Mailman 3 September 2019 - Scikit-learn-commits

[scikit-learn/scikit-learn] 4b6273: ENH Native support for missing values in GBDTs (#1...
by Nicolas Hug 26 Jul '24

26 Jul '24

Branch: refs/heads/master Home: https://github.com/scikit-learn/scikit-learn Commit: 4b6273b87442a4437d8b3873ea3022ae163f4fdf https://github.com/scikit-learn/scikit-learn/commit/4b6273b87442a4437d8b387… Author: Nicolas Hug <contact(a)nicolas-hug.com> Date: 2019-08-21 (Wed, 21 Aug 2019) Changed paths: M benchmarks/bench_hist_gradient_boosting.py M doc/modules/ensemble.rst M doc/whats_new/v0.22.rst M sklearn/ensemble/_hist_gradient_boosting/_binning.pyx M sklearn/ensemble/_hist_gradient_boosting/_gradient_boosting.pyx M sklearn/ensemble/_hist_gradient_boosting/_loss.pyx M sklearn/ensemble/_hist_gradient_boosting/_predictor.pyx M sklearn/ensemble/_hist_gradient_boosting/binning.py A sklearn/ensemble/_hist_gradient_boosting/common.pxd A sklearn/ensemble/_hist_gradient_boosting/common.pyx M sklearn/ensemble/_hist_gradient_boosting/gradient_boosting.py M sklearn/ensemble/_hist_gradient_boosting/grower.py M sklearn/ensemble/_hist_gradient_boosting/histogram.pyx M sklearn/ensemble/_hist_gradient_boosting/loss.py M sklearn/ensemble/_hist_gradient_boosting/predictor.py M sklearn/ensemble/_hist_gradient_boosting/splitting.pyx M sklearn/ensemble/_hist_gradient_boosting/tests/test_binning.py M sklearn/ensemble/_hist_gradient_boosting/tests/test_compare_lightgbm.py M sklearn/ensemble/_hist_gradient_boosting/tests/test_gradient_boosting.py M sklearn/ensemble/_hist_gradient_boosting/tests/test_grower.py M sklearn/ensemble/_hist_gradient_boosting/tests/test_histogram.py M sklearn/ensemble/_hist_gradient_boosting/tests/test_loss.py M sklearn/ensemble/_hist_gradient_boosting/tests/test_predictor.py M sklearn/ensemble/_hist_gradient_boosting/tests/test_splitting.py R sklearn/ensemble/_hist_gradient_boosting/types.pxd R sklearn/ensemble/_hist_gradient_boosting/types.pyx M sklearn/ensemble/_hist_gradient_boosting/utils.pyx M sklearn/ensemble/setup.py Log Message: ----------- ENH Native support for missing values in GBDTs (#13911) * Added NaN support in mapper * pep * WIP * some more * WIP * WIP * bug fix * basic tests * some doc * avoid some interactions * Added tag * better test * decent test + fix bug * add missing_fraction param to benchmark * bin training and validation data separately * shorter test * Map missing values to first bin instead of last * pep8 * Added whats new entry * avoid some python interactions * make predict_binned work * fixed bug due to offset in bin_thresholds_ attribute * more sensible binning strat * typo * user name * Add small test * convert to fortran array in tests * some doc * Added function test * pep8 * Bin validation data using binmaper of training data * Allocate first bin for missing entries based on the whole data, not just training data. * Addressed Thomas' comments * Update sklearn/ensemble/_hist_gradient_boosting/tests/test_grower.py * Addressed Guillaume's comments * always allocate first bin for missing values * reduce diff * minor more consistent test * typo * WIP * some doc * reduce diff * pep8 * minor * remove prints * towards nan only splits * don't check right to left on split_on_nan * cleaups * format and comment * Fixed bug + added more tests * refactor tests * put back n_threads to max value * minor changes * minor cleaning * Add (failing) test that checks equivalence with min max imputation * Decrease the likelihood of ties when training the trees * More robust test * Fix pytest parametrization * Check bin thresholds in test * Try to make the test even easier to see if the Linux 32bit build would pass in this case * Don't check last non-missing bin if there's no nan * Improve min-max imputation test * FIX: _find_best_bin_to_split_right_to_left is still required even when left to right wants to split on nans * comments * remove split_on_nan * ooops deleted useless files * Got rid of individual checks in predictor code +inf thresholds are only allowed in a split on nan situation. Thresholds that are computed as +inf are capped to a very high constant value * can also remove special case in binning code * minor typos + more consistent test * renamed types -> common * 1e300 -> almost inf * added user guide section on missing values * Addressed Olivier's comment + updated whatsnew * addressed comments * Fix doctest formatting * Fix nan predictive doctest

15 19

[scikit-learn/scikit-learn] 63e5ae: TST Use same random seeds for both GaussianMixture...
by GitHub 07 Mar '24

07 Mar '24

Branch: refs/heads/master Home: https://github.com/scikit-learn/scikit-learn Commit: 63e5ae6319285c44b1a9519aa6acd9006c82a10a https://github.com/scikit-learn/scikit-learn/commit/63e5ae6319285c44b1a9519… Author: Oleksandr Pavlyk <oleksandr-pavlyk(a)users.noreply.github.com> Date: 2018-10-07 (Sun, 07 Oct 2018) Changed paths: M sklearn/mixture/tests/test_gaussian_mixture.py Log Message: ----------- TST Use same random seeds for both GaussianMixture.fit (#12307) **NOTE:** This service has been marked for deprecation: https://developer.github.com/changes/2018-04-25-github-services-deprecation/ Functionality will be removed from GitHub.com on January 31st, 2019.

4 3

[scikit-learn/scikit-learn] af8a6e: MAINT Use C99 functions from Cython (#15098)
by Roman Yurchak 28 Sep '19

28 Sep '19

Branch: refs/heads/master Home: https://github.com/scikit-learn/scikit-learn Commit: af8a6e592a1a15d92d77011856d5aa0ec4db4c6c https://github.com/scikit-learn/scikit-learn/commit/af8a6e592a1a15d92d77011… Author: Roman Yurchak <rth.yurchak(a)pm.me> Date: 2019-09-28 (Sat, 28 Sep 2019) Changed paths: M sklearn/cluster/_hierarchical.pyx M sklearn/neighbors/binary_tree.pxi M sklearn/neighbors/quad_tree.pyx M sklearn/tree/_tree.pyx Log Message: ----------- MAINT Use C99 functions from Cython (#15098)

1 0

[scikit-learn/scikit-learn] 7a48b6: DOC fix the odd rendering of the section title in ...
by Adrin Jalali 28 Sep '19

28 Sep '19

Branch: refs/heads/master Home: https://github.com/scikit-learn/scikit-learn Commit: 7a48b6754d61e6bda63ee324c1c1ae7ab18685f5 https://github.com/scikit-learn/scikit-learn/commit/7a48b6754d61e6bda63ee32… Author: Adrin Jalali <adrin.jalali(a)gmail.com> Date: 2019-09-28 (Sat, 28 Sep 2019) Changed paths: M examples/compose/plot_compare_reduction.py Log Message: ----------- DOC fix the odd rendering of the section title in `plot_compar… (#15101)

1 0

[scikit-learn/scikit-learn] d4803c: MNT fix some links in compose.rst (#15062)
by Adrin Jalali 28 Sep '19

28 Sep '19

Branch: refs/heads/master Home: https://github.com/scikit-learn/scikit-learn Commit: d4803c1eb47b09a6a7b6286f3cc02cd4263e543a https://github.com/scikit-learn/scikit-learn/commit/d4803c1eb47b09a6a7b6286… Author: Adrin Jalali <adrin.jalali(a)gmail.com> Date: 2019-09-28 (Sat, 28 Sep 2019) Changed paths: M doc/modules/compose.rst Log Message: ----------- MNT fix some links in compose.rst (#15062)

1 0

[scikit-learn/scikit-learn] 80a4cf: DOC Changed Cross Validate Return Section Doc (#14...
by Shubham Mehta 28 Sep '19

28 Sep '19

Branch: refs/heads/master Home: https://github.com/scikit-learn/scikit-learn Commit: 80a4cf05016a07ef98a4914734b69ccbcff63f85 https://github.com/scikit-learn/scikit-learn/commit/80a4cf05016a07ef98a4914… Author: Shubham Mehta <43666035+shubhambmehta(a)users.noreply.github.com> Date: 2019-09-28 (Sat, 28 Sep 2019) Changed paths: M sklearn/model_selection/_validation.py Log Message: ----------- DOC Changed Cross Validate Return Section Doc (#14924)

1 0

[scikit-learn/scikit-learn] e6e00a: DOC clarified f-beta score docs for beta param (#1...
by nxorable 27 Sep '19

27 Sep '19

Branch: refs/heads/master Home: https://github.com/scikit-learn/scikit-learn Commit: e6e00a3f76303156844bf51fbe1a241629ac0bf6 https://github.com/scikit-learn/scikit-learn/commit/e6e00a3f76303156844bf51… Author: nxorable <brianbien(a)gmail.com> Date: 2019-09-28 (Sat, 28 Sep 2019) Changed paths: M sklearn/metrics/classification.py Log Message: ----------- DOC clarified f-beta score docs for beta param (#14854)

1 0

[scikit-learn/scikit-learn] a07392: TST improve coverage of fastica function (#15102)
by Nicolas Hug 27 Sep '19

27 Sep '19

Branch: refs/heads/master Home: https://github.com/scikit-learn/scikit-learn Commit: a07392f7899cfb47b22943eb81dae914d499537d https://github.com/scikit-learn/scikit-learn/commit/a07392f7899cfb47b22943e… Author: Nicolas Hug <contact(a)nicolas-hug.com> Date: 2019-09-27 (Fri, 27 Sep 2019) Changed paths: M sklearn/decomposition/tests/test_fastica.py Log Message: ----------- TST improve coverage of fastica function (#15102)

1 0

[scikit-learn/scikit-learn] c4f372: Deprecate utils.{optimize.newton_cg,random.random_...
by Nicolas Hug 27 Sep '19

27 Sep '19

Branch: refs/heads/master Home: https://github.com/scikit-learn/scikit-learn Commit: c4f372c2de33db77e4dbc5a136d1443a20a3cb45 https://github.com/scikit-learn/scikit-learn/commit/c4f372c2de33db77e4dbc5a… Author: Nicolas Hug <contact(a)nicolas-hug.com> Date: 2019-09-27 (Fri, 27 Sep 2019) Changed paths: M doc/whats_new/v0.22.rst M sklearn/dummy.py M sklearn/linear_model/logistic.py M sklearn/utils/optimize.py M sklearn/utils/random.py M sklearn/utils/tests/test_deprecated_utils.py M sklearn/utils/tests/test_optimize.py M sklearn/utils/tests/test_random.py Log Message: ----------- Deprecate utils.{optimize.newton_cg,random.random_choice_csc} (#15040)

1 0

[scikit-learn/scikit-learn] c96c73: MAINT Make fastica call FastICA (#14987)
by Nicolas Hug 26 Sep '19

26 Sep '19

Branch: refs/heads/master Home: https://github.com/scikit-learn/scikit-learn Commit: c96c73bd32859fadb1a9d6aa2c105c411d0c4b98 https://github.com/scikit-learn/scikit-learn/commit/c96c73bd32859fadb1a9d6a… Author: Nicolas Hug <contact(a)nicolas-hug.com> Date: 2019-09-26 (Thu, 26 Sep 2019) Changed paths: M sklearn/decomposition/fastica_.py Log Message: ----------- MAINT Make fastica call FastICA (#14987)

1 0