Salt Lake City R Users Group cover photo

Tue, Jan 28, 2025, 7:00 PM UTCFrom hours to minutes: accelerating your tidymodels code
Link visible for attendees
Our January Meetup will be a remote gathering; the Zoom link will be posted the week before the event.

This talk demonstrates a 145-fold speedup in training time for a machine learning pipeline with tidymodels through 4 small changes. By adapting a grid search on a canonical model to use a more performant modeling engine, hooking into a parallel computing framework, transitioning to an optimized search strategy, and defining the grid to search over carefully, users can drastically cut down on the time to develop machine learning models with tidymodels without sacrificing predictive performance. The talk is based on Efficient Machine Learning with R, an in-progress book available at emlwr.org.
44 attendees+39
Wed, Mar 12, 2025, 6:00 PM UTCNonlinear continuous predictors in regression models
Link visible for attendees
Our March Meetup will be a remote gathering; the Zoom link will be posted the week before the event.

It's easy to build regression models where the continuous predictors have a linear relationship to the outcome variable. However, sometimes an important variable has a non-linear relationship to some outcome of interest; age is a common example. In situations like these, neither simple linear regression nor a standard transformation (e.g., taking the log of the predictor variable) provides an adequate model. This talk describes several alternative techniques for handling predictors like these, and illustrates how to implement them in R.
46 attendees+41
Tue, May 13, 2025, 6:00 PM UTCHack your way to a good git history
Link visible for attendees
Our May Meetup will be a remote gathering; the Zoom link will be posted the week before the event.

A confident git practice can change the work life of anyone writing code or prose with R, resulting in a useful history to browse or go back to, the possibility to work in parallel on different aspects, etc. In particular, it is best git practice to create small, atomic commits with informative messages. Why? And how?

Learn three reasons why small git commits are worth it. Discover how to realistically create them, without too much hassle. Find out how the saperlipopette R package can help you practice safely, and share your own git tips and questions!
43 attendees+38

Salt Lake City R Users Group