R recipes step_YeoJohnson 楊約翰遜轉變

step_YeoJohnson(
  recipe,
  ...,
  role = NA,
  trained = FALSE,
  lambdas = NULL,
  limits = c(-5, 5),
  num_unique = 5,
  na_rm = TRUE,
  skip = FALSE,
  id = rand_id("YeoJohnson")
)

其他單獨的轉換步驟：step_BoxCox() , step_bs() , step_harmonic() , step_hyperbolic() , step_inverse() , step_invlogit() , step_logit() , step_log() , step_mutate() , step_ns() , step_percentile() , step_poly() , step_relu() , step_sqrt()

data(biomass, package = "modeldata")

biomass_tr <- biomass[biomass$dataset == "Training", ]
biomass_te <- biomass[biomass$dataset == "Testing", ]

rec <- recipe(
  HHV ~ carbon + hydrogen + oxygen + nitrogen + sulfur,
  data = biomass_tr
)

yj_transform <- step_YeoJohnson(rec, all_numeric())

yj_estimates <- prep(yj_transform, training = biomass_tr)

yj_te <- bake(yj_estimates, biomass_te)

plot(density(biomass_te$sulfur), main = "before")

plot(density(yj_te$sulfur), main = "after")


tidy(yj_transform, number = 1)
#> # A tibble: 1 × 3
#>   terms         value id              
#>   <chr>         <dbl> <chr>           
#> 1 all_numeric()    NA YeoJohnson_A4Lkd
tidy(yj_estimates, number = 1)
#> # A tibble: 6 × 3
#>   terms      value id              
#>   <chr>      <dbl> <chr>           
#> 1 carbon   -0.0225 YeoJohnson_A4Lkd
#> 2 hydrogen  2.10   YeoJohnson_A4Lkd
#> 3 oxygen    1.78   YeoJohnson_A4Lkd
#> 4 nitrogen -0.830  YeoJohnson_A4Lkd
#> 5 sulfur   -4.09   YeoJohnson_A4Lkd
#> 6 HHV      -0.388  YeoJohnson_A4Lkd