define_ridge: Define ridge regularization object for predictor and external...

In xrnet: Hierarchical Regularized Regression

Description

Helper function to define a ridge penalty regularization object. See define_penalty for more details.

Usage

define_ridge(
  num_penalty = 20,
  penalty_ratio = NULL,
  user_penalty = NULL,
  custom_multiplier = NULL
)

Arguments

num_penalty	number of penalty values to fit in grid. Default is 20.
penalty_ratio	ratio between minimum and maximum penalty for x. Default is 1e-04 if n > p and 0.01 if n <= p.
user_penalty	user-defined vector of penalty values to use in penalty path.
custom_multiplier	variable-specific penalty multipliers to apply to overall penalty. Default is 1 for all variables. 0 is no penalization.

Value

A list object with regularization settings that are used to define the regularization for predictors or external data in xrnet and tune_xrnet. The list elements will match those returned by define_penalty, but with the penalty_type automatically set to 0.

xrnet documentation built on March 26, 2020, 9:13 p.m.