b6a5ed2aab
Merge pull request #5465 from massil94/dev-massil
...
[MRG+1] partly fixed issue #3450 for hamming loss
2015-10-21 16:46:26 +02:00
e3afc0e8c9
MAINT move custom error/warning classes into sklearn.exceptions
...
ENH NonBLASDotWarning -> EfficiencyWarning; Improve error message
DOC Add exceptions module to modules/classes.rst
MAINT Move ConvergenceWarning, UndefinedMetricWarning et al into exceptions
MAINT Remove ChangedBehaviorWarning from base
DOC/FIX Improve DataConversionWarning's docstring
2015-10-19 22:35:35 +02:00
4861730fb9
added test to compare scipy implementation of hamming loss with ours, in sklean/metrics/tests/test_classification.py
2015-10-19 17:54:45 +02:00
a0fc0edda1
changed weighting in hamming_loss in sklearn/metrics/classification.py
2015-10-19 17:36:25 +02:00
628ed2c867
ENH remove some warnings in test suit
2015-09-16 18:27:58 +02:00
5005d38b2e
MAINT Remove ignore_warnings from test_matthews_corrcoef_nan
2015-08-11 22:27:34 +05:30
dd2cb651ab
FIX/REVERT undo removal of ignore_warnings to avoid a few warnings in tests
2015-08-11 22:27:16 +05:30
1da46797d7
TST (in metrics) change error message for seq. of seqs
2015-08-11 22:27:15 +05:30
72f6225f7b
MAINT/ENH inline the logic for _is_sequence_of_sequences
2015-08-11 22:27:14 +05:30
94891f0db4
MAINT deprecate seq of seq in metrics fully with tests
...
TST Make sure all multilabel metrics raise ValueError on seq of seqs
2015-08-11 22:27:14 +05:30
664d78eb7c
MAINT Remove support for the deprecated sequence of sequences
...
MAINT Remove sequence of sequence support from datasets
MAINT Remove return_indicator param
MAINT Remove multilabel-seq test in OVR
MAINT Remove multilable-seq test in check_cv
MAINT Remove multilabel seq test in label_binarizer
TST type_of_target returns "unknown" for multilabel-sequence types
TST _check_targets should raise a ValueError
DOC show multilabel indicator as an example; remove return_indicator param
DOC use consistent lower case y for target
2015-08-11 22:26:44 +05:30
b802ca2f1b
ENH: add Cohen's kappa score to metrics
2015-07-30 17:27:48 +02:00
019fc9b8e7
ENH labels parameter in P/R/F may extend or reduce label set
2015-06-09 01:02:57 +10:00
12b2f166e8
COSMIT missing newlines in metrics test
2015-03-23 11:21:57 -04:00
cd2ee7e454
MAINT docstring --> comments to prevent nose from using doc in verbose mode
2015-03-21 11:16:49 +05:30
681352827b
Merge pull request #4192 from jnothman/binary_iff_binary
...
[MRG+2] P/R/F: in future, average='binary' iff 2 labels in y one of which is pos_label
2015-03-03 09:21:36 +01:00
6bf5d7e2c8
ENH Brier-score loss metric for classifiers
...
The Brier score allows to evaluate the quality of the predicted probabilities of a classifier. It is defined as the mean squared difference between (1) the predicted probability assigned to the possible outcomes for an item and (2) the actual outcome.
2015-02-20 19:37:11 +01:00
4fcf20a5d2
TST/FIX in future, average='binary' iff 2 labels in y one of which is pos_label
2015-02-02 00:18:08 +11:00
fd9b03a048
sort labels in precision_recall_fscore_support
2015-01-26 17:07:30 -05:00
081a554698
FIX P/R/F metrics and scorers are now for binary problems only by default
...
Scorers for different average parameters have been added.
2014-12-09 13:56:51 +11:00
8eee4bc7e1
Implements Multiclass Hinge loss
2014-11-03 15:18:47 +01:00
20a5952fe5
ENH added digits as optional arg for classification_report
2014-10-13 10:36:19 +11:00
cd7b43ccf9
TST make catch_warnings blocks more robust
2014-10-12 18:20:18 +02:00
0e31553de5
ENH Sparse multilabel target support
...
All multilabel metric calculation is now performed efficiently over
sparse CSR matrices.
2014-07-30 22:13:11 +10:00
85c9c84bc7
MAINT move log_loss and hinge_loss to the classification metrics
2014-07-22 14:27:42 +02:00
6d881d3fb1
MAINT split sklearn/metrics/metrics.py
2014-07-19 14:37:52 +02:00
Alexandre Gramfort