def test_targetvalidator_inversetransform():
"""
Test that the encoding/decoding works in 1D
"""
validator = TabularTargetValidator(is_classification=True)
validator.fit(
pd.DataFrame(data=['a', 'a', 'b', 'c', 'a'], dtype='category'), )
y = validator.transform(
pd.DataFrame(data=['a', 'a', 'b', 'c', 'a'], dtype='category'), )
np.testing.assert_array_almost_equal(np.array([0, 0, 1, 2, 0]), y)
y_decoded = validator.inverse_transform(y)
assert ['a', 'a', 'b', 'c', 'a'] == y_decoded.tolist()
assert validator.classes_.tolist() == ['a', 'b', 'c']
validator = TabularTargetValidator(is_classification=True)
multi_label = pd.DataFrame(np.array([[1, 0, 0, 1], [0, 0, 1, 1],
[0, 0, 0, 0]]),
dtype=bool)
validator.fit(multi_label)
y = validator.transform(multi_label)
y_decoded = validator.inverse_transform(y)
np.testing.assert_array_almost_equal(y, y_decoded)
# Multilabel classification is not encoded
# For this reason, classes_ attribute does not contain a class
np.testing.assert_array_almost_equal(validator.classes_, np.array([]))
def test_is_single_column_target():
validator = TabularTargetValidator(is_classification=True)
validator.fit(np.array([1, 2, 3, 4]))
assert validator.is_single_column_target()
validator = TabularTargetValidator(is_classification=True)
validator.fit(np.array([[1, 0, 1, 0], [1, 1, 1, 1]]))
assert not validator.is_single_column_target()
def test_targetvalidator_continuous_multioutput(input_data_targettest):
assert type_of_target(input_data_targettest) == 'continuous-multioutput'
validator = TabularTargetValidator(is_classification=False)
# Test the X_test also!
validator.fit(input_data_targettest, input_data_targettest)
transformed_y = validator.transform(input_data_targettest)
assert type_of_target(transformed_y) == 'continuous-multioutput'
def test_targetvalidator_multilabel(input_data_targettest):
assert type_of_target(input_data_targettest) == 'multilabel-indicator'
validator = TabularTargetValidator(is_classification=True)
# Test the X_test also!
validator.fit(input_data_targettest, input_data_targettest)
transformed_y = validator.transform(input_data_targettest)
assert type_of_target(transformed_y) == 'multilabel-indicator'
def test_targetvalidator_supported_types_noclassification(
input_data_targettest):
validator = TabularTargetValidator(is_classification=False)
validator.fit(input_data_targettest)
transformed_y = validator.transform(input_data_targettest)
if sparse.issparse(input_data_targettest):
assert sparse.issparse(transformed_y)
else:
assert isinstance(transformed_y, np.ndarray)
epected_shape = np.shape(input_data_targettest)
if len(epected_shape) > 1 and epected_shape[1] == 1:
# The target should have (N,) dimensionality instead of (N, 1)
epected_shape = (epected_shape[0], )
assert epected_shape == np.shape(transformed_y)
assert np.issubdtype(transformed_y.dtype, np.number)
assert validator._is_fitted
# Because there is no classification, we do not expect a encoder
assert validator.encoder is None
if hasattr(input_data_targettest, "iloc"):
np.testing.assert_array_equal(
np.ravel(input_data_targettest.to_numpy()),
np.ravel(transformed_y))
elif sparse.issparse(input_data_targettest):
np.testing.assert_array_equal(
np.ravel(input_data_targettest.todense()),
np.ravel(transformed_y.todense()))
else:
np.testing.assert_array_equal(
np.ravel(np.array(input_data_targettest)), np.ravel(transformed_y))
def test_type_of_target_unsupported(input_data_targettest):
"""
Makes sure we raise a proper message to the user,
when providing not supported data input
"""
validator = TabularTargetValidator()
with pytest.raises(ValueError,
match=r"legacy multi-.* data representation."):
validator.fit(input_data_targettest)
def test_targetvalidator_supported_types_classification(input_data_targettest):
validator = TabularTargetValidator(is_classification=True)
validator.fit(input_data_targettest)
transformed_y = validator.transform(input_data_targettest)
if sparse.issparse(input_data_targettest):
assert sparse.issparse(transformed_y)
else:
assert isinstance(transformed_y, np.ndarray)
epected_shape = np.shape(input_data_targettest)
if len(epected_shape) > 1 and epected_shape[1] == 1:
# The target should have (N,) dimensionality instead of (N, 1)
epected_shape = (epected_shape[0], )
assert epected_shape == np.shape(transformed_y)
assert np.issubdtype(transformed_y.dtype, np.number)
assert validator._is_fitted
# Because there is no classification, we do not expect a encoder
if not sparse.issparse(input_data_targettest):
assert validator.encoder is not None
# The encoding should be per column
if len(transformed_y.shape) == 1:
assert np.min(transformed_y) == 0
assert np.max(transformed_y) == len(np.unique(transformed_y)) - 1
else:
for col in range(transformed_y.shape[1]):
assert np.min(transformed_y[:, col]) == 0
assert np.max(transformed_y[:, col]) == len(
np.unique(transformed_y[:, col])) - 1
# Make sure we can perform inverse transform
y_inverse = validator.inverse_transform(transformed_y)
if hasattr(input_data_targettest, 'dtype'):
# In case of numeric, we need to make sure dtype is preserved
if is_numeric_dtype(input_data_targettest.dtype):
assert y_inverse.dtype == input_data_targettest.dtype
# Then make sure every value is properly inverse-transformed
np.testing.assert_array_equal(np.array(y_inverse),
np.array(input_data_targettest))
elif hasattr(input_data_targettest, 'dtypes'):
if is_numeric_dtype(input_data_targettest.dtypes[0]):
assert y_inverse.dtype == input_data_targettest.dtypes[0]
# Then make sure every value is properly inverse-transformed
np.testing.assert_array_equal(
np.array(y_inverse),
# pandas is always (N, 1) but targets are ravel()
input_data_targettest.to_numpy().reshape(-1))
else:
# Sparse is not encoded, mainly because the sparse data is expected
# to be numpy of numerical type -- which currently does not require encoding
np.testing.assert_array_equal(
np.ravel(input_data_targettest.todense()),
np.ravel(transformed_y.todense()))
def test_unknown_categories_in_targets(input_data_targettest):
validator = TabularTargetValidator(is_classification=True)
validator.fit(input_data_targettest)
# Add an extra category
if isinstance(input_data_targettest, list):
input_data_targettest.append(input_data_targettest[-1] + 5000)
elif isinstance(input_data_targettest, (pd.DataFrame, pd.Series)):
input_data_targettest.iloc[-1] = 5000
elif isinstance(input_data_targettest, np.ndarray):
input_data_targettest[-1] = 5000
x_t = validator.transform(input_data_targettest)
assert x_t[-1].item(0) == -1
def test_targetvalidator_fitontypeA_transformtypeB(input_data_targettest):
"""
Check if we can fit in a given type (numpy) yet transform
if the user changes the type (pandas then)
This is problematic only in the case we create an encoder
"""
validator = TabularTargetValidator(is_classification=True)
validator.fit(input_data_targettest)
if isinstance(input_data_targettest, pd.DataFrame):
complementary_type = input_data_targettest.to_numpy()
elif isinstance(input_data_targettest, pd.Series):
complementary_type = pd.DataFrame(input_data_targettest)
elif isinstance(input_data_targettest, np.ndarray):
complementary_type = pd.DataFrame(input_data_targettest)
elif isinstance(input_data_targettest, list):
complementary_type = pd.DataFrame(input_data_targettest)
validator.transform(complementary_type)
def __init__(
self,
is_classification: bool = False,
logger_port: Optional[int] = None,
) -> None:
self.is_classification = is_classification
self.logger_port = logger_port
if self.logger_port is not None:
self.logger: Union[
logging.Logger,
PicklableClientLogger] = get_named_client_logger(
name='Validation',
port=self.logger_port,
)
else:
self.logger = logging.getLogger('Validation')
self.feature_validator = TabularFeatureValidator(logger=self.logger)
self.target_validator = TabularTargetValidator(
is_classification=self.is_classification, logger=self.logger)
self._is_fitted = False
def test_target_unsupported():
"""
Makes sure we raise a proper message to the user,
when providing not supported data input
"""
validator = TabularTargetValidator(is_classification=True)
with pytest.raises(
ValueError,
match=r"The dimensionality of the train and test targets"):
validator.fit(
np.array([[0, 1, 0], [0, 1, 1]]),
np.array([[0, 1, 0, 0], [0, 1, 1, 1]]),
)
with pytest.raises(
ValueError,
match=r"Train and test targets must both have the same dtypes"):
validator.fit(
pd.DataFrame({'a': [1, 2, 3]}),
pd.DataFrame({'a': [True, False, False]}),
)
with pytest.raises(ValueError,
match=r"Provided targets are not supported.*"):
validator.fit(
np.array([[0, 1, 2], [0, 3, 4]]),
np.array([[0, 1, 2, 5], [0, 3, 4, 6]]),
)
with pytest.raises(ValueError,
match="Train and test targets must both have the same"):
validator.fit(
pd.DataFrame({'string': ['foo']}),
pd.DataFrame({'int': [1]}),
)
with pytest.raises(ValueError,
match=r"AutoPyTorch only supports Numpy arrays, .*"):
validator.fit({'input1': 1, 'input2': 2})
with pytest.raises(
ValueError,
match=r"arget values cannot contain missing/NaN values"):
validator.fit(np.array([np.nan, 1, 2]))
with pytest.raises(
ValueError,
match=r"arget values cannot contain missing/NaN values"):
validator.fit(sparse.csr_matrix(np.array([1, 2, np.nan])))
with pytest.raises(
ValueError,
match=r"Cannot call transform on a validator that is not fit"):
validator.transform(np.array([1, 2, 3]))
with pytest.raises(
ValueError,
match=r"Cannot call inverse_transform on a validator that is"):
validator.inverse_transform(np.array([1, 2, 3]))
with pytest.raises(
ValueError,
match=r"Multi-dimensional classification is not yet supported"):
validator._fit(np.array([[1, 2, 3], [1, 5, 6]]))
# Dia/ DOK are not supported as type of target makes calls len on the array
# which causes TypeError: len() of unsized object. Basically, sparse data as
# multi-label is the only thing that makes sense in this format.
with pytest.raises(
ValueError,
match=r"The provided data could not be interpreted by AutoPyTorch"
):
validator.fit(sparse.dia_matrix(np.array([1, 2, 3])))
validator.fit(np.array([[0, 1, 0], [0, 1, 1]]))
with pytest.raises(ValueError, match=r"Number of outputs changed from"):
validator.fit(np.array([0, 1, 0]))