31a5a5ff12
Fixed warnings for DataDimensionalityWarning, decision_function and decision_function_shape.
2015-10-14 15:38:07 -04:00
735dd1fdca
Fix warnings during tests
2015-10-08 14:52:21 -04:00
176427e284
Fix SGD partial_fit multiclass w/ average.
...
See https://github.com/scikit-learn/scikit-learn/issues/5246#issuecomment-140062688 .
`_fit_multiclass` was setting `self.intercept_` to a single element of the intercept, instead of the entire intercept.
2015-10-07 11:39:57 +02:00
f8486a5b25
fixes scikit-learn/scikit-learn#5329
2015-10-01 21:42:27 -07:00
2f099334f9
MAINT deprecate 1d input arrays for all estimators
...
Passing 1D arrays to check_array, without setting `ensure_2d` to false now
raises a deprecation warning before reshaping it. This will later throw an
error.
All Scaler classes also throw warnings when 1D arrays are passed.
All unit tests/doctests are modified to ensure that no 1D arrays are passed,
except in explicit 1D array tests where the warnings have been silenced.
Additional tests are also included which check for different 1D array cases.
2D array tests with one samples and one features are also added and where
they failed, `check_array` call has been modified to give a more useful error
message
2015-09-09 15:49:58 +02:00
eedc1cddab
Use more natural class_weight="auto" heuristic
2015-06-01 12:49:53 -04:00
cd2ee7e454
MAINT docstring --> comments to prevent nose from using doc in verbose mode
2015-03-21 11:16:49 +05:30
6beacc3fb6
remove deprecated stuff from 0.17
2015-03-18 14:49:04 -04:00
cf3b120aea
TST Fixes #4386
2015-03-13 20:05:49 +03:00
deeaf0ad35
change default to shuffle=True in SGDClassifier and friends.
2015-03-03 11:56:23 -05:00
4e270a5157
remove deprecation tests.
2014-12-29 14:00:06 -05:00
69d393af6f
Merge pull request #3931 from dsullivan7/cwwarn
...
[MRG+1] raising warning for class_weight in fit method
2014-12-12 14:57:37 +01:00
6cb191cfd8
changing warning test to use assert_raises_message
2014-12-12 13:27:49 +01:00
5a019b7202
adding simplefilter for warning
2014-12-10 16:07:46 +01:00
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
b99824fb46
changing warn message, making it Deprecation Warning, and removing negative index for py2.7
2014-12-05 09:39:39 +01:00
afe890b2a8
adding warning if passing class_weight through fit
2014-12-04 13:17:34 +01:00
8dd7f16bef
adding support for class_weight in fit method
2014-12-03 17:15:49 +01:00
37f11953d0
TST update numerical overflow (non-regression) tests
2014-11-25 17:55:33 +01:00
a2d7f89901
fixing duplicated classifier in asgd test
2014-10-15 09:17:36 +02:00
04f6d12282
fix to a minor bug with intercept
2014-10-13 18:21:41 +02:00
a0f0d461bc
fixing merge conflicts
2014-10-09 16:23:45 +02:00
984e9aa8f3
increasing testing precision, putting comment on one line and adding asgd to regression benchmark
2014-10-06 14:39:16 +02:00
e5ae879ea0
clean up and average can now be set to an int indicating the number of iterations before averaging
2014-10-03 15:44:15 +02:00
5fe405bd65
cleaning up floating point and unneeded todos, also removing constant learning rate for asgd
2014-09-29 12:58:30 +02:00
39c87018b2
cleaning up commented out code and previous_coef_ parameter
2014-09-22 15:40:48 +02:00
38f5b6c263
adding escape characters to regex
2014-09-13 16:03:19 +02:00
3b292b28e5
adding a more descriptive error message
2014-09-13 16:03:19 +02:00
e95a7f0e8e
adding value error for partial fit with auto weights
2014-09-13 16:02:29 +02:00
a5852c67e8
changing averaging to use sparse trick
2014-09-12 18:25:18 +02:00
1ceb885f6b
rephrase doc, rename unseen, fix pep8
2014-09-10 22:40:55 +02:00
149d97f78e
making optimal for asgd the constant learning rate
2014-09-10 11:10:01 +02:00
14eb82bfeb
removing standard_coef and standard_intercept from plain sgd
2014-09-01 13:24:52 +02:00
ebbc5b1b55
adding test to make sure plain sgd does not have average parameters
2014-08-18 10:19:24 +02:00
ec4f5743b4
fixing typos
2014-08-13 10:19:42 +02:00
0943c922e1
adding faster implementation of asgd with sparse data
2014-08-05 13:37:25 +02:00
07560e45c2
FIX #3485 : class_weight='auto' on SGDClassifier
2014-08-01 15:05:32 +02:00
6a0e7f7f68
adding support for multiclass with a test included
2014-07-30 16:04:16 +02:00
e147df52dc
adding test for intercept part of asgd
2014-07-30 11:36:20 +02:00
3fad0a224c
adding support for averaged intercept
2014-07-29 17:13:54 +02:00
a38577cd9e
adding support for partial fit and adding test for partial fit
2014-07-29 11:17:48 +02:00
63fc314dad
adding test for binary classifier
2014-07-29 10:51:54 +02:00
fcec373a30
converting to setting coef after the fit has been made
2014-07-28 13:22:06 +02:00
66ce06dd56
adding more precision to almost equal
2014-07-25 17:21:53 +02:00
82b3de7a30
adding test that contains a simple asgd implementation and compares it with the output of sgd_fast
2014-07-25 16:49:10 +02:00
4b6a5d267d
fixing documentation
2014-07-24 14:46:17 +02:00
a7a696e673
fixing tests
2014-07-24 14:45:58 +02:00
d085d88ce8
checkpoint for classifier
2014-07-24 14:45:55 +02:00
67622b4b64
adding test that computes the average sgd
2014-07-24 14:45:50 +02:00
2f4ea66dd8
asgd is added
2014-07-24 14:45:44 +02:00
Andreas Mueller