def test_valid_predict_data_formats(self, mock_open, mock_load_model):
def _valid_check(data):
try:
print("\tChecking data format: {}".format(str(type(data))))
data = BaseDataLabeler._check_and_return_valid_data_format(
data, fit_or_predict='predict')
except Exception as e:
self.fail("Exception raised on input of accepted types.")
return data
valid_data = [
CSVData(data=pd.DataFrame([])),
JSONData(data=pd.DataFrame([])),
ParquetData(data=pd.DataFrame([])),
AVROData(data=pd.DataFrame([])),
pd.DataFrame([]),
list(),
np.array([]),
pd.Series([], dtype=object)
]
print("\nValid Data Predict Checks:")
for data in valid_data:
data = _valid_check(data)
self.assertTrue(
isinstance(data, np.ndarray) or isinstance(data, pd.Series)
or isinstance(data, pd.DataFrame))
def test_valid_fit_data_formats(self, *mocks):
def _valid_check(data):
try:
print("\tChecking data format: {}".format(str(type(data))))
data = UnstructuredDataLabeler._check_and_return_valid_data_format(
data, fit_or_predict="fit")
except Exception as e:
self.fail("Exception raised on input of accepted types.")
return data
valid_data = [
CSVData(data=pd.DataFrame([])),
JSONData(data=pd.DataFrame([])),
ParquetData(data=pd.DataFrame([])),
AVROData(data=pd.DataFrame([])),
pd.DataFrame([]),
list(),
np.array([]),
]
print("\nValid Data Fit Checks:")
for data in valid_data:
data = _valid_check(data)
self.assertIsInstance(data, np.ndarray)