Fit, explore, and evaluate the model
Once you have defined a workflow with a recipe and a model, you can fit the data to the workflow. This is done with the training data set. The trained model is then evaluated using the test set. In this example, the target variable is categorical and you are using a logistic regression model. So you will evaluate the test predictions using the F measure. feature_selection_recipe
, lr_model
, attrition_wflow
, train
, and test
from the previous exercise are available for your use.
The tidyverse
and tidymodels
packages have been loaded for you.
This exercise is part of the course
Dimensionality Reduction in R
Exercise instructions
- Fit
attrition_wflow
using the training data. - Add the test predictions to the test data with the original
Attrition
values. - Use
f_meas()
to evaluate the model's performance on the test data. - Display the model estimates of
attrition_fit
.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Fit workflow to train data
attrition_fit <-
___ %>% ___(___ = ___)
# Add the test predictions to the test data
attrition_pred_df <- ___(___, ___) %>%
bind_cols(___ %>% select(___))
# Evaluate F score
___(___, ___, ___)
# Display model estimates
___(___)