Save a model in tidymodels

Machine Learning and Modeling
,
1

I have a large fitted random forest model, created in a tidymodels framework. It is a large (~1Gb) object of class workflow.

My question: How do a save/ reload this object to disk?

Here is a simple reprex using everyone's fav dataset:

library(ranger)
library(dplyr)
library(rsample)
library(recipes)
library(parsnip)
library(workflows)


split_mtcars <- rsample::initial_split(mtcars, .75)

train_mtcars <- rsample::training(split_mtcars)

test_mtcars <- rsample::testing(split_mtcars)



mtcars_recipe <- recipes::recipe(mpg ~ hp + wt, data = train_mtcars)

# specify random forest model

rf_mod_mtcars <- parsnip::rand_forest() %>%
  parsnip::set_engine("ranger") %>%
  parsnip::set_mode("regression")

rf_wflow_mtcars <- workflows::workflow() %>%
  workflows::add_recipe(mtcars_recipe) %>%
  workflows::add_model(rf_mod_mtcars)

rf_model_fit_mtcars <- rf_wflow_mtcars %>%
  generics::fit(data = train_mtcars)

predict(rf_model_fit_mtcars, test_mtcars) %>%
  cbind(select(test_mtcars, mpg))

#######  THE QUESTION: HOW TO SAVE rf_model_fit_mtcars  #######

Thank you

2

Probably saveRDS() would do it

1 Like
3

This topic was automatically closed 7 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.