Variable Importance Tidymodels versus Caret with Interactions

Question

Why are the variable importance plots different between tidymodels and caret when including interaction terms? I have demonstrated with the Ames housing data below. I used the same alpha/mixture and lambda/penalty in both models. The only difference between the models it the cross validation folds (I cannot figure out how to use tidymodel's folds with caret's train). Any ideas on why this is happening?

library(AmesHousing)
library(tidymodels)
library(caret)
library(vip)

df <- data.frame(ames_raw)
head(df)



# replace any missing observation with the mean

for(i in 1:ncol(df)){

  df[is.na(df[,i]), i] <- mean(df[,i], na.rm = TRUE)

}



# Create a data split object

set.seed(1994)
home_split <- initial_split(df,
                        
                        prop = 0.7,
                        
                        strata = SalePrice)



home_train <- home_split %>%

  training()



home_test <- home_split %>%

  testing()


# pre-process recipe

recipe_home <- recipe(SalePrice ~ Yr.Sold + Fireplaces + Full.Bath + Half.Bath + Year.Built +     Lot.Area,
                  
                  data = home_train) %>%

  step_interact(terms = ~ Yr.Sold:Fireplaces:Full.Bath:Half.Bath:Year.Built:Lot.Area)



# model with hyperparameters

glmnet_model <- linear_reg(penalty = tune(), # lambda
                      
                       mixture = tune()) %>% # alpha

  set_engine('glmnet') %>%

  set_mode('regression')



# model + recipe = workflow

wkfl <- workflow() %>%

  add_model(glmnet_model) %>%

  add_recipe(recipe_home)



# cv

set.seed(1994)

myfolds <- vfold_cv(home_train,
                
                v = 10,
                
                strata = SalePrice)



# grid search with cv

set.seed(1994)

glmnet_tuning <- wkfl %>%

  tune_grid(resamples = myfolds,
        
        grid = 25, # let the model find the best hyperparameters
        
        metrics = metric_set(rmse))



glmnet_tuning





# select the best model

best_glmnet_model <- glmnet_tuning %>%

  select_best(metric = 'rmse')

best_glmnet_model


# finalize the workflow

final_glmnet_wkfl <- wkfl %>%

  finalize_workflow(best_glmnet_model)



# last_fit:


glmnet_final_fit <- final_glmnet_wkfl %>%

  last_fit(split = home_split)



# extract the final model

final_glmnet <- extract_workflow(glmnet_final_fit)


# VIP final model

final_glmnet %>%

  extract_fit_parsnip() %>%

  vip(geom = "point", scale = TRUE)

set.seed(1994)

myGrid <- expand.grid(lambda = 0.00386,
                  alpha = 0.0874)

 model_glmnet <- train(SalePrice ~ (Yr.Sold + Fireplaces + Full.Bath + Half.Bath + Year.Built 
                                   + Lot.Area)^2,
                  
                  data=home_train,
                  
                  method = "glmnet",
                  
                  tune_grid = myGrid,
                  
                  metric = "RMSE",
                  
                  maximize = FALSE,
                  
                  trControl = trainControl(
                    
                    method = "cv",
                    
                    number = 10))





# variable importance

vip(model_glmnet, geom = "point", scale = TRUE)