baohan
/
scikit-learn
mirror of https://github.com/scikit-learn/scikit-learn.git
0
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
10,497 Commits 31 Branches 142 Tags 892 MiB
Commit Graph

73 Commits

Author SHA1 Message Date
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 463ea619c7 Turn off warnings 2012-07-17 15:37:13 +02:00
Gilles Louppe 2eb9e2fdad FIX: gradient boosting (2) 2012-07-16 15:59:10 +02:00
Gilles Louppe 532c54c5ac Merge branch 'master' of github.com:scikit-learn/scikit-learn into tree-mo 
Conflicts:
	sklearn/tree/_tree.c
 2012-07-09 17:32:43 +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
Gilles Louppe b4131f9ed1 FIX: log_proba + DOC 2012-07-02 11:51:50 +02:00
Gilles Louppe 7b6ef37d01 TEST: test_multioutput 2012-07-02 11:16:18 +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 34c2904a95 FIX testing: random state problem in forest testing. 2012-05-06 20:20:05 +02:00
Andreas Mueller eeb6dcc4cc ENH use random states everywhere, never call np.random. 2012-05-06 18:35:14 +02:00
Andreas Mueller 3e5f2e5e08 ENH backport "assert_less" and "assert_greater", rename "assert_lower" and use it everywhere :) 2012-05-06 15:43:29 +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 47a335b87d Cosmits + Fix to a test 2012-03-19 15:33:27 +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
Alexandre Gramfort ad8e4912cb TST: use assert_true instead of assert + remove some relative imports 2012-02-11 15:43:03 +01:00
Andreas Mueller df2a786fd4 MISC forest tests: boston faster, probability test faster and no warning. 2012-02-10 22:07:53 +01:00
Peter Prettenhofer 209d23de5e Merge remote branch 'upstream/master' into gradient_boosting 
Conflicts:
	sklearn/ensemble/tests/test_forest.py
 2012-01-31 21:12:49 +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
Andreas Mueller cb00e97dc2 COSMIT pep8 2012-01-23 10:02:01 +01:00
Peter Prettenhofer 8b7b620514 test_oob_score_regression oob_score below 0.8 if n_estimators < 50 
removed raise exception on underflow error in gradient boosting - random forest test breaks.
 2012-01-23 08:46:14 +01:00
Peter Prettenhofer 0d54938e58 Merge branch 'master' into gradient_boosting 
Conflicts:
	sklearn/ensemble/tests/test_forest.py
 2012-01-23 08:17:04 +01:00
Andreas Mueller 015da641ed ENH made oob_score an ``__init__`` param as suggested by @agramfort 2012-01-20 15:03:57 +01:00
Andreas Mueller 7e33fff113 ENH: added oob_score_ and oob_prediction_ to regression ensembles 2012-01-18 23:40:39 +01:00
Andreas Mueller cb0a9d71f5 ENH oob score as attribute, not separate function. 2012-01-18 20:40:23 +01:00
Andreas Mueller a83bc7ea1a ENH use self.classes_, check input on predict_oob, add test 2012-01-18 19:20:19 +01:00
Peter Prettenhofer b10226ba4b fix: undo compte_importances property merge in forest module and examples 2012-01-09 22:33:30 +01:00
Peter Prettenhofer 83bedfdfcf merge with master finally resolved! 2012-01-06 21:38:10 +01:00
Peter Prettenhofer 4a70636701 Merge branch 'tree-feature-importance' into old-gradient-boosting 
Conflicts:
	sklearn/tree/_tree.c
	sklearn/tree/tree.py
 2012-01-06 20:02:15 +01:00
Peter Prettenhofer c057dabed4 eliminate `compute_importances` fit parameter - make `feature_importances_` a property that will be computed on demand. 2012-01-06 18:00:33 +01:00
Olivier Grisel c71dbdf521 oops, the last test is about classification, not regression 2012-01-04 03:14:48 +01:00
Olivier Grisel 8735140e11 FIX: Boston is a regression dataset 2012-01-04 03:09:24 +01:00
Gilles Louppe ae564d7c8f DOC: Added missing BSD3 licenses 2011-12-30 20:39:18 +01:00