Tuning hyperparameters and stacking models with "tidymodels" | R Tutorial (2021)

Published: 06 April 2021
on channel: RichardOnData
2,324
73

Subscribe to RichardOnData here:    / @richardondata  

Patreon:   / richardondata  

GitHub: https://github.com/RichardOnData/YouT...

Caret tutorial series:
Part 1:    • Preprocessing Data in R for ML with "...  
Part 2:    • Feature Elimination and Variable Impo...  
Part 3:    • Training and Tuning ML Models in R wi...  
Part 4:    • Creating ROC curves and ensembling mo...  

Tidymodels:
Part 1:    • Intro to machine learning in R with "...  
Part 2:    • Evaluating ML Performance, Resampling...  

In the previous tutorial series, we walked through the "caret" package in R for machine learning. We used the raw "GermanCredit" dataset, performed a brief exploration of it, and used the package to walk through a variety of steps: pre-processing, removing low information features, tuning hyperparameters, correcting for class imbalance, and summarizing results based on metrics we deem important. Where possible, we will perform the exact same exercise here, except we will use the "tidymodels" suite of packages to do so.

There are a few sources from which this tutorial draws influence and structure.

- "Tutorial on tidymodels for Machine Learning": https://hansjoerg.me/2020/02/09/tidym...
- "Tidymodels: tidy machine learning in R": http://www.rebeccabarter.com/blog/202...
- "Caret vs. tidymodels - comparing the old and new" by Konrad Semsch: https://konradsemsch.netlify.app/2019...
- "Tidy Modeling with R" by Max Kuhn and Julia Silge: https://www.tmwr.org/
- Recursive feature elimination example by Max Kuhn: https://github.com/stevenpawley/recip...
- Documentation for "stacks": https://stacks.tidymodels.org/article...


Watch video Tuning hyperparameters and stacking models with "tidymodels" | R Tutorial (2021) online without registration, duration hours minute second in high quality. This video was added by user RichardOnData 06 April 2021, don't forget to share it with your friends and acquaintances, it has been viewed on our site 2,324 once and liked it 73 people.