In this chapter, you will gain proficiency with decision trees, the primary machine learning algorithm from which XGBoost models are built. You will also gain first-hand experience in the science and art of hyperparameter fine-tuning. Since decision trees are the foundation of XGBoost models, the skills that you learn in this chapter are essential to building robust XGBoost models going forward.
In this chapter, you will build and evaluate decision tree classifiers and decision tree regressors, visualize and analyze decision trees in terms of variance and bias, and fine-tune decision tree hyperparameters. In addition, you will apply decision trees to a case study that predicts heart disease in patients.
This chapter covers the following main topics:
Introducing decision trees with XGBoost
Exploring decision trees
Contrasting variance and bias
Tuning decision tree hyperparameters
Predicting heart disease – a case...