67dcd99d82
TST fix tests with numpy 1.6.1
...
np.bincount raises an Exception with empty input arrays for numpy versions < 1.6.2
Add utils.fixes.bincount to tackle this issue and use it instead of np.bincount
2015-02-01 15:49:49 +01:00
b3fbccca38
FIX various mismatch between docstring and signature params
...
DOC max_iterations -> max_iter. Make it consistent with kmeans
MAINT Replace the deprecated dx parameter with d in the docstrings
MAINT Deprecation warning for max_iterations parameter.
2015-01-16 11:54:57 -05:00
2198a84388
Manage explicit zeros manualy in class_distribution, test with explicit zeros
2014-08-09 10:33:35 -04:00
1873ef867c
Test explicit sample wieghts in the sparse case of class_distribution
2014-08-07 17:20:07 -04:00
7b7784e0aa
Make cosmetic changes
...
Break list comprehenesions differently in dummy precit
Drop uncesseray float() in multiclass class_distrribtuion
Combine two lines in random_choice_csc
2014-08-06 23:01:42 -04:00
5ba7df8b6c
Include dense case support in class_distribution, pep8 revisions
...
Make The function previoulsy sparse_class_distribution support both the sparse and
dense case, and make some cosmetic updates for imporved readability
2014-08-05 09:45:20 -04:00
478f9adc23
Comment .eliminate_zeros() in sparse class distribution
2014-08-04 18:45:31 -04:00
81f82682d6
Move test_sparse_class_distribution to utils/multiclass from utils/sparsefuncs
2014-08-04 18:24:07 -04:00
6e2a83b4e1
remove check_arrays stuff and old input validation
2014-07-20 13:31:45 +02:00
81b86f1077
COSMIT: fix indentation
2014-07-17 11:44:07 +02:00
7768a3059b
ENH: enable y to only implement the array interface
...
For instance y could be a pandas' dataframe
2014-07-17 11:44:07 +02:00
bbf7ae7565
BUG: Support array interface
2014-07-17 11:44:07 +02:00
be5826d6b9
BUG: Support array interface
2014-07-16 15:30:39 +02:00
9c1217ce5b
TYPO remove mutli (did you mean Muttley?)
2014-07-15 12:09:45 +02:00
d709833247
Preserve public API
2014-07-04 12:50:23 -07:00
2bfca14c49
ENH sparse matrix support in label binarization
2014-06-25 16:15:19 -04:00
28eb1ebe15
Assert or ignore all sequence of sequences deprecation warnings
2014-06-05 11:20:36 +02:00
18c399e20a
MAINT deprecate sequences of sequences support
...
* add warnings
* provide alternative binarizer, sklearn.preprocessing.MultiLabelBinarizer
* fix documentation
2014-06-05 11:20:35 +02:00
dbc26ce996
COSMIT remove unused imports and variables
2014-02-03 19:43:56 +11:00
de7bee4f22
ENH support multiclass targets of string objects
2013-12-05 21:56:54 +11:00
08de819b2c
Rename helper partial_fit function
2013-07-25 11:16:29 +02:00
aa44a2160c
Use unique_labels more consistently in the multiclass model
2013-07-25 10:21:25 +02:00
1505af9832
Add missing test for sample weight with partial_fit + fix issue classes passed as a list instead of an array
2013-07-25 10:21:24 +02:00
84397fb09b
Factorize common classes checks in partial_fit implementations
2013-07-25 10:21:24 +02:00
da7fe8964a
DOC add example is_multilabel
2013-07-22 15:49:31 +02:00
a62abe66ff
ENH use a comprehension over imap
2013-07-08 13:49:25 +02:00
a9197f3dad
FIX bug with indicator format
2013-07-08 13:49:25 +02:00
109f2fb630
OPTIM + ENH simplify mix string and number check
2013-07-08 13:49:25 +02:00
7699100be8
PY3K use six.string_type
2013-07-08 13:49:25 +02:00
7856a72da8
Flatten label type checking
2013-07-08 13:49:25 +02:00
aef47a751a
ENH check that we don't mix number and strings
2013-07-08 13:49:25 +02:00
61d9f41d58
ENH improve documentation with allowed label types
2013-07-08 13:49:25 +02:00
91e4b9a91f
ENH use type_of_target within unique_labels
2013-07-08 13:49:24 +02:00
46d4718712
Typo
2013-07-08 13:49:24 +02:00
45847a7b42
COSMIT better name
2013-07-08 13:49:24 +02:00
825b2c0cad
ENH simpler check for mix of string and number input
2013-07-08 13:49:24 +02:00
adcb0a811e
ENH don't allow mix of input multilabel format
2013-07-08 13:49:24 +02:00
e3ca5c13eb
FIX issue with comparable but different dtype
2013-07-08 13:49:24 +02:00
e40a7f56f0
FIX unique_labels in corner case
2013-07-08 13:49:24 +02:00
bf15dcff86
FIX numpy 1.3 throws error with array of arrays
2013-06-10 11:50:01 +10:00
785c596521
FIX need explicit dtype for array of sequences in numpy 1.3
2013-06-09 22:42:07 +10:00
fd3bd2d200
FIX/COSMIT helper to identify target types
...
* Fixes bugs related to simply checking type(..) equality
* Refactors metrics and preprocessing
* Invalidates mix of sequences of sequences and label indicators in
metrics
* Invalidates row vectors in metrics
* Fixes bug where single-class target led to incorrect F-score
2013-06-09 22:05:56 +10:00
ecf135a49b
ENH faster unique_labels for big sequences of sequences
2013-05-28 16:57:04 +10:00
dacfd8bd5d
DOC: Replaced all BSD style licenses with "BSD 3 clause"
...
Replaced all BSD style licenses with "BSD 3 clause"
Not checked yet!
Removed duplicate "3 clause, 3 clause"
Removed trailing period if exists
Fixed some missed licences, still about 50 to do, but those can be automated
Think I got the last of them.
Apparently me and sed have different ideas of regex.
Found a few more
2013-04-30 08:34:46 +02:00
2cb8b5e94b
P3K some more fixes in random places
2013-03-08 18:31:35 +01:00
5bcf25fc2f
ENH multilabel metrics: accuracy, Hamming, 0-1 loss
2013-03-02 20:41:34 +01:00
Loïc Estève