Joel Nothman
fd3bd2d200
FIX/COSMIT helper to identify target types
...
* Fixes bugs related to simply checking type(..) equality
* Refactors metrics and preprocessing
* Invalidates mix of sequences of sequences and label indicators in
metrics
* Invalidates row vectors in metrics
* Fixes bug where single-class target led to incorrect F-score
2013-06-09 22:05:56 +10:00
Mathieu Blondel
de560bfcfb
Move balance_weights out of preprocessing.
...
See #1763 .
2013-06-04 18:45:07 +09:00
Jaques Grobler
2ffb484adb
COSMIT pep8
2013-05-04 10:43:39 +02:00
Robert Layton
dacfd8bd5d
DOC: Replaced all BSD style licenses with "BSD 3 clause"
...
Replaced all BSD style licenses with "BSD 3 clause"
Not checked yet!
Removed duplicate "3 clause, 3 clause"
Removed trailing period if exists
Fixed some missed licences, still about 50 to do, but those can be automated
Think I got the last of them.
Apparently me and sed have different ideas of regex.
Found a few more
2013-04-30 08:34:46 +02:00
Stefano Lattarini
67ece78da4
COSMIT various typofixes
...
As suggested by codespell <https://github.com/lucasdemarchi/codespell >
Signed-off-by: Stefano Lattarini <stefano.lattarini@gmail.com>
2013-04-11 21:22:14 +02:00
Mikhail Korobov
2af2c73a01
PY3 fix OneHotEncoder doctest ( "<type 'float'>" is "<class 'float'>" in Python 3.x)
2013-03-26 07:27:34 +06:00
Lars Buitinck
91d9dc9b23
BUG StandardScaler would ignore with_std for CSR input
...
Also clarified the docs and added the explanation promised in the
exception message.
Fixes #1724 .
2013-03-14 14:11:29 +01:00
Mathieu Blondel
cacf6f9fe8
FIX: X was converted twice.
2013-03-12 11:28:16 +09:00
Arnaud Joly
5bcf25fc2f
ENH multilabel metrics: accuracy, Hamming, 0-1 loss
2013-03-02 20:41:34 +01:00
Andreas Mueller
a2ed7a329b
FIX MinMaxScaler bug.
2013-03-02 14:04:52 +01:00
Lars Buitinck
1c6061823c
BUG MinMaxScaler missing from preprocessing.__all__
2013-02-16 16:37:50 +01:00
Olivier Grisel
1967a0b323
P3K use six to have a python 2 & 3 compatible code base
2013-02-09 18:08:44 +01:00
Andreas Mueller
2297306edf
COSMIT pep8
2013-02-08 22:10:40 +01:00
Lars Buitinck
68d04232ac
BUG fix import problem in preprocessing
...
All tests pass on my box, except a CRC error in downloading the
LFW people dataset.
2013-02-04 00:55:53 +01:00
Lars Buitinck
57b86fc434
P3K use six.string_types and six.PY3
2013-02-03 20:12:42 +01:00
Andreas Mueller
9bbca58343
DOC cosmit fix column span alignment errors.
2013-01-19 15:45:27 +01:00
Andreas Mueller
dee73f9a24
DOC more sphinx fixes
2013-01-17 00:04:40 +01:00
Andreas Mueller
9e3ef3985e
DOC some sphinx fixes
2013-01-16 22:51:24 +01:00
Mathieu Blondel
0cf30e27fb
Merge pull request #1536 from kyleabeauchamp/issue-1403
...
issue #1403 : binarize always converts to CSR format
2013-01-11 00:34:07 -08:00
Kyle Beauchamp
61cb459ff5
Added MinMaxScaler inverse_transform for issue #1552
2013-01-10 13:32:19 -08:00
Gilles Louppe
9fe2e93550
Checkout files from ndawe:treeweights
2013-01-08 23:28:14 +01:00
Kyle Beauchamp
4ebd382f8c
In preprocessing.binarize, eliminate zeros from sparse matrices
2013-01-08 11:25:04 -08:00
Kyle Beauchamp
0acce47b6c
Added code to address issue #1403
2013-01-07 23:19:14 -08:00
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