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

Skip to content

[WIP] minimize validation of X in adaboost #8304

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

Closed
wants to merge 1 commit into from

Conversation

dalmia
Copy link
Contributor

@dalmia dalmia commented Feb 6, 2017

Reference Issue

Fixes #7768

What does this implement/fix? Explain your changes.

This removes the restriction on X to be 2D and transfers the duty of validation of X to the base estimator.

Any other comments?

This has been implemented for only AdaboostClassifier till now. If this seems fine, will extend it to other ensembles. Also, docstring hasn't been updated yet.

@dalmia
Copy link
Contributor Author

dalmia commented Feb 6, 2017

Estimators like MultinomialNB, SVC, etc. don't allow ndim > 2. Hence, I haven't found any suitable example where I could test that my implementation works and the current one fail. Please provide suggestions.

Copy link
Member

@jnothman jnothman left a comment

Choose a reason for hiding this comment

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

This still requires that X be converted to an ndarray (not pandas), that it is finite, and selects sparse types whose preference should be determined by the base estimator, etc. I don't think X needs any validation. Does y? Read the code, work it out. This will depend on the ensemble technique.

@GaelVaroquaux
Copy link
Member

GaelVaroquaux commented Feb 7, 2017 via email

@jnothman
Copy link
Member

jnothman commented Feb 7, 2017 via email

@amueller
Copy link
Member

amueller commented Aug 7, 2019

fixed in #13174.

@amueller amueller closed this Aug 7, 2019
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.

Minimize validation of X in ensembles with a base estimator
4 participants