7c50e6c8eb
various docstring fixes for web docs
2014-11-30 17:59:42 -08:00
373e641c52
MAINT refactor gradient boosting code
...
Fixes gh-3790
2014-11-25 17:23:00 +01:00
e6835a7aac
Merge pull request #3779 from arjoly/sw-dummy-regressor
...
[MRG+1] Add sample_weight support to Dummy Regressor
2014-11-04 09:50:01 +01:00
6b548f96f1
MAINT remove deprecated loss in gradient boosting
2014-10-24 12:58:13 +02:00
d4405cbf6c
MAINT remove deprecated oob_score_
2014-10-21 17:33:48 +02:00
da31344751
Add sample_weight support to Dummy Regressor
2014-10-16 16:41:49 +02:00
0241b65afb
GradientBoostingClassifier docstring incorrectly specified default for max_features as "auto" when it is None.
2014-09-28 13:45:12 -07:00
85b2c783ce
add probability output for exponential loss
2014-09-22 00:29:38 +02:00
4966b12e33
cosmit arr -> array
2014-09-18 10:44:31 +02:00
05fbc6423d
fix: sample_weight is None in Huber.deviance
...
fix: sample_weight multiplication in Huber leaf updates
more tests (non-uniform weights, weight consistency and invariance to scaling, deviance consistence)
2014-09-18 10:42:36 +02:00
73a8c3a555
cosmit
2014-09-17 12:14:26 +02:00
d9925961df
fix: add **kwargs to Multinomial loss' negative_gradient
2014-09-17 12:14:26 +02:00
93b2b7dae1
fix: consider sample_weights in robost init estimator and negative_gradient
2014-09-17 12:14:26 +02:00
fd952cc0ec
sample weight support for robust regression via weighted percentile algo
2014-09-17 12:14:26 +02:00
6fe6c34c15
adressed Olivier's feedback
2014-09-17 12:14:26 +02:00
58329985d9
more elegant PriorProbabilityEstimator
2014-09-17 12:14:26 +02:00
7064e2013b
bincount supports weights
2014-09-17 12:14:26 +02:00
2503d35039
cosmit: doc
...
raise ValueError for sample_weights and robust regression
2014-09-17 12:14:26 +02:00
f98388e31f
more tests
2014-09-17 12:14:26 +02:00
7f4c974d6b
Sample weights for gradient boosting
...
Exponential loss for classification + predict_proba refactoring
2014-09-17 12:14:26 +02:00
d9288f012f
ENH micro-optimize gradient boosting
2014-09-05 13:33:34 +02:00
e1891d801b
Merge pull request #3489 from jnothman/attributes-doc
...
[MRG] DOC fix formatting of Attributes sections in documentation
2014-08-02 20:14:53 +10:00
ffd13c389b
fix: i might be undefined
2014-07-31 23:47:51 +02:00
b3bdb08964
DOC fix formatting of attributes etc. in docstrings
2014-07-28 19:04:59 +10:00
6e2a83b4e1
remove check_arrays stuff and old input validation
2014-07-20 13:31:45 +02:00
e23d9c9462
ENH Make all decision functions have the same shape. Fixes SVC and GradientBoosting. Closes #1490 .
2014-07-19 10:22:03 +02:00
7e9c093585
tree: add min_weight_fraction_leaf
2014-07-02 11:47:31 +02:00
99f2860c8a
Merge pull request #2966 from maheshakya/feature_selector
...
[MRG] Added _LearntSelectorMixin in BaseGradientBoosting
2014-03-19 08:19:01 +01:00
71ce1d5ac7
DOC: the search for a split does not until one valid partition is found
2014-03-18 14:19:40 +01:00
ffb89eb3a2
Added _LearntSelectorMixin in BaseGradientBoosting
2014-03-13 23:46:23 +05:30
1d0da8a5bd
staged_predict predicts classes, not probabilites
2014-03-13 17:23:24 +01:00
b97fb3c5fc
MAINT drop support for NumPy < 1.6.1
2014-03-02 20:13:57 +01:00
7c621fc261
DOC no more "arithmetical order" for classes
2014-02-17 11:47:51 +01:00
6ebcf4d020
COSMIT fix PEP8 errors
2014-02-02 00:30:28 +11:00
3e6402f1f4
COSMIT: Fix some PEP8 in gradient_boosting
2014-01-16 14:21:48 +01:00
bac878f22e
fix: remaining time not currectly computed
2014-01-14 11:25:27 +01:00
ae3fe45926
fix: use six.string_types instead of basestring
2014-01-08 16:25:29 +01:00
73c7de32e2
cosmit: better exception
...
remove troublesome 32bit test
2014-01-08 12:10:05 +01:00
a8bdbff5f9
do not alter n_estimators after early stopping
2014-01-06 16:26:08 +01:00
dce1d49e85
cosmit: better errors
2014-01-06 16:11:11 +01:00
e0c635f11b
cosmit
2014-01-06 11:07:46 +01:00
bae41e7339
fix: use estimators_.shape[0] rather than n_estimators to make predictions; what if user just changes n_estimators of an already fitted obj.
2014-01-05 12:00:37 +01:00
f9104f64d1
warm_start semantics now fit exactly n_estimators rather than self.estimators_ + self.n_estimators
2014-01-05 11:57:38 +01:00
6c033bd585
fix: resize oob improvements, train score when early stopping
2014-01-04 17:57:04 +01:00
181c515993
moved fit_more to warm_start=True
2014-01-04 16:25:16 +01:00
f512bd82c9
renamed partial_fit -> fit_more for GBRT
2014-01-04 14:07:42 +01:00
547c9d69c9
Nitpicks
2013-12-16 10:46:40 +01:00
1b8ea52741
max_leaf_nodes has precedence over max_depth if the former is not None.
2013-12-02 20:13:57 +01:00
c281adf2b7
Add max_leaf_nodes to forest + DOC
2013-11-30 18:34:13 +01:00
8e41ba208b
cosmit: doc undocumented functions
2013-11-29 16:11:55 +01:00
trevorstephens