Exercise

Tuning preparation

Tuning preparation is the foundation for tuning success. There are two main steps in preparing your tuning: marking hyperparameters using tune() in the model specification and creating a grid of hyperparameters that is used in tuning.

You are going to execute these two fundamental steps of the tuning process in this exercise.

Instructions

100 XP

Create a boosting specification with an "xgboost" engine for a classification model using 500 trees and mark the following parameters as tuning parameters: learn_rate, tree_depth, and sample_size. Save the result as boost_spec.
Build a regular tuning grid for the tuning parameters of boost_spec with three levels for each parameter.