1. Learn
    2. /
  2. Courses
    3. /
  3. Supervised Learning in R: Classification

Exercise

Preventing overgrown trees

The tree grown on the full set of applicant data grew to be extremely large and extremely complex, with hundreds of splits and leaf nodes containing only a handful of applicants. This tree would be almost impossible for a loan officer to interpret.

Using the pre-pruning methods for early stopping, you can prevent a tree from growing too large and complex. See how the rpart control options for maximum tree depth and minimum split count impact the resulting tree.

rpart has been pre-loaded.

Instructions 1/2

undefined XP
  • 1
    • Use rpart() to build a loan model using the training dataset and all of the available predictors.
      • Set the model controls using rpart.control() with parameters cp set to 0 and maxdepth set to 6.
    • See how the test set accuracy of the simpler model compares to the original accuracy of 58.3%.
      • First create a vector of predictions using the predict() function.
      • Compare the predictions to the actual outcomes and use mean() to calculate the accuracy.
  • 2

    In the model controls, remove maxdepth and add a minimum split parameter, minsplit, set to 500.