Class "SparseGroupFit"

Class of object returned by the fitting function group_sparse_lm(). Inherits fields and methods of QuadrupenFit

See also

QuadrupenFit, group_sparse_lm()

Super class

QuadrupenFit -> SparseGroupFit

Active bindings

lambda1

vector of tuning parameters for the l1 group penalty

lambda2

vector of tuning parameters for the l2 penalty

alpha

mixing parameter of the sparse group-penalty

penalty

character describing the regularizer/penalty

group

vector of integers indicating group belonging

type

string the type of group-wise regularization applied

mixture_tuning

mixture coefficient of the sparse group penalty

is_group_sparse

boolean indicating if sparse group or group penalty is applied

Methods

Public methods

• SparseGroupFit$new()

• SparseGroupFit$clone()

Inherited methods

• QuadrupenFit$criteria()
• QuadrupenFit$cross_validate()
• QuadrupenFit$fit()
• QuadrupenFit$get_model()
• QuadrupenFit$plot()
• QuadrupenFit$plot_path()
• QuadrupenFit$predict()
• QuadrupenFit$print()
• QuadrupenFit$show()
• QuadrupenFit$stability()

---

SparseGroupFit$new()

Initialize a SparseGroupFit model

Usage

SparseGroupFit$new(data, intercept, group, type, regParam)

Arguments

data

a DataModel object

intercept

a logical; should an intercept be included in the mode?

group

vector of integers indicating group belonging.

type

string indicating whether the \(\ell_1/\ell_2\) or the \(\ell_1/\ell_\infty\) group-Lasso must be fitted.

regParam

a list with two elements, a vector and a scalar, for the regularization

---

SparseGroupFit$clone()

The objects of this class are cloneable with this method.

Usage

SparseGroupFit$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.