def test_targetvalidator_continuous_multioutput(input_data_targettest):
assert type_of_target(input_data_targettest) == 'continuous-multioutput'
validator = TargetValidator(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_inversetransform():
"""
Test that the encoding/decoding works in 1D
"""
validator = TargetValidator(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 = TargetValidator(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_targetvalidator_multilabel(input_data_targettest):
assert type_of_target(input_data_targettest) == 'multilabel-indicator'
validator = TargetValidator(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 = TargetValidator(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_targetvalidator_inversetransform():
"""
Test that the encoding/decoding works in 1D
"""
validator = TargetValidator(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()
validator = TargetValidator(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)
def test_is_single_column_target():
validator = TargetValidator(is_classification=True)
validator.fit(np.array([1, 2, 3, 4]))
assert validator.is_single_column_target()
validator = TargetValidator(is_classification=True)
validator.fit(np.array([[1, 0, 1, 0], [1, 1, 1, 1]]))
assert not validator.is_single_column_target()
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 = TargetValidator()
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 = TargetValidator(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 = TargetValidator(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 = TargetValidator(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)
class InputValidator(BaseEstimator):
"""
Makes sure the input data complies with Auto-sklearn requirements.
Categorical inputs are encoded via a Label Encoder, if the input
is a dataframe.
This class also perform checks for data integrity and flags the user
via informative errors.
Attributes
----------
feat_type: typing.Optional[typing.List[str]]
In case the dataset is not a pandas DataFrame:
+ If provided, this list indicates which columns should be treated as categorical
it is internally transformed into a dictionary that indicates a mapping from
column index to categorical/numerical
+ If not provided, by default all columns are treated as numerical
If the input dataset is of type pandas dataframe, this argument
must be none, as the column type will be inferred from the pandas dtypes.
is_classification: bool
For classification task, this flag indicates that the target data
should be encoded
feature_validator: FeatureValidator
A FeatureValidator instance used to validate and encode feature columns to match
sklearn expectations on the data
target_validator: TargetValidator
A TargetValidator instance used to validate and encode (in case of classification)
the target values
"""
def __init__(
self,
feat_type: typing.Optional[typing.List[str]] = None,
is_classification: bool = False,
logger_port: typing.Optional[int] = None,
) -> None:
self.feat_type = feat_type
self.is_classification = is_classification
self.logger_port = logger_port
if self.logger_port is not None:
self.logger = get_named_client_logger(
name='Validation',
port=self.logger_port,
)
else:
self.logger = logging.getLogger('Validation')
self.feature_validator = FeatureValidator(feat_type=self.feat_type,
logger=self.logger)
self.target_validator = TargetValidator(
is_classification=self.is_classification, logger=self.logger)
self._is_fitted = False
def fit(
self,
X_train: SUPPORTED_FEAT_TYPES,
y_train: SUPPORTED_TARGET_TYPES,
X_test: typing.Optional[SUPPORTED_FEAT_TYPES] = None,
y_test: typing.Optional[SUPPORTED_TARGET_TYPES] = None,
) -> BaseEstimator:
"""
Validates and fit a categorical encoder (if needed) to the features, and
a encoder for targets in the case of classification. Specifically:
For features:
+ Valid data types are enforced (List, np.ndarray, pd.DataFrame, pd.Series, scipy
sparse) as well as dimensionality checks
+ If the provided data is a pandas DataFrame with categorical/boolean/int columns,
such columns will be encoded using an Ordinal Encoder
For targets:
+ Checks for dimensionality as well as missing values are performed.
+ If performing a classification task, the data is going to be encoded
Parameters
----------
X_train: SUPPORTED_FEAT_TYPES
A set of features that are going to be validated (type and dimensionality
checks). If this data contains categorical columns, an encoder is going to
be instantiated and trained with this data.
y_train: SUPPORTED_TARGET_TYPES
A set of targets that are going to be encoded if the task is for classification
X_test: typing.Optional[SUPPORTED_FEAT_TYPES]
A hold out set of features used for checking
y_test: SUPPORTED_TARGET_TYPES
A hold out set of targets used for checking. Additionally, if the current task
is a classification task, this y_test categories are also going to be used to
fit a pre-processing encoding (to prevent errors on unseen classes).
Returns
-------
self
"""
# Check that the data is valid
if np.shape(X_train)[0] != np.shape(y_train)[0]:
raise ValueError(
"Inconsistent number of train datapoints for features and targets,"
" {} for features and {} for targets".format(
np.shape(X_train)[0],
np.shape(y_train)[0],
))
if X_test is not None and np.shape(X_test)[0] != np.shape(y_test)[0]:
raise ValueError(
"Inconsistent number of test datapoints for features and targets,"
" {} for features and {} for targets".format(
np.shape(X_test)[0],
np.shape(y_test)[0],
))
self.feature_validator.fit(X_train, X_test)
self.target_validator.fit(y_train, y_test)
self._is_fitted = True
return self
def transform(
self,
X: SUPPORTED_FEAT_TYPES,
y: typing.Optional[SUPPORTED_TARGET_TYPES] = None,
) -> typing.Tuple[np.ndarray, typing.Optional[np.ndarray]]:
"""
Transform the given target or features to a numpy array
Parameters
----------
X: SUPPORTED_FEAT_TYPES
A set of features to transform
y: typing.Optional[SUPPORTED_TARGET_TYPES]
A set of targets to transform
Return
------
np.ndarray:
The transformed features array
np.ndarray:
The transformed targets array
"""
if not self._is_fitted:
raise NotFittedError(
"Cannot call transform on a validator that is not fitted")
X_transformed = self.feature_validator.transform(X)
if y is not None:
return X_transformed, self.target_validator.transform(y)
else:
return X_transformed, y
def test_target_unsupported():
"""
Makes sure we raise a proper message to the user,
when providing not supported data input
"""
validator = TargetValidator(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"Auto-sklearn 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 Sklearn"):
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]))