8.6 TIDY A RECIPE

tidy() method for recipes

ames_rec <- 
  recipe(Sale_Price ~ Neighborhood + Gr_Liv_Area + Year_Built + Bldg_Type + 
           Latitude + Longitude, data = ames_train) %>%
  step_log(Gr_Liv_Area, base = 10) %>% 
  step_other(Neighborhood, threshold = 0.01) %>% 
  step_dummy(all_nominal_predictors()) %>% 
  step_interact( ~ Gr_Liv_Area:starts_with("Bldg_Type_") ) %>% 
  step_ns(Latitude, Longitude, deg_free = 20)

tidy(ames_rec)

## # A tibble: 5 × 6
##   number operation type     trained skip  id            
##    <int> <chr>     <chr>    <lgl>   <lgl> <chr>         
## 1      1 step      log      FALSE   FALSE log_qfevz     
## 2      2 step      other    FALSE   FALSE other_92ULm   
## 3      3 step      dummy    FALSE   FALSE dummy_4lh10   
## 4      4 step      interact FALSE   FALSE interact_DFf9K
## 5      5 step      ns       FALSE   FALSE ns_EvmMV

we add the id = "my_id" in the step_other()

ames_rec <- 
  recipe(Sale_Price ~ Neighborhood + Gr_Liv_Area + Year_Built + Bldg_Type + 
           Latitude + Longitude, data = ames_train) %>%
  step_log(Gr_Liv_Area, base = 10) %>% 
  step_other(Neighborhood, threshold = 0.01, id = "my_id") %>% 
  step_dummy(all_nominal_predictors()) %>% 
  step_interact( ~ Gr_Liv_Area:starts_with("Bldg_Type_") ) %>% 
  step_ns(Latitude, Longitude, deg_free = 20)


lm_wflow <- 
  workflow() %>% 
  add_model(lm_model) %>% 
  add_recipe(ames_rec)

lm_fit <- fit(lm_wflow, ames_train)

estimated_recipe <- 
  lm_fit %>% 
  extract_recipe(estimated = TRUE)

tidy(estimated_recipe, id = "my_id")

## # A tibble: 21 × 3
##    terms        retained           id   
##    <chr>        <chr>              <chr>
##  1 Neighborhood North_Ames         my_id
##  2 Neighborhood College_Creek      my_id
##  3 Neighborhood Old_Town           my_id
##  4 Neighborhood Edwards            my_id
##  5 Neighborhood Somerset           my_id
##  6 Neighborhood Northridge_Heights my_id
##  7 Neighborhood Gilbert            my_id
##  8 Neighborhood Sawyer             my_id
##  9 Neighborhood Northwest_Ames     my_id
## 10 Neighborhood Sawyer_West        my_id
## # ℹ 11 more rows

tidy(estimated_recipe, number = 2)

## # A tibble: 21 × 3
##    terms        retained           id   
##    <chr>        <chr>              <chr>
##  1 Neighborhood North_Ames         my_id
##  2 Neighborhood College_Creek      my_id
##  3 Neighborhood Old_Town           my_id
##  4 Neighborhood Edwards            my_id
##  5 Neighborhood Somerset           my_id
##  6 Neighborhood Northridge_Heights my_id
##  7 Neighborhood Gilbert            my_id
##  8 Neighborhood Sawyer             my_id
##  9 Neighborhood Northwest_Ames     my_id
## 10 Neighborhood Sawyer_West        my_id
## # ℹ 11 more rows