nemos.regularizer.ElasticNet#

class nemos.regularizer.ElasticNet[source]#

Bases: Regularizer

Regularizer class for Elastic Net (L1 + L2 regularization).

The Elastic Net penalty [3] [4] is defined as:

\[P(\beta) = \alpha \left((1 - \lambda) \frac{1}{2} ||\beta||_{\ell_2}^2 + \lambda ||\beta||_{\ell_1} \right)\]

where \(\alpha\) is the regularizer strength, and \(\lambda\) is the regularizer ratio. The regularizer ratio controls the balance between L1 (Lasso) and L2 (Ridge) regularization, where \(\lambda = 0\) is equivalent to Ridge regularization and \(\lambda = 1\) is equivalent to Lasso regularization.

This class equips models with the Elastic Net proximal operator and the Elastic Net penalized loss function.

References

Attributes

`allowed_solvers`
`default_solver`

__init__()#

Methods

`__init__`()
`allow_solver`(algo_name)	Add an algorithm to the list of compatible solvers.
`check_solver`(solver_name)	Raise an error if the given solver is not allowed.
`get_params`([deep])	From scikit-learn, get parameters by inspecting init.
`get_proximal_operator`(params, strength)	Retrieve the proximal operator.
`penalized_loss`(loss, params, strength)	Return a function for calculating the penalized loss.
`set_params`(**params)	Set the parameters of this estimator.

classmethod __init_subclass__(**kwargs)#

Set the set_{method}_request methods.

This uses PEP-487 [1] to set the set_{method}_request methods. It looks for the information available in the set default values which are set using __metadata_request__* class attributes, or inferred from method signatures.

The __metadata_request__* class attributes are used when a method does not explicitly accept a metadata through its arguments or if the developer would like to specify a request value for those metadata which are different from the default None.

References

classmethod allow_solver(algo_name)#

Add an algorithm to the list of compatible solvers.

Parameters:: algo_name (str) – Name of the optimization algorithm to add.
Return type:: None

property allowed_solvers: Tuple[str]#

check_solver(solver_name)#

Raise an error if the given solver is not allowed.

Return type:: None
Parameters:: solver_name (str)

property default_solver: str#

get_metadata_routing()#

Get metadata routing of this object.

Please check User Guide on how the routing mechanism works.

Returns:: routing – A MetadataRequest encapsulating routing information.
Return type:: MetadataRequest

get_params(deep=True)#

From scikit-learn, get parameters by inspecting init.

Parameters:: deep – If True, will return the parameters for this estimator and contained subobjects that are estimators.
Return type:: dict
Returns:: A dictionary containing the parameters. Key is the parameter name, value is the parameter value.

get_proximal_operator(params, strength)#

Retrieve the proximal operator.

Parameters:

params (Any) – The parameters to be regularized.
strength (Any)

Return type:

Callable[[Any, float, float], Tuple[Array, Array]]

Returns:

The proximal operator, applying regularization to the provided parameters.

penalized_loss(loss, params, strength)#

Return a function for calculating the penalized loss.

Return type:

Callable

Parameters:

loss (Callable)
params (Any)
strength (Any)

set_params(**params)#

Set the parameters of this estimator.

The method works on simple estimators as well as on nested objects (such as Pipeline). The latter have parameters of the form <component>__<parameter> so that it’s possible to update each component of a nested object.

Parameters:: **params (Any) – Estimator parameters.
Returns:: self – Estimator instance.
Return type:: estimator instance