mlens.utils.exceptions module

ML-ENSEMBLE

Exception handling classes.

exception mlens.utils.exceptions.DataConversionWarning

Bases: UserWarning

Warning used to notify implicit data conversions happening in the code.

This warning occurs when some input data needs to be converted or interpreted in a way that may not match the user’s expectations.

For example, this warning may occur when the user

• passes an integer array to a function which expects float input and will convert the input
• requests a non-copying operation, but a copy is required to meet the implementation’s data-type expectations;
• passes an input whose shape can be interpreted ambiguously.

Changed in version 0.18: Moved from sklearn.utils.validation.

Note

imported from Scikit-learn for validation compatibility.

exception mlens.utils.exceptions.EfficiencyWarning

Bases: UserWarning

Warning used to notify the user of inefficient computation.

This warning notifies the user that the efficiency may not be optimal due to some reason which may be included as a part of the warning message. This may be subclassed into a more specific Warning class.

New in version 0.18.

Note

imported from Scikit-learn for validation compatibility

exception mlens.utils.exceptions.FitFailedError

Bases: RuntimeError, TypeError

Error for failed estimator ‘fit’ call.

Inherits type error to accommodate Scikit-learn expectation of a TypeError on failed array checks in estimators.

exception mlens.utils.exceptions.FitFailedWarning

Bases: RuntimeWarning

Warning for a failed estimator ‘fit’ call.

exception mlens.utils.exceptions.InputDataWarning

Bases: UserWarning

Warning used to notify that an array does not behave as expected.

Raised if data looks suspicious, but not outright fatal. Used sparingly, as it is often better to raise an error if input does not look like expected. Debugging corrupt data during parallel estimation is difficult and requires knowledge of backend operations.

exception mlens.utils.exceptions.LayerSpecificationError

Bases: TypeError, ValueError

Error class for incorrectly specified layers.

exception mlens.utils.exceptions.LayerSpecificationWarning

Bases: UserWarning

Warning class if layer has been specified in a dubious form.

This warning is raised when the input does not look like expected, but is not fatal and a best guess of how to fix it will be made.

exception mlens.utils.exceptions.NonBLASDotWarning

Bases: mlens.utils.exceptions.EfficiencyWarning

Warning used when the dot operation does not use BLAS.

FROM SCIKIT-LEARN

This warning is used to notify the user that BLAS was not used for dot operation and hence the efficiency may be affected.

Changed in version 0.18: Moved from sklearn.utils.validation, extends EfficiencyWarning.

Note

imported from Scikit-learn for validation compatibility

exception mlens.utils.exceptions.NotFittedError

Bases: ValueError, AttributeError

Error class for an ensemble or estimator that is not fitted yet

Raised when some method has been called that expects the instance to be fitted.

exception mlens.utils.exceptions.ParallelProcessingError

Bases: AttributeError, RuntimeError

Error class for fatal errors related to ParallelProcessing.

Can be subclassed for more specific error classes.

exception mlens.utils.exceptions.ParallelProcessingWarning

Bases: UserWarning

Warnings related to methods on ParallelProcessing.

Can be subclassed for more specific warning classes.

exception mlens.utils.exceptions.PredictFailedError

Bases: RuntimeError, TypeError

Error for a failed estimator ‘predict’ call.

Inherits type error to accommodate Scikit-learn expectation of a TypeError on failed array checks in estimators.

exception mlens.utils.exceptions.PredictFailedWarning

Bases: RuntimeWarning

Warning for a failed estimator ‘predict’ call.