R recipes step_indicate_na 创建缺失数据列指示器

step_indicate_na(
  recipe,
  ...,
  role = "predictor",
  trained = FALSE,
  columns = NULL,
  prefix = "na_ind",
  keep_original_cols = TRUE,
  skip = FALSE,
  id = rand_id("indicate_na")
)

其他虚拟变量和编码步骤：step_bin2factor() , step_count() , step_date() , step_dummy_extract() , step_dummy_multi_choice() , step_dummy() , step_factor2string() , step_holiday() , step_integer() , step_novel() , step_num2factor() , step_ordinalscore() , step_other() , step_regex() , step_relevel() , step_string2factor() , step_time() , step_unknown() , step_unorder()

data("credit_data", package = "modeldata")

## missing data per column
purrr::map_dbl(credit_data, function(x) mean(is.na(x)))
#>       Status    Seniority         Home         Time          Age 
#> 0.0000000000 0.0000000000 0.0013471037 0.0000000000 0.0000000000 
#>      Marital      Records          Job     Expenses       Income 
#> 0.0002245173 0.0000000000 0.0004490346 0.0000000000 0.0855410867 
#>       Assets         Debt       Amount        Price 
#> 0.0105523125 0.0040413112 0.0000000000 0.0000000000 

set.seed(342)
in_training <- sample(1:nrow(credit_data), 2000)

credit_tr <- credit_data[in_training, ]
credit_te <- credit_data[-in_training, ]

rec <- recipe(Price ~ ., data = credit_tr)

impute_rec <- rec %>%
  step_indicate_na(Income, Assets, Debt)

imp_models <- prep(impute_rec, training = credit_tr)

imputed_te <- bake(imp_models, new_data = credit_te, everything())