def test__load_files(self):
tp = TopicProcessor()
statements, topics = tp._load_files()
if not len(statements):
self.fail()
def test__build_dictionary(self):
tp = TopicProcessor()
_, topics = tp._load_files()
dictionary, reverse_dictionary, num_topics = tp._build_dictionarys(topics)
if not len(dictionary) > 1:
self.fail()
def test__create_tokenizer(self):
tp = TopicProcessor()
statements, _ = tp._load_files()
tokenizer = tp._create_tokenizer(statements)
if not isinstance(tokenizer, keras.preprocessing.text.Tokenizer):
self.fail()
def test__vectorize_text(self):
tp = TopicProcessor()
statements, _ = tp._load_files()
vectorized_text = tp._vectorize_text(statements)
self.assertNotEqual(statements, vectorized_text)
def test__clean_text(self):
tp = TopicProcessor()
statements_1, topics_1 = tp._load_files()
statements_2, topics_2 = tp._clean_text(statements_1, topics_1)
self.assertNotEqual(statements_1, statements_2)