recipe

1 create recipe step_xxx

tree_rec <- recipe(legal_status ~ ., data = trees_train) %>%
  
 # update the role for tree_id, since this is a variable we might like to keep around for convenience as an identifier for rows but is not a predictor or outcome. 
  update_role(tree_id, new_role = "ID") %>%
  
# step_other() to collapse categorical levels for species, caretaker, and the site info. Before this step, there were 300+ species!
  step_other(species, caretaker, threshold = 0.01) %>%
  
# create dummy for nominal data exclude outcome
  step_dummy(all_nominal(), -all_outcomes()) %>%
  
# The date column with when each tree was planted may be useful for fitting this model, but probably not the exact date, given how slowly trees grow. Let’s create a year feature from the date, and then remove the original date variable.  
  step_date(date, features = c("year")) %>%step_rm(date) %>%
  
# There are many more DPW maintained trees than not, so let’s downsample the data for training.  
  step_downsample(legal_status)%>%

# will remove all. predictor variables that contain only a single value
    step_zv(all_numeric(all_predictors())) %>% 
  
#  normalize all numeric data
  step_normalize(all_numeric()) %>% 

# use KNN to impute all predictors
step_impute_knn(all_predictors()) 

2 check recipe check_xxx

#> [1] "check_class"      "check_cols"       "check_missing"   
#> [4] "check_name"       "check_new_data"   "check_new_values"
#> [7] "check_range"      "check_type"

3 roles to select variables

In most cases, the right approach for users will be use to use the predictor-specific selectors such as all_numeric_predictors() and all_nominal_predictors().

has_role(match = "predictor")

has_type(match = "numeric")

all_outcomes()

all_predictors()

all_date()

all_date_predictors()

all_datetime()

all_datetime_predictors()

all_double()

all_double_predictors()

all_factor()

all_factor_predictors()

all_integer()

all_integer_predictors()

all_logical()

all_logical_predictors()

all_nominal()

all_nominal_predictors()

all_numeric()

all_numeric_predictors()

all_ordered()

all_ordered_predictors()

all_string()

all_string_predictors()

all_unordered()

all_unordered_predictors()

current_info()

4 reference:

https://recipes.tidymodels.org/reference/has_role.html