e8a2e2705a
Test edit.
2015-10-23 11:42:53 +02:00
1c5d6d75c4
Merge pull request #5274 from MechCoder/liblinear_samples_weights
...
[MRG+1] Patch liblinear for sample_weights in LogisticRegression(and CV)
2015-10-23 10:23:34 +02:00
9f8e062571
fix docs and doctests for KernelPCA
2015-10-23 08:57:30 +02:00
6cb51b2a28
Initialize ARPACK eigsh
...
`v0 = random_state.rand(M.shape[0])` leads to an initial residual vector in ARPACK which is all positive. However, this is not the absolute or squared residual, but a true difference. Thus, it is better to initialize with `v0=random_state.uniform(-1, 1, M.shape[0])` to have an equally distributed sign. This is the way that ARPACK initializes the residuals.
The effect of the previous initialization is that eigsh frequently does not converge to the correct eigenvalues, e.g. negative eigenvalues for s.p.d. matrix, which leads to an incorrect null-space.
- initialized all occurences of sklearn.utils.arpack.eigsh the same way it would be initialzed by ARPACK
- regression test to test behavior of new initialization
2015-10-23 08:57:30 +02:00
80e22b3ddf
Patch liblinear for sample_weights in LogisticRegression(and CV)
2015-10-23 00:00:31 -04:00
efe8399d86
update whats_new for #5008
2015-10-22 19:01:49 +02:00
1c7168d398
Fix fit_transform, stability issue and scale issue in PLS
2015-10-22 14:25:59 +02:00
f45f260ff7
DOC versionadded randomized_svd
2015-10-21 18:28:37 +02:00
b18f2951e4
randomized_svd: power iter, normalization, benchmark
2015-10-21 11:21:40 +02:00
6a88fb6b24
Merge pull request #5319 from nicodv/patch-1
...
[MRG + 1] Add k-modes clustering project to related projects
2015-10-21 10:02:46 +02:00
f634bc2da0
Merge pull request #5438 from aabadie/datasets_doc
...
[MRG + 1] : documentation, referencing datasets documentation in toc
2015-10-21 08:14:22 +02:00
baf4ade61f
Update my website on whats_new.rst
2015-10-20 14:16:32 +02:00
d4e9d7991a
Merge pull request #4826 from rvraghav93/exceptions
...
[MRG + 1] move custom error/warning classes into sklearn.exceptions (and move `deprecated` away from `utils.__init__.py`)
2015-10-20 10:48:44 +02:00
056b02977b
doc: fix typo
2015-10-20 08:42:07 +02:00
69a09f66c2
Merge pull request #5468 from jmschrei/pomegranate
...
[MRG+1] add pomegranate to related projects
2015-10-20 08:39:26 +02:00
09f0fa7745
DOC/SPHINX Add template for classes which don't have init (Exception classes)
2015-10-19 22:35:36 +02:00
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
b910ab8cce
ENH add pomegranate to related
2015-10-19 11:55:26 -07:00
2f15969d69
DOC: added entry for new GP implementation
2015-10-19 18:34:33 +02:00
e2a340a4ee
REF More meaningful names for hyperparameters of GP kernels
2015-10-19 18:07:14 +02:00
d21b648754
FIX Changing bounds in GP doctest
2015-10-19 18:07:14 +02:00
266b9e9ebb
FIX Fixing a python2.6-related issue
2015-10-19 18:07:14 +02:00
98e8093c93
FIX Further python3 related fixes
2015-10-19 18:07:14 +02:00
e6f028455c
FIX python3 compatibility in doctest
2015-10-19 18:07:14 +02:00
f76e64c9c7
FIX Fix failing tests (doctest, order of hyperparameters, pairwise_kernels)
2015-10-19 18:07:14 +02:00
47721922d8
DOC Fixing some minor issues in narrative doc of GPs
2015-10-19 18:07:14 +02:00
1813322d0a
DOC Documenting GP kernel API
2015-10-19 18:07:14 +02:00
35aace4c30
DOC Revising GP documentation based on @kastnerkyle comments
2015-10-19 18:07:14 +02:00
7f7455c91c
DOC Updating documentation of multi-class GPC
2015-10-19 18:07:13 +02:00
5c2725b4e0
DOC Cleaning up documenation of legacy GPs
2015-10-19 18:07:13 +02:00
0de854a8b0
DOC Updated documentation of Gaussian process classifier
2015-10-19 18:07:12 +02:00
7299cb6607
DOC Added further doc for GPC
2015-10-19 18:07:12 +02:00
955aa60571
DOC Adding documentation on Matern kernel
2015-10-19 18:07:12 +02:00
cb9935b729
DOC Extending further the GP documentation
2015-10-19 18:07:11 +02:00
a5c1187737
DOC Documentation of the CO2 example
2015-10-19 18:07:11 +02:00
d26c355374
DOC Adding documentation for GP kernels
2015-10-19 18:07:11 +02:00
0cd3d635da
referencing datasets documentation in toc
2015-10-19 14:58:19 +02:00
56796e42d0
Merge branch 'master' of https://github.com/scikit-learn/scikit-learn into patch-1
...
Conflicts:
doc/whats_new.rst
2015-10-19 13:53:13 +02:00
60cff80db2
Merge branch 'patch-1' of https://github.com/yanlend/scikit-learn into patch-1
...
Conflicts:
doc/whats_new.rst
2015-10-19 13:46:33 +02:00
8cff95f171
Revert "- removed incorrectly commited file"
...
This reverts commit b97e5b495a
2015-10-19 13:44:59 +02:00
b97e5b495a
- removed incorrectly commited file
2015-10-19 13:37:21 +02:00
7f6b79b7bd
Update whats_new.rst
...
added information for this bugfix
2015-10-19 13:37:04 +02:00
008adf11ad
Merge pull request #5375 from rvraghav93/set_precision
...
[MRG + 2] FIX precision to float64 across the codebase
2015-10-19 11:02:04 +02:00
2300bdd865
MAINT switching master to 0.18.dev0
2015-10-16 17:17:57 +02:00
a87011262a
FIX precision to float64 across the codebase
2015-10-16 11:20:29 +02:00
67ab08429a
Merge pull request #5399 from lesteve/update-joblib-to-0.9
...
[MRG+1] Update joblib to 0.9.2
2015-10-15 21:37:04 +02:00
1b9e791d92
Merge pull request #5398 from rvraghav93/fix_for_numpy_10
...
[MRG + 2] FIX dtypes to conform to the stricter type cast rules of numpy 1.10
2015-10-15 12:45:43 -04:00
4f4c3598e6
FIX dtypes to conform to the stricter type cast rules of numpy 1.10
...
FIX set copy to (copy & whiten).
FIX/DOC Use float outputs for doctest
2015-10-15 18:21:51 +02:00
4e2f20bba3
DOC whats_new entry for randomized_svd heuristic
2015-10-15 15:04:37 +02:00
6db0037d81
DOC add link to the joblib 0.9.2 release notes
...
in doc/whats_new.rst
2015-10-15 11:20:18 +02:00
John Boersma