tests/testthat/_snaps/downsample.md

In themis: Extra Recipes Steps for Dealing with Unbalanced Data

ratio deprecation

Code
  new_rec <- step_downsample(recipe(~., data = circle_example), class, ratio = 2)
Condition
  Error:
  ! The `ratio` argument of `step_downsample()` was deprecated in themis 0.2.0 and is now defunct.
  i Please use the `under_ratio` argument instead.

bad data

Code
  prep(step_downsample(rec, x))
Condition
  Error in `step_downsample()`:
  Caused by error in `prep()`:
  ! `x` should be a factor variable.

Code
  prep(step_downsample(rec, class, id))
Condition
  Error in `step_downsample()`:
  Caused by error in `prep()`:
  ! The selector should select at most a single variable.

case_weights

Code
  rec1_p
Message

  -- Recipe ----------------------------------------------------------------------

  -- Inputs 
  Number of variables by role
  predictor:    4
  case_weights: 1

  -- Training information 
  Training data contained 400 data points and no incomplete rows.

  -- Operations 
  * Down-sampling based on: class | Trained, weighted

Code
  rec1_p
Message

  -- Recipe ----------------------------------------------------------------------

  -- Inputs 
  Number of variables by role
  predictor:    4
  case_weights: 1

  -- Training information 
  Training data contained 400 data points and no incomplete rows.

  -- Operations 
  * Down-sampling based on: class | Trained, ignored weights

bad args

Code
  prep(step_downsample(recipe(~., data = mtcars), under_ratio = "yes"))
Condition
  Error in `step_downsample()`:
  Caused by error in `prep()`:
  ! `under_ratio` must be a number, not the string "yes".

Code
  step_downsample(recipe(~., data = mtcars), seed = TRUE)
Condition
  Error in `step_downsample()`:
  ! `seed` must be a whole number, not `TRUE`.

Code
  step_downsample(recipe(~., data = mtcars), replacement = "yes")
Condition
  Error in `step_downsample()`:
  ! `replacement` must be `TRUE` or `FALSE`, not the string "yes".

unused outcome levels are skipped with a warning (#238)

Code
  res <- bake(prep(step_downsample(recipe(class ~ ., data = circle_example),
  class)), new_data = NULL)
Condition
  Warning in `prep()`:
  Unused factor level "unused" in `class` was dropped.
  i  Level with zero observations is skipped when computing sampling targets.

step_downsample() errors on a bad under_ratio vector (#323)

Code
  prep(step_downsample(recipe(class ~ x, data = df), class, under_ratio = c(a = 1,
    potato = 1)))
Condition
  Error in `step_downsample()`:
  Caused by error in `prep()`:
  ! `under_ratio` names must be levels of the outcome.
  x Unknown name: "potato".
  i Available levels: "a" and "b".

Code
  prep(step_downsample(recipe(class ~ x, data = df), class, under_ratio = c(a = 1,
    a = 2)))
Condition
  Error in `step_downsample()`:
  Caused by error in `prep()`:
  ! `under_ratio` must have unique names, but "a" is duplicated.

step_downsample() checks under_ratio names when prepped (#323)

Code
  prep(step_downsample(recipe(class ~ ., data = df), class, under_ratio = c(a = 1,
    potato = 1)))
Condition
  Error in `step_downsample()`:
  Caused by error in `prep()`:
  ! `under_ratio` names must be levels of the outcome.
  x Unknown name: "potato".
  i Available levels: "a", "b", and "c".

bake method errors when needed non-standard role columns are missing

Code
  bake(trained, new_data = circle_example[, -3])
Condition
  Error in `step_downsample()`:
  ! The following required column is missing from `new_data`: class.

empty printing

Code
  rec
Message

  -- Recipe ----------------------------------------------------------------------

  -- Inputs 
  Number of variables by role
  outcome:    1
  predictor: 10

  -- Operations 
  * Down-sampling based on: <none>

Code
  rec
Message

  -- Recipe ----------------------------------------------------------------------

  -- Inputs 
  Number of variables by role
  outcome:    1
  predictor: 10

  -- Training information 
  Training data contained 32 data points and no incomplete rows.

  -- Operations 
  * Down-sampling based on: <none> | Trained

printing

Code
  print(rec)
Message

  -- Recipe ----------------------------------------------------------------------

  -- Inputs 
  Number of variables by role
  predictor: 4

  -- Operations 
  * Down-sampling based on: class

Code
  prep(rec)
Message

  -- Recipe ----------------------------------------------------------------------

  -- Inputs 
  Number of variables by role
  predictor: 4

  -- Training information 
  Training data contained 400 data points and no incomplete rows.

  -- Operations 
  * Down-sampling based on: class | Trained

themis documentation built on Aug. 2, 2026, 9:07 a.m.