Gilles Louppe
|
562b60ce8a
|
EXAMPLE: merge plot_adaboost_iris into plot_forest_iris
|
2013-01-08 22:19:02 -08:00 |
|
Gilles Louppe
|
81aaedeae6
|
EXAMPLE: reduce the number of samples
|
2013-01-08 22:19:01 -08:00 |
|
Gilles Louppe
|
0f620c1062
|
ENH: staged_score
|
2013-01-08 22:19:01 -08:00 |
|
Gilles Louppe
|
f3873eabb3
|
TEST: errors
|
2013-01-08 22:19:01 -08:00 |
|
Gilles Louppe
|
a5723e0706
|
FIX: drop support for multi-output
|
2013-01-08 22:19:01 -08:00 |
|
Noel Dawe
|
f3b0e656ee
|
fix variable naming in weight_boosting
|
2013-01-08 22:19:01 -08:00 |
|
Noel Dawe
|
4c81a1ec43
|
rm doctest in make_gaussian_quantiles
|
2013-01-08 22:19:01 -08:00 |
|
Noel Dawe
|
f1c9babc1c
|
FIX: use generator instead of np.random
|
2013-01-08 22:19:01 -08:00 |
|
Noel Dawe
|
aa5d3d9bc0
|
FIX: overlapping y-axis labels
|
2013-01-08 22:19:01 -08:00 |
|
Noel Dawe
|
491379d994
|
FIX: import not used
|
2013-01-08 22:19:01 -08:00 |
|
Gilles Louppe
|
b1fd7db089
|
DOC
|
2013-01-08 22:19:01 -08:00 |
|
Gilles Louppe
|
f188ed6883
|
ENH: WeightedClassifier/Regressor mixins
|
2013-01-08 22:19:01 -08:00 |
|
Gilles Louppe
|
af8384c521
|
TEST: multi-output problems
|
2013-01-08 22:19:01 -08:00 |
|
Gilles Louppe
|
aaaf1cd712
|
TEST: importances
|
2013-01-08 22:19:01 -08:00 |
|
Gilles Louppe
|
78c484d787
|
EXAMPLE: simplify n_estimators and n_samples
|
2013-01-08 22:19:01 -08:00 |
|
Gilles Louppe
|
5f8049c13b
|
TEST: added some more tests
|
2013-01-08 22:19:01 -08:00 |
|
Gilles Louppe
|
f6a8313721
|
FIX: NaN problem + Added some tests
|
2013-01-08 22:19:01 -08:00 |
|
Gilles Louppe
|
f227f9ce7c
|
FIX: compute weighted oob scores
|
2013-01-08 22:19:01 -08:00 |
|
Noel Dawe
|
4826fbac5b
|
FIX: DecisionTreeRegressor.score
|
2013-01-08 22:19:01 -08:00 |
|
Gilles Louppe
|
6b77b825ab
|
FIX: test_oob_score_regression
|
2013-01-08 22:19:01 -08:00 |
|
Gilles Louppe
|
a5e35d9890
|
ENH: added some tests
|
2013-01-08 22:19:01 -08:00 |
|
Gilles Louppe
|
9ff1754e8b
|
ENH: Added balance_weights
|
2013-01-08 22:19:01 -08:00 |
|
Gilles Louppe
|
0c1ae9335b
|
COSMITs
|
2013-01-08 22:19:01 -08:00 |
|
Gilles Louppe
|
7e97ca000a
|
ENH: weighted r2 score for regression
|
2013-01-08 22:19:00 -08:00 |
|
Noel Dawe
|
df4ecef3da
|
use weighted mean in ClassifierMixin.score
|
2013-01-08 22:18:30 -08:00 |
|
Noel Dawe
|
b454d56bd3
|
implement AdaBoost
|
2013-01-08 16:50:38 -08:00 |
|
Gilles Louppe
|
f4ce71eb19
|
Typo
|
2013-01-08 23:29:20 +01:00 |
|
Gilles Louppe
|
f8b81022a0
|
DOC: updated docstring
|
2013-01-08 23:29:20 +01:00 |
|
Noel Dawe
|
64c671a05b
|
DOC: document negative weight treatment in the case of classification
|
2013-01-08 23:29:20 +01:00 |
|
Gilles Louppe
|
78fc091a2c
|
FIX: set min_samples_split=2 by default
|
2013-01-08 23:29:19 +01:00 |
|
Gilles Louppe
|
8fc565fee9
|
FIX: do not overwrite min_samples_split
|
2013-01-08 23:29:19 +01:00 |
|
Gilles Louppe
|
f0167120e9
|
TEST: use rng
|
2013-01-08 23:29:19 +01:00 |
|
Noel Dawe
|
7f745b8738
|
FIX: negative weight test. do not allow any class to have negative weight after a split
|
2013-01-08 23:29:19 +01:00 |
|
Noel Dawe
|
4a5a507693
|
add negative weights test (currently fails): predict_proba should still be valid probabilities
|
2013-01-08 23:29:19 +01:00 |
|
Gilles Louppe
|
7945e9d7df
|
FIX: raise an exception if negative number of samples
|
2013-01-08 23:29:19 +01:00 |
|
Gilles Louppe
|
4bf2866516
|
FIX: iris.target
|
2013-01-08 23:29:19 +01:00 |
|
Noel Dawe
|
8d9bb14692
|
add note about negative weight treatment in BaseDecisionTree.fit
|
2013-01-08 23:29:19 +01:00 |
|
Noel Dawe
|
329c1cda59
|
rm unneeded negative weight logic in Criterion.init_value and Gini.eval
|
2013-01-08 23:29:19 +01:00 |
|
Noel Dawe
|
9cdb787897
|
ignore splits that yield nodes with net negative weight in find_best_split
|
2013-01-08 23:29:19 +01:00 |
|
Gilles Louppe
|
72d767c7e6
|
TEST: sample_weight (once more)
|
2013-01-08 23:29:18 +01:00 |
|
Gilles Louppe
|
dda9c60822
|
TEST: sample_weight
|
2013-01-08 23:29:18 +01:00 |
|
Gilles Louppe
|
fa35dec328
|
PEP8 (some)
|
2013-01-08 23:29:18 +01:00 |
|
Gilles Louppe
|
68e25b1134
|
ENH: import aliases (3)
|
2013-01-08 23:29:18 +01:00 |
|
Gilles Louppe
|
a314c9d198
|
ENH: import aliases (2)
|
2013-01-08 23:29:18 +01:00 |
|
Gilles Louppe
|
d8c9365e61
|
ENH: import aliases
|
2013-01-08 23:29:18 +01:00 |
|
Gilles Louppe
|
e949a42997
|
ENH: use random_state.shuffle
|
2013-01-08 23:29:18 +01:00 |
|
Gilles Louppe
|
d981f8510a
|
FIX: use sklearn.utils.fixes.bincount
|
2013-01-08 23:29:18 +01:00 |
|
Gilles Louppe
|
9593b83dde
|
DOC: cosmit
|
2013-01-08 23:29:18 +01:00 |
|
Gilles Louppe
|
b9df8774c3
|
DOC: typo
|
2013-01-08 23:29:17 +01:00 |
|
Gilles Louppe
|
25616ced02
|
DOC: what's new
|
2013-01-08 23:29:17 +01:00 |