update_workflow_model: Update components of a workflow within a workflow set

In workflowsets: Create a Collection of 'tidymodels' Workflows

Update components of a workflow within a workflow set

Description

Workflows can take special arguments for the recipe (e.g. a blueprint) or a model (e.g. a special formula). However, when creating a workflow set, there is no way to specify these extra components.

update_workflow_model() and update_workflow_recipe() allow users to set these values after the workflow set is initially created. They are analogous to workflows::add_model() or workflows::add_recipe().

Usage

update_workflow_model(x, id, spec, formula = NULL)

update_workflow_recipe(x, id, recipe, blueprint = NULL)

Arguments

x	A workflow set outputted by workflow_set() or workflow_map().
id	A single character string from the wflow_id column indicating which workflow to update.
spec	A parsnip model specification.
formula	An optional formula override to specify the terms of the model. Typically, the terms are extracted from the formula or recipe preprocessing methods. However, some models (like survival and bayesian models) use the formula not to preprocess, but to specify the structure of the model. In those cases, a formula specifying the model structure must be passed unchanged into the model call itself. This argument is used for those purposes.
recipe	A recipe created using recipes::recipe()
blueprint	A hardhat blueprint used for fine tuning the preprocessing. If NULL, hardhat::default_recipe_blueprint() is used. Note that preprocessing done here is separate from preprocessing that might be done automatically by the underlying model.

Note

The package supplies two pre-generated workflow sets, two_class_set and chi_features_set, and associated sets of model fits two_class_res and chi_features_res.

The ⁠two_class_*⁠ objects are based on a binary classification problem using the two_class_dat data from the modeldata package. The six models utilize either a bare formula or a basic recipe utilizing recipes::step_YeoJohnson() as a preprocessor, and a decision tree, logistic regression, or MARS model specification. See ?two_class_set for source code.

The ⁠chi_features_*⁠ objects are based on a regression problem using the Chicago data from the modeldata package. Each of the three models utilize a linear regression model specification, with three different recipes of varying complexity. The objects are meant to approximate the sequence of models built in Section 1.3 of Kuhn and Johnson (2019). See ?chi_features_set for source code.

Examples

library(parsnip)

new_mod <-
  decision_tree() %>%
  set_engine("rpart", method = "anova") %>%
  set_mode("classification")

new_set <- update_workflow_model(two_class_res, "none_cart", spec = new_mod)

new_set

extract_workflow(new_set, id = "none_cart")

workflowsets documentation built on April 7, 2023, 1:05 a.m.