test_pls.test_scale_and_stability failure #6279
Description
This is a bug revealed by enabling some missing tests as part of #6274. It occurs under Windows with Python 2.7.8 (64 bit) and numpy 1.9.3 with MKL.
https://ci.appveyor.com/project/sklearn-ci/scikit-learn/build/1.0.5133
======================================================================
FAIL: sklearn.cross_decomposition.tests.test_pls.test_scale_and_stability
----------------------------------------------------------------------
Traceback (most recent call last):
File "C:\Python27-x64\lib\site-packages\nose\case.py", line 197, in runTest
self.test(*self.arg)
File "C:\Python27-x64\lib\site-packages\sklearn\cross_decomposition\tests\test_pls.py", line 347, in test_scale_and_stability
assert_array_almost_equal(X_s_score, X_score)
File "C:\Python27-x64\lib\site-packages\numpy\testing\utils.py", line 842, in assert_array_almost_equal
precision=decimal)
File "C:\Python27-x64\lib\site-packages\numpy\testing\utils.py", line 665, in assert_array_compare
raise AssertionError(msg)
AssertionError:
Arrays are not almost equal to 6 decimals
(mismatch 50.0%)
x: array([[-1.337317, -0.041705],
[-1.108472, 0.098154],
[ 0.407632, -0.103084],
[ 2.038158, 0.046634]])
y: array([[-1.337317, 0. ],
[-1.108472, 0. ],
[ 0.407632, 0. ],
[ 2.038158, 0. ]])