Commit Graph

19 Commits

Author SHA1 Message Date
Andreas Mueller cb00e97dc2 COSMIT pep8 2012-01-23 10:02:01 +01:00
Mathieu Blondel f9701d34b8 Add deprecation warning. 2012-01-14 03:45:46 +09:00
Mathieu Blondel 0d48f49bbf Merge dense and sparse SGD implementations. 2012-01-14 03:21:40 +09:00
Mathieu Blondel 5048670baf Fix more bugs + tests. 2012-01-14 00:16:11 +09:00
Mathieu Blondel 7b62b29850 Fix a few more bugs. 2012-01-14 00:02:08 +09:00
Mathieu Blondel 944ff6e81e Partial tests + fix bugs. 2012-01-13 23:35:34 +09:00
Peter Prettenhofer 746d686a4d remove obsolete `sparse_coef_` doc string 2012-01-08 18:34:33 +01:00
Lars Buitinck 5b00f4414a BUG refactor SGD classes to not store sample_weight 2012-01-08 17:41:52 +01:00
Andreas Mueller 78f64c54d8 FIX two more underscores 2011-12-28 00:03:34 +01:00
Andreas Mueller 25c93f4af6 COSMIT: pep8 2011-12-15 17:24:53 +01:00
Peter Prettenhofer 87cf1b32dd fix: sgd module clone issue w/ rho parameter 2011-11-15 21:06:32 +01:00
Lars Buitinck e0ec08946a BUG fix SGD doctests 2011-11-07 14:08:06 +01:00
Olivier Grisel 1e4e6012ac ENH: make it possible to pass class_weight='auto' as constructor param for SGDClassifier 2011-11-01 19:00:50 +01:00
Lars Buitinck 3bde2bf97b ENH accept matrix input throughout
Simple solution: replace np.asanyarray with np.asarray throughout.
Also, use utils.as_float_array where appropriate.
2011-10-21 13:51:12 +02:00
Peter Prettenhofer 8a20cb97e7 unified predict for sparse and dense SGD. 2011-10-02 18:15:33 +02:00
Lars Buitinck 02ec8e41a0 prevent some copying in sparse SGD
Some methods would copy CSR input matrices twice.
2011-09-26 17:17:29 +02:00
Fabian Pedregosa ddf4b72109 Move project directory from scikits.learn to sklearn 2011-09-02 12:06:57 +02:00
Fabian Pedregosa 68f27e3790 Revert "Move project directory from scikits.learn to sklearn"
This reverts commit fd0d3b879d.
2011-09-02 12:03:18 +02:00
Fabian Pedregosa fd0d3b879d Move project directory from scikits.learn to sklearn 2011-09-02 11:38:24 +02:00