def make_config_for_type(self, type: TargetType):
csv_path = create_random_csv(5, 5, 'ABCDE')
config = Config.make_default_config(csv_path=csv_path,
target_name='E',
target_type=type,
train_ratio=0.9)
return config
def test_default_config(self):
random_csv = create_random_csv()
target = 'D'
config = Config.make_default_config(
csv_path=random_csv,
target_name=target,
target_type=TargetType.BINARY_CLASSIFICATION,
train_ratio=0.9)
self.assertIsNotNone(config)
remove_random_csv()
def make_default_config(self) -> Config:
random_csv = create_random_csv()
target = 'D'
config = Config.make_default_config(
csv_path=random_csv,
target_name=target,
target_type=TargetType.BINARY_CLASSIFICATION,
train_ratio=0.9)
return config
def test_custom_config(self):
random_csv = create_random_csv()
target = 'D'
processor = CustomProcessor()
assembler = CustomAssembler()
config = Config.make_custom_config(csv_path=random_csv,
target_name=target,
train_ratio=0.9,
target_processor=processor,
model_assembler=assembler)
self.assertIsNotNone(config)
remove_random_csv()
def test_create_and_remove_random_csv(self):
rows = 5
cols = 5
columns = 'ABCDE'
csv_path = create_random_csv(rows, cols, columns)
exists_csv = os.path.exists(csv_path)
self.assertEqual(exists_csv, True)
df = pd.read_csv(csv_path)
self.__check_dataframe_data(df, rows, cols, columns)
remove_random_csv()
exists_csv = os.path.exists(csv_path)
self.assertEqual(exists_csv, False)
def test_model_embedding_size(self):
random_csv = create_random_csv()
target = 'D'
config = Config.make_default_config(
csv_path=random_csv,
target_name=target,
target_type=TargetType.BINARY_CLASSIFICATION,
train_ratio=0.9)
network = EmbeddingNetwork(config)
for layer in network.model.layers:
if isinstance(layer, Embedding):
embedding_size = int(layer.embeddings.initial_value.shape[1])
self.assertEqual(
get_embedding_size(config.df[layer.name].nunique()),
embedding_size)
remove_random_csv()