Explore the process of tuning hyperparameters for an XGBoost model using tidymodels and #TidyTuesday data on beach volleyball matches. Dive into data reshaping, gameplay statistics analysis, and error handling. Learn to set up and rename variables, create model specifications, and implement a comprehensive tuning process. Visualize results, reshape data for plotting, and examine variable importance. Conclude with a final model fit and gain insights into optimizing XGBoost performance for predictive modeling in sports analytics.
Overview
Syllabus
Introduction
Data
Data reshaping
Gameplay stats
Errors
Setup
Rename with
Exploring
Model specification
Tuning
Finalize
Preprocessor
Tuning process
Visualization
Reshape
Plot
Variable importance
Last fit
Conclusion
Taught by
Julia Silge
Related Courses
-
Tuning Random Forest Hyperparameters with Tidymodels
-
Feature Engineering & Interpretability for XGBoost with Board Game Ratings
-
Predict Housing Prices in Austin TX with Tidymodels and XGBoost
-
Hyperparameter Tuning Using Tidymodels
-
Lasso Regression with Tidymodels and The Office
-
Build a Predictive Text Model for Avatar: The Last Airbender with Tidymodels
