Skip to content

DOC More notes about the difference between the three base scorers#14358

Merged
qinhanmin2014 merged 3 commits intoscikit-learn:masterfrom
qinhanmin2014:make_scorer_doc
Jul 19, 2019
Merged

DOC More notes about the difference between the three base scorers#14358
qinhanmin2014 merged 3 commits intoscikit-learn:masterfrom
qinhanmin2014:make_scorer_doc

Conversation

@qinhanmin2014
Copy link
Copy Markdown
Member

Closes #10247
summarize the difference of the three base scorers, though this is not always the case (e.g., when needs_threshold is True, we'll still accept the output of predict_proba when decision_function is not available, but in this case, users can set needs_proba to True instead)

Copy link
Copy Markdown
Member

@NicolasHug NicolasHug left a comment

Choose a reason for hiding this comment

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

Thanks, this is definitely useful info.

The doc renderring is bit odd https://64673-843222-gh.circle-artifacts.com/0/doc/modules/generated/sklearn.metrics.make_scorer.html

Also, why not simply add these notes in the parameter docstrings?

LGTM anyway, apart from the formatting issue.

@qinhanmin2014
Copy link
Copy Markdown
Member Author

Also, why not simply add these notes in the parameter docstrings?

IMO If we put these things in parameter docstring, we split these things everywhere.

@qinhanmin2014
Copy link
Copy Markdown
Member Author

Copy link
Copy Markdown
Member

@glemaitre glemaitre left a comment

Choose a reason for hiding this comment

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

A couple of nitpicks. Otherwise LGTM

Co-Authored-By: Guillaume Lemaitre <g.lemaitre58@gmail.com>
@qinhanmin2014 qinhanmin2014 merged commit 9310d5e into scikit-learn:master Jul 19, 2019
@qinhanmin2014 qinhanmin2014 deleted the make_scorer_doc branch July 19, 2019 02:43
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.

Assymetry of roc_auc_score

3 participants