R recipes step_impute_lower 估算低於測量閾值的數值數據

step_impute_lower(
  recipe,
  ...,
  role = NA,
  trained = FALSE,
  threshold = NULL,
  skip = FALSE,
  id = rand_id("impute_lower")
)

step_lowerimpute(
  recipe,
  ...,
  role = NA,
  trained = FALSE,
  threshold = NULL,
  skip = FALSE,
  id = rand_id("impute_lower")
)

其他插補步驟： step_impute_bag() 、 step_impute_knn() 、 step_impute_linear() 、 step_impute_mean() 、 step_impute_median() 、 step_impute_mode() 、 step_impute_roll()

library(recipes)
data(biomass, package = "modeldata")

## Truncate some values to emulate what a lower limit of
## the measurement system might look like

biomass$carbon <- ifelse(biomass$carbon > 40, biomass$carbon, 40)
biomass$hydrogen <- ifelse(biomass$hydrogen > 5, biomass$carbon, 5)

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

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

impute_rec <- rec %>%
  step_impute_lower(carbon, hydrogen)

tidy(impute_rec, number = 1)
#> # A tibble: 2 × 3
#>   terms    value id                
#>   <chr>    <dbl> <chr>             
#> 1 carbon      NA impute_lower_b4CM3
#> 2 hydrogen    NA impute_lower_b4CM3

impute_rec <- prep(impute_rec, training = biomass_tr)

tidy(impute_rec, number = 1)
#> # A tibble: 2 × 3
#>   terms    value id                
#>   <chr>    <dbl> <chr>             
#> 1 carbon      40 impute_lower_b4CM3
#> 2 hydrogen     5 impute_lower_b4CM3

transformed_te <- bake(impute_rec, biomass_te)

plot(transformed_te$carbon, biomass_te$carbon,
  ylab = "pre-imputation", xlab = "imputed"
)