R recipes step_mutate 使用 dplyr 添加新变量

step_mutate(
  recipe,
  ...,
  role = "predictor",
  trained = FALSE,
  inputs = NULL,
  skip = FALSE,
  id = rand_id("mutate")
)

其他单独的转换步骤：step_BoxCox() , step_YeoJohnson() , step_bs() , step_harmonic() , step_hyperbolic() , step_inverse() , step_invlogit() , step_logit() , step_log() , step_ns() , step_percentile() , step_poly() , step_relu() , step_sqrt()

其他 dplyr 步骤：step_arrange() , step_filter() , step_mutate_at() , step_rename_at() , step_rename() , step_sample() , step_select() , step_slice()

rec <-
  recipe(~., data = iris) %>%
  step_mutate(
    dbl_width = Sepal.Width * 2,
    half_length = Sepal.Length / 2
  )

prepped <- prep(rec, training = iris %>% slice(1:75))

library(dplyr)

dplyr_train <-
  iris %>%
  as_tibble() %>%
  slice(1:75) %>%
  mutate(
    dbl_width = Sepal.Width * 2,
    half_length = Sepal.Length / 2
  )

rec_train <- bake(prepped, new_data = NULL)
all.equal(dplyr_train, rec_train)
#> [1] TRUE

dplyr_test <-
  iris %>%
  as_tibble() %>%
  slice(76:150) %>%
  mutate(
    dbl_width = Sepal.Width * 2,
    half_length = Sepal.Length / 2
  )
rec_test <- bake(prepped, iris %>% slice(76:150))
all.equal(dplyr_test, rec_test)
#> [1] TRUE

# Embedding objects:
const <- 1.414

qq_rec <-
  recipe(~., data = iris) %>%
  step_mutate(
    bad_approach = Sepal.Width * const,
    best_approach = Sepal.Width * !!const
  ) %>%
  prep(training = iris)

bake(qq_rec, new_data = NULL, contains("appro")) %>% slice(1:4)
#> # A tibble: 4 × 2
#>   bad_approach best_approach
#>          <dbl>         <dbl>
#> 1         4.95          4.95
#> 2         4.24          4.24
#> 3         4.52          4.52
#> 4         4.38          4.38

# The difference:
tidy(qq_rec, number = 1)
#> # A tibble: 2 × 3
#>   terms         value               id          
#>   <chr>         <chr>               <chr>       
#> 1 bad_approach  Sepal.Width * const mutate_p75TX
#> 2 best_approach Sepal.Width * 1.414 mutate_p75TX