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
d89c215013
Add tags to classifiers and regressors to identify them as such.
2015-03-31 19:59:49 -04:00
cd2ee7e454
MAINT docstring --> comments to prevent nose from using doc in verbose mode
2015-03-21 11:16:49 +05:30
9e1377a447
FIX revert wrong previous fix and make weighted scorer test deterministic
2015-03-07 17:10:11 +01:00
c23d4f31a3
FIX #4358 : more tolerant test_scorer_sample_weight for windows
2015-03-07 13:58:31 +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
c779eff964
add some nonregression tests.
2014-12-29 20:08:51 -05:00
cc8c3f83b4
tighten tests and adjust for new logic.
2014-12-29 19:47:51 -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
577651753e
ENH: Added median_absolute_error to metrics
2014-10-10 20:25:22 +02:00
41d02e0a0f
TST: fix tests on numpy 1.9.b2
2014-07-20 00:57:13 +02:00
6598ae89dd
TST default scorers with sample_weight
2014-07-19 18:03:30 +02:00
c997cdee9f
COSMIT pep8 + full stop police
...
metrics/tests/test_score_objects.py made stricter by replacing . with \.
in regular expressions.
2014-02-01 15:28:53 +01:00
57916b7801
Use assert_raises_regexp to check error messages
2014-01-17 08:20:49 +01:00
5010f393a2
Remove '_deprecate_loss_and_score_funcs'
2014-01-16 12:43:16 +09:00
046e20c6eb
Check substrings of error messages
2014-01-16 12:43:16 +09:00
7c60251d11
Fix PEP8, style and documentation
2014-01-16 12:43:16 +09:00
f95219f05d
Clean up
2014-01-16 12:43:16 +09:00
e9b4fcf3e0
FIX decision function scorer multilabel
2013-12-02 11:32:41 +01:00
7ee45a56a1
flake8
2013-12-02 11:32:41 +01:00
afc82c5a93
TST scorer works with multi-output decision function
2013-12-02 11:32:40 +01:00
3df6e8a1ee
ENH add scorer support for multi-label threshold scorer
2013-12-02 11:32:40 +01:00
5f5e96af8a
TST classification_report example that does not trigger warning
2013-09-11 00:21:00 +10:00
cf73a9ed85
ENH more explicit name for auc + consistency for scorer, fix #2096
2013-08-07 10:23:37 +02:00
89886e59fb
Revert "ENH add log_likelihood_score as -log_loss"
...
log_likelihood_score is too generic a name and
{categorical,classifier,multinomial}_log_likelihood_score is too long.
This reverts commit 377c61e899
2013-07-28 12:58:32 +02:00
5a1fde1194
COSMIT fixing some unused imports, adding stuff to __all__, and light pep8 (not all whitespace to make rebasing less painful)
2013-07-27 15:44:17 +02:00
d0474aeb47
ENH Scorer object for log loss
2013-07-26 19:40:56 +02:00
2109b1be6d
ENH consistency mse=> mean_squared_error ari => adjusted_rand_score
2013-07-26 11:00:22 +02:00
5597d6f1bc
FIX bug in scorers that take probabilities
...
The class implementing this did not actually work and was never tested.
Found this out while rebasing #2103 .
2013-07-24 15:20:03 +02:00
393b99636b
ENH simplify the Scorer API
...
A Scorer is now a function that returns a score that should be maximized.
2013-07-24 14:47:47 +02:00
8ca3647356
TST smoke test repr
2013-02-03 17:08:58 +01:00
3d3a305d35
FIX imports for Scorer and SCORERS
2013-02-03 16:42:24 +01:00
e375677b56
MISC pep8: rename scorers to SCORERS, remove score_objects getter
2013-02-03 16:24:46 +01:00
b5cc3bad87
COSMIT rename AsScorer to Scorer
2013-02-03 15:49:40 +01:00
99f6a56b8e
TST add test for pickling custom scorer objects
2013-02-03 15:49:39 +01:00
2d9cb81b8f
ENH GridSearchCV and cross_val_score check whether the returned score is actually a number, not an array (otherwise cross_val_score returns bogus).
2013-02-03 15:49:39 +01:00
2734befb4b
COSMIT address @ogrisel's comment.
2013-02-03 15:49:38 +01:00
53f8973b46
FIX rename error
2013-02-03 15:49:37 +01:00
e6484c4f9d
ENH fbeta score working, more tests
2013-02-03 15:49:37 +01:00
Raghav R V