no_split_lasso: Internal lassoenet function

In MokyoZhou/lassoenet: An Interactive Implementation of Penalised Regressions

Description

Internal lassoenet function

Usage

no_split_lasso(err.curves = 0, x = x, y = y, type.lambda = type.lambda,
  al = 1, parallel = parallel)

Arguments

err.curves	The number of error curves to be fitted. Default is 0.
x	A model.matrix for the predictors.
y	A vector of response values.
type.lambda	Either "lambda.min" or "lambda.1se", default is "lambda.min.
al	1 for the Lasso and 0 for ridge regression.
parallel	Parallelisation

Value

A vector of results for the best Lasso model under the condition where the full dataset has been used for modelling. The return from this function will enter prediction_Lasso.

Details

These are not intended for use by users. This function is one of the main engines for the Lasso computation. This function is used when the user does not want to split the dataset into a training and a test set. This together with the function split_lasso form the overall computation operator for the Lasso models. The return from this function will enter prediction_Lasso for futher wrapping.

Author(s)

Mokyo Zhou

MokyoZhou/lassoenet documentation built on May 20, 2019, 11:38 a.m.