step_regex() creates a specification of a recipe step that will create a
new dummy variable based on a regular expression.
step_regex(
recipe,
...,
role = "predictor",
trained = FALSE,
pattern = ".",
options = list(),
result = make.names(pattern),
input = NULL,
keep_original_cols = TRUE,
skip = FALSE,
id = rand_id("regex")
)A recipe object. The step will be added to the sequence of operations for this recipe.
A single selector function to choose which variable
will be searched for the regex pattern. The selector should resolve
to a single variable. See selections() for more details.
For model terms created by this step, what analysis role should they be assigned? By default, the new columns created by this step from the original variables will be used as predictors in a model.
A logical to indicate if the quantities for preprocessing have been estimated.
A character string containing a regular
expression (or character string for fixed = TRUE) to be
matched in the given character vector. Coerced by
as.character to a character string if possible.
A list of options to grepl() that
should not include x or pattern.
A single character value for the name of the new variable. It should be a valid column name.
A single character value for the name of the
variable being searched. This is NULL until computed by
prep().
A logical to keep the original variables in the
output. Defaults to TRUE.
A logical. Should the step be skipped when the
recipe is baked by bake()? While all operations are baked
when prep() is run, some operations may not be able to be
conducted on new data (e.g. processing the outcome variable(s)).
Care should be taken when using skip = TRUE as it may affect
the computations for subsequent operations.
A character string that is unique to this step to identify it.
An updated version of recipe with the new step added to the
sequence of any existing operations.
When you tidy() this step, a tibble is returned with
columns terms, result , and id:
character, the selectors or variables selected
character, new column name
character, id of this step
The underlying operation does not allow for case weights.
Other dummy variable and encoding steps:
step_bin2factor(),
step_count(),
step_date(),
step_dummy(),
step_dummy_extract(),
step_dummy_multi_choice(),
step_factor2string(),
step_holiday(),
step_indicate_na(),
step_integer(),
step_novel(),
step_num2factor(),
step_ordinalscore(),
step_other(),
step_relevel(),
step_string2factor(),
step_time(),
step_unknown(),
step_unorder()
data(covers, package = "modeldata")
rec <- recipe(~description, covers) %>%
step_regex(description, pattern = "(rock|stony)", result = "rocks") %>%
step_regex(description, pattern = "ratake families")
rec2 <- prep(rec, training = covers)
rec2
#>
#> ── Recipe ──────────────────────────────────────────────────────────────────────
#>
#> ── Inputs
#> Number of variables by role
#> predictor: 1
#>
#> ── Training information
#> Training data contained 40 data points and no incomplete rows.
#>
#> ── Operations
#> • Regular expression dummy variable using: "(rock|stony)" | Trained
#> • Regular expression dummy variable using: "ratake families" | Trained
with_dummies <- bake(rec2, new_data = covers)
with_dummies
#> # A tibble: 40 × 3
#> description rocks ratake.families
#> <fct> <int> <int>
#> 1 1,cathedral family,rock outcrop complex,extremely stony 1 0
#> 2 2,vanet,ratake families complex,very stony 1 1
#> 3 3,haploborolis,rock outcrop complex,rubbly 1 0
#> 4 4,ratake family,rock outcrop complex,rubbly 1 0
#> 5 5,vanet family,rock outcrop complex complex,rubbly 1 0
#> 6 6,vanet,wetmore families,rock outcrop complex,stony 1 0
#> 7 7,gothic family 0 0
#> 8 8,supervisor,limber families complex 0 0
#> 9 9,troutville family,very stony 1 0
#> 10 10,bullwark,catamount families,rock outcrop complex,ru… 1 0
#> # ℹ 30 more rows
tidy(rec, number = 1)
#> # A tibble: 1 × 3
#> terms result id
#> <chr> <chr> <chr>
#> 1 description NA regex_0cUH6
tidy(rec2, number = 1)
#> # A tibble: 1 × 3
#> terms result id
#> <chr> <chr> <chr>
#> 1 description rocks regex_0cUH6