Peter Prettenhofer
|
2c97793d32
|
rm CV class tests
|
2012-09-04 07:56:53 +02:00 |
|
Peter Prettenhofer
|
d7fc786273
|
GradientBoosting classes with built in cross-validation; implemented via Decorator pattern
|
2012-09-04 07:56:52 +02:00 |
|
Gael Varoquaux
|
a12bd7bc7c
|
ENH: understandable error message for X sparse
|
2012-08-10 11:23:00 +01:00 |
|
Andreas Mueller
|
408d3ef86d
|
COSMIT, removed scikits.learn things, removed orphan file.
|
2012-07-23 22:50:12 +01:00 |
|
Gilles Louppe
|
c6aa56846b
|
TEST: disable test_feature_importances for now
|
2012-07-18 11:43:08 +02:00 |
|
Gilles Louppe
|
2562842067
|
FIX: test_feature_importances?
|
2012-07-17 17:58:48 +02:00 |
|
Gilles Louppe
|
734cf7daa0
|
FIX: test_feature_importances
|
2012-07-17 16:29:29 +02:00 |
|
Gilles Louppe
|
2eb9e2fdad
|
FIX: gradient boosting (2)
|
2012-07-16 15:59:10 +02:00 |
|
Peter Prettenhofer
|
549c0d0c8e
|
more tests
|
2012-07-05 22:07:49 +02:00 |
|
Peter Prettenhofer
|
4689d69761
|
added test case for symbol labels
|
2012-07-05 21:37:20 +02:00 |
|
Peter Prettenhofer
|
878ddaf39c
|
test for quantile loss function
|
2012-06-14 21:27:06 +02:00 |
|
Peter Prettenhofer
|
c696ce9a98
|
added test for max_features
|
2012-06-02 17:09:06 +02:00 |
|
Peter Prettenhofer
|
104bb82c67
|
add huber loss to test
|
2012-05-25 23:07:57 +02:00 |
|
Andreas Mueller
|
eeb6dcc4cc
|
ENH use random states everywhere, never call np.random.
|
2012-05-06 18:35:14 +02:00 |
|
Peter Prettenhofer
|
faf035d3f4
|
more test cases (input check at prediction time, degenerate inputs)
|
2012-03-30 08:27:28 +02:00 |
|
Peter Prettenhofer
|
5ace41b99b
|
more test cases
|
2012-03-29 22:46:13 +02:00 |
|
Peter Prettenhofer
|
c5dc1f6061
|
test for staged predict and cosmit
|
2012-03-29 22:08:19 +02:00 |
|
Peter Prettenhofer
|
6c09415926
|
update tests
|
2012-03-20 16:02:42 +01:00 |
|
Gilles Louppe
|
f6a36a3366
|
PEP8
|
2012-03-19 13:39:52 +01:00 |
|
Peter Prettenhofer
|
d340e0e69b
|
fix: forgot to rename classes
|
2012-03-12 16:09:30 +01:00 |
|
Peter Prettenhofer
|
9aec58630a
|
test case for multi-class
|
2012-03-11 14:16:58 +01:00 |
|
Peter Prettenhofer
|
6737f3baad
|
added serialization test case
|
2012-03-08 13:16:18 +01:00 |
|
Peter Prettenhofer
|
24a1b3aa02
|
expose 'ls' loss function for classification
added new example (GB regularization)
fix: min_split -> min_samples_split in examples
|
2012-03-05 22:26:06 +01:00 |
|
Peter Prettenhofer
|
73320c4545
|
Merge branch 'master' into gradient_boosting
Conflicts:
doc/modules/ensemble.rst
sklearn/ensemble/tests/test_forest.py
sklearn/tree/_tree.c
sklearn/tree/tree.py
|
2012-03-03 11:40:01 +01:00 |
|
Peter Prettenhofer
|
8648cfefec
|
renamed estimators to estimators_
|
2012-01-24 22:59:47 +01:00 |
|
Peter Prettenhofer
|
ad288a34eb
|
changed ``n_iter`` to ``n_estimators`` and attribute ``trees`` to ``estimators``.
|
2012-01-24 09:45:12 +01:00 |
|
Peter Prettenhofer
|
83bedfdfcf
|
merge with master finally resolved!
|
2012-01-06 21:38:10 +01:00 |
|
Peter Prettenhofer
|
dfa2d08660
|
added input type and shape test
|
2011-12-05 21:44:37 +01:00 |
|
Peter Prettenhofer
|
227770f0c4
|
better test coverage
|
2011-11-23 21:27:29 +01:00 |
|
Peter Prettenhofer
|
aaeaa14a4a
|
added unit tests for gradient boosting (coverage ~95%)
|
2011-11-23 09:44:15 +01:00 |