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

Skip to content

[WIP] Ensure delegated ducktyping in MetaEstimators#2018

Closed
jnothman wants to merge 2 commits into
scikit-learn:masterfrom
jnothman:master
Closed

[WIP] Ensure delegated ducktyping in MetaEstimators#2018
jnothman wants to merge 2 commits into
scikit-learn:masterfrom
jnothman:master

Conversation

@jnothman
Copy link
Copy Markdown
Member

This intends to solve #1805, ensuring that appropriate metaestimators have hasattr(metaest, method) == True iff the sub-estimator does for the set of standard methods: inverse_transform, transform, predict, predict_proba, predict_log_proba, decision_function, score.

I am posting this as a WIP so that you can:

  • check the testing is reasonable;
  • offer patches to relevant estimators

(I have pulled in the relevant commit from #1769 and removed its Pipeline-particular testing.)

jnothman added 2 commits May 21, 2013 13:41
Also rename FeatureSelectionMixin -> SelectorMixin -> _LearntSelectorMixin
And rename sklearn.feature_selection.{selector_mixin -> from_model}
Also rename FeatureSelectionMixin -> SelectorMixin -> _LearntSelectorMixin
And rename sklearn.feature_selection.{selector_mixin -> from_model}
@jnothman
Copy link
Copy Markdown
Member Author

Wrong branch! closing and trying again!

@jnothman jnothman closed this May 30, 2013
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

Successfully merging this pull request may close these issues.

1 participant