Hi folks,
This is my first post to scikit-learn-general. I am trying to install
the package on my system. I got pretty far, but not all the way.
My system has an AMD 6-core CPU. I'm running Ubuntu 13.10 64-bit, and
Python 3.3. I downloaded the source files for scikit-learn 0.14. The
Ubuntu repository only has scikit-learn 0.13, and I also suspect that
that package is probably expecting to install on Python 2.
I read the build instructions at
http://scikit-learn.org/stable/install.html. I did a manual setup.py
build and installation with Python3. I saw many warnings, but no
errors. I can import sklearn from the Python 3.3 interpreter. I CANNOT
import sklearn in Python 2.7. That's what I want. So far, so good.
Back out at the shell, unfortunately, the nosetest fails. Here is the
tail of the output from "nosetests --exe sklearn":
======================================================================
ERROR: sklearn.cluster.tests.test_spectral.test_spectral_lobpcg_mode
----------------------------------------------------------------------
Traceback (most recent call last):
File "/usr/local/lib/python3.3/dist-packages/nose/case.py", line 198,
in runTest
self.test(*self.arg)
File
"/usr/local/lib/python3.3/dist-packages/sklearn/cluster/tests/test_spectral.py",
line 66, in test_spectral_lobpcg_mode
random_state=0, eigen_solver="lobpcg")
File
"/usr/local/lib/python3.3/dist-packages/sklearn/cluster/spectral.py",
line 268, in spectral_clustering
eigen_tol=eigen_tol, drop_first=False)
File
"/usr/local/lib/python3.3/dist-packages/sklearn/manifold/spectral_embedding_.py",
line 303, in spectral_embedding
largest=False, maxiter=2000)
File
"/usr/lib/python3/dist-packages/scipy/sparse/linalg/eigen/lobpcg/lobpcg.py",
line 405, in lobpcg
activeBlockVectorBP, retInvR = True )
File
"/usr/lib/python3/dist-packages/scipy/sparse/linalg/eigen/lobpcg/lobpcg.py",
line 142, in b_orthonormalize
gramVBV = sla.cholesky( gramVBV )
File
"/usr/lib/python3/dist-packages/scipy/linalg/decomp_cholesky.py", line
80, in cholesky
check_finite=check_finite)
File
"/usr/lib/python3/dist-packages/scipy/linalg/decomp_cholesky.py", line
30, in _cholesky
raise LinAlgError("%d-th leading minor not positive definite" % info)
numpy.linalg.linalg.LinAlgError: 2-th leading minor not positive definite
----------------------------------------------------------------------
Ran 1712 tests in 79.958s
FAILED (SKIP=14, errors=1)
I tried the alternative testing method suggested at
http://scikit-learn.org/stable/install.html#testing, however that
approach is now deprecated.
I would appreciate any advice you may have on correcting this error.
Many thanks.
------------------------------------------------------------------------------
CenturyLink Cloud: The Leader in Enterprise Cloud Services.
Learn Why More Businesses Are Choosing CenturyLink Cloud For
Critical Workloads, Development Environments & Everything In Between.
Get a Quote or Start a Free Trial Today.
http://pubads.g.doubleclick.net/gampad/clk?id=119420431&iu=/4140/ostg.clktrk
_______________________________________________
Scikit-learn-general mailing list
Scikit-learn-general@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
