Description Usage Arguments Value
Creates an object designed to be passed to init_stacker that describes an glm/penalized regression model be added to the stacking ensemble.
1 2 | init_penalized(model_name = "pen", arguments = list(alpha = 1),
emp_logit = F, standardize = F)
|
model_name |
name of the penalized regression model model |
arguments |
named list. Arguments to be passed to the glmnet function. See help glmnet::glmnet for more information. The main arguement to be passed is alpha: 0 is ridge regression and 1 is lasso penalty. Between 0 and 1 refers to elastic net. |
emp_logit |
logical. If family is binomial, should the regression be run as gaussian (empirical logit of cases/N) |
standardize |
logical. Standardize numeric columns to have zero mean and unit variance. Defaults to False unlike the glmnet default settings. This is set to F, because centre scaling/normalizing is a default preprocessing step |
named list of lists with the parameters required to run an penalized regression model
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.