How do I add blueprint for sparse model in a workflow_set?

Machine Learning and Modeling
,
1

Hi, I want to build and screen multiple models, and in one of the workflows, i'd like to use the hardhat blueprint for sparse dataset.

I primarily followed these 2 links

Link 1 - Sparse Matrix Sparse data structures in tidymodels
Link 2 - Workflow_sets 15 Screening many models | Tidy Modeling with R

In the example below: the setting of workflow_set

no_pre_proc <- 
   workflow_set(
      preproc = list(simple = model_vars), 
      models = list(MARS = mars_spec, CART = cart_spec, CART_bagged = bag_cart_spec,
                    RF = rf_spec, boosting = xgb_spec, Cubist = cubist_spec)
   )

In this example, is the setting of workflow (not workflow_set)

wf_sparse <- 
  workflow() %>%
  add_recipe(text_rec, blueprint = sparse_bp) %>%
  add_model(lasso_spec)
  
wf_default <- 
  workflow() %>%
  add_recipe(text_rec) %>%
  add_model(lasso_spec)

How do i introduce into the workflow_set the option of "blueprint = sparse_bp"?

thanks,

James

2

This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.

If you have a query related to it or one of the replies, start a new topic and refer back with a link.