def predict(self, test_file, verbose=False):
start = time.time()
self.test = dh.loaddata(test_file,
self._word_file_path,
normalize_text=True,
split_hashtag=True,
ignore_profiles=False)
end = time.time()
if (verbose == True):
print('test resource loading time::', (end - start))
self._vocab = self.load_vocab()
start = time.time()
tX, tY, tD, tC, tA = dh.vectorize_word_dimension(
self.test, self._vocab)
tX = dh.pad_sequence_1d(tX, maxlen=self._line_maxlen)
tC = dh.pad_sequence_1d(tC, maxlen=self._line_maxlen)
tD = dh.pad_sequence_1d(tD, maxlen=11)
end = time.time()
if (verbose == True):
print('test resource preparation time::', (end - start))
self.__predict_model([tC, tX, tD], self.test)
def load_train_validation_test_data(self):
print("Loading resource...")
self.train = dh.loaddata(self._train_file,
self._word_file_path,
normalize_text=True,
split_hashtag=True,
ignore_profiles=False,
lowercase=True)
self.validation = dh.loaddata(self._validation_file,
self._word_file_path,
normalize_text=True,
split_hashtag=True,
ignore_profiles=False,
lowercase=True)
if (self._test_file != None):
self.test = dh.loaddata(self._test_file,
self._word_file_path,
normalize_text=True,
split_hashtag=True,
ignore_profiles=True)