Logistic estimators (binomial)

Binomial logistic datafit (cross-entropy loss with sigmoid link). Solved via prox-Newton outer iterations around the M1 LS coordinate descent inner solver — see Concepts: Datafits for the algorithm.

All classes share predict (class labels {0, 1}), predict_proba (P(y=1)), and decision_function (η = Xβ + α) inherited from the logistic base class.

Scalar — single λ

class skein_glm.estimators.LogisticMCPRegressor(lambda_=0.1, gamma=3.0, *, weights=None, max_iter=100, tol=1e-06, fit_intercept=True, standardize=False, acceleration=5, max_outer=10, outer_tol=1e-06)

Bases: _LogisticRegressorBase

Logistic regression with MCP penalty at a single λ (prox-Newton).

Parameters:

• lambda_ (float)

• gamma (float)

• weights (NDArray[np.float64] | None)

• max_iter (int)

• tol (float)

• fit_intercept (bool)

• standardize (bool)

• acceleration (int | None)

• max_outer (int)

• outer_tol (float)

set_decision_function_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the decision_function method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to decision_function if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to decision_function.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in decision_function.

• self (LogisticMCPRegressor)

Returns:

self – The updated object.

Return type:

object

set_fit_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the fit method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to fit if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to fit.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in fit.

• self (LogisticMCPRegressor)

Returns:

self – The updated object.

Return type:

object

set_predict_proba_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the predict_proba method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to predict_proba if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to predict_proba.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in predict_proba.

• self (LogisticMCPRegressor)

Returns:

self – The updated object.

Return type:

object

set_predict_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the predict method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to predict if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to predict.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in predict.

• self (LogisticMCPRegressor)

Returns:

self – The updated object.

Return type:

object

class skein_glm.estimators.LogisticSCADRegressor(lambda_=0.1, a=3.7, *, weights=None, max_iter=100, tol=1e-06, fit_intercept=True, standardize=False, acceleration=5, max_outer=10, outer_tol=1e-06)

Bases: _LogisticRegressorBase

Logistic regression with SCAD penalty at a single λ.

Parameters:

• lambda_ (float)

• a (float)

• weights (NDArray[np.float64] | None)

• max_iter (int)

• tol (float)

• fit_intercept (bool)

• standardize (bool)

• acceleration (int | None)

• max_outer (int)

• outer_tol (float)

set_decision_function_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the decision_function method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to decision_function if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to decision_function.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in decision_function.

• self (LogisticSCADRegressor)

Returns:

self – The updated object.

Return type:

object

set_fit_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the fit method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to fit if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to fit.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in fit.

• self (LogisticSCADRegressor)

Returns:

self – The updated object.

Return type:

object

set_predict_proba_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the predict_proba method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to predict_proba if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to predict_proba.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in predict_proba.

• self (LogisticSCADRegressor)

Returns:

self – The updated object.

Return type:

object

set_predict_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the predict method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to predict if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to predict.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in predict.

• self (LogisticSCADRegressor)

Returns:

self – The updated object.

Return type:

object

class skein_glm.estimators.LogisticElasticNetRegressor(lambda_=0.1, alpha=0.5, *, weights=None, max_iter=100, tol=1e-06, fit_intercept=True, standardize=False, acceleration=5, max_outer=10, outer_tol=1e-06)

Bases: _LogisticRegressorBase

Logistic regression with elastic-net penalty at a single λ.

Convex penalty α λ |β_j| + (1 - α) λ β_j² / 2 per feature. alpha = 1 is pure logistic lasso; alpha = 0 is ridge. The LogisticLassoRegressor subclass pins alpha = 1 for convenience.

Solver: prox-Newton with the existing weighted-LS surrogate (build_glm_path_outputs) — same machinery as the MCP / SCAD siblings, but with a convex ElasticNet penalty so the path is one-shot rather than the LLA outer loop. max_outer / outer_tol still control the prox-Newton iteration count.

Parameters:

• lambda_ (float)

• alpha (float)

• weights (NDArray[np.float64] | None)

• max_iter (int)

• tol (float)

• fit_intercept (bool)

• standardize (bool)

• acceleration (int | None)

• max_outer (int)

• outer_tol (float)

set_decision_function_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the decision_function method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to decision_function if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to decision_function.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in decision_function.

• self (LogisticElasticNetRegressor)

Returns:

self – The updated object.

Return type:

object

set_fit_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the fit method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to fit if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to fit.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in fit.

• self (LogisticElasticNetRegressor)

Returns:

self – The updated object.

Return type:

object

set_predict_proba_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the predict_proba method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to predict_proba if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to predict_proba.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in predict_proba.

• self (LogisticElasticNetRegressor)

Returns:

self – The updated object.

Return type:

object

set_predict_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the predict method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to predict if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to predict.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in predict.

• self (LogisticElasticNetRegressor)

Returns:

self – The updated object.

Return type:

object

class skein_glm.estimators.LogisticLassoRegressor(lambda_=0.1, *, weights=None, max_iter=100, tol=1e-06, fit_intercept=True, standardize=False, acceleration=5, max_outer=10, outer_tol=1e-06)

Bases: LogisticElasticNetRegressor

Logistic regression with L1 penalty at a single λ.

Convex L1 — proper logistic lasso via prox-Newton with the ElasticNet penalty pinned to alpha = 1. Use this rather than LogisticMCPRegressor at very large gamma; the latter pays for nonconvex LLA machinery to approximate this convex problem.

Parameters:

• lambda_ (float)

• weights (NDArray[np.float64] | None)

• max_iter (int)

• tol (float)

• fit_intercept (bool)

• standardize (bool)

• acceleration (int | None)

• max_outer (int)

• outer_tol (float)

set_decision_function_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the decision_function method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to decision_function if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to decision_function.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in decision_function.

• self (LogisticLassoRegressor)

Returns:

self – The updated object.

Return type:

object

set_fit_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the fit method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to fit if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to fit.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in fit.

• self (LogisticLassoRegressor)

Returns:

self – The updated object.

Return type:

object

set_predict_proba_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the predict_proba method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to predict_proba if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to predict_proba.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in predict_proba.

• self (LogisticLassoRegressor)

Returns:

self – The updated object.

Return type:

object

set_predict_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the predict method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to predict if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to predict.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in predict.

• self (LogisticLassoRegressor)

Returns:

self – The updated object.

Return type:

object

Scalar — path

class skein_glm.estimators.LogisticMCPPathRegressor(gamma=3.0, *, lambdas=None, n_lambdas=100, lambda_min_ratio=0.001, weights=None, sample_weights=None, max_iter=100, tol=1e-06, fit_intercept=True, standardize=False, acceleration=5, max_outer=10, outer_tol=1e-06)

Bases: _LogisticPathRegressorBase

Logistic regression with MCP penalty along an entire λ-path.

Parameters:

• gamma (float)

• lambdas (NDArray[np.float64] | None)

• n_lambdas (int)

• lambda_min_ratio (float)

• weights (NDArray[np.float64] | None)

• sample_weights (NDArray[np.float64] | None)

• max_iter (int)

• tol (float)

• fit_intercept (bool)

• standardize (bool)

• acceleration (int | None)

• max_outer (int)

• outer_tol (float)

set_decision_function_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the decision_function method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to decision_function if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to decision_function.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in decision_function.

• self (LogisticMCPPathRegressor)

Returns:

self – The updated object.

Return type:

object

set_fit_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the fit method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to fit if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to fit.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in fit.

• self (LogisticMCPPathRegressor)

Returns:

self – The updated object.

Return type:

object

set_predict_proba_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the predict_proba method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to predict_proba if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to predict_proba.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in predict_proba.

• self (LogisticMCPPathRegressor)

Returns:

self – The updated object.

Return type:

object

set_predict_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the predict method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to predict if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to predict.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in predict.

• self (LogisticMCPPathRegressor)

Returns:

self – The updated object.

Return type:

object

class skein_glm.estimators.LogisticSCADPathRegressor(a=3.7, *, lambdas=None, n_lambdas=100, lambda_min_ratio=0.001, weights=None, sample_weights=None, max_iter=100, tol=1e-06, fit_intercept=True, standardize=False, acceleration=5, max_outer=10, outer_tol=1e-06)

Bases: _LogisticPathRegressorBase

Logistic regression with SCAD penalty along an entire λ-path.

Parameters:

• a (float)

• lambdas (NDArray[np.float64] | None)

• n_lambdas (int)

• lambda_min_ratio (float)

• weights (NDArray[np.float64] | None)

• sample_weights (NDArray[np.float64] | None)

• max_iter (int)

• tol (float)

• fit_intercept (bool)

• standardize (bool)

• acceleration (int | None)

• max_outer (int)

• outer_tol (float)

set_decision_function_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the decision_function method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to decision_function if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to decision_function.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in decision_function.

• self (LogisticSCADPathRegressor)

Returns:

self – The updated object.

Return type:

object

set_fit_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the fit method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to fit if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to fit.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in fit.

• self (LogisticSCADPathRegressor)

Returns:

self – The updated object.

Return type:

object

set_predict_proba_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the predict_proba method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to predict_proba if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to predict_proba.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in predict_proba.

• self (LogisticSCADPathRegressor)

Returns:

self – The updated object.

Return type:

object

set_predict_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the predict method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to predict if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to predict.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in predict.

• self (LogisticSCADPathRegressor)

Returns:

self – The updated object.

Return type:

object

class skein_glm.estimators.LogisticElasticNetPathRegressor(alpha=0.5, *, lambdas=None, n_lambdas=100, lambda_min_ratio=0.001, weights=None, sample_weights=None, max_iter=100, tol=1e-06, fit_intercept=True, standardize=False, acceleration=5, max_outer=10, outer_tol=1e-06)

Bases: _LogisticPathRegressorBase

Logistic regression with elastic-net penalty along an entire λ-path.

See LogisticElasticNetRegressor for the single-λ variant.

Parameters:

• alpha (float)

• lambdas (NDArray[np.float64] | None)

• n_lambdas (int)

• lambda_min_ratio (float)

• weights (NDArray[np.float64] | None)

• sample_weights (NDArray[np.float64] | None)

• max_iter (int)

• tol (float)

• fit_intercept (bool)

• standardize (bool)

• acceleration (int | None)

• max_outer (int)

• outer_tol (float)

set_decision_function_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the decision_function method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to decision_function if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to decision_function.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in decision_function.

• self (LogisticElasticNetPathRegressor)

Returns:

self – The updated object.

Return type:

object

set_fit_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the fit method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to fit if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to fit.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in fit.

• self (LogisticElasticNetPathRegressor)

Returns:

self – The updated object.

Return type:

object

set_predict_proba_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the predict_proba method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to predict_proba if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to predict_proba.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in predict_proba.

• self (LogisticElasticNetPathRegressor)

Returns:

self – The updated object.

Return type:

object

set_predict_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the predict method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to predict if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to predict.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in predict.

• self (LogisticElasticNetPathRegressor)

Returns:

self – The updated object.

Return type:

object

class skein_glm.estimators.LogisticLassoPathRegressor(*, lambdas=None, n_lambdas=100, lambda_min_ratio=0.001, weights=None, sample_weights=None, max_iter=100, tol=1e-06, fit_intercept=True, standardize=False, acceleration=5, max_outer=10, outer_tol=1e-06)

Bases: LogisticElasticNetPathRegressor

Logistic regression with L1 penalty along an entire λ-path.

See LogisticLassoRegressor for the single-λ variant.

Parameters:

• lambdas (NDArray[np.float64] | None)

• n_lambdas (int)

• lambda_min_ratio (float)

• weights (NDArray[np.float64] | None)

• sample_weights (NDArray[np.float64] | None)

• max_iter (int)

• tol (float)

• fit_intercept (bool)

• standardize (bool)

• acceleration (int | None)

• max_outer (int)

• outer_tol (float)

set_decision_function_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the decision_function method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to decision_function if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to decision_function.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in decision_function.

• self (LogisticLassoPathRegressor)

Returns:

self – The updated object.

Return type:

object

set_fit_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the fit method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to fit if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to fit.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in fit.

• self (LogisticLassoPathRegressor)

Returns:

self – The updated object.

Return type:

object

set_predict_proba_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the predict_proba method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to predict_proba if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to predict_proba.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in predict_proba.

• self (LogisticLassoPathRegressor)

Returns:

self – The updated object.

Return type:

object

set_predict_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the predict method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to predict if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to predict.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in predict.

• self (LogisticLassoPathRegressor)

Returns:

self – The updated object.

Return type:

object

Group — single λ

class skein_glm.estimators.LogisticGroupLassoRegressor(groups, lambda_=0.1, *, weights=None, max_iter=100, tol=1e-06, fit_intercept=True, standardize=False, acceleration=5, max_outer=10, outer_tol=1e-06)

Bases: _LogisticGroupSingleLambdaBase

Logistic regression with group lasso penalty at a single λ.

Parameters:

• groups (NDArray[np.int64])

• lambda_ (float)

• weights (NDArray[np.float64] | None)

• max_iter (int)

• tol (float)

• fit_intercept (bool)

• standardize (bool)

• acceleration (int | None)

• max_outer (int)

• outer_tol (float)

set_decision_function_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the decision_function method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to decision_function if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to decision_function.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in decision_function.

• self (LogisticGroupLassoRegressor)

Returns:

self – The updated object.

Return type:

object

set_fit_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the fit method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to fit if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to fit.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in fit.

• self (LogisticGroupLassoRegressor)

Returns:

self – The updated object.

Return type:

object

set_predict_proba_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the predict_proba method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to predict_proba if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to predict_proba.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in predict_proba.

• self (LogisticGroupLassoRegressor)

Returns:

self – The updated object.

Return type:

object

set_predict_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the predict method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to predict if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to predict.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in predict.

• self (LogisticGroupLassoRegressor)

Returns:

self – The updated object.

Return type:

object

class skein_glm.estimators.LogisticGroupMCPRegressor(groups, lambda_=0.1, gamma=3.0, *, weights=None, max_iter=100, tol=1e-06, fit_intercept=True, standardize=False, acceleration=5, max_outer=10, outer_tol=1e-06)

Bases: _LogisticGroupSingleLambdaBase

Logistic regression with group MCP at a single λ (prox-Newton + LLA).

Parameters:

• groups (NDArray[np.int64])

• lambda_ (float)

• gamma (float)

• weights (NDArray[np.float64] | None)

• max_iter (int)

• tol (float)

• fit_intercept (bool)

• standardize (bool)

• acceleration (int | None)

• max_outer (int)

• outer_tol (float)

set_decision_function_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the decision_function method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to decision_function if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to decision_function.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in decision_function.

• self (LogisticGroupMCPRegressor)

Returns:

self – The updated object.

Return type:

object

set_fit_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the fit method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to fit if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to fit.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in fit.

• self (LogisticGroupMCPRegressor)

Returns:

self – The updated object.

Return type:

object

set_predict_proba_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the predict_proba method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to predict_proba if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to predict_proba.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in predict_proba.

• self (LogisticGroupMCPRegressor)

Returns:

self – The updated object.

Return type:

object

set_predict_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the predict method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to predict if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to predict.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in predict.

• self (LogisticGroupMCPRegressor)

Returns:

self – The updated object.

Return type:

object

class skein_glm.estimators.LogisticSparseGroupLassoRegressor(groups, lambda_=0.1, alpha=0.5, *, weights=None, max_iter=100, tol=1e-06, fit_intercept=True, standardize=False, acceleration=5, max_outer=10, outer_tol=1e-06)

Bases: _LogisticGroupSingleLambdaBase

Logistic regression with sparse-group lasso at a single λ.

Parameters:

• groups (NDArray[np.int64])

• lambda_ (float)

• alpha (float)

• weights (NDArray[np.float64] | None)

• max_iter (int)

• tol (float)

• fit_intercept (bool)

• standardize (bool)

• acceleration (int | None)

• max_outer (int)

• outer_tol (float)

set_decision_function_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the decision_function method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to decision_function if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to decision_function.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in decision_function.

• self (LogisticSparseGroupLassoRegressor)

Returns:

self – The updated object.

Return type:

object

set_fit_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the fit method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to fit if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to fit.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in fit.

• self (LogisticSparseGroupLassoRegressor)

Returns:

self – The updated object.

Return type:

object

set_predict_proba_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the predict_proba method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to predict_proba if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to predict_proba.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in predict_proba.

• self (LogisticSparseGroupLassoRegressor)

Returns:

self – The updated object.

Return type:

object

set_predict_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the predict method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to predict if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to predict.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in predict.

• self (LogisticSparseGroupLassoRegressor)

Returns:

self – The updated object.

Return type:

object

class skein_glm.estimators.LogisticSparseGroupMCPRegressor(groups, lambda_=0.1, gamma=3.0, alpha=0.5, *, weights=None, coord_weights=None, max_iter=100, tol=1e-06, fit_intercept=True, standardize=False, acceleration=5, max_outer=10, outer_tol=1e-06)

Bases: _LogisticGroupSingleLambdaBase

Logistic regression with sparse-group MCP at a single λ.

Parameters:

• groups (NDArray[np.int64])

• lambda_ (float)

• gamma (float)

• alpha (float)

• weights (NDArray[np.float64] | None)

• coord_weights (NDArray[np.float64] | None)

• max_iter (int)

• tol (float)

• fit_intercept (bool)

• standardize (bool)

• acceleration (int | None)

• max_outer (int)

• outer_tol (float)

set_decision_function_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the decision_function method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to decision_function if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to decision_function.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in decision_function.

• self (LogisticSparseGroupMCPRegressor)

Returns:

self – The updated object.

Return type:

object

set_fit_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the fit method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to fit if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to fit.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in fit.

• self (LogisticSparseGroupMCPRegressor)

Returns:

self – The updated object.

Return type:

object

set_predict_proba_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the predict_proba method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to predict_proba if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to predict_proba.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in predict_proba.

• self (LogisticSparseGroupMCPRegressor)

Returns:

self – The updated object.

Return type:

object

set_predict_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the predict method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to predict if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to predict.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in predict.

• self (LogisticSparseGroupMCPRegressor)

Returns:

self – The updated object.

Return type:

object

class skein_glm.estimators.LogisticSparseGroupSCADRegressor(groups, lambda_=0.1, a=3.7, alpha=0.5, *, weights=None, coord_weights=None, max_iter=100, tol=1e-06, fit_intercept=True, standardize=False, acceleration=5, max_outer=10, outer_tol=1e-06)

Bases: _LogisticGroupSingleLambdaBase

Logistic regression with sparse-group SCAD at a single λ. SCAD shape a > 2 (default 3.7).

Parameters:

• groups (NDArray[np.int64])

• lambda_ (float)

• a (float)

• alpha (float)

• weights (NDArray[np.float64] | None)

• coord_weights (NDArray[np.float64] | None)

• max_iter (int)

• tol (float)

• fit_intercept (bool)

• standardize (bool)

• acceleration (int | None)

• max_outer (int)

• outer_tol (float)

set_decision_function_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the decision_function method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to decision_function if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to decision_function.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in decision_function.

• self (LogisticSparseGroupSCADRegressor)

Returns:

self – The updated object.

Return type:

object

set_fit_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the fit method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to fit if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to fit.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in fit.

• self (LogisticSparseGroupSCADRegressor)

Returns:

self – The updated object.

Return type:

object

set_predict_proba_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the predict_proba method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to predict_proba if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to predict_proba.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in predict_proba.

• self (LogisticSparseGroupSCADRegressor)

Returns:

self – The updated object.

Return type:

object

set_predict_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the predict method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to predict if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to predict.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in predict.

• self (LogisticSparseGroupSCADRegressor)

Returns:

self – The updated object.

Return type:

object

Group — path

class skein_glm.estimators.LogisticGroupLassoPathRegressor(groups, *, lambdas=None, n_lambdas=100, lambda_min_ratio=0.001, weights=None, max_iter=100, tol=1e-06, fit_intercept=True, standardize=False, acceleration=5, max_outer=10, outer_tol=1e-06)

Bases: _LogisticGroupPathBase

Logistic regression with group lasso along an entire λ-path.

Parameters:

• groups (NDArray[np.int64])

• lambdas (NDArray[np.float64] | None)

• n_lambdas (int)

• lambda_min_ratio (float)

• weights (NDArray[np.float64] | None)

• max_iter (int)

• tol (float)

• fit_intercept (bool)

• standardize (bool)

• acceleration (int | None)

• max_outer (int)

• outer_tol (float)

set_decision_function_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the decision_function method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to decision_function if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to decision_function.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in decision_function.

• self (LogisticGroupLassoPathRegressor)

Returns:

self – The updated object.

Return type:

object

set_fit_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the fit method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to fit if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to fit.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in fit.

• self (LogisticGroupLassoPathRegressor)

Returns:

self – The updated object.

Return type:

object

set_predict_proba_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the predict_proba method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to predict_proba if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to predict_proba.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in predict_proba.

• self (LogisticGroupLassoPathRegressor)

Returns:

self – The updated object.

Return type:

object

set_predict_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the predict method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to predict if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to predict.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in predict.

• self (LogisticGroupLassoPathRegressor)

Returns:

self – The updated object.

Return type:

object

class skein_glm.estimators.LogisticGroupMCPPathRegressor(groups, gamma=3.0, *, lambdas=None, n_lambdas=100, lambda_min_ratio=0.001, weights=None, max_iter=100, tol=1e-06, fit_intercept=True, standardize=False, acceleration=5, max_outer=10, outer_tol=1e-06)

Bases: _LogisticGroupPathBase

Logistic regression with group MCP along an entire λ-path.

Parameters:

• groups (NDArray[np.int64])

• gamma (float)

• lambdas (NDArray[np.float64] | None)

• n_lambdas (int)

• lambda_min_ratio (float)

• weights (NDArray[np.float64] | None)

• max_iter (int)

• tol (float)

• fit_intercept (bool)

• standardize (bool)

• acceleration (int | None)

• max_outer (int)

• outer_tol (float)

set_decision_function_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the decision_function method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to decision_function if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to decision_function.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in decision_function.

• self (LogisticGroupMCPPathRegressor)

Returns:

self – The updated object.

Return type:

object

set_fit_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the fit method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to fit if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to fit.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in fit.

• self (LogisticGroupMCPPathRegressor)

Returns:

self – The updated object.

Return type:

object

set_predict_proba_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the predict_proba method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to predict_proba if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to predict_proba.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in predict_proba.

• self (LogisticGroupMCPPathRegressor)

Returns:

self – The updated object.

Return type:

object

set_predict_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the predict method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to predict if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to predict.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in predict.

• self (LogisticGroupMCPPathRegressor)

Returns:

self – The updated object.

Return type:

object

class skein_glm.estimators.LogisticSparseGroupLassoPathRegressor(groups, alpha=0.5, *, lambdas=None, n_lambdas=100, lambda_min_ratio=0.001, weights=None, max_iter=100, tol=1e-06, fit_intercept=True, standardize=False, acceleration=5, max_outer=10, outer_tol=1e-06)

Bases: _LogisticGroupPathBase

Logistic regression with sparse-group lasso along an entire λ-path.

Parameters:

• groups (NDArray[np.int64])

• alpha (float)

• lambdas (NDArray[np.float64] | None)

• n_lambdas (int)

• lambda_min_ratio (float)

• weights (NDArray[np.float64] | None)

• max_iter (int)

• tol (float)

• fit_intercept (bool)

• standardize (bool)

• acceleration (int | None)

• max_outer (int)

• outer_tol (float)

set_decision_function_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the decision_function method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to decision_function if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to decision_function.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in decision_function.

• self (LogisticSparseGroupLassoPathRegressor)

Returns:

self – The updated object.

Return type:

object

set_fit_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the fit method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to fit if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to fit.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in fit.

• self (LogisticSparseGroupLassoPathRegressor)

Returns:

self – The updated object.

Return type:

object

set_predict_proba_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the predict_proba method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to predict_proba if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to predict_proba.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in predict_proba.

• self (LogisticSparseGroupLassoPathRegressor)

Returns:

self – The updated object.

Return type:

object

set_predict_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the predict method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to predict if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to predict.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in predict.

• self (LogisticSparseGroupLassoPathRegressor)

Returns:

self – The updated object.

Return type:

object

class skein_glm.estimators.LogisticSparseGroupMCPPathRegressor(groups, gamma=3.0, alpha=0.5, *, lambdas=None, n_lambdas=100, lambda_min_ratio=0.001, weights=None, coord_weights=None, max_iter=100, tol=1e-06, fit_intercept=True, standardize=False, acceleration=5, max_outer=10, outer_tol=1e-06)

Bases: _LogisticGroupPathBase

Logistic regression with sparse-group MCP along an entire λ-path.

Parameters:

• groups (NDArray[np.int64])

• gamma (float)

• alpha (float)

• lambdas (NDArray[np.float64] | None)

• n_lambdas (int)

• lambda_min_ratio (float)

• weights (NDArray[np.float64] | None)

• coord_weights (NDArray[np.float64] | None)

• max_iter (int)

• tol (float)

• fit_intercept (bool)

• standardize (bool)

• acceleration (int | None)

• max_outer (int)

• outer_tol (float)

set_decision_function_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the decision_function method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to decision_function if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to decision_function.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in decision_function.

• self (LogisticSparseGroupMCPPathRegressor)

Returns:

self – The updated object.

Return type:

object

set_fit_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the fit method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to fit if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to fit.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in fit.

• self (LogisticSparseGroupMCPPathRegressor)

Returns:

self – The updated object.

Return type:

object

set_predict_proba_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the predict_proba method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to predict_proba if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to predict_proba.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in predict_proba.

• self (LogisticSparseGroupMCPPathRegressor)

Returns:

self – The updated object.

Return type:

object

set_predict_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the predict method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to predict if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to predict.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in predict.

• self (LogisticSparseGroupMCPPathRegressor)

Returns:

self – The updated object.

Return type:

object

class skein_glm.estimators.LogisticSparseGroupSCADPathRegressor(groups, a=3.7, alpha=0.5, *, lambdas=None, n_lambdas=100, lambda_min_ratio=0.001, weights=None, coord_weights=None, max_iter=100, tol=1e-06, fit_intercept=True, standardize=False, acceleration=5, max_outer=10, outer_tol=1e-06)

Bases: _LogisticGroupPathBase

Logistic regression with sparse-group SCAD along an entire λ-path.

Parameters:

• groups (NDArray[np.int64])

• a (float)

• alpha (float)

• lambdas (NDArray[np.float64] | None)

• n_lambdas (int)

• lambda_min_ratio (float)

• weights (NDArray[np.float64] | None)

• coord_weights (NDArray[np.float64] | None)

• max_iter (int)

• tol (float)

• fit_intercept (bool)

• standardize (bool)

• acceleration (int | None)

• max_outer (int)

• outer_tol (float)

set_decision_function_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the decision_function method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to decision_function if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to decision_function.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in decision_function.

• self (LogisticSparseGroupSCADPathRegressor)

Returns:

self – The updated object.

Return type:

object

set_fit_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the fit method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to fit if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to fit.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in fit.

• self (LogisticSparseGroupSCADPathRegressor)

Returns:

self – The updated object.

Return type:

object

set_predict_proba_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the predict_proba method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to predict_proba if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to predict_proba.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in predict_proba.

• self (LogisticSparseGroupSCADPathRegressor)

Returns:

self – The updated object.

Return type:

object

set_predict_request(*, x='$UNCHANGED$')

Configure whether metadata should be requested to be passed to the predict method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

• True: metadata is requested, and passed to predict if provided. The request is ignored if metadata is not provided.

• False: metadata is not requested and the meta-estimator will not pass it to predict.

• None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

• str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

• x (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for x parameter in predict.

• self (LogisticSparseGroupSCADPathRegressor)

Returns:

self – The updated object.

Return type:

object