Skip to content

Conversation

simonpcouch
Copy link
Contributor

A little bit of developer complexity for the sake of participant simplicity. Given that we're already teaching a binary classification problem, I thought it'd be nice if the colors matched the ones that participants would expect with the example plot, i.e. green and tan mean two levels of an outcome variable.

Source for the original image: https://github.com/topepo/2022-nyr-workshop/blob/19266c8254a7c53b7a29bf424e4cafcbab91d5b5/5-tuning.Rmd#L173C1-L276C4

@simonpcouch simonpcouch requested a review from hfrick August 7, 2024 16:38
@topepo
Copy link
Member

topepo commented Aug 7, 2024

Just FYI... this plot is my current favorite for showing overfitting. (code). There's also a figure for the test set data too.

image

Copy link
Member

@hfrick hfrick left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think it's helpful to have the code in here but I'm wondering if using the green/tan colors is really helpful here. It does link it back to the data at hand but that might also cause people to think that this is the forested data while it's a "generic" example. 🤔

If you think that that's unlikely, you're welcome to merge.

I also like the newer illustrations that Max posted (🙌 ), I'm gonna turn this into an issue for the next iteration of the material after conf. (Or this conf, if we feel ready.)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants