Skip to content

step_string2factor will convert one or more character vectors to factors (ordered or unordered).

Use this step only in special cases (see Details) and instead convert strings to factors before using any tidymodels functions.


  role = NA,
  trained = FALSE,
  levels = NULL,
  ordered = FALSE,
  skip = FALSE,
  id = rand_id("string2factor")



A recipe object. The step will be added to the sequence of operations for this recipe.


One or more selector functions to choose variables for this step. See selections() for more details.


Not used by this step since no new variables are created.


A logical to indicate if the quantities for preprocessing have been estimated.


An options specification of the levels to be used for the new factor. If left NULL, the sorted unique values present when bake is called will be used.


A single logical value; should the factor(s) be ordered?


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 should you use this step?

In most cases, if you are planning to use step_string2factor() without setting levels, you will be better off converting those character variables to factor variables before using a recipe.

This can be done using dplyr with the following code

df <- mutate(df, across(where(is.character), as.factor))

During resampling, the complete set of values might not be in the character data. Converting them to factors with step_string2factor() then will misconfigure the levels.

If the levels argument to step_string2factor()is used, it will convert all variables affected by this step to have the same levels. Because of this, you will need to know the full set of level when you define the recipe.

Also, note that prep() has an option strings_as_factors that defaults to TRUE. This should be changed so that raw character data will be applied to step_string2factor(). However, this step can also take existing factors (but will leave them as-is).


When you tidy() this step, a tibble with columns terms (the selectors or variables selected) and ordered is returned.

Case weights

The underlying operation does not allow for case weights.


data(Sacramento, package = "modeldata")

# convert factor to string to demonstrate
Sacramento$city <- as.character(Sacramento$city)

rec <- recipe(~ city + zip, data = Sacramento)

make_factor <- rec %>%

make_factor <- prep(make_factor,
  training = Sacramento

#> Recipe
#> Inputs:
#>       role #variables
#>  predictor          2
#> Training data contained 932 data points and no missing data.
#> Operations:
#> Factor variables from city [trained]

# note that `city` is a factor in recipe output
bake(make_factor, new_data = NULL) %>% head()
#> # A tibble: 6 × 2
#>   city       zip   
#>   <fct>      <fct> 
#> 1 SACRAMENTO z95838
#> 2 SACRAMENTO z95823
#> 3 SACRAMENTO z95815
#> 4 SACRAMENTO z95815
#> 5 SACRAMENTO z95824
#> 6 SACRAMENTO z95841

# ...but remains a string in the data
Sacramento %>% head()
#> # A tibble: 6 × 9
#>   city       zip     beds baths  sqft type        price latitude longitude
#>   <chr>      <fct>  <int> <dbl> <int> <fct>       <int>    <dbl>     <dbl>
#> 1 SACRAMENTO z95838     2     1   836 Residential 59222     38.6     -121.
#> 2 SACRAMENTO z95823     3     1  1167 Residential 68212     38.5     -121.
#> 3 SACRAMENTO z95815     2     1   796 Residential 68880     38.6     -121.
#> 4 SACRAMENTO z95815     2     1   852 Residential 69307     38.6     -121.
#> 5 SACRAMENTO z95824     2     1   797 Residential 81900     38.5     -121.
#> 6 SACRAMENTO z95841     3     1  1122 Condo       89921     38.7     -121.