Skip to content

Random failure on sklearn.linear_model.tests.test_ridge:test_class_weight_vs_sample_weight under Windows #4914

Closed
@ogrisel

Description

@ogrisel

The following seems to happen randomly on appveyor, at least under 32 bit Python 2.7:

======================================================================
FAIL: Check class_weights resemble sample_weights behavior.
----------------------------------------------------------------------
Traceback (most recent call last):
  File "C:\Python27\lib\site-packages\nose\case.py", line 197, in runTest
    self.test(*self.arg)
  File "C:\Python27\lib\site-packages\sklearn\linear_model\tests\test_ridge.py", line 518, in test_class_weight_vs_sample_weight
    assert_almost_equal(clf1.coef_, clf2.coef_)
  File "C:\Python27\lib\site-packages\numpy\testing\utils.py", line 454, in assert_almost_equal
    return assert_array_almost_equal(actual, desired, decimal, err_msg)
  File "C:\Python27\lib\site-packages\numpy\testing\utils.py", line 811, in assert_array_almost_equal
    header=('Arrays are not almost equal to %d decimals' % decimal))
  File "C:\Python27\lib\site-packages\numpy\testing\utils.py", line 644, in assert_array_compare
    raise AssertionError(msg)
AssertionError: 
Arrays are not almost equal to 7 decimals

(mismatch 100.0%)
 x: array([[ 0.10965375,  0.61707134, -0.50021659, -0.01239003],
       [-0.13067805, -1.45138219,  0.45900018, -0.78576024],
       [ 0.0210243 ,  0.83431085,  0.04121641,  0.79815027]])
 y: array([[ 0.13644731,  0.73780242, -0.55678018,  0.12087149],
       [-0.06131714, -1.75113362,  0.74417571, -1.64203741],
       [-0.07513018,  1.0133312 , -0.18739553,  1.52116592]])

I have never seen this happen on travis so it might be windows-specific. The difference is large so it it probably not a trivial rounding issue.

Metadata

Metadata

Assignees

No one assigned

    Labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions