Create reduced random forest
Now, it's time to fit a reduced model using train_reduced
and evaluate it using test_reduced
. rf_spec
is available for you to fit the reduced model. The full model had an F1 value of 0.948. As you fit and evaluate a reduced model, keep in mind there is always a trade-off between model simplicity and model performance. You have to make a judgment call about whether the benefits of the model reduction are worth any decrease in model performance, if there is any.
The tidyverse
, tidymodels
, and vip
packages have been loaded for you.
This exercise is part of the course
Dimensionality Reduction in R
Exercise instructions
- Use the
rf_spec
to fit the reduced random forest model. - Bind the reduced model predictions to
test_reduced
. - Calculate the F1 metric for the reduced model.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Fit a reduced model
rf_reduced_fit <- ___ %>%
___(___, ___ = ___)
# Create test set prediction data frame
predict_reduced_df <- ___ %>%
___(predict = ___(___, ___))
# Calculate F1 performance
___(___, ___, ___)