Fitting and assessing the model
Now that you have addressed missing values and created dummy variables, it is time to assess your model's performance!
The attrition
dataset, along with the test
and train
splits, the lr_recipe
and your declared logistic_model()
are all loaded for you.
This exercise is part of the course
Feature Engineering in R
Exercise instructions
- Bundle model and recipe in workflow.
- Fit workflow to the train data.
- Generate an augmented data frame for performance assessment.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Bundle model and recipe in workflow
lr_workflow <- ___() %>%
add_model(lr_model) %>%
add_recipe(lr_recipe)
# Fit workflow to the train data
lr_fit <- ___(lr_workflow, data = train)
# Generate an augmented data frame for performance assessment
lr_aug <- lr_fit %>% ___(test)
lr_aug %>% roc_curve(truth = Attrition, .pred_No) %>% autoplot()
bind_rows(lr_aug %>% roc_auc(truth = Attrition, .pred_No),
lr_aug %>% accuracy(truth = Attrition, .pred_class))