Commit Graph

174 Commits

Author SHA1 Message Date
Andreas Mueller 7c0d1b686e FIX typo in dataset generation 2012-10-28 09:04:38 +00:00
Andreas Mueller 72c360ceb4 ENH simplify circles dataset generator, make classes balanced. 2012-10-28 09:04:38 +00:00
Mathieu Blondel 6eec2e651b Even more sklearn.utils.testing. 2012-10-26 00:09:46 +09:00
Andreas Mueller 1406cdfbb7 ENH use the numbers module introduced in Python 2.6 to check for number types.
Fixes 1255.
2012-10-24 18:44:53 +02:00
Lars Buitinck 262cbdf8ad DOC clarify zero_based's implications in SVMlight loader 2012-10-11 11:26:22 +02:00
Andreas Mueller 57001002bb COSMIT pep8 2012-10-10 09:38:10 +02:00
Gael Varoquaux 7c70198efc FIX: doctests under Windows 64bit
Thanks to @bdholt1 for reporting these errors
2012-10-07 23:12:56 +02:00
Andreas Mueller d50c0cb06c COSMIT pep8 2012-10-02 17:31:00 +01:00
Gilles Louppe 3f49b216cd DOC: return values of make_moons and make_circles 2012-10-02 11:57:38 +02:00
Fabian Pedregosa 04b5e98400 Add support for query_id in dump_svmlight_file
Added a test and docstring
2012-09-29 10:19:07 +02:00
Fabian Pedregosa 6c1e0ed858 FIX: typo in ValueError message.
It was printing the full array when it should be printing the shape
2012-09-29 09:46:06 +02:00
Fabian Pedregosa 58c1b5decd Add test for load_svmlight_files 2012-09-28 20:56:15 +02:00
Fabian Pedregosa 398fa9d136 FIX: query_id parameter and other cosmetic changes 2012-09-28 11:24:28 +02:00
Fabian Pedregosa 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
Lars Buitinck 91aaabc745 ENH micro-optimizations in SVMlight loader
* Some more type annotations
* Prevent (copying) string slice; instead, trust str.split
  to handle trailing newlines.
2012-09-15 14:52:42 +02:00
Lars Buitinck 6eb4bb3841 TST (near-)empty lines and explicit zeros in SVMlight loader 2012-09-05 15:39:57 +02:00
Vlad Niculae 7f76aa1def Add __all__ for half of the scikit 2012-09-04 18:00:49 +01:00
Andreas Mueller 713ba6006e COSMIT pep8 2012-09-04 17:24:01 +01:00
Vlad Niculae f692fafe28 Removed load_filenames and load_20newsgroups
These were deprecated in 0.9 as far as I can tell
2012-09-01 20:02:12 +02:00
Andreas Mueller 4c8c3be75c ENH more robust testing if parameter is int or float, as suggested by @larsmans in #1066. 2012-09-01 14:29:35 +02:00
Mathieu Blondel ef8aa402ed Add missing test file. 2012-08-05 20:42:47 +09:00
Mathieu Blondel 6f54691eb3 Check that feature indices are sorted. 2012-08-05 20:34:59 +09:00
Lars Buitinck 35b24cac4c ENH allow user-specified comment in SVMlight dumper 2012-07-23 10:46:18 +02:00
Lars Buitinck 7896f7281d COSMIT don't call magic methods directly
One tricky case left in doc/sphinxext/gen_rst.py.

Also, don't use relative imports in tests.
2012-07-21 17:38:15 +02:00
Lars Buitinck 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
Lars Buitinck 2530791e2e ENH better input validation for dump_svmlight_file
Also, do validation *before* opening any files.
2012-07-21 14:32:29 +02:00
Andreas Mueller bf990e2890 COSMIT some RST fixes for the docs 2012-07-21 12:40:49 +01:00
Lars Buitinck f6bd86e290 COSMIT cleanup tests with pyflakes 2012-07-21 12:57:49 +02:00
Olivier Grisel 0240e3d85b work on smmlight serualizaer to preserve double precision values 2012-07-10 01:05:50 +02:00
Olivier Grisel 51661e7bb3 FIX #937: preserve double precision values in svmlight serializer 2012-07-07 20:14:58 +02:00
Lars Buitinck 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
Lars Buitinck ddb7b4df81 ENH always support file descriptors in SVMlight loader
Previously only supported in Python 3.x
2012-06-11 14:11:50 +02:00
Immanuel Bayer 0586bfe23b fix docstring example 2012-06-07 17:09:33 +02:00
Vlad Niculae 3c02e6cc6c Update make_regression return shapes in docstring 2012-06-05 19:50:29 +03:00
Vlad Niculae f26e2371b6 ENH: make_regression supports multiple targets 2012-06-05 18:18:00 +03:00
Lars Buitinck 4eedded8db ENH support opening compressed files in SVMlight reader 2012-06-04 10:50:51 +02:00
Nelle Varoquaux 0619753d3c Knuth load_cities dataset isn't used anymore 2012-06-01 18:24:21 +02:00
Nelle Varoquaux 62a348406c Changed dataset from france's mileage to knuth's USA mileage dataset 2012-06-01 18:24:20 +02:00
Nelle Varoquaux ebaee5ae18 Added more documentation on the cities dataset 2012-06-01 18:24:20 +02:00
Nelle Varoquaux f568e36b36 Added a new dataset: traveling distances between 17 cities in france 2012-06-01 18:24:20 +02:00
Subhodeep Moitra 68062a2462 P3K: Fixed print related Python3 errors 2012-05-11 11:21:01 +02:00
Andreas Mueller 3e5f2e5e08 ENH backport "assert_less" and "assert_greater", rename "assert_lower" and use it everywhere :) 2012-05-06 15:43:29 +02:00
Andreas Mueller c0e46e19e6 COSMIT typos by `git grep independant` 2012-05-05 18:33:24 +02:00
Lars Buitinck 7bc2ca74c7 Merge pull request #756 from larsmans/svmlight_fix
MRG re-allow zero-based indexes in SVMlight files
2012-04-16 06:13:13 -07:00
Lars Buitinck d38f4d0e91 DOC + PEP8 SVMlight loader 2012-04-16 10:09:57 +02:00
Lars Buitinck 96af5ae934 TEST + FIX zero_based="auto" behavior in SVMlight loader 2012-04-15 16:50:51 +02:00
Lars Buitinck 7b4842d1db BUG close files in time in SVMlight loader (with statement) 2012-04-15 16:39:29 +02:00
Lars Buitinck 2ddf1a7b6d COSMIT pep8 SVMlight loader 2012-04-15 16:33:22 +02:00
Lars Buitinck c2eeca76ae COSMIT refactor SVMlight loader 2012-04-14 23:03:53 +02:00
Lars Buitinck 6d6c9a8937 ENH zero_based="auto" support + better n_features=None in load_svmlight_files 2012-04-10 18:20:28 +02:00