baohan
/
scikit-learn
mirror of https://github.com/scikit-learn/scikit-learn.git
0
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
28,153 Commits 31 Branches 142 Tags 892 MiB
Commit Graph

39 Commits

Author SHA1 Message Date
Olivier Grisel 4ca4f3bbcd
FIX make the shape of LogisticRegression(solver="liblinear") consistent with other solvers (#21998) 
Co-authored-by: Julien Jerphanion <git@jjerphan.xyz>
Co-authored-by: Jérémie du Boisberranger <34657725+jeremiedbb@users.noreply.github.com>
 2022-02-15 16:40:10 +01:00
Christian Lorentzen d8d5637cfe
ENH Loss module LogisticRegression (#21808) 
* ENH replace loss in linear logistic regression

* MNT remove logistic regression's own loss functions

* CLN remove comment

* DOC add whatsnew

* DOC more precise whatsnew

* CLN restore improvements of #19571

* ENH improve fit time by separating mat-vec in multiclass

* DOC update whatsnew

* not only a bit ;-)

* DOC note memory benefit for multiclass case

* trigger CI

* trigger CI

* CLN rename variable to hess_prod

* DOC address reviewer comments

* CLN remove C/F for 1d arrays

* CLN rename to gradient_per_sample

* CLN rename alpha to l2_reg_strength

* ENH respect F-contiguity

* TST fix sag tests

* CLN rename to LinearModelLoss

* CLN improve comments according to review

* CLN liblinear comment

* TST add / move test to test_linear_loss.py

* CLN comment placement

* trigger CI

* CLN add comment about contiguity of raw_prediction

* DEBUG debian-32

* DEBUG test only linear_model module

* Revert "DEBUG test only linear_model module"

This reverts commit 9d6e6987ff.

* DEBUG test -k LogisticRegression

* Revert "DEBUG test -k LogisticRegression"

This reverts commit c203167041.

* Revert "DEBUG debian-32"

This reverts commit ef0b98f232.

* DEBUG set n_jobs=1

* Revert "DEBUG set n_jobs=1"

This reverts commit c7f6f72a8c.

* CLN always use n_threads=1

* CLN address review

* ENH avoid array copy

* CLN simplify L2 norm

* CLN rename w to weights

* CLN rename to hessian_sum and hx_sum

* CLN address review

* CLN rename to init arg and attribute to base_loss

* CLN apply review suggestion

Co-authored-by: Alexandre Gramfort <alexandre.gramfort@m4x.org>

* CLN base_loss instead of _loss attribute

Co-authored-by: Olivier Grisel <olivier.grisel@ensta.org>
Co-authored-by: Alexandre Gramfort <alexandre.gramfort@m4x.org>
 2022-02-14 11:55:17 +01:00
Thomas J. Fan 5f75acdd12
MNT Bump joblib version dependency to 1.0.0 (#22365) 2022-02-09 13:47:18 +01:00
Sultan Orazbayev cd892f9688
DOC use the arxiv directive in the docstrings (#21418) 
Co-authored-by: aufarkari <aufar.di.sini@gmail.com>
Co-authored-by: Chiara Marmo <cmarmo@users.noreply.github.com>
Co-authored-by: Julien Jerphanion <git@jjerphan.xyz>
Co-authored-by: Guillaume Lemaitre <g.lemaitre58@gmail.com>
 2022-01-28 17:55:55 +01:00
Tom Dupré la Tour 762eca546a
FIX improve error message for large sparse matrix input in LogisticRegression (#21093) 2021-09-24 11:05:53 +02:00
genvalen 642127806a
DOC use backticks for n_samples and n_features in X docstring (#20914) 2021-09-02 13:35:03 +02:00
Thomas J. Fan 786c4e5e39
DOC Adds feature_names_in_ to docstrings (#20787) 2021-08-26 13:44:45 +02:00
Thomas J. Fan 3ae7c76153
STY Enables black with experimental_string_processing=true (#20412) 2021-06-29 09:47:04 +02:00
Luccas Quadros 209b096721
DOC Ensures that LogisticRegressionCV passes numpydoc validation (#20376) 
Co-authored-by: Guillaume Lemaitre <g.lemaitre58@gmail.com>
 2021-06-28 10:03:06 +02:00
Thomas J. Fan 351ace7935
STY Uses black's with target_version >= 3.7 (#20294) 2021-06-17 15:50:27 -04:00
Thomas J. Fan 82df48934e
MNT Applies black formatting to most of the code base (#18948) 2021-06-17 14:21:09 -04:00
Thomas J. Fan 9a13bdfaf1
MNT Adds black config and fixes formatting before black (#19031) 
Co-authored-by: Roman Yurchak <rth.yurchak@gmail.com>
Co-authored-by: Christian Lorentzen <lorentzen.ch@gmail.com>
 2021-06-12 17:14:09 +02:00
Guillaume Lemaitre 1cd282d600
DOC add n_features_in_ in the documentation (#20236) 2021-06-09 16:58:03 +02:00
michalkrawczyk bc91f01e54
DOC improve penalty/solver/muticlass support in LogisticRegression* (#19855) 
Co-authored-by: Guillaume Lemaitre <g.lemaitre58@gmail.com>
 2021-05-28 12:25:55 +02:00
Tom Dupré la Tour f6e6ad2d9e
MNT clean futurewarning for 1.0 | _deprecate_positional_args (#20002) 
Co-authored-by: Olivier Grisel <olivier.grisel@ensta.org>
Co-authored-by: Thomas J. Fan <thomasjpfan@gmail.com>
 2021-05-14 11:30:27 -04:00
Julien Jerphanion 0c74b8b7d5
ENH Optimize dot product order for LogisticRegression for dense matrices (#19571) 
* Use multi_dot for Hessian and gradient product. 
  np.linalg.multi_dot quickly chooses the best order for the multiplication of three matrices.
 2021-03-14 15:43:51 +01:00
Yosuke KOBAYASHI 81a56bd8bf
FIX Don't overwrite input sample_weight in LogisticRegression (#19182) 2021-02-01 21:15:36 +01:00
Alex Henrie f35457f1fc
MNT Remove unnecessary assignments from LogisticRegression.fit (#18539) 2020-10-05 22:43:38 +02:00
Thomas J. Fan 06d6f8a9f6
FIX Passes global configuration when spawning joblib jobs (#17634) 
* WIP

* BUG Passes context to joblib jobs

* BUG Fix

* BUG Fix

* CLN Moves delayed into fixes

* CLN Adds linter

* REV Revert diff

* DOC Adds comment for removal

* Use a simple implementation
 2020-09-21 16:59:42 +02:00
Albert Villanova del Moral 647fcb1ac1
DOC Fix A to uppercase in See Also docstring section (#18332) 2020-09-04 10:35:01 -04:00
Nicolas Hug 1dedc7e6a8
[MRG] Prototype 4 for strict check_estimator mode (#17361) 2020-08-06 12:02:15 +02:00
Juan Carlos Alfaro Jiménez 9cd13a1fa1
FIX Change MRO for some estimators (#17837) 2020-07-05 13:52:42 +02:00
Roman Yurchak 8feb04524c
Common check for sample weight invariance with removed samples (#17176) 
Co-Authored-By: Nicolas Hug <contact@nicolas-hug.com>
 2020-06-04 00:30:01 +02:00
Thomas J Fan e770715c43
MNT Completes position arg deprecation (#17272) 
* ENH Adds public functions with position args warning

* BUG Circlar import

* STY

* BUG Add keywords

* BUG Fixes warnings

* ENH Adds other public functions

* CLN Suggestion

* CLN Suggestion

* REV Revert pairwise

* ENH Positoinal args for compute_class_weight
 2020-05-19 09:07:25 +02:00
Roman Yurchak 818e16a1ea Revert "Common check for sample weight invariance with removed samples (#16507)" 
This reverts commit 77279d6b3e.
 2020-05-10 17:05:01 +02:00
Roman Yurchak 77279d6b3e
Common check for sample weight invariance with removed samples (#16507) 
Co-Authored-By: Nicolas Hug <contact@nicolas-hug.com>
 2020-05-10 15:41:53 +02:00
Adrin Jalali dc0cc6e9be
[MRG] API kwonly args in impute, inspection, kernel_ridge (#16926) 
, and linear_model
 2020-04-19 22:58:47 +02:00
Christian Lorentzen a2ccc330bf
STY PEP8 fix E731 in linear_model/_logistic.py (#16786) 2020-03-30 17:49:40 +02:00
Roman Yurchak 75d3f29e72
MAINT Remove outdated numpy and scipy backports (#16725) 
* Remove unecessary numpy & scipy backports

* More fixes

* Remove unused imports
 2020-03-20 13:57:18 +01:00
Alex Henrie 438bb3a438
MNT Remove unused imports (#16665) 2020-03-11 10:01:51 +11:00
Nicolas Hug d205638475
MNT Introduction of n_features_in_ attr with _validate_data mtd (#16112) 2020-02-29 09:05:11 -05:00
Johann Faouzi dd93e01061 DOC Add missing backquote in LogisticRegression docstring (#16106) 2020-01-13 11:18:03 +01:00
Marie Douriez 3f9f7d5f7d DOC improve random_state docstring in _logistic.py (#15729) 2020-01-08 15:47:22 +01:00
@nkish 8fc16206e8 DOC Improve default values in logistic documentation (#15966) 
Co-authored-by: Guillaume Lemaitre <g.lemaitre58@gmail.com>
 2019-12-26 12:46:03 +01:00
Nicolas Hug 5573abbb99 MNT Removed deprecated logistic_regression_path (#15791) 2019-12-04 12:24:10 -05:00
Olivier Grisel 43d8dee07b MNT improve the convergence warning message for LogisticRegression (#15665) 2019-11-20 09:48:26 +11:00
Tola A 9c2c263f9b DOC numpydoc validations for LogisticRegression (#15445) 2019-11-02 15:38:50 +01:00
Roman Yurchak 1ede443b7a MNT Docstring validation with numpydoc (#15404) 2019-11-02 09:59:56 +01:00
Thomas J Fan 0a7adef005 MNT Make modules private in linear_model (#15324) 2019-10-23 15:34:26 +02:00