baohan
/
scikit-learn
mirror of https://github.com/scikit-learn/scikit-learn.git
0
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
19,942 Commits 31 Branches 142 Tags 892 MiB
Commit Graph

151 Commits

Author SHA1 Message Date
Raghav R V fffa98ad1f MAINT Remove deprecated stuff that will be removed in 0.18 
MAINT Remove support for gamma == 0.0
MAINT Remove support for uppercase values for loss and penalty
 2015-10-20 18:24:35 +02:00
Raghav R V e3afc0e8c9 MAINT move custom error/warning classes into sklearn.exceptions 
ENH NonBLASDotWarning -> EfficiencyWarning; Improve error message
DOC Add exceptions module to modules/classes.rst
MAINT Move ConvergenceWarning, UndefinedMetricWarning et al into exceptions
MAINT Remove ChangedBehaviorWarning from base
DOC/FIX Improve DataConversionWarning's docstring
 2015-10-19 22:35:35 +02:00
Andreas Mueller 31a5a5ff12 Fixed warnings for DataDimensionalityWarning, decision_function and decision_function_shape. 2015-10-14 15:38:07 -04:00
Vighnesh Birodkar 735dd1fdca Fix warnings during tests 2015-10-08 14:52:21 -04:00
Vighnesh Birodkar 2f099334f9 MAINT deprecate 1d input arrays for all estimators 
Passing 1D arrays to check_array, without setting `ensure_2d` to false now
raises a deprecation warning before reshaping it. This will later throw an
error.

All Scaler classes also throw warnings when 1D arrays are passed.

All unit tests/doctests are modified to ensure that no 1D arrays are passed,
except in explicit 1D array tests where the warnings have been silenced.

Additional tests are also included which check for different 1D array cases.

2D array tests with one samples and one features are also added and where
they failed, `check_array` call has been modified to give a more useful error
message
 2015-09-09 15:49:58 +02:00
Joel Nothman d517846cc5 FIX #4902: SV*.predict_proba visible before fit 2015-07-06 12:35:47 +10:00
Alexandre Gramfort fcf9cb4150 Merge pull request #4835 from tw991/feature2 
[MRG] fix SVM can be tricked into running proba() #4791
 2015-06-10 06:11:37 -07:00
jnothman 8b44fa197d Merge pull request #4824 from amueller/testing_less_warnings 
minor fixes to the tests, don't raise as many warnings in the test suite
 2015-06-09 22:30:22 +10:00
= 4c4bca1715 fix SVM can be tricked into running proba() #4791 2015-06-08 16:48:42 -04:00
Lars Buitinck 567a956338 Merge branch 'pr/4714' + pep8 fixes 
Conflicts:
	doc/modules/model_persistence.rst
	doc/modules/pipeline.rst
	doc/modules/svm.rst
	doc/tutorial/basic/tutorial.rst
	doc/tutorial/statistical_inference/supervised_learning.rst
	sklearn/svm/classes.py
 2015-06-08 11:31:51 +02:00
Andreas Mueller f0f174b74f ENH minor fixes to the tests, don't raise as many warnings in the test suite 2015-06-05 13:50:46 -04:00
Andreas Mueller 6d4bcda876 ENH refactor OVO decision function, use it in SVC for sklearn-like decision_function shape 2015-06-05 13:14:45 -04:00
Gael Varoquaux 01aff46402 Merge pull request #4347 from amueller/class_weight_auto 
[MRG+1] Use more natural class_weight="auto" heuristic
 2015-06-01 16:15:37 -04:00
Andreas Mueller eedc1cddab Use more natural class_weight="auto" heuristic 2015-06-01 12:49:53 -04:00
Andreas Mueller a8626b36a6 TST/COSMIT remove nose call boilerplate 2015-05-28 14:54:01 -04:00
Raghav R V cd2ee7e454 MAINT docstring --> comments to prevent nose from using doc in verbose mode 2015-03-21 11:16:49 +05:30
Olivier Grisel 119bc20abb Merge pull request #4377 from vortex-ape/intercept_scaling 
[MRG + 1] Fixes #4374: LinearSVC(intercept_scaling=0) breaks
 2015-03-20 12:56:11 +01:00
Vinayak Mehta a4f8f083a5 Specified original intercept_scaling value 2015-03-19 20:27:11 +05:30
Vinayak Mehta 5f44a8e2a3 Raising an error when intercept_scaling is zero 
Added test for intercept_scaling

Fixed silly mistake

Added assert_raise_message

added test for logistic regression

removed None

added more tests
 2015-03-17 23:23:39 +05:30
Barmaley.exe b15941b6c7 TST Adds sanity check for SVR's decision_function 2015-03-13 00:28:10 +03:00
Olivier Grisel f7efb1a67c Merge pull request #4326 from Barmaley-exe/svm-dual-coef-fix 
[MRG + 1] Flip sign of SVM's dual_coef_ in a binary case
 2015-03-03 22:08:22 +01:00
Barmaley.exe 663c236cca Removes RBF calculation by hand 2015-03-03 23:38:52 +03:00
Barmaley.exe 8ab4649fef FIX Flips sign of SVM's dual_coef_ in binary case 
Makes it consistent with other sign adjustments, adds
a test to reproduce decision_function in a kernel case
 2015-03-03 02:29:23 +03:00
Andreas Mueller f1b8283c95 catch some warnings, be less verbose in testing. 2015-03-02 14:40:35 -05:00
Raghav R V 6d222fde10 TST test deprecation warning and support for uppercase 2015-02-25 19:12:27 +05:30
Fabian Pedregosa dbc5d707c6 Change loss names for LinearSVC and LinearSVR() 
the names are now consistent across methods

In LinearSVC:
   'l1' -> 'hinge'
   'l2' -> 'squared_hinge'
In LinearSVR:
   'l1' -> 'epsilon_insensitive'
   'l2' -> 'squared_epsilon_insensitive'
 2015-02-09 11:09:16 +01:00
Raghav R V 88555987cc PEP8 Fix E101, E111 errors and W191, W293, W293 and W391 warnings. 2015-01-08 04:28:24 +05:30
Joel Nothman 081a554698 FIX P/R/F metrics and scorers are now for binary problems only by default 
Scorers for different average parameters have been added.
 2014-12-09 13:56:51 +11:00
Fabian Pedregosa 7e1a0eee08 ENH LinearSVR using liblinear code 
Fixes gh-3877.
 2014-12-03 20:44:04 +01:00
Lars Buitinck 4d1692c9a2 FIX sign flip in (Nu)SVR with linear kernel 
Fixes #2933.
 2014-10-12 17:51:40 +02:00
Olivier Grisel 4e2960df24 FIX call srand whenever random_seed >= 0 in libsvm 
This bug was discovered by #3691 (failing test under windows).
 2014-10-01 16:26:07 +02:00
Lars Buitinck b1119bbb74 ENH friendlier message for calling predict before fit on SVMs 
Fixes #3601.
 2014-09-03 12:56:57 +02:00
MechCoder a7ccbb8096 MAINT: Made the following changes 
1. Use a single loop for both ovr and multinomial conditions
2. Better warning messages for penalty and loss conditions
3. Convergence warnings print only if verbose > 0
4. Used check_X_y instead of check_X
 2014-08-30 12:26:40 +02:00
MechCoder 959a4ac698 MAINT: Remove BaseLibLinear for LogisticRegression 2014-08-26 13:58:07 +02:00
MechCoder ad5773cfca TST: Added test to check ConvergenceWarning 2014-08-01 12:15:57 +02:00
Andreas Mueller e23d9c9462 ENH Make all decision functions have the same shape. Fixes SVC and GradientBoosting. Closes #1490. 2014-07-19 10:22:03 +02:00
Lars Buitinck b97fb3c5fc MAINT drop support for NumPy < 1.6.1 2014-03-02 20:13:57 +01:00
Manoj-Kumar-S 566237dbab FIX: Label encoding done in compute_class_weight 
Changed API such that weight[i] corresponds to sorted_weight[i].
 2014-03-01 17:04:55 +01:00
Lars Buitinck f54ffa0eac FIX error message with sparse precomputed kernels (second try) 
This time, all tests pass.
 2014-02-08 13:50:06 +01:00
Lars Buitinck 67e21b1b80 Revert "FIX error message with sparse precomputed kernels" 
This reverts commit 71fa2683de.

The issue is more complicated than I thought.
 2014-02-08 13:31:38 +01:00
Lars Buitinck 71fa2683de FIX error message with sparse precomputed kernels 
Reported at SO, http://stackoverflow.com/q/21639685/166749.
 2014-02-08 12:51:58 +01:00
Jaques Grobler 6ebcf4d020 COSMIT fix PEP8 errors 2014-02-02 00:30:28 +11:00
Joel Nothman 224a4d593b TST/COSMIT cleaner make_classification and fix tests 
* refactored make_classification
* new test for make_classification
* skip problematic common test for class_weights
 2014-01-01 23:00:50 +11:00
Joel Nothman f4af1ec0ca FIX update data-dependent test assertion 2013-12-31 15:44:52 +01:00
dengemann 9b1207b01d ENH: final fix: clear all regisitries 2013-11-29 13:55:39 +01:00
dengemann 3a6c0344e9 ENH: more of this 2013-11-29 13:55:39 +01:00
dengemann d2f3a8a3da ENH: refactor warnings 1 2013-11-29 13:55:38 +01:00
balu 3e9971d412 fix too many blank lines 2013-08-31 12:19:31 +05:30
Lars Buitinck a82b31547d MAINT remove deprecated parameters (the easy cases) 2013-08-08 10:00:22 +02:00
Mathieu Blondel 053723c2b1 Optim for Crammer-Singer formulation in binary case. 2013-08-02 11:22:12 +09:00