This project is designed to introduce R users, or potential R users, to the tidymodels workflow for using machine learning in R. Adopting the tidymodels workflow for machine learning is useful because it allows the user to keep a consistent workflow while being able to "plug and play" different machine learning algorithms.
It will be useful to have some basic familiarity with R and it is recommended to have an installation of R and RStudio on your computer or a remote desktop (e.g. Nectar environment), or RStudio Cloud. We'll be using the penguins dataset from the palmerpenguins package. We'll be using the tidymodels, tidyverse, vip, fastshap, lubridate, janitor and ggcorrplot to do data processing, modeling and machine learning. We'll need to install these packages first. An R script to do this can be found in the "./R" folder, or the install.pacakges() command can be used. To follow along with the workshop tutorial, open the imas-tidymodels.Rmd or imas-tidymodels.R (if you don't like markdown format) file in your Rstudio or Rstudio Cloud, otherwise the document can be read in the imas-tidymodels.html file.