Skip to content

Make regressors list always consistent with the dataset columns #444

Closed
1 task done
alex-hse-repository opened this issue Jan 11, 2022 · 0 comments
Closed
1 task done
Assignees
Labels
enhancement New feature or request

Comments

@alex-hse-repository
Copy link
Collaborator

alex-hse-repository commented Jan 11, 2022

🚀 Feature Request

The contract: "list of regressors is a subset of list of the columns" should be checked after modifying the dataset in transform loop. The extra regressors should be deleted in _update_regressors method.

Motivation

In #328 we added the regressors updating logic to TSDataset. However after applying any feature selection we get the list of regressors inconsistent with the list of columns in dataset.

Proposal

  1. Intersect the list of regressors with the list of columns in the end of _update_regressors method
  2. Remove "xfail" mark from this test and make sure that it passes

Test cases

Check that the list of regressors is consistent with the list of columns after applying FilterFeaturesTransform

Alternatives

No response

Additional context

Is blocked by #443

Checklist

  • I discussed this issue with ETNA Team
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

3 participants