Lars Buitinck
|
f8d7bd43fd
|
ENH OneHotEncoder docs + TypeError + test active_features_
|
2012-11-07 17:02:56 +01:00 |
|
Lars Buitinck
|
bf87bf5893
|
Merge branch 'master' into pr/1279
Conflicts:
doc/whats_new.rst
|
2012-11-07 13:36:51 +01:00 |
|
Gael Varoquaux
|
e3d369d38c
|
MISC: minor clean ups in hmm code
|
2012-10-27 23:39:54 +02:00 |
|
Shiqiao Du
|
d5fcb73241
|
- check input format of MultinomialHMM.fit
raise ValueError in MultinominalHMM if the input does not pass the check
- pep8
|
2012-10-27 23:39:54 +02:00 |
|
Shiqiao Du
|
e9f46455f5
|
- avoid startprob, transmat, emissionprob containing a zero element by
adding small number and re-normalize
- test case for above problem
|
2012-10-27 23:39:54 +02:00 |
|
Shiqiao Du
|
67558036a6
|
pep8, ignored E126-E128
|
2012-10-27 23:39:54 +02:00 |
|
Shiqiao Du
|
0ad0b3cd59
|
added test_fit_with_init to tests/test_hmm.py
also fixed a bug by this test
|
2012-10-27 23:39:54 +02:00 |
|
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
|
fd9e1c2379
|
ENH added OneHotEncoder
|
2012-10-25 21:07:02 +01:00 |
|
Mathieu Blondel
|
afb666c1d0
|
Use sklearn.utils.testing in tests.
|
2012-10-25 15:31:35 +09:00 |
|
GaelVaroquaux
|
8141cb188a
|
ENH: make RandomizedPCA.fit idempotent
|
2012-10-15 12:36:53 +02:00 |
|
GaelVaroquaux
|
4b66eba3b7
|
BUG: RandomizedPCA needs random_state set
Fitting twice on the same data is not garanteed to give the
same result
|
2012-10-15 12:12:57 +02:00 |
|
Andreas Mueller
|
1b367e56e5
|
ENH set n_fold default to 3, rename k to n_fold in all doctests, docs, and examples
|
2012-10-10 19:10:29 +01:00 |
|
Mathieu Blondel
|
852363e7a3
|
Merge pull request #1215 from amueller/pipeline_muliclass
MRG make multi-class more robust in discovering scoring functions
|
2012-10-08 03:08:58 -07:00 |
|
Andreas Mueller
|
f18295c8ae
|
TST improve test-coverage in base, remove unreachable code-path
|
2012-10-07 22:25:06 +01:00 |
|
Andreas Mueller
|
10d9023fca
|
ENH make multi-class more robust in discovering scoring functions
|
2012-10-07 20:25:50 +02:00 |
|
Andreas Mueller
|
40328ed685
|
FIX bug in pipeline.inverse_transform, improve coverage.
|
2012-10-02 20:53:41 +01:00 |
|
Andreas Mueller
|
7a75fa3e1a
|
ENH remove deprecated sparse SVM class from cross-validation test.
|
2012-10-01 22:19:53 +01:00 |
|
Olivier Grisel
|
244e8a68fa
|
Merge pull request #1187 from ogrisel/bugfix-logistic-ovr-probabilities
MRG: FIX: wrong probabilities for OvR LogisticRegression
|
2012-09-30 06:09:51 -07:00 |
|
Andreas Mueller
|
78789a1c84
|
MISC renaming FeatureStacker to FeatureUnion, adding docs
|
2012-09-30 11:55:32 +01:00 |
|
Andreas Mueller
|
dac5e5904d
|
TST add test for feature weights in feature stacker
|
2012-09-30 11:55:32 +01:00 |
|
Andreas Mueller
|
d27e8fc97a
|
TST added tests, fix feature names.
|
2012-09-30 11:55:32 +01:00 |
|
Olivier Grisel
|
531dcb0090
|
ENH: make test_common check normalized probabilities
|
2012-09-29 17:29:34 +02:00 |
|
Andreas Mueller
|
c0a057843c
|
ENH rename Scaler to StandardScaler everywhere
|
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 |
|
Lars Buitinck
|
f11454d6f3
|
BUG make GridSearchCV work with non-CSR sparse matrix
|
2012-09-18 18:31:23 +02:00 |
|
Andreas Mueller
|
52a9f4dbb1
|
FIX remove test for deprecated parameter.
|
2012-09-15 16:43:08 +01:00 |
|
Nelle Varoquaux
|
1f59e07c12
|
FIX IsotonicRegression only takes vector input, hence don't test it in the common estimators
|
2012-09-15 16:40:43 +02:00 |
|
Alexandre Gramfort
|
13be59db7f
|
TST : use nose assert_true and not python assert
|
2012-09-13 11:47:26 +02:00 |
|
Alexandre Gramfort
|
c599668f1f
|
fix failing test
|
2012-09-13 11:27:34 +02:00 |
|
Christian Jauvin
|
cf9444b190
|
replaced assert with assert_true + error msg
|
2012-09-13 11:27:34 +02:00 |
|
Christian Jauvin
|
ba857ef33c
|
make sure that param has len attr + a test
|
2012-09-13 11:27:34 +02:00 |
|
Andreas Mueller
|
d11e6d1998
|
ENH more robust transformer testing.... don't ask why that came up
|
2012-09-04 20:48:12 +01:00 |
|
Andreas Mueller
|
713ba6006e
|
COSMIT pep8
|
2012-09-04 17:24:01 +01:00 |
|
Gael Varoquaux
|
58ed136173
|
Revert "Rename Y to y in PLS"
This reverts commit a10928c553.
|
2012-09-02 22:14:09 +02:00 |
|
Vlad Niculae
|
3a7125fa12
|
Skip CCA in test_regressors_int
|
2012-09-02 16:27:29 +03:00 |
|
Vlad Niculae
|
a10928c553
|
Rename Y to y in PLS
|
2012-09-02 16:14:07 +03:00 |
|
Vlad Niculae
|
2b7c336b2f
|
Make PLS degrade gracefully on sparse data
|
2012-09-02 15:34:14 +03:00 |
|
Vlad Niculae
|
30e1597635
|
fit_transform in PLS to support y
|
2012-09-02 15:29:22 +03:00 |
|
Vlad Niculae
|
f0585934d2
|
Support y-dependent transform as in PLS
|
2012-09-02 14:51:56 +03:00 |
|
Vlad Niculae
|
9829179a4c
|
Improve the common tests, make fast_ica pipelinable
|
2012-09-02 14:22:19 +03:00 |
|
Vlad Niculae
|
ad339a4ec0
|
Merge branch 'master' into mixins
Conflicts:
sklearn/tests/test_common.py
|
2012-09-02 13:50:40 +03:00 |
|
Vlad Niculae
|
e0c6c117b1
|
MDS is not a transformer, fix the test to skip PLS
|
2012-09-02 13:46:13 +03:00 |
|
Vlad Niculae
|
b515066ee4
|
Remove deprecated properties in naive_bayes
These were scheduled for removal in 0.12.
|
2012-09-01 20:02:14 +02:00 |
|
Andreas Mueller
|
069936c627
|
ENH add ClassifierMixin with ``fit_predict`` and some tests.
|
2012-09-01 18:51:19 +02:00 |
|
Andreas Mueller
|
f3b76d231b
|
ENH test that regressors can handle integer data.
|
2012-09-01 18:32:48 +02:00 |