c3f973b1de
FIX supports 64 bit group ID and indexes ( #12736 )
2019-01-09 09:52:10 +11:00
952ef6637a
MRG Drop legacy python / remove six dependencies ( #12639 )
2019-01-03 15:50:05 +02:00
2bd87f6ed8
Remove python < 3.5 from CI ( #12746 )
2018-12-14 10:53:12 +01:00
5592a2eda9
[MRG] PyPy support for all but a couple of estimators ( #11010 )
2018-07-20 14:39:53 +10:00
d582e97944
TST Pytest parametrization part2 - cluster, datasets and decomposition modules ( #11142 )
2018-06-01 10:26:02 +08:00
7400775633
[MRG+1] MAINT Replace assert_array_equal with -assert_array_almost_equal where necessary. ( #9774 )
2017-09-18 19:55:23 +10:00
846313b570
[MRG+1] Deprecate sklearn.utils.testing.raises and remove it from tests ( #9660 )
2017-09-01 12:53:59 +02:00
ebf2bf8107
Fix typos ( #9205 )
2017-06-23 11:43:46 +02:00
a39c8ab75c
ENH svmlight chunk loader ( #935 )
2017-06-16 18:11:47 +02:00
928f72447e
[MRG] fix #5269 : Overflow error with sklearn.datasets.load_svmlight ( #7101 )
...
* fix for #5269 , overflow error
* test with long qid added
* What's new section added
2016-08-03 13:53:35 +10:00
22d7cd5cd0
Make dump_svmlight_file support sparse y
2016-03-24 01:22:48 +08:00
82ea224dfa
Add multilabel support for dump_svmlight_file.
2015-07-12 13:51:27 +08:00
eff590ab63
add another test case with empty labelset
2015-04-11 08:27:36 +08:00
0a4c12f58a
TST remove tempfiles that we create in svmlight tests and agglomerative clustering tests
2015-01-23 11:36:46 -05:00
cf3d69be29
Moved code out of context block where not required for #3612
2014-08-31 17:30:16 +01:00
dd9e512ddb
Changed f=open() to with open() as f to eliminate ResourceWarnings. Fixes #3410 .
2014-08-31 14:44:11 +01:00
724b63a16c
Replacing the test .todense() methods with .toarray()
2014-05-20 21:44:34 -04:00
dbc26ce996
COSMIT remove unused imports and variables
2014-02-03 19:43:56 +11:00
0a8538ec77
FIX: test failure under windows caused by temp files handling
2013-12-23 16:28:50 +01:00
119cc2407f
BUG SVMlight loader should check whether n_features is big enough
...
scipy.sparse won't complain when it gets a dimensionality that is
too large, causing crashes in estimators.
Fixes #1630 .
2013-11-25 19:09:43 +01:00
8a0b317dd1
TST clean up after ourselves in SVMlight test
...
As spotted by @yarikoptic in #2553 ; also, the test was previously not
loading the bzip'd file.
2013-10-27 17:59:48 +01:00
77695ee27a
COSMIT pep8
2013-07-11 11:50:23 +02:00
d420aafb0f
TST + PY3 various fixes
...
* Little hack in fixes.py that can be removed when NumPy's
https://github.com/numpy/numpy/issues/3484 is fixed.
* Little cleanup to the fixes implementation.
* Change the numpy workaround and added a test. Fixed some xrange usage.
* Fix the weight boosting test.
* None is not comparable in python3
* Fix a test that depended on dictionary iteration order.
* Python3 removed execfile
* More test fixes.
Fixes #2122 .
2013-07-05 20:17:23 +02:00
ff0e88213f
ENH reduce size of files produced by dump_svmlight_file
2013-04-16 12:14:58 +02:00
461b58559a
PY3 fixing utf8 comments in svm through try/except and six.b
2013-03-19 18:03:45 +01:00
5993ef5082
PY3: use b() convenience function for string literals
...
Had to use an exception in lfw.py; six.u didn't work
2013-03-19 17:57:02 +01:00
578034eccd
TST sorting CSR matrix indices in SVMlight file handling
2013-01-17 17:11:04 +01:00
49e9391168
BUG don't write comments in SVMlight dumper by default
...
Fixes part of Issue #1501
2013-01-16 17:19:23 +01:00
6eec2e651b
Even more sklearn.utils.testing.
2012-10-26 00:09:46 +09:00
d50c0cb06c
COSMIT pep8
2012-10-02 17:31:00 +01:00
04b5e98400
Add support for query_id in dump_svmlight_file
...
Added a test and docstring
2012-09-29 10:19:07 +02:00
58c1b5decd
Add test for load_svmlight_files
2012-09-28 20:56:15 +02:00
398fa9d136
FIX: query_id parameter and other cosmetic changes
2012-09-28 11:24:28 +02:00
6fd39fbf12
Add support for preference contraints in svmlight format.
...
This feature is explained in http://svmlight.joachims.org/ and adds
the ability to control which pairs are considered when dealing with
pairwise loss functions (e.g. for SVMrank).
In order to preserve API compatibility, I return this information (if
present) as a second column to the y vector.
2012-09-26 17:48:13 +02:00
6eb4bb3841
TST (near-)empty lines and explicit zeros in SVMlight loader
2012-09-05 15:39:57 +02:00
6f54691eb3
Check that feature indices are sorted.
2012-08-05 20:34:59 +09:00
35b24cac4c
ENH allow user-specified comment in SVMlight dumper
2012-07-23 10:46:18 +02:00
e1ba110829
ENH make generated SVMlight files self-describing in a comment
...
Comment is *not* used to parse the files, since that would break
compatibility with other tools; it's just there for the user.
2012-07-21 14:32:29 +02:00
2530791e2e
ENH better input validation for dump_svmlight_file
...
Also, do validation *before* opening any files.
2012-07-21 14:32:29 +02:00
51661e7bb3
FIX #937 : preserve double precision values in svmlight serializer
2012-07-07 20:14:58 +02:00
669bbf2de1
BUG do not close fd passed by user in SVMlight loader
...
+ document the behavior of load_svmlight_file better
2012-06-13 16:31:39 +02:00
ddb7b4df81
ENH always support file descriptors in SVMlight loader
...
Previously only supported in Python 3.x
2012-06-11 14:11:50 +02:00
4eedded8db
ENH support opening compressed files in SVMlight reader
2012-06-04 10:50:51 +02:00
96af5ae934
TEST + FIX zero_based="auto" behavior in SVMlight loader
2012-04-15 16:50:51 +02:00
2ddf1a7b6d
COSMIT pep8 SVMlight loader
2012-04-15 16:33:22 +02:00
2c293ebc40
BUG re-allow zero-based indexes in SVMlight files
...
Fixes issue #750 .
2012-04-04 22:44:53 +02:00
0f8b3c2097
FIX: fix test: integers are valid file descriptors in py3k
2011-12-26 17:42:06 +01:00
bc18af34bd
FIX: py3k need explicit bytes buffers for svmlight format serialization
2011-12-26 10:58:38 +01:00
ad53ecd657
Merge branch 'master' into multilabel
...
Conflicts:
sklearn/datasets/_svmlight_format.c
Solved by re-cythonizing.
2011-12-21 11:15:33 +01:00
ef6a563f25
BUG fix off-by-one error in SVMlight format loader
...
Apparently, column indices in SVMlight/LibSVM data files are one-indexed.
2011-12-20 17:18:40 +01:00
Bryan Woods