Make cross_val_score accept multi-metric scoring

I'm not sure why we deliberately exclude multi-metric scoring in cross_val_score. cross_validate (which cross_val_score calls, supports it, and we could simply return the multi-metric scores calculated by it.

This is our cross_val_score:

scikit-learn/sklearn/model_selection/_validation.py

Lines 576 to 591 in 405a5a0

    
           scorer = check_scoring(estimator, scoring=scoring) 
        
           cv_results = cross_validate( 
        
               estimator=estimator, 
        
               X=X, 
        
               y=y, 
        
               groups=groups, 
        
               scoring={"score": scorer}, 
        
               cv=cv, 
        
               n_jobs=n_jobs, 
        
               verbose=verbose, 
        
               fit_params=fit_params, 
        
               pre_dispatch=pre_dispatch, 
        
               error_score=error_score, 
        
           ) 
        
           return cv_results["test_score"]

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Uh oh!

Make cross_val_score accept multi-metric scoring #26955

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

	scorer = check_scoring(estimator, scoring=scoring)

	cv_results = cross_validate(
	estimator=estimator,
	X=X,
	y=y,
	groups=groups,
	scoring={"score": scorer},
	cv=cv,
	n_jobs=n_jobs,
	verbose=verbose,
	fit_params=fit_params,
	pre_dispatch=pre_dispatch,
	error_score=error_score,
	)
	return cv_results["test_score"]

Search code, repositories, users, issues, pull requests...

Uh oh!

Make cross_val_score accept multi-metric scoring #26955

Description

Metadata

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

Issue actions