Summary
In this chapter, you prepared for hyperparameter fine-tuning by establishing a baseline XGBoost model using StratifiedKFold. Then, you combined GridSearchCV and RandomizedSearchCV to form one powerful function. You learned the standard definitions, ranges, and applications of key XGBoost hyperparameters, in addition to a new technique called early stopping. You synthesized all functions, hyperparameters, and techniques to fine-tune the heart disease dataset, gaining an impressive five percentage points from the default XGBoost classifier.
XGBoost hyperparameter fine-tuning takes time to master, and you are well on your way. Fine-tuning hyperparameters is a key skill that separates machine learning experts from machine learning novices. Knowledge of XGBoost hyperparameters is not just useful, it's essential to get the most out of the machine learning models that you build.
Congratulations on completing this important chapter.
Next, we present a case study of XGBoost...
