IMultipleParametric#
- class anomalearn.algorithms.IMultipleParametric.IMultipleParametric#
Bases:
IParametric
Interface identifying a machine learning parametric model with multiple fit.
This class implements extends the standard IParametric interface to describe a model that can be trained on multiple datasets at the same time. E.g., if we want to train on two different datasets the model we should use the function
models.IMultipleParametric.IMultipleParametric.fit_multiple()
.List of decorated methods
fit_multiple
(x[, y])Fits the model to the given training data.
List of inherited decorated methods
fit
(x[, y])Fits the model to the given training data.
Decorated methods
- abstract fit_multiple(x: list, y: list | None = None, *args, **kwargs) None #
Fits the model to the given training data.
- Parameters:
x (list) – The list of the fitting data to be used. The elements of the list must respect the requirements of
algorithms.IParametric.fit()
.y (list, default=None) – The target for the fitting data. The list must have the same dimension as x. Moreover, y elements are pairwise constrained to x elements as stated in
algorithms.IParametric.fit()
.args – Not used, present to allow multiple inheritance and signature change.
kwargs – Not used, present to allow multiple inheritance and signature change.
- Return type:
None
Inherited decorated methods
- abstract fit(x, y=None, *args, **kwargs) None #
Fits the model to the given training data.
- Parameters:
x (array-like) – The data used for fitting. Data must have at least two dimensions in which the first dimension represent the number of samples.
y (array-like, default=None) – The target for the fitting data. Data must have at least two dimensions in which the first dimension represent the number of samples. Moreover, if not None, the first dimension must be the same as that of x.
args – Not used, present to allow multiple inheritance and signature change.
kwargs – Not used, present to allow multiple inheritance and signature change.
- Return type:
None