baohan
/
scikit-learn
mirror of https://github.com/scikit-learn/scikit-learn.git
0
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
21,216 Commits 31 Branches 142 Tags 892 MiB
Commit Graph

1716 Commits

Author SHA1 Message Date
Gael Varoquaux 4b2304f05a Merge pull request #7261 from betatim/negative-scorers 
[MRG + 2] Rename scorers like `mse` to `neg_mse`
 2016-09-08 20:40:17 +02:00
Yen 845e702ab9 [MRG+2] Make `enet_coordinate_descent_gram` support fused types (#7218) 
* Make cd_gram support fused types

* Add test
 2016-08-29 15:59:06 +02:00
Olivier Grisel ebb0645966 DOC reference CalibratedClassifierCV in SGDClassifier.predict_proba (#7281) 2016-08-29 21:44:27 +10:00
Tim Head ef64969f91 Introduce deprecation warning and fix tests 
get_scrorer now warns if you use an old name for a scorer
and tests have been updated to use new naming convention.
 2016-08-27 14:56:40 +02:00
LeightonZhang d6299c03d9 DOC: minor docstring format fixed (#7249) 2016-08-26 11:50:53 +10:00
Yen 084ef97f16 [MRG+2] ElasticNet and Lasso now support float32 dtype input (#6913) 
ElasticNet and Lasso no longer implicitly convert float32 dtype input to float64 internally.

* Make helper functions in cd use fused types

* Import cblas float functions

* Make enet_coordinate_descent support fused types

* Make dense case work

* Refactor format

* Remove redundant change

* Add cblas files

* Avoid redundant code

* Remove redundant c files and import

* Recover unnecessary change

* Update comment

* Make coef_ type consistent

* Test float32 input

* Add user warning when fitting float32 data with small alpha

* Fix bug

* Change variable to floating type

* Make cd sparse support fused types

* Make CD support fused types when data is sparse

* Add referenced src files

* Avoid duplicated code

* Avoid type casting

* Fix indentation in test

* Avoid type casting in sparse implementation

* Fix indentation

* Fix duplicated intialization code

* Follow PEP8

* Raise tmp precision to double

* Add 64 bit computer check

* Fix test

* Add constraint

* PEP 8

* Make saxpy have the same structure as daxpy

Hopefully this fixes the problems outlined in PR #6913

* Remove wrong hardware test

* Remove dsdot

* Remove redundant asarray

* Add test for fit_intercept

* Make _preprocess_data support other dtypes

* Add concrete value

* Workaround

* Fix error msg

* Move declarartion

* Remove redundant comment

* Add tests

* Test normalize

* Delete warning

* Fix comment

* Add error msg

* Add error msg

* Add what's new

* Fix error msg
 2016-08-25 09:36:39 -07:00
Alexandre Gramfort fa8fe859c4 update what's new + simplify test 2016-08-20 15:19:13 +02:00
Behzad Tabibian 388df6be18 fixing alignment 2016-08-20 15:15:38 +02:00
Behzad Tabibian 2d39122898 droping extra y 2016-08-20 15:15:38 +02:00
Behzad Tabibian fe20981c39 removing extra fit call and cleanup code 2016-08-20 15:15:38 +02:00
Behzad Tabibian 02cd2fbc37 removing make_sparse_data call 2016-08-20 15:15:38 +02:00
Behzad Tabibian 540e2a0a92 pushing Transpose into dot product 2016-08-20 15:15:38 +02:00
Behzad Tabibian 076d9553d1 test case for ElasticNet multiple output matching with dense 2016-08-20 15:15:38 +02:00
Behzad Tabibian 444cf519d5 fixing ElasticNet sparse decision function to match output with dense output 2016-08-20 15:15:38 +02:00
Kyle Jackson 9d0c2dd618 [MRG] DOC updated normalize param docstring (#7161) 
* DOC updated normalize param docstring

* DOC corrected StandardScaler reference

* DOC changes to alpha param docstring

* DOC :class:
 2016-08-17 22:34:44 +02:00
Olivier Grisel 668b329d42 FIX make HuberRegressor tests stable under 32 bit Linux (#7196) 2016-08-17 15:50:34 +02:00
Joel Nothman 55de9bb30c DOC improve formatting for learning_rate docstrings 2016-08-17 15:13:15 +10:00
Loïc Estève 8ad12edde7 Use pgtol parameter in fmin_l_bfgs call (#7167) 
in HuberRegressor. Since fmin_l_bfgs does not take a 'tol' parameter it
resulted in the scipy < 0.9 branch always being called.
 2016-08-09 21:48:40 -07:00
tKammy 4c7753c7f8 fixed typo 2016-08-09 14:05:30 +09:00
David Staub 12d5f07831 [MR] Speed issues in sample_without_replacement - bugfix (#7104) 
* Remove cdivision=True Cython compiler directive causing incorrect int division.

* Decrease tol for LogisticRegression fit test, perhaps needed due to test not controlling `random_state`.
 2016-08-06 21:23:19 +10:00
Raghav RV 2a9492b38f [MRG] MAINT Removing more deprecated stuff for v0.18 (#5528) 
* MNT Removing more deprecated stuff for v0.18

* MNT+TST Remove support for loss='l2'

* MNT Remove support for precompute='auto' for ElasticNet

* FIX/TST precompute=auto should raise a generic message
 2016-08-03 22:16:04 +10:00
jrfiedler dcca31c40b Modify v0.18 DeprecationWarning messages (#7067) 2016-07-28 12:44:33 -04:00
Nate George 9b25f5d37a Fix docs links (#7005) 
* docs: fix broken and redirect links

see #7000

* docs: fix links

see #7000

* docs: merge with master

* docs: fix fnrs and tinyclues logo links

* docs: fix link reference in text

* docs: fix typo

* docs: added back in metaoptimize-qa paragraph

* docs: update language for defunct site

* docs: update stackexchange section

* docs: remove defunct site, move quora to top

* docs: remove defunct link and rearrange links
 2016-07-27 16:58:25 -04:00
Samuel St-Jean d9c9c01c7b DOC: fix typo 
Seems like I forgot some from the other day, all fixed now (according to the search bar at least).
 2016-07-22 17:05:58 +02:00
Samuel St-Jean 48d27c59e9 DOC: fix typo (#7044) 
Small fix in the comments.
 2016-07-18 23:47:01 +02:00
Vikram 4c32aa2cc1 update for issue #6523 (add logistic_regression_path to classes.rst (#6970) 
* update for issue #6523 (add logistic_regression_path to classes.rst

* Clarifies statement about no warm-start and no speedup with liblinear
 2016-07-13 23:26:21 +02:00
Francis T. O'Donovan fe03879cd3 Fix doc refs to StratifiedKFold and KFold (#6936) 
Fix links to `StratifiedKFold` and `KFold` in docstrings.
 2016-06-28 09:22:05 +02:00
Shota e2a2b4d403 Fix typos (#6942) 2016-06-27 18:13:49 +02:00
Ryan Yu f485fce970 fix a typo in ridge.py (#6917) 2016-06-22 09:31:14 +02:00
Gael Varoquaux 1837224751 Merge pull request #6613 from nelson-liu/correct_license_spelling 
[MRG+1] DOC: fix spellings of 'license'
 2016-06-15 13:58:59 +02:00
Marco De Nadai d9b8ece02c Lasso docs fixed (#6880) 2016-06-12 08:16:22 +02:00
Samuel St-Jean 9795916433 Doc: Fix typo (#6854) 2016-06-02 15:43:47 +02:00
Bernhard Kratzwald c7465f2c0e DOC - improved doc on ridges alpha parameter (#6844) 
* improved doc on ridges alpha parameter

* updated alpha doc for all ridge classes

* fixed grammar
 2016-05-31 14:32:20 +02:00
Tom Dupré la Tour 1107f223d5 use class_weight through sample_weight in LogisticRegression with liblinear 2016-05-25 14:54:02 +02:00
Kevin Wang a2498218ac DOC cross-reference preprocessing estimators and functions in their docstrings 2016-05-10 11:00:41 +02:00
Olivier Grisel 89247fcd7f FIX SquaredHinge is a classification loss (#6771) 2016-05-10 10:41:04 +02:00
Wenhua Yang 7ce4f5c517 FIX incorrect gradient computation for SquaredEpsilonInsensitive loss 2016-05-10 09:32:15 +02:00
Colin Ni 93ffce31d5 [DOC] Added return values to _intercept_dot docstring in linear.logistic 2016-04-28 12:08:46 -04:00
Thierry Guillemot 78a674875e Correct the deprecation of the random_integers numpy function. (#6712) 2016-04-26 16:08:48 +02:00
hlin117 30fcef41fd Fixed minor typo in multitasklasso docs 2016-04-20 01:11:14 -05:00
Preston Parry c9b082a008 [DOC] Moves comma to make sentence more clear 
The comma placement in the docs was confusing. The sentence is now broken into logical clauses.
 2016-04-13 15:20:44 -07:00
Matteo Visconti di Oleggio Castello 589fcadbb7 [DOC] fix reference to examples 2016-04-05 20:22:20 +02:00
Nelson Liu d2aaf0f4bb doc: fix spellings of 'license' 2016-03-31 17:25:31 -07:00
Rémy Léone 9b7176dd9d [DOC] Fix broken links 2016-03-23 12:45:34 -07:00
hlin117 54af09e6f1 Fixing typos in logistic regression docs 2016-03-21 18:57:03 -05:00
Gilles Louppe e2e6bde71a Merge pull request #6498 from clamus/rand-lasso-fix-6493 
[MRG+1] Fix to documentation and docstring of randomized lasso and randomized logistic regression
 2016-03-19 12:00:47 +01:00
Tom Dupré la Tour 06bf797c0d DOC update docstring in LogisticRegression 2016-03-15 11:11:59 +01:00
Davide Lasagna edd0eabf14 change "lasso_path" to use "return_n_iter" argument 2016-03-13 18:06:01 +00:00
Alexandre Gramfort 5e41327276 Merge pull request #6530 from Arafatk/master 
Correcting Typo in sklearn.linear_model.Ridge
 2016-03-13 14:34:15 +01:00
Arafat 77c17bc85d Correcting Typo 2016-03-13 18:38:37 +05:30