu phí 3 lần liên tục đề nghị vietcombank xem xét lại "
actual = sentiment(text)
expected = "INTEREST RATE#NEGATIVE"
self.assertEquals(actual[0], expected)
def test_sentiment_3(self):
sentence = "Dịch vụ rắc rối."
tags = "NEGATIVE"
actual = sentiment(sentence)
self.assertEquals(tags, actual[0])
def test_sentiment_4(self):
sentence = "Thật sự mình rất hài lòng khi làm việc với VietcomBank"
actual = sentiment(sentence)
expected = "POSITIVE"
self.assertEquals(expected, actual[0])
def test_sentiment_2(self):
sentence = "Không tin tưởng vào ngân hàng BIDV."
tags = "NEGATIVE"
actual = sentiment(sentence)
self.assertEquals(tags, actual[0])
def test_sentiment_1(self):
sentence = "Nhân viên BIDV dễ thương nhiệt tình lắm ạ"
tags = "POSITIVE"
actual = sentiment(sentence)
self.assertEquals(tags, actual[0])
config.word_num = len(SENTENCE.vocab)
print("Labels:", LABEL.vocab.itos)
print("Vocabulary Size: {}".format(config.words_num))
if args.resume_snapshot:
if args.cuda:
model = torch.load(
args.resume_snapshot,
map_location=lambda storage, location: storage.cuda(args.gpu))
else:
model = torch.load(args.resume_snapshot,
map_location=lambda storage, location: storage)
else:
if args.data == 'SST1':
model = sentiment(config)
if args.cuda:
model.cuda()
print("Shift model to GPU")
parameter = filter(lambda p: p.requires_grad, model.parameters())
optimizer = torch.optim.Adadelta(parameter,
lr=args.lr,
weight_decay=args.weight_decay)
criterion = nn.MarginRankingLoss()
early_stop = False
best_dev_acc = 0
iteration = 0
iters_not_improved = 0
def test_sentiment_3(self):
text = "VCB Mobile B@bking. Chuyển rất nhanh. Giao diện đẹp, thân thiện. Dễ thao tác"
actual = sentiment(text)
expected = "INTERNET BANKING#POSITIVE"
self.assertEquals(actual[0], expected)
def test_sentiment_7(self):
sentence = "éo tin"
tags = "NEGATIVE"
actual = sentiment(sentence)
self.assertEquals(tags, actual[0])
def test_sentiment(self):
text = "Gọi mấy lần mà lúc nào cũng là các chuyên viên đang bận hết ạ "
actual = sentiment(text)
expected = "CUSTOMER SUPPORT#NEGATIVE"
self.assertEquals(actual[0], expected)
def test_sentiment_1(self):
text = "Chúc mừng VCB, luôn thành công và tạo niềm tin cho khách hàng an tâm khi đồng hành cùng VCB."
actual = sentiment(text)
expected = "TRADEMARK#POSITIVE"
self.assertEquals(actual[0], expected)
