Skip to content

Add default params_to_tune for encoders transforms #1222

Closed
Mr-Geekman opened this issue Apr 13, 2023 · 1 comment
Closed

Add default params_to_tune for encoders transforms #1222

Mr-Geekman opened this issue Apr 13, 2023 · 1 comment
Assignees
Labels
enhancement New feature or request
Milestone

Comments

@Mr-Geekman
Copy link
Contributor

Mr-Geekman commented Apr 13, 2023

🚀 Feature Request

Add default params_to_tune for timestamp transforms.

Proposal

Suggested grid for SegmentEncoderTransform: None.

Suggested grid for MeanSegmentEncoderTransform: None.

Suggested grid for OneHotEncoderTransform: None.

Suggested grid for LabelEncoderTransform:

{
    "strategy": CategoricalDistribution(["new_value", "mean"]),
}

To discuss:

  • Strategy "none" won't work properly for some models. For example, LinearPerSegmentModel will fail on None values during prediction.
    • It was decided not to add "none" to the grid.

Test cases

Look at #1221. Check empty grid as well.

Additional context

No response

@Mr-Geekman Mr-Geekman added the enhancement New feature or request label Apr 13, 2023
@Mr-Geekman Mr-Geekman added this to the AutoML 2.0 milestone Apr 13, 2023
@github-project-automation github-project-automation bot moved this to Specification in etna board Apr 13, 2023
@Mr-Geekman Mr-Geekman moved this from Specification to Todo in etna board Apr 14, 2023
@martins0n martins0n moved this from Todo to In Progress in etna board Apr 24, 2023
@ostreech1997
Copy link
Collaborator

Closed by #1242.

@github-project-automation github-project-automation bot moved this from In Progress to Done in etna board Apr 25, 2023
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
enhancement New feature or request
Projects
Status: Done
Development

No branches or pull requests

2 participants