Fit the best model

lasso_grid contains 50 different model specs with 50 different penalty values in penalty_grid. In this exercise, you will find and fit the model with the optimal penalty value. In doing so, you will end up with a lasso regression model that optimizes feature selection for best model performance.

lasso_workflow and train are available for your use. The tidyverse and tidymodels packages have also been loaded for you.

This exercise is part of the course

Dimensionality Reduction in R

View Course

Exercise instructions

Retrieve the best fitted model based on RMSE.
Use finalize_workflow() to fit a model based on best_rmse.
Display of the model coefficients of final_lasso.

Hands-on interactive exercise

Have a go at this exercise by completing this sample code.

# Retrieve the best RMSE
best_rmse <- ___ %>% 
  ___("___")

# Refit the model with the best RMSE
final_lasso <- 
  ___(___, ___) %>% 
  fit(train)

# Display the non-zero model coefficients
tidy(___) %>% 
  filter(___ > ___)

Edit and Run Code