Thanks to visit codestin.com
Credit goes to github.com

Skip to content

TST make sure to test SearchCV on both classification and regression #20202

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

Merged
merged 1 commit into from
Jun 9, 2021

Conversation

glemaitre
Copy link
Member

We should use the product of the SearchCV, classifier, and regressor instead of a zip.
I don't think that I intended the current behaviour when creating the test.

Copy link
Member

@ogrisel ogrisel left a comment

Choose a reason for hiding this comment

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

That should yield 8 test cases instead of 4 previously? I think this is fine.

Alternatively one could have just swapped Ridge and LogisticRegression to keep 4 cases but ensured that to have:

  • GS + Ridge
  • RS + LR
  • GS + pipeline(PCA + LR)
  • RS + pipeline(PCA + Ridge)

with a comment to explain that this would offers tradeoff exhaustive of the combinations with test speed.

This way we have test for GS and RS both in regression and classification problem, both with and without pipelines.

@lesteve lesteve merged commit a253826 into scikit-learn:main Jun 9, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants