Hi Yaroslav,
I cannot replicate this (just checked quickly). I am travelling, so I
cannot spend too much time on it, but we'll definitely look at it and try
to address it.
Gael
On Mon, Jul 02, 2012 at 01:37:31PM -0400, Yaroslav Halchenko wrote:
> > > self.test(*self.arg)
> > > File
> > > "/build/buildd-scikit-learn_0.11.0-1-mipsel-ZOiuQA/scikit-learn-0.11.0/debian/python-sklearn/usr/lib/python2.6/dist-packages/sklearn/covariance/tests/test_robust_covariance.py",
> > > line 28, in test_mcd
> > > launch_mcd_on_dataset(100, 5, 20, 0.01, 0.01, 70)
> > > File
> > > "/build/buildd-scikit-learn_0.11.0-1-mipsel-ZOiuQA/scikit-learn-0.11.0/debian/python-sklearn/usr/lib/python2.6/dist-packages/sklearn/covariance/tests/test_robust_covariance.py",
> > > line 67, in launch_mcd_on_dataset
> > > assert(error_cov < tol_cov)
> > > AssertionError
> ok -- that one reliably replicates on current master
> 0.11-branching-379-g898d953 with
> SKLEARN_SEED=113 PYTHONPATH=$PWD nosetests -s -v
> sklearn/covariance/tests/test_robust_covariance.py
> if you could seed it with this seed prior the tests
> > actually this one can fail on my laptop ... since no seeding facility is
> > available ( ;-) ), here is the line I ran
> > ( set -e; for s in {1..1000}; do echo seed=$s; SKLEARN_SEED=$s
> > PYTHONPATH=$PWD nosetests -s -v
> > sklearn/covariance/tests/test_robust_covariance.py; done; )
> > and here is the cut out of the failing output:
> > ======================================================================
> > FAIL: Tests the FastMCD algorithm implementation
> > ----------------------------------------------------------------------
> > Traceback (most recent call last):
> > File "/usr/lib/python2.7/dist-packages/nose/case.py", line 197, in runTest
> > self.test(*self.arg)
> > File
> > "/home/yoh/deb/gits/scikit-learn/sklearn/covariance/tests/test_robust_covariance.py",
> > line 28, in test_mcd
> > launch_mcd_on_dataset(100, 5, 20, 0.01, 0.01, 70)
> > File
> > "/home/yoh/deb/gits/scikit-learn/sklearn/covariance/tests/test_robust_covariance.py",
> > line 67, in launch_mcd_on_dataset
> > assert(error_cov < tol_cov)
> > AssertionError:
> > 0.0049211381236789111 = <module 'numpy' from
> > '/usr/lib/pymodules/python2.7/numpy/__init__.pyc'>.mean((array([[
> > 1.76405235, 0.40015721, 0.97873798, 2.2408932 , 1.86755799],
> > [-0.97727788, 0.95008842, -0.15135721, -0.10321885, 0.4105985
> > ],
> > ...
> > [ 0.16505432, 0.11554982, -0.01784241, 0.14433467,
> > 0.61933516]])) ** 2)
> > assert(0.010874013902418312 < 0.01)
> > assert(<module 'numpy' from
> > '/usr/lib/pymodules/python2.7/numpy/__init__.pyc'>.sum(array([ True, True,
> > True, True, False, True, True, True, True,
> > ....
> > True, True, False, True, False, True, False, False, False,
> > True], dtype=bool)) >= 70)
> > I will try now on master
--
Gael Varoquaux
Researcher, INRIA Parietal
Laboratoire de Neuro-Imagerie Assistee par Ordinateur
NeuroSpin/CEA Saclay , Bat 145, 91191 Gif-sur-Yvette France
Phone: ++ 33-1-69-08-79-68
http://gael-varoquaux.info http://twitter.com/GaelVaroquaux
------------------------------------------------------------------------------
Live Security Virtual Conference
Exclusive live event will cover all the ways today's security and
threat landscape has changed and how IT managers can respond. Discussions
will include endpoint security, mobile security and the latest in malware
threats. http://www.accelacomm.com/jaw/sfrnl04242012/114/50122263/
_______________________________________________
Scikit-learn-general mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
