* Initial implementation
* Forgot to add to second __add__ list
* Update split method parameter doc
* Added example; changed default test_size to 0.1; added to author list
* StratifiedGroupKFold impl and other improvements
* Add class to __all__ spec
* Remove random_state when no shuffle
* Tighter formatting
* Update the implementation of StratifiedGroupKFold
* Add StratifiedGroupKFold to __init__
* Add y checks to StartifiedGroupKFold
* Raise error if n_splits > max num samples in class
* Warn if n_splits > mn num samples in class
* Add SGKfold to general repr test
* Add SGKFold to 2d_y test case
* Add SGKfold to value erros test case
Parameters are the same as for StratifiedKFold
to ensure similar behavior given n_groups == n_samples
* Add SGKFold to StratifiedKFold test cases
The idea is to ensure similar behavior when groups are trivial
(n_groups == n_samples)
* Add SGKFold to reproducibility test case
* Add SGKFold to GroupKFold test case
* Add SGKFold to nested cv test case
* Add SGKFold to random_state with shuffle=False test case
* Add SGKFold to constant splits test case
* Fix repr test case
* Fix formatting issues
* Add samples to a fold with least num samples
Required to produce balanced size folds when the distribution of y is
more or less the same
* Remove GroupShuffleSplit impl
* Add notes to StratifiedGroupKFold
* Fix doctest
* Added stratified group kfold tests
* Better variable naming
* Add section to documentation
* Remove leftover StratifiedGroupShuffleSplit import
* Add changelist and reference to original kernel
* Better naming for least populated class check
* Better expression for number of labels
* Remove use of Counter
We already have this data in output of np.unique
* Add tests for homogeneous groups
* Add StratifiedGroupKFold test against GroupKFold
* Add changes to changelist in docstring
* Add StratifiedGroupKFold to classes.rst
* Fix description of StratifiedGroupKFold
* Move license notice out of docstring
* Disambiguate labels to classes in doc
* Add changelog entry
* Fix changelog author entry
* Fix StratifiedGroupKFold docstring
* Better variable names
* Remove defaultdict in favor of numpy indexing
* Extracted best_fold search into a separate method
* Make use of numpy broadcasting instead of for loop
* Encode groups and use arrays instead of dicts
* Use numpy sort instead of python
* Clarify shuffling behavior of StratifiedGroupKF in docs
* Switch name from label_idx to class_idx
* Remove accidentally leftover comment
* Fix np.sort keyword to support numpy < 1.15
* Fix typo in docstring
* Add StratifiedGroupKFold to visualization doc
* Add visualization for uneven group as an example
* Fix image numbers to match updated example
* Add author
* Add SGKF visualization to docs
* Add comments for groups in stratified CV tests
Co-authored-by: Leandro Hermida <hermidal@cs.umd.edu>
Co-authored-by: marrodion <rodion_martynov@epam.com>
* More flexible grid search interface
* added info dict parameter
* Put back removed test
* renamed info into more_results
* Passed grroups as well since we need n_to use get_n_splits(X, y, groups)
* port
* pep8
* dabl -> sklearn
* add _required_parameters
* skipping check in rst file if pandas not installed
* Update sklearn/model_selection/_search_successive_halving.py
Co-Authored-By: Joel Nothman <joel.nothman@gmail.com>
* renamed into GridHalvingSearchCV and RandomHalvingSearchCV
* Addressed thomas' comments
* repr
* removed passing group as a parameter to evaluate_candidates
* Joels comments
* pep8
* reorganized user user guide
* renaming
* update user guide
* remove groups support + pass fit_params
* parameter renaming
* pep8
* r_i -> resource_iter
* fixed r_i issues
* examples + removed use of word budget
* Added inpute checking tests
* added cv_resutlts_ user guide
* minor title change
* fixed doc layout
* Addressed some comments
* properly pass down fit_params
* change default value of force_exhaust_resources and update doc
* should fix doc
* Used check_fit_params
* Update section about min_resources and number of candidates
* Clarified ratio section
* Use ~ to refer to classes
* fixed doc checks
* Apply suggestions from code review
Co-authored-by: Joel Nothman <joel.nothman@gmail.com>
* Addressed easy comments from Joel
* missed some
* updated docstring of run_search
* Used f strings instead of format
* remove candidate duplication checks
* fix example
* Addressed easy comments
* rotate ticks labels
* Added discussion in the intro as suggested by Joel
* Split examples into sections
* minor changes
* remove force_exhaust_budget and introduce min_resources=exhaust
* some minor validation
* Added a n_resources_ attribute
* update examples
* Addressed comments
* passing CV instead of X,y
* minor revert for handling fit_params
* updated docs
* fix len
* whatsnew
* Add test for sampling when all_list
* minor change to top-k
* Force CV splits to be consistent across calls
* reorder parameters
* reduced diff
* added tests for top_k
* put back doc for groups
* not sure what went wrong
* put import at its place
* some comment
* Addressed comments
* Added tests for cv_results_ and base estimator inputs
* pep8
* avoid monkeypatching
* rename df
* use Joel's suggestions for testing masks
* Made it experimental
* Should fix docs
* whats new entry
* Apply suggestions from code review
Co-authored-by: Andreas Mueller <t3kcit@gmail.com>
* Addressed comments to docs
* Addressed comments in examples
* minor doc update
* minor renaming in UG
* forgot some
* some sad note about splitter statefulness :'(
* Addressed comments
* ratio -> factor
Co-authored-by: Joel Nothman <joel.nothman@gmail.com>
Co-authored-by: Andreas Mueller <t3kcit@gmail.com>
* normalize_components in sparsePCA
* changed default strategy of Dummy to prior and removed outputs_2d ttribute
* removed usage of None to drop estimator in ensemble and behaviour param of IsolationForest
* remove support for drop=None in Voting
* removed some warning decorators
* remove feature_extraction.extract_patches
* removed VectorizerMixin and copy parameter from TFIDFVectorizer
* kernel.set_params now raises attributeerror
* removed fig from plot_partial_dependence
* removed iid parameter of search estimators
* removed brier_scorer
* raise error in split when shuffle is False and random_state is not None
* removed MultiOutputEstimator
* removed base classes of NaiveBayes
* removed drop from pipeline
* removed utils in random_projection
* removed presort and classes_ in trees
* flake8
* fixed some tests
* flake
* fixed docstring
* fixed other one
* some left
* mmmm
* Enable StratifiedKFold to produce different splits
* what's new
* redundant statement
* update what's new
* redundant comment
* add a test
* move what's new entry
* review comment
* review comment
* Fixed typo in an example
* Removed un-needed lines from example
* Added tests on the validity of parameters
* Fixed error msg for train_size issue
* Added tests to check the validation of test and train sizes
* Switched to parameterized test
* Fixed typo in error msg
* Swithced to pytest.raises
* Swithced to pytest.raises also when checking msg
* Improved the validity tests and their unit testing
Part of #11992.
These were all the things that seemed pretty straight-forward. It's actually a bit bulky but should still be easy to review, hopefully.
* add FutureWarning for methods with defaults=3
* add explicit cv values to fix assertion errors
* add tests for catching the FutureWarning
* Write current deprecation version
* Add deprecation in docstring
* change default cv value to None
* change cv from 3 to 5 in the examples
* upgrade doctests
* update doctest in tutorial
* update doctest in cross-validation doc
* fix tests
* add entry to whats new
* address Gael comments
* address Gael comments 2
* fix wrong indentation
* update doc
* add docstring deprecation warning in CV subclasses
* address Andy's comments
* fix PR number
* fix flake8
* add filterwarnings in tests
* fix doctests
* cv=None mendatory in Ridge
* fix warning related errors
* skip some doctests warnings
* make travis happy
* change from deprecated to versionchanged
* fix doctests and remove skipping
* address comments
Megabyte
Hanmin Qin