def _invalid_check(data):
with self.assertRaisesRegex(
TypeError,
"Data must be imported using the "
"data_readers, pd.DataFrames, "
"np.ndarrays, or lists.",
):
BaseDataLabeler._check_and_return_valid_data_format(data)
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
def _invalid_check(data):
with self.assertRaisesRegex(
TypeError, "Data must either be imported using "
"the data_readers or pd.DataFrame."):
BaseDataLabeler._check_and_return_valid_data_format(data)
def test_check_and_return_valid_data_format(self):
# test incorrect fit_or_predict value
with self.assertRaisesRegex(ValueError, '`fit_or_predict` must equal '
'`fit` or `predict`'):
BaseDataLabeler._check_and_return_valid_data_format([], 'oops')
# test incorrect data type
with self.assertRaisesRegex(TypeError, "Data must be imported using the"
" data_readers, pd.DataFrames, "
"np.ndarrays, or lists."):
BaseDataLabeler._check_and_return_valid_data_format('oops')
# test proper conversion of 2 dimensional structured data
two_dim = [["this", "is"], ["two", "dimensions"]]
two_dim_pred = np.array(["this", "is", "two", "dimensions"])
# for fit
self.assertTrue(
np.array_equal(np.array(two_dim),
BaseDataLabeler._check_and_return_valid_data_format(
two_dim, fit_or_predict='fit')))
self.assertTrue(
np.array_equal(np.array(two_dim),
BaseDataLabeler._check_and_return_valid_data_format(
pd.DataFrame(two_dim), fit_or_predict='fit')))
self.assertTrue(
np.array_equal(np.array(two_dim),
BaseDataLabeler._check_and_return_valid_data_format(
np.array(two_dim), fit_or_predict='fit')))
# for predict
self.assertTrue(
np.array_equal(two_dim_pred,
BaseDataLabeler._check_and_return_valid_data_format(
two_dim, fit_or_predict='predict')))
self.assertTrue(
np.array_equal(two_dim_pred,
BaseDataLabeler._check_and_return_valid_data_format(
pd.DataFrame(two_dim), fit_or_predict='predict')))
self.assertTrue(
np.array_equal(two_dim_pred,
BaseDataLabeler._check_and_return_valid_data_format(
np.array(two_dim), fit_or_predict='predict')))
# test proper conversion of 1 dimensional data
one_dim = ["this", "is", "one", "dimension"]
one_dim_pred = np.array(one_dim)
# for fit
self.assertTrue(
np.array_equal(np.array(one_dim),
BaseDataLabeler._check_and_return_valid_data_format(
one_dim, fit_or_predict='fit')))
self.assertTrue(
np.array_equal(np.array(one_dim),
BaseDataLabeler._check_and_return_valid_data_format(
pd.Series(one_dim), fit_or_predict='fit')))
self.assertTrue(
np.array_equal(np.array(one_dim),
BaseDataLabeler._check_and_return_valid_data_format(
np.array(one_dim), fit_or_predict='fit')))
# for predict
self.assertTrue(
np.array_equal(one_dim_pred,
BaseDataLabeler._check_and_return_valid_data_format(
one_dim, fit_or_predict='predict')))
self.assertTrue(
np.array_equal(one_dim_pred,
BaseDataLabeler._check_and_return_valid_data_format(
pd.DataFrame(one_dim), fit_or_predict='predict')))
self.assertTrue(
np.array_equal(one_dim_pred,
BaseDataLabeler._check_and_return_valid_data_format(
np.array(one_dim), fit_or_predict='predict')))
# test proper conversion of unstructured labels
labels = [[(0, 4, "UNKNOWN"), (4, 10, "ADDRESS")],
[(0, 5, "SSN"), (5, 8, "UNKNOWN")]]
validated_labels = \
BaseDataLabeler._check_and_return_valid_data_format(labels)
self.assertIsInstance(validated_labels, np.ndarray)
self.assertEqual(len(validated_labels), 2)
self.assertEqual(len(validated_labels[0]), 2)
self.assertEqual(len(validated_labels[0][0]), 3)
self.assertEqual(validated_labels[0][0][0], 0)
self.assertEqual(validated_labels[0][1][1], 10)
self.assertEqual(validated_labels[1][0][2], "SSN")
# test proper conversion of data reader objects
for dt in ["csv", "json", "parquet"]:
data_obj = dp.Data(data=pd.DataFrame(two_dim), data_type=dt)
val = BaseDataLabeler._check_and_return_valid_data_format(data_obj)
self.assertTrue(np.array_equal(np.array(two_dim), val))