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

AutoTuner should maybe use $predict_type from the tuned learner. #476

Closed
sebffischer opened this issue Nov 28, 2024 · 1 comment
Closed

Comments

@sebffischer
Copy link
Member

I just ran into this that I passed a learner with predict_type "prob" to the AutoTuner, but forgot to set the predict type for the AutoTuner itself. I would argue that it is a better default to set the predict type of the AutoTuner during $initialize() to the predict type of the learner that is being tuned.

@be-marc
Copy link
Member

be-marc commented Jan 14, 2025

Actually there is a unit test for this. Not sure why it didn't work for you.

at = AutoTuner$new(tuner, lrn("classif.rpart", predict_type = "prob"), r_inner, ms, te, param_set)
expect_null(at$tuning_instance)
expect_equal(at$predict_type, "prob")

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

2 participants