f65efcf8eb
More use sklearn.utils.testing.
...
My model is training :)
2012-10-25 21:21:22 +09:00
ec07896195
Add minimalistic test for each solver.
2012-09-29 02:16:05 +09:00
4183cb3b34
COSMIT use LinearClassifierMixin in RidgeClassifier
...
Had to change a test due to different tie breaking.
2012-09-17 23:22:16 +02:00
88a0e5dccf
TST improve Ridge test
2012-09-17 23:22:16 +02:00
466479fe03
API : consistent use alpha_/alphas_ for alpha/alphas estimated by CV in linear models (issue #1041 )
2012-09-02 23:16:54 +02:00
e18a32d93b
Fix #1080 .
2012-08-28 21:33:35 +09:00
c70afcb17d
FIX: use rng with fixed seed
2012-07-18 07:42:04 +02:00
129fd7b7bf
COSMIT: -loo_values +cv_values
2012-07-18 07:42:04 +02:00
29d5dc2f09
FIX: expose loo_values_ in RidgeCV instead of the private _RidgeGCV
2012-07-18 07:42:04 +02:00
602725274f
ENH: add store_loo_values attribute to _RidgeGCV see Issue #957
2012-07-18 07:42:04 +02:00
eeb6dcc4cc
ENH use random states everywhere, never call np.random.
2012-05-06 18:35:14 +02:00
3e5f2e5e08
ENH backport "assert_less" and "assert_greater", rename "assert_lower" and use it everywhere :)
2012-05-06 15:43:29 +02:00
3e391c809f
COSMIT pep8
2012-03-31 15:54:10 +02:00
57e81471a5
Merge pull request #648 from amueller/linear_model_class_weights
...
MRG class_weights constructor parameter in RidgeCV
2012-03-25 07:54:45 -07:00
ba7ab750dc
TST : add test failing test to reproduce #708
2012-03-19 11:20:19 +01:00
3c428f4a66
TST : add test on ridge shapes for different y shapes
2012-03-19 11:14:43 +01:00
922dc91e09
FIX make class weight nosetests work
2012-03-17 23:28:58 +01:00
9061131d7f
Merge branch 'master' into linear_model_class_weights
...
Conflicts:
sklearn/linear_model/ridge.py
2012-03-03 17:01:50 +01:00
4508438445
ENH Added tests and fixes
2012-03-03 15:02:48 +01:00
1021a82752
fixed tests to work with Ridge GCV
2012-02-28 20:46:18 +09:00
23a330a8ba
optimisations to Ridge Regression GCV
...
Optimisations follow from noting that we do
not need to explicitly form the matrix for
the regularised inverse, we just need to
compute its action upon the response vector
y. Similarly, we don't need to compute the
whole explicit matrix in order to evaluate
its diagonal, instead just evaluate the
diagonal entries.
This leads to a large performance increase
when GCV is applied to training datasets
with larger numbers of points. E.g. I observe
a ~ 11x speedup on the UCI Communities and
Crime dataset even for modest training set
sizes of 398 examples only (20% of the data).
2012-02-28 20:46:18 +09:00
be621453b5
MISC replaced deprecated mean_square_error in test.
2012-02-11 16:10:54 +01:00
ad8e4912cb
TST: use assert_true instead of assert + remove some relative imports
2012-02-11 15:43:03 +01:00
b62b97ac51
COSMIT more pyflakes
2011-11-28 23:55:41 +01:00
78fa279dc6
COSMIT more pep8
2011-11-28 23:55:33 +01:00
ca48f82ab8
s/\bcross_val\b/cross_validation/g
2011-09-06 14:44:32 +02:00
ddf4b72109
Move project directory from scikits.learn to sklearn
2011-09-02 12:06:57 +02:00
68f27e3790
Revert "Move project directory from scikits.learn to sklearn"
...
This reverts commit fd0d3b879d
2011-09-02 12:03:18 +02:00
fd0d3b879d
Move project directory from scikits.learn to sklearn
2011-09-02 11:38:24 +02:00
Mathieu Blondel