baohan
/
scikit-learn
mirror of https://github.com/scikit-learn/scikit-learn.git
0
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
11,538 Commits 31 Branches 142 Tags 892 MiB
Commit Graph

55 Commits

Author SHA1 Message Date
Gilles Louppe 9fe2e93550 Checkout files from ndawe:treeweights 2013-01-08 23:28:14 +01:00
Olivier Grisel 5fbb227e1a ENH: issue warning when minmax scaling integer data + test 2012-12-27 22:38:19 +01:00
Olivier Grisel c718bf969d Simpler inline comment 2012-12-27 02:02:26 +01:00
Olivier Grisel f0f1e06608 FIX: MinMaxScaler on zero variance features 2012-12-27 01:59:50 +01:00
Andreas Mueller e12c67306e cosmit pep8 2012-12-16 23:28:10 +01:00
Andreas Mueller a3af91943c TST better coverage in preprocessing module 2012-12-02 21:10:36 +00:00
Mathieu Blondel cfd8b7913e Add example in docstring. 2012-11-22 02:58:20 +09:00
Mathieu Blondel aab8162ecf Add comments. 
The code was bit cryptic if you don't know the sparse formats.
 2012-11-19 23:33:15 +09:00
Mathieu Blondel 2fc7080048 Add add_dummy_feature. 2012-11-19 18:18:59 +09:00
Mathieu Blondel a88ee541f2 Improve KernelCenterer docstring. 2012-11-19 16:53:03 +09:00
Andreas Mueller 67e1770353 Merge pull request #1279 from amueller/one_hot_encoder 
MRG added OneHotEncoder
 2012-11-13 23:10:32 -08:00
Andreas Mueller 863816debc ENH added check for non-negative input. 2012-11-13 20:45:14 +00:00
Andreas Mueller 261f07ead3 MISC address Gael's comments 2012-11-10 15:53:57 +00:00
Andreas Mueller d71ba5f357 FIX revert old behavior, all tests work :) 2012-11-10 15:53:57 +00:00
Andreas Mueller a351355510 ENH add checks for clustering, regressors, transformers 2012-11-10 15:53:57 +00:00
Lars Buitinck f8d7bd43fd ENH OneHotEncoder docs + TypeError + test active_features_ 2012-11-07 17:02:56 +01:00
Andreas Mueller c326b1fabe ENH removed ``remove_zeros`` parameter. 2012-10-27 18:19:57 +01:00
Andreas Mueller e04614ca03 TST fixed doctests, added more tests. Still 100% line coverage :) 2012-10-26 19:08:42 +01:00
Andreas Mueller f2e9d5b21f enh masking out zero features 2012-10-26 19:46:16 +02:00
Andreas Mueller c305629f17 TST skip test in common_tests, reach 100% coverage on new code. 2012-10-25 22:57:53 +01:00
Andreas Mueller 086018288d ENH user-specified dtype, defaults to np.float, nicer numpy stuff :) 2012-10-25 22:11:53 +01:00
Andreas Mueller 2660482629 DOC minor fixes / typos. Thanks @larsmans. 2012-10-25 21:57:53 +01:00
Andreas Mueller fd9e1c2379 ENH added OneHotEncoder 2012-10-25 21:07:02 +01:00
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 c0a057843c ENH rename Scaler to StandardScaler everywhere 2012-09-23 17:31:15 +01:00
Andreas Mueller 485854a981 DOC added missing docstrings 2012-09-23 17:31:15 +01:00
Andreas Mueller cf4940a5b1 ENH do normalization in single pass over data 2012-09-23 17:31:15 +01:00
Andreas Mueller 77dc060af3 ENH add MinMaxScaler, #1111 2012-09-23 17:31:15 +01:00
Vlad Niculae 006e7ef801 Add __all__ for the second half of the scikit 2012-09-04 18:00:49 +01:00
Andreas Mueller 1aaa7ac140 TST check that transformers fail gracefully on sparse input 2012-08-26 16:01:33 +02:00
Mathieu Blondel 56c6bfb61d Simplify LabelEncoder.transform. 2012-08-26 12:25:52 +09:00
Mathieu Blondel f77930199f Simplify LabelEncoder.fit_transform. 2012-08-18 01:28:39 +09:00
Mathieu Blondel c8dde782ad Remove needless loop in inverse_transform. 2012-08-18 00:31:53 +09:00
Mathieu Blondel fcced589f5 Optim in LabelEncoder. 2012-08-08 18:50:37 +09:00
Andreas Mueller 48055deed7 FIX doctests for changed dtype 2012-07-25 22:04:57 +01:00
Andreas Mueller d0d9588efe ENH corrected errormessages for always present labels. ugh 2012-07-25 22:04:57 +01:00
Florian Hoenig 7bd5fb527b removed bug in Scaler.fit 2012-06-28 13:30:53 +02:00
Lars Buitinck 855257f6bd ENH fix and test LabelBinarizer's handling of string labels 
Solves Issue #856. Not advertised in the documentation yet.
 2012-05-24 16:09:12 +02:00
Lars Buitinck 6d041623a8 BUG in LabelBinarizer (forgot to run the full testsuite) 2012-05-18 12:28:30 +02:00
Lars Buitinck 7b0602673d ENH generalize LabelBinarizer to arbitrary Sequence types 2012-05-18 09:26:02 +02:00
Mathieu Blondel b49c7e6de9 Address @larsmans' comments. 2012-05-10 20:26:48 +09:00
Mathieu Blondel 86f543c2a0 Add documentation for non-numerical label case. 2012-05-10 20:26:48 +09:00
Mathieu Blondel da2bf54d25 LabelNormalizer -> LabelEncoder. 2012-05-10 20:26:48 +09:00
Mathieu Blondel 769c481699 Add test for non-numerical labels. 2012-05-10 20:26:48 +09:00
Mathieu Blondel 270bd303e8 Doc cosmit. 2012-05-10 20:26:48 +09:00
Mathieu Blondel 530a0d7f56 More useful error message. 2012-05-10 20:26:48 +09:00
Mathieu Blondel 54310a9716 Cosmit: LabelBinarizer and LabelNormalizer are not classifiers. 2012-05-10 20:26:48 +09:00
Mathieu Blondel 699d832ddf Pep8. 2012-05-10 20:26:48 +09:00
Mathieu Blondel bd23d74e89 Add LabelNormalizer. 2012-05-10 20:26:48 +09:00
Gael Varoquaux 67dc16d321 Cosmit: comment on 'clever' code 2012-05-04 23:46:38 +02:00