brunocarlin / tidy.outliers Goto Github PK

library(recipes)
#> Loading required package: dplyr
#> 
#> Attaching package: 'dplyr'
#> The following objects are masked from 'package:stats':
#> 
#>     filter, lag
#> The following objects are masked from 'package:base':
#> 
#>     intersect, setdiff, setequal, union
#> 
#> Attaching package: 'recipes'
#> The following object is masked from 'package:stats':
#> 
#>     step
library(tidy.outliers)

rec <-
  recipe(mpg ~ ., data = mtcars) %>%
  step_outliers_outForest(all_numeric_predictors()) %>%
  prep(mtcars)
#> Due to small sample size, reduced 'min.node.size' to 11

bake(rec, new_data = NULL) %>% 
  select(.outliers_outForest)
#> # A tibble: 32 × 1
#>    .outliers_outForest$score
#>                        <dbl>
#>  1                         0
#>  2                         0
#>  3                         0
#>  4                         0
#>  5                         0
#>  6                         0
#>  7                         0
#>  8                         0
#>  9                         1
#> 10                         0
#> # … with 22 more rows

library(tidymodels)
library(tidy.outliers)

# split data into the training and testing sets
set.seed(123)
split <- mtcars %>% 
  initial_split(prop = 0.8)
df_train = training(split)
df_test = testing(split)

# preprocessing steps
rec <-
  recipe(mpg ~ ., data = mtcars) %>%
  step_outliers_lookout(all_numeric_predictors(), skip = FALSE) %>%
  step_outliers_remove(contains(".outliers"), skip = FALSE) %>% 
  prep(training = df_train, retain = TRUE)

# processing the training data
df_train_preprocessed <- bake(rec, new_data = NULL)

# processing the testing data
df_test_preprocessed <- bake(rec, new_data = df_test)
#> Error:
#> ! Assigned data `object$outlier_score` must be compatible with existing data.
#> ✖ Existing data has 7 rows.
#> ✖ Assigned data has 25 rows.
#> ℹ Only vectors of size 1 are recycled.

#> Backtrace:
#>      ▆
#>   1. ├─recipes::bake(rec, new_data = df_test)
#>   2. ├─recipes:::bake.recipe(rec, new_data = df_test)
#>   3. │ ├─recipes::bake(step, new_data = new_data)
#>   4. │ └─tidy.outliers:::bake.step_outliers_lookout(step, new_data = new_data)
#>   5. │   ├─base::`[[<-`(`*tmp*`, object$name_mutate, value = `<dbl>`)
#>   6. │   └─tibble:::`[[<-.tbl_df`(`*tmp*`, object$name_mutate, value = `<dbl>`)
#>   7. │     └─tibble:::tbl_subassign(...)
#>   8. │       └─tibble:::vectbl_recycle_rhs_rows(...)
#>   9. │         ├─base::withCallingHandlers(...)
#>  10. │         └─vctrs::vec_recycle(value[[j]], nrow)
#>  11. ├─vctrs:::stop_recycle_incompatible_size(...)
#>  12. │ └─vctrs:::stop_vctrs(...)
#>  13. │   └─rlang::abort(message, class = c(class, "vctrs_error"), ..., call = vctrs_error_call(call))
#>  14. │     └─rlang:::signal_abort(cnd, .file)
#>  15. │       └─base::signalCondition(cnd)
#>  16. └─tibble (local) `<fn>`(`<vctrs___>`)
#>  17.   └─rlang::cnd_signal(...)