Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Discuss the changes in #2099 #2204

Closed
ja-thomas opened this issue Mar 2, 2018 · 2 comments
Closed

Discuss the changes in #2099 #2204

ja-thomas opened this issue Mar 2, 2018 · 2 comments

Comments

@ja-thomas
Copy link
Contributor

ja-thomas commented Mar 2, 2018

#2099

ed18b6a

@mb706
Copy link
Contributor

mb706 commented Mar 2, 2018

The problem here is that learners that don't have the "missings" property show one of three behaviours:

  1. Actually is able to do predictions with NA features
  2. Does not handle NA features during prediction, but makes NA predictions for affected rows
  3. Does not handle NA features during prediction and actually returns an error when they are present

#2099 tries to avoid 3) by forcing the behaviour in 2). There are only very few of kind 1), so this may or may not be an acceptable tradeoff (and having a "missings.predict" or so property would help). Behaviour 3) is annoying, however, especially when unseen classes are turned into NAs.

@pat-s
Copy link
Member

pat-s commented Jun 6, 2019

Discussion ported to mlr3.

@pat-s pat-s closed this as completed Jun 6, 2019
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

No branches or pull requests

3 participants