Join GitHub today
GitHub is home to over 40 million developers working together to host and review code, manage projects, and build software together.Sign up
[MRG] Fix selection of solver in ridge_regression when solver=='auto' #13363
What does this implement/fix? Explain your changes.
The solver that was selected when
Any other comments?
Thanks @jnothman. I fixed the error message. I agree that it might be better to raise instead of changing automagically the solver, but it was the old behaviour and I didn't want to change it in this PR. However, if there is a consensus to raise, I will update this PR.
@jeremiedbb I made the changes as you suggested. I still kept the warning, because I don't want to break people's code, when the used return_intercept=True and set a solver to a different value than
I tried fitting intercept with saga and it did not work (see my comment above).
Sorry, I am a bit confused with the review process. I meant approving not merging the PR.
@NicolasHug for the moment only _BaseRidge estimator implements fit_intercept for sparse_cg. This still does not work for ridge_regression function, which only supports the intercept in solvers that fit it directly (sag). This will be changed in the future, but requires some refactoring, see comment: #13336 (comment)
DOC Adds recent core devs to _contributors.rst (scikit-learn#13640) DOC t-SNE perplexity docstring update (scikit-learn#13069) FIX feature importances in random forests sum up to 1 (scikit-learn#13636) DOC Removed a typo from the examples of normalized_mutual_info_score (scikit-learn#13646) MAINT: n_jobs=-1 replaced with n_jobs=4 in tests (scikit-learn#13644) This change is to work around the hang scikit-learn#12263 afflicting Windows on machines with > 62 hyperthreads. Add parameter for stacking missing indicator into iterative imputer (scikit-learn#13601) FIX ignore single node trees in gbm's feature importances (scikit-learn#13620) DOC typo in sklearn.utils.extmath.weighted_mode (scikit-learn#13655) 1.5+2 = 3.5, not 3. ENH Extension of v_measure_score metric to include beta parameter (scikit-learn#13607) BUG Fix missing 'const' in a few memoryview declaration in trees. (scikit-learn#13626) BLD: check OpenMP support and add a switch to build without it (scikit-learn#13543) FIX initialise Birch centroid_ in all cases (scikit-learn#13651) DOC Improve performance of the plot_rbm_logistic_classification.py example (scikit-learn#13383) (scikit-learn#13648) MNT Import linear assignment from scipy (scikit-learn#13465) DOC Fixes formatting issue in webkit (scikit-learn#13657) Fixing parameter description (for assume_centered) (scikit-learn#13456) * Fixing parameter description (for assume_centered) Fixing parameter description (for assume_centered) * Update shrunk_covariance_.py * Update empirical_covariance_.py MAINT Unvendor joblib (scikit-learn#13531) Improve comment in setup.py (scikit-learn#13661) MAINT Replace absolute imports with relative imports (scikit-learn#13653) [MRG] Fix various solver issues in ridge_regression and Ridge classes (scikit-learn#13363) [MRG + 1] Fix pprint ellipsis (scikit-learn#13436) DOC Remove space in "cross-entropy" (scikit-learn#13671) FIX broken references in documentation (scikit-learn#13664) DOC Remove synonyms in documentation of linear models (scikit-learn#13663) MNT Correctly handle deprecated attribute warnings and docstrings (scikit-learn#13635) Deprecate "warn_on_dtype" from check_array (scikit-learn#13382) Fix MultiOutputClassifier checking for predict_proba method of base estimator (scikit-learn#12222) fix small latex issue (scikit-learn#13680) Fix sample_weight in label_ranking_average_precision_score (scikit-learn#13447) DOC Emeritus core devs final call (scikit-learn#13673) ENH Add verbose option to Pipeline, FeatureUnion, and ColumnTransformer (scikit-learn#11364)