finetune
Additional functions for model tuning
The finetune package extends the tidymodels tune package with additional hyperparameter optimization methods for machine learning models. It provides two main approaches: simulated annealing for iterative search and racing methods for efficient grid search.
Simulated annealing explores the parameter space iteratively to find optimal values, accepting both better and occasionally worse configurations to escape local optima. Racing methods start by evaluating all parameter combinations on a small number of resamples, then use statistical testing (ANOVA-based or win/loss tournament-style) to eliminate poor performers early and focus computational resources on promising candidates. This makes hyperparameter tuning faster by avoiding full evaluation of parameter combinations that are unlikely to perform well.
Contributors#
Resources featuring finetune#
posit::conf(2023) Workshop: Advanced tidymodels
Register now: http://pos.it/conf Instructor: Max Kuhn, Software Engineer, Posit Workshop Duration: 1-Day Workshop
This workshop is for you if you: • have used tidymodels packages like recipes, rsample, and parsnip • are comfortable with tidyverse syntax (e.g. piping, mutates, pivoting) • have some experience with resampling and modeling (e.g., linear regression, random forests, etc.), but we don’t expect you to be an expert in these
In this workshop, you will learn more about model optimization using the tune and finetune packages, including racing and iterative methods. You’ll be able to do more sophisticated feature engineering with recipes. Time permitting, model ensembles via stacking will be introduced. This course is focused on the analysis of tabular data and does not include deep learning methods.
Participants who have completed the “Introduction to tidymodels” workshop will be well-prepared for this course. Participants who are new to tidymodels will benefit from taking the Introduction to tidymodels workshop before joining this one
Quarto with the Quarto Team | An Open-Source Chat
Join Al Manning, Carlos SchIidegger, & Charles Teague, members of the Quarto Team, as they take our questions.
Quarto is an open-source tool for scientific and technical publishing. Create dynamic content with Python, R, Julia, and Observable. Author documents as plain text markdown or Jupyter notebooks. Publish high-quality articles, reports, presentations, websites, blogs, and books in HTML, PDF, MS Word, ePub, and more. Author with scientific markdown, including equations, citations, crossrefs, figure panels, callouts, advanced layout, and more.
Key Resources: ⬡ Learn more and get started with Quarto at quarto.org
Contact ⬡ Bug reports and feature requests - https://github.com/quarto-dev/quarto-cli/issues ⬡ Need help? Github discussions - https://github.com/quarto-dev/quarto-cli/discussions
Introduction Videos for Quarto ⬡ Mine and Julia talk, https://www.youtube.com/watch?v=p7Hxu4coDl8 ⬡ Quarto Series, 1️⃣ Welcome to Quarto Workshop led by Tom Mock: https://www.youtube.com/watch?v=yvi5uXQMvu4 2️⃣ Building a Blog with Quarto led by Isabella Velásquez: https://www.youtube.com/watch?v=CVcvXfRyfE0&feature=youtu.be 3️⃣ Beautiful reports and presentations with Quarto led by Tom Mock: https://www.youtube.com/watch?v=hbf7Ai3jnxY&feature=youtu.be
Timestamps
00:00:00 Introductions
2:55 Why open source?
6:20 Can we expect to see Quarto available to R-users via CRAN any time soon?
9:10 Quarto and Google Docs?
9:49 Lua filters/shortcodes. Advice for a good development environment for prototyping and debugging?
14:59 Is there a single documentation page for ALL the quarto-specific YAML options? https://quarto.org/docs/reference
16:15 Navigating Quarto’s documentation.
18:00 Is there something like Observable SQL cells on the roadmap?
20:10 Is there something closer to {bookdown} for Quarto? What is the best way to retain data and environment objects in a quarto book? Is there any path to enabling this? See Includes, https://quarto.org/docs/authoring/includes.html
24:20 Flexdashboard? Coming soon.
26:30 A big challenge in the adoption is that Quarto is competing with ipython notebooks for mindspace, what does the Quarto team think about that? Quarto and Jupyter Notebooks will hopefully be thought of as complementary to one another, with Quarto helping a lot with narrative, layout, and appearance for publication and sharing.
30:10 Where should I go to contact you about an issue? What if the issue isn’t just Quarto, say, Quarto + Jupyter?
31:50: What is the Quarto team hoping to see the community produce? Feedback, reporting in github issues. Quarto Extensions.
34:05 Custom styling, configuring grid options. Any tips or anything in the roadmap that will help users finetune the look and feel of their output?
38:40 Terminology question; what do we call a published Quarto doc? (or webpage, blog, etc.?)
40:00 How do I stay up to date with Quarto? Getting the latest release and learning about what is new?
See what’s up on quarto.org. Look under get-started and under downloads for pre-releases
