Select variables using dplyr
step_select() creates a specification of a recipe step
that will select variables using dplyr::select().
step_select(
recipe,
...,
role = NA,
trained = FALSE,
skip = FALSE,
id = rand_id("select")
)
## S3 method for class 'step_select'
tidy(x, ...)recipe |
A recipe object. The step will be added to the sequence of operations for this recipe. |
... |
One or more selector functions to choose which
variables will be selected when baking. See
|
role |
For model terms selected by this step, what analysis role should they be assigned? |
trained |
A logical to indicate if the quantities for preprocessing have been estimated. |
skip |
A logical. Should the step be skipped when the
recipe is baked by |
id |
A character string that is unique to this step to identify it. |
x |
A |
When an object in the user's global environment is
referenced in the expression defining the new variable(s),
it is a good idea to use quasiquotation (e.g. !!) to embed
the value of the object in the expression (to be portable
between sessions). See the examples.
An updated version of recipe with the new step
added to the sequence of existing steps (if any). For the
tidy method, a tibble with column terms which
contains the select expressions as character strings
(and are not reparsable).
library(dplyr)
iris_tbl <- as_tibble(iris)
iris_train <- slice(iris_tbl, 1:75)
iris_test <- slice(iris_tbl, 76:150)
dplyr_train <- select(iris_train, Species, starts_with("Sepal"))
dplyr_test <- select(iris_test, Species, starts_with("Sepal"))
rec <- recipe(~., data = iris_train) %>%
step_select(Species, starts_with("Sepal")) %>%
prep(training = iris_train)
rec_train <- bake(rec, new_data = NULL)
all.equal(dplyr_train, rec_train)
rec_test <- bake(rec, iris_test)
all.equal(dplyr_test, rec_test)
# Local variables
sepal_vars <- c("Sepal.Width", "Sepal.Length")
qq_rec <-
recipe(~., data = iris_train) %>%
# fine for interactive usage
step_select(Species, all_of(sepal_vars)) %>%
# best approach for saving a recipe to disk
step_select(Species, all_of(!!sepal_vars))
# Note that `sepal_vars` is inlined in the second approach
qq_recPlease choose more modern alternatives, such as Google Chrome or Mozilla Firefox.