Mailman 3 March 2006 - NumPy-Discussion

Numpy build on Solaris 8 fails beginning on 3/19/06
by Christopher Hanley 20 Mar '06

20 Mar '06

Solaris builds began failing yesterday with the following output: Your "cron" job on basil.stsci.edu /home/chanley/bin/numpy_update.csh produced the following output: Sun Mar 19 07:20:04 EST 2006 ### NUMPY Daily Build / Build Test ### ### Setup test environment. ### /usr/ra/pyssg/Python-2.4.2/bin/python ### Checkout, build, and install new version of numpy. ### /data/basil5 A numpy/LICENSE.txt A numpy/scipy_compatibility A numpy/TODO.txt A numpy/THANKS.txt A numpy/TEST_COMMIT A numpy/setup.py A numpy/numpy A numpy/numpy/_import_tools.py A numpy/numpy/f2py A numpy/numpy/f2py/f2py.1 A numpy/numpy/f2py/diagnose.py A numpy/numpy/f2py/rules.py A numpy/numpy/f2py/info.py A numpy/numpy/f2py/capi_maps.py A numpy/numpy/f2py/auxfuncs.py A numpy/numpy/f2py/TODO.txt A numpy/numpy/f2py/cb_rules.py A numpy/numpy/f2py/__init__.py A numpy/numpy/f2py/setup.py A numpy/numpy/f2py/src A numpy/numpy/f2py/src/test A numpy/numpy/f2py/src/test/foo.f A numpy/numpy/f2py/src/test/bar.f A numpy/numpy/f2py/src/test/foo90.f90 A numpy/numpy/f2py/src/test/foomodule.c A numpy/numpy/f2py/src/test/Makefile A numpy/numpy/f2py/src/test/wrap.f A numpy/numpy/f2py/src/fortranobject.c A numpy/numpy/f2py/src/fortranobject.h A numpy/numpy/f2py/docs A numpy/numpy/f2py/docs/HISTORY.txt A numpy/numpy/f2py/docs/pytest.py A numpy/numpy/f2py/docs/usersguide A numpy/numpy/f2py/docs/usersguide/scalar_session.dat A numpy/numpy/f2py/docs/usersguide/fib2.pyf A numpy/numpy/f2py/docs/usersguide/callback.f A numpy/numpy/f2py/docs/usersguide/calculate.f A numpy/numpy/f2py/docs/usersguide/run_main_session.dat A numpy/numpy/f2py/docs/usersguide/index.txt A numpy/numpy/f2py/docs/usersguide/var.pyf A numpy/numpy/f2py/docs/usersguide/string.f A numpy/numpy/f2py/docs/usersguide/spam.pyf A numpy/numpy/f2py/docs/usersguide/ftype_session.dat A numpy/numpy/f2py/docs/usersguide/extcallback.f A numpy/numpy/f2py/docs/usersguide/setup_example.py A numpy/numpy/f2py/docs/usersguide/array.f A numpy/numpy/f2py/docs/usersguide/common_session.dat A numpy/numpy/f2py/docs/usersguide/var_session.dat A numpy/numpy/f2py/docs/usersguide/moddata.f90 A numpy/numpy/f2py/docs/usersguide/callback_session.dat A numpy/numpy/f2py/docs/usersguide/calculate_session.dat A numpy/numpy/f2py/docs/usersguide/spam_session.dat A numpy/numpy/f2py/docs/usersguide/docutils.conf A numpy/numpy/f2py/docs/usersguide/callback2.pyf A numpy/numpy/f2py/docs/usersguide/string_session.dat A numpy/numpy/f2py/docs/usersguide/moddata_session.dat A numpy/numpy/f2py/docs/usersguide/extcallback_session.dat A numpy/numpy/f2py/docs/usersguide/array_session.dat A numpy/numpy/f2py/docs/usersguide/scalar.f A numpy/numpy/f2py/docs/usersguide/allocarr.f90 A numpy/numpy/f2py/docs/usersguide/compile_session.dat A numpy/numpy/f2py/docs/usersguide/fib1.f A numpy/numpy/f2py/docs/usersguide/fib3.f A numpy/numpy/f2py/docs/usersguide/allocarr_session.dat A numpy/numpy/f2py/docs/usersguide/ftype.f A numpy/numpy/f2py/docs/usersguide/default.css A numpy/numpy/f2py/docs/usersguide/common.f A numpy/numpy/f2py/docs/usersguide/fib1.pyf A numpy/numpy/f2py/docs/pyforttest.pyf A numpy/numpy/f2py/docs/simple_session.dat A numpy/numpy/f2py/docs/FAQ.txt A numpy/numpy/f2py/docs/THANKS.txt A numpy/numpy/f2py/docs/hello.f A numpy/numpy/f2py/docs/OLDNEWS.txt A numpy/numpy/f2py/docs/docutils.conf A numpy/numpy/f2py/docs/README.txt A numpy/numpy/f2py/docs/TESTING.txt A numpy/numpy/f2py/docs/default.css A numpy/numpy/f2py/docs/simple.f A numpy/numpy/f2py/common_rules.py A numpy/numpy/f2py/NEWS.txt A numpy/numpy/f2py/use_rules.py A numpy/numpy/f2py/f2py2e.py A numpy/numpy/f2py/setup.cfg A numpy/numpy/f2py/f90mod_rules.py A numpy/numpy/f2py/func2subr.py A numpy/numpy/f2py/tests A numpy/numpy/f2py/tests/c A numpy/numpy/f2py/tests/c/return_real.py A numpy/numpy/f2py/tests/f77 A numpy/numpy/f2py/tests/f77/return_logical.py A numpy/numpy/f2py/tests/f77/return_character.py A numpy/numpy/f2py/tests/f77/callback.py A numpy/numpy/f2py/tests/f77/return_integer.py A numpy/numpy/f2py/tests/f77/return_real.py A numpy/numpy/f2py/tests/f77/return_complex.py A numpy/numpy/f2py/tests/run_all.py A numpy/numpy/f2py/tests/array_from_pyobj A numpy/numpy/f2py/tests/array_from_pyobj/wrapmodule.c A numpy/numpy/f2py/tests/array_from_pyobj/tests A numpy/numpy/f2py/tests/array_from_pyobj/tests/test_array_from_pyobj.py A numpy/numpy/f2py/tests/array_from_pyobj/__init__.py A numpy/numpy/f2py/tests/array_from_pyobj/setup.py A numpy/numpy/f2py/tests/mixed A numpy/numpy/f2py/tests/mixed/foo_fixed.f90 A numpy/numpy/f2py/tests/mixed/foo_free.f90 A numpy/numpy/f2py/tests/mixed/foo.f A numpy/numpy/f2py/tests/mixed/run.py A numpy/numpy/f2py/tests/f90 A numpy/numpy/f2py/tests/f90/return_logical.py A numpy/numpy/f2py/tests/f90/return_character.py A numpy/numpy/f2py/tests/f90/return_integer.py A numpy/numpy/f2py/tests/f90/return_real.py A numpy/numpy/f2py/tests/f90/return_complex.py A numpy/numpy/f2py/f2py_testing.py A numpy/numpy/f2py/doc A numpy/numpy/f2py/doc/notes.tex A numpy/numpy/f2py/doc/win32_notes.txt A numpy/numpy/f2py/doc/multiarray A numpy/numpy/f2py/doc/multiarray/run.pyf A numpy/numpy/f2py/doc/multiarray/array_from_pyobj.c A numpy/numpy/f2py/doc/multiarray/bar.c A numpy/numpy/f2py/doc/multiarray/fun.pyf A numpy/numpy/f2py/doc/multiarray/foo.f A numpy/numpy/f2py/doc/multiarray/transpose.txt A numpy/numpy/f2py/doc/multiarray/fortran_array_from_pyobj.txt A numpy/numpy/f2py/doc/f2python9-final A numpy/numpy/f2py/doc/f2python9-final/structure.jpg A numpy/numpy/f2py/doc/f2python9-final/mk_ps.sh A numpy/numpy/f2py/doc/f2python9-final/mk_html.sh A numpy/numpy/f2py/doc/f2python9-final/aerostructure.jpg A numpy/numpy/f2py/doc/f2python9-final/flow.jpg A numpy/numpy/f2py/doc/f2python9-final/src A numpy/numpy/f2py/doc/f2python9-final/src/examples A numpy/numpy/f2py/doc/f2python9-final/src/examples/exp1session.txt A numpy/numpy/f2py/doc/f2python9-final/src/examples/foo.pyf A numpy/numpy/f2py/doc/f2python9-final/src/examples/exp1.f A numpy/numpy/f2py/doc/f2python9-final/src/examples/exp1mess.txt A numpy/numpy/f2py/doc/f2python9-final/src/examples/foom.pyf A numpy/numpy/f2py/doc/f2python9-final/mk_pdf.sh A numpy/numpy/f2py/doc/f2python9-final/README.txt A numpy/numpy/f2py/doc/intro.tex A numpy/numpy/f2py/doc/multiarrays.txt A numpy/numpy/f2py/doc/options.tex A numpy/numpy/f2py/doc/collectinput.py A numpy/numpy/f2py/doc/ex1 A numpy/numpy/f2py/doc/ex1/foobar.f90 A numpy/numpy/f2py/doc/ex1/runme A numpy/numpy/f2py/doc/ex1/foo.f A numpy/numpy/f2py/doc/ex1/arr.f A numpy/numpy/f2py/doc/ex1/bar.f A numpy/numpy/f2py/doc/ex1/foobar-smart.f90 A numpy/numpy/f2py/doc/ex1/foobarmodule.tex A numpy/numpy/f2py/doc/bugs.tex A numpy/numpy/f2py/doc/commands.tex A numpy/numpy/f2py/doc/signaturefile.tex A numpy/numpy/f2py/doc/fortranobject.tex A numpy/numpy/f2py/doc/apps.tex A numpy/numpy/f2py/doc/Release-1.x.txt A numpy/numpy/f2py/doc/using_F_compiler.txt A numpy/numpy/f2py/doc/Release-2.x.txt A numpy/numpy/f2py/doc/Release-3.x.txt A numpy/numpy/f2py/doc/Release-4.x.txt A numpy/numpy/f2py/doc/f2py2e.tex A numpy/numpy/f2py/doc/python9.tex A numpy/numpy/f2py/doc/index.html A numpy/numpy/f2py/doc/Makefile A numpy/numpy/f2py/doc/oldnews.html A numpy/numpy/f2py/crackfortran.py A numpy/numpy/f2py/cfuncs.py A numpy/numpy/f2py/__version__.py A numpy/numpy/f2py/README.txt A numpy/numpy/f2py/Makefile A numpy/numpy/f2py/BUGS.txt A numpy/numpy/random A numpy/numpy/random/info.py A numpy/numpy/random/mtrand A numpy/numpy/random/mtrand/Python.pxi A numpy/numpy/random/mtrand/distributions.c A numpy/numpy/random/mtrand/initarray.c A numpy/numpy/random/mtrand/mtrand.pyx A numpy/numpy/random/mtrand/mtrand.c A numpy/numpy/random/mtrand/numpy.pxi A numpy/numpy/random/mtrand/distributions.h A numpy/numpy/random/mtrand/generate_mtrand_c.py A numpy/numpy/random/mtrand/initarray.h A numpy/numpy/random/mtrand/randomkit.c A numpy/numpy/random/mtrand/randomkit.h A numpy/numpy/random/__init__.py A numpy/numpy/random/setup.py A numpy/numpy/add_newdocs.py A numpy/numpy/distutils A numpy/numpy/distutils/core.py A numpy/numpy/distutils/misc_util.py A numpy/numpy/distutils/fcompiler A numpy/numpy/distutils/fcompiler/mips.py A numpy/numpy/distutils/fcompiler/gnu.py A numpy/numpy/distutils/fcompiler/intel.py A numpy/numpy/distutils/fcompiler/vast.py A numpy/numpy/distutils/fcompiler/absoft.py A numpy/numpy/distutils/fcompiler/__init__.py A numpy/numpy/distutils/fcompiler/none.py A numpy/numpy/distutils/fcompiler/compaq.py A numpy/numpy/distutils/fcompiler/lahey.py A numpy/numpy/distutils/fcompiler/g95.py A numpy/numpy/distutils/fcompiler/hpux.py A numpy/numpy/distutils/fcompiler/nag.py A numpy/numpy/distutils/fcompiler/sun.py A numpy/numpy/distutils/fcompiler/pg.py A numpy/numpy/distutils/fcompiler/ibm.py A numpy/numpy/distutils/info.py A numpy/numpy/distutils/line_endings.py A numpy/numpy/distutils/from_template.py A numpy/numpy/distutils/__init__.py A numpy/numpy/distutils/system_info.py A numpy/numpy/distutils/conv_template.py A numpy/numpy/distutils/setup.py A numpy/numpy/distutils/cpuinfo.py A numpy/numpy/distutils/lib2def.py A numpy/numpy/distutils/intelccompiler.py A numpy/numpy/distutils/tests A numpy/numpy/distutils/tests/f2py_ext A numpy/numpy/distutils/tests/f2py_ext/tests A numpy/numpy/distutils/tests/f2py_ext/tests/test_fib2.py A numpy/numpy/distutils/tests/f2py_ext/__init__.py A numpy/numpy/distutils/tests/f2py_ext/setup.py A numpy/numpy/distutils/tests/f2py_ext/src A numpy/numpy/distutils/tests/f2py_ext/src/fib2.pyf A numpy/numpy/distutils/tests/f2py_ext/src/fib1.f A numpy/numpy/distutils/tests/pyrex_ext A numpy/numpy/distutils/tests/pyrex_ext/tests A numpy/numpy/distutils/tests/pyrex_ext/tests/test_primes.py A numpy/numpy/distutils/tests/pyrex_ext/__init__.py A numpy/numpy/distutils/tests/pyrex_ext/setup.py A numpy/numpy/distutils/tests/pyrex_ext/primes.pyx A numpy/numpy/distutils/tests/setup.py A numpy/numpy/distutils/tests/gen_ext A numpy/numpy/distutils/tests/gen_ext/tests A numpy/numpy/distutils/tests/gen_ext/tests/test_fib3.py A numpy/numpy/distutils/tests/gen_ext/__init__.py A numpy/numpy/distutils/tests/gen_ext/setup.py A numpy/numpy/distutils/tests/swig_ext A numpy/numpy/distutils/tests/swig_ext/tests A numpy/numpy/distutils/tests/swig_ext/tests/test_example.py A numpy/numpy/distutils/tests/swig_ext/tests/test_example2.py A numpy/numpy/distutils/tests/swig_ext/__init__.py A numpy/numpy/distutils/tests/swig_ext/setup.py A numpy/numpy/distutils/tests/swig_ext/src A numpy/numpy/distutils/tests/swig_ext/src/example.i A numpy/numpy/distutils/tests/swig_ext/src/zoo.cc A numpy/numpy/distutils/tests/swig_ext/src/example.c A numpy/numpy/distutils/tests/swig_ext/src/zoo.h A numpy/numpy/distutils/tests/swig_ext/src/zoo.i A numpy/numpy/distutils/tests/f2py_f90_ext A numpy/numpy/distutils/tests/f2py_f90_ext/tests A numpy/numpy/distutils/tests/f2py_f90_ext/tests/test_foo.py A numpy/numpy/distutils/tests/f2py_f90_ext/include A numpy/numpy/distutils/tests/f2py_f90_ext/include/body.f90 A numpy/numpy/distutils/tests/f2py_f90_ext/__init__.py A numpy/numpy/distutils/tests/f2py_f90_ext/setup.py A numpy/numpy/distutils/tests/f2py_f90_ext/src A numpy/numpy/distutils/tests/f2py_f90_ext/src/foo_free.f90 A numpy/numpy/distutils/tests/test_misc_util.py A numpy/numpy/distutils/extension.py A numpy/numpy/distutils/ccompiler.py A numpy/numpy/distutils/log.py A numpy/numpy/distutils/__version__.py A numpy/numpy/distutils/unixccompiler.py A numpy/numpy/distutils/exec_command.py A numpy/numpy/distutils/mingw32ccompiler.py A numpy/numpy/distutils/command A numpy/numpy/distutils/command/build_clib.py A numpy/numpy/distutils/command/egg_info.py A numpy/numpy/distutils/command/__init__.py A numpy/numpy/distutils/command/build.py A numpy/numpy/distutils/command/build_ext.py A numpy/numpy/distutils/command/config_compiler.py A numpy/numpy/distutils/command/install_data.py A numpy/numpy/distutils/command/install_headers.py A numpy/numpy/distutils/command/bdist_rpm.py A numpy/numpy/distutils/command/config.py A numpy/numpy/distutils/command/build_scripts.py A numpy/numpy/distutils/command/build_src.py A numpy/numpy/distutils/command/install.py A numpy/numpy/distutils/command/sdist.py A numpy/numpy/distutils/command/build_py.py A numpy/numpy/doc A numpy/numpy/doc/records.txt A numpy/numpy/doc/ufuncs.txt A numpy/numpy/doc/DISTUTILS.txt A numpy/numpy/doc/pyrex A numpy/numpy/doc/pyrex/numpyx.pyx A numpy/numpy/doc/pyrex/numpyx.c A numpy/numpy/doc/pyrex/c_numpy.pxd A numpy/numpy/doc/pyrex/MANIFEST A numpy/numpy/doc/pyrex/setup.py A numpy/numpy/doc/pyrex/notes A numpy/numpy/doc/pyrex/run_test.py A numpy/numpy/doc/pyrex/Makefile A numpy/numpy/doc/pyrex/c_python.pxd A numpy/numpy/doc/swig A numpy/numpy/doc/swig/numpy.i A numpy/numpy/doc/swig/series.h A numpy/numpy/doc/swig/Series.i A numpy/numpy/doc/swig/testSeries.py A numpy/numpy/doc/swig/HelperFunctions.txt A numpy/numpy/doc/swig/setup.py A numpy/numpy/doc/swig/series.cxx A numpy/numpy/doc/swig/Makefile A numpy/numpy/doc/swig/README A numpy/numpy/doc/CAPI.txt A numpy/numpy/doc/README.txt A numpy/numpy/__init__.py A numpy/numpy/lib A numpy/numpy/lib/scimath.py A numpy/numpy/lib/shape_base.py A numpy/numpy/lib/machar.py A numpy/numpy/lib/info.py A numpy/numpy/lib/twodim_base.py A numpy/numpy/lib/__init__.py A numpy/numpy/lib/src A numpy/numpy/lib/src/_compiled_base.c A numpy/numpy/lib/setup.py A numpy/numpy/lib/utils.py A numpy/numpy/lib/getlimits.py A numpy/numpy/lib/tests A numpy/numpy/lib/tests/test_shape_base.py A numpy/numpy/lib/tests/test_arraysetops.py A numpy/numpy/lib/tests/test_twodim_base.py A numpy/numpy/lib/tests/test_type_check.py A numpy/numpy/lib/tests/test_function_base.py A numpy/numpy/lib/tests/test_getlimits.py A numpy/numpy/lib/tests/test_polynomial.py A numpy/numpy/lib/tests/test_ufunclike.py A numpy/numpy/lib/tests/test_index_tricks.py A numpy/numpy/lib/mlab.py A numpy/numpy/lib/convertcode.py A numpy/numpy/lib/arraysetops.py A numpy/numpy/lib/UserArray.py A numpy/numpy/lib/type_check.py A numpy/numpy/lib/function_base.py A numpy/numpy/lib/polynomial.py A numpy/numpy/lib/ufunclike.py A numpy/numpy/lib/index_tricks.py A numpy/numpy/linalg A numpy/numpy/linalg/blas_lite.c A numpy/numpy/linalg/lapack_litemodule.c A numpy/numpy/linalg/f2c.h A numpy/numpy/linalg/info.py A numpy/numpy/linalg/zlapack_lite.c A numpy/numpy/linalg/old.py A numpy/numpy/linalg/__init__.py A numpy/numpy/linalg/setup.py A numpy/numpy/linalg/f2c_lite.c A numpy/numpy/linalg/dlamch.c A numpy/numpy/linalg/dlapack_lite.c A numpy/numpy/linalg/linalg.py A numpy/numpy/setup.py A numpy/numpy/core A numpy/numpy/core/info.py A numpy/numpy/core/defchararray.py A numpy/numpy/core/arrayprint.py A numpy/numpy/core/include A numpy/numpy/core/include/numpy A numpy/numpy/core/include/numpy/arrayobject.h A numpy/numpy/core/include/numpy/arrayscalars.h A numpy/numpy/core/include/numpy/ufuncobject.h A numpy/numpy/core/include/numpy/fenv A numpy/numpy/core/include/numpy/fenv/fenv.c A numpy/numpy/core/include/numpy/fenv/fenv.h A numpy/numpy/core/ma.py A numpy/numpy/core/__init__.py A numpy/numpy/core/setup.py A numpy/numpy/core/src A numpy/numpy/core/src/_signbit.c A numpy/numpy/core/src/multiarraymodule.c A numpy/numpy/core/src/arraytypes.inc.src A numpy/numpy/core/src/_sortmodule.c.src A numpy/numpy/core/src/arraymethods.c A numpy/numpy/core/src/ucsnarrow.c A numpy/numpy/core/src/arrayobject.c A numpy/numpy/core/src/_isnan.c A numpy/numpy/core/src/scalartypes.inc.src A numpy/numpy/core/src/ufuncobject.c A numpy/numpy/core/src/umathmodule.c.src A numpy/numpy/core/src/scalarmathmodule.c.src A numpy/numpy/core/records.py A numpy/numpy/core/oldnumeric.py A numpy/numpy/core/blasdot A numpy/numpy/core/blasdot/_dotblas.c A numpy/numpy/core/blasdot/cblas.h A numpy/numpy/core/numeric.py A numpy/numpy/core/_internal.py A numpy/numpy/core/tests A numpy/numpy/core/tests/test_multiarray.py A numpy/numpy/core/tests/test_ma.py A numpy/numpy/core/tests/test_umath.py A numpy/numpy/core/tests/test_oldnumeric.py A numpy/numpy/core/tests/test_records.py A numpy/numpy/core/tests/test_numeric.py A numpy/numpy/core/tests/test_defmatrix.py A numpy/numpy/core/tests/test_unicode.py A numpy/numpy/core/tests/test_numerictypes.py A numpy/numpy/core/tests/testdata.fits A numpy/numpy/core/memmap.py A numpy/numpy/core/code_generators A numpy/numpy/core/code_generators/generate_umath.py A numpy/numpy/core/code_generators/array_api_order.txt A numpy/numpy/core/code_generators/ufunc_api_order.txt A numpy/numpy/core/code_generators/generate_array_api.py A numpy/numpy/core/code_generators/genapi.py A numpy/numpy/core/code_generators/generate_ufunc_api.py A numpy/numpy/core/code_generators/multiarray_api_order.txt A numpy/numpy/core/defmatrix.py A numpy/numpy/core/numerictypes.py A numpy/numpy/dual.py A numpy/numpy/version.py A numpy/numpy/dft A numpy/numpy/dft/fftpack.c A numpy/numpy/dft/fftpack_litemodule.c A numpy/numpy/dft/info.py A numpy/numpy/dft/tests A numpy/numpy/dft/tests/test_helper.py A numpy/numpy/dft/fftpack.h A numpy/numpy/dft/fftpack.py A numpy/numpy/dft/__init__.py A numpy/numpy/dft/helper.py A numpy/numpy/dft/setup.py A numpy/numpy/testing A numpy/numpy/testing/numpytest.py A numpy/numpy/testing/info.py A numpy/numpy/testing/__init__.py A numpy/numpy/testing/setup.py A numpy/numpy/testing/utils.py A numpy/COMPATIBILITY A numpy/DEV_README.txt A numpy/MANIFEST.in A numpy/README.txt A numpy/benchmarks A numpy/benchmarks/sorting.py U numpy Checked out revision 2259. ### Start build. ### /data/basil5/numpy build: No such file or directory Running from numpy source directory. Warning: not existing path in numpy/distutils: site.cfg /data/basil5/numpy/numpy/distutils/system_info.py:531: UserWarning: Library error: libs=['mkl', 'vml', 'guide'] found_libs=[] warnings.warn("Library error: libs=%s found_libs=%s" % \ /data/basil5/numpy/numpy/distutils/system_info.py:531: UserWarning: Library error: libs=['ptf77blas', 'ptcblas', 'atlas'] found_libs=[] warnings.warn("Library error: libs=%s found_libs=%s" % \ /data/basil5/numpy/numpy/distutils/system_info.py:531: UserWarning: Library error: libs=['f77blas', 'cblas', 'atlas'] found_libs=[] warnings.warn("Library error: libs=%s found_libs=%s" % \ /data/basil5/numpy/numpy/distutils/system_info.py:1264: UserWarning: Atlas (http://math-atlas.sourceforge.net/) libraries not found. Directories to search for the libraries can be specified in the numpy/distutils/site.cfg file (section [atlas]) or by setting the ATLAS environment variable. warnings.warn(AtlasNotFoundError.__doc__) /data/basil5/numpy/numpy/distutils/system_info.py:531: UserWarning: Library error: libs=['blas'] found_libs=[] warnings.warn("Library error: libs=%s found_libs=%s" % \ /data/basil5/numpy/numpy/distutils/system_info.py:1273: UserWarning: Blas (http://www.netlib.org/blas/) libraries not found. Directories to search for the libraries can be specified in the numpy/distutils/site.cfg file (section [blas]) or by setting the BLAS environment variable. warnings.warn(BlasNotFoundError.__doc__) /data/basil5/numpy/numpy/distutils/system_info.py:1276: UserWarning: Blas (http://www.netlib.org/blas/) sources not found. Directories to search for the sources can be specified in the numpy/distutils/site.cfg file (section [blas_src]) or by setting the BLAS_SRC environment variable. warnings.warn(BlasSrcNotFoundError.__doc__) /data/basil5/numpy/numpy/distutils/system_info.py:531: UserWarning: Library error: libs=['lapack_atlas'] found_libs=[] warnings.warn("Library error: libs=%s found_libs=%s" % \ /data/basil5/numpy/numpy/distutils/system_info.py:1183: UserWarning: Atlas (http://math-atlas.sourceforge.net/) libraries not found. Directories to search for the libraries can be specified in the numpy/distutils/site.cfg file (section [atlas]) or by setting the ATLAS environment variable. warnings.warn(AtlasNotFoundError.__doc__) /data/basil5/numpy/numpy/distutils/system_info.py:531: UserWarning: Library error: libs=['lapack'] found_libs=[] warnings.warn("Library error: libs=%s found_libs=%s" % \ /data/basil5/numpy/numpy/distutils/system_info.py:1207: UserWarning: Blas (http://www.netlib.org/blas/) libraries not found. Directories to search for the libraries can be specified in the numpy/distutils/site.cfg file (section [blas]) or by setting the BLAS environment variable. warnings.warn(BlasNotFoundError.__doc__) /data/basil5/numpy/numpy/distutils/system_info.py:1210: UserWarning: Blas (http://www.netlib.org/blas/) sources not found. Directories to search for the sources can be specified in the numpy/distutils/site.cfg file (section [blas_src]) or by setting the BLAS_SRC environment variable. warnings.warn(BlasSrcNotFoundError.__doc__) No module named __svn_version__ F2PY Version 2_2259 blas_opt_info: blas_mkl_info: NOT AVAILABLE atlas_blas_threads_info: Setting PTATLAS=ATLAS NOT AVAILABLE atlas_blas_info: NOT AVAILABLE blas_info: NOT AVAILABLE blas_src_info: NOT AVAILABLE NOT AVAILABLE lapack_opt_info: lapack_mkl_info: mkl_info: NOT AVAILABLE NOT AVAILABLE atlas_threads_info: Setting PTATLAS=ATLAS numpy.distutils.system_info.atlas_threads_info NOT AVAILABLE atlas_info: numpy.distutils.system_info.atlas_info NOT AVAILABLE lapack_info: FOUND: libraries = ['lapack'] library_dirs = ['/usr/local/lib'] language = f77 NOT AVAILABLE running build running config_fc running build_src building py_modules sources creating build creating build/src creating build/src/numpy creating build/src/numpy/distutils building extension "numpy.core.multiarray" sources creating build/src/numpy/core Generating build/src/numpy/core/config.h customize SunFCompiler compiler version not matched (None) customize GnuFCompiler customize Gnu95FCompiler customize G95FCompiler customize GnuFCompiler customize Gnu95FCompiler customize SunFCompiler Traceback (most recent call last): File "setup.py", line 76, in ? setup_package() File "setup.py", line 69, in setup_package setup( **config.todict() ) File "/data/basil5/numpy/numpy/distutils/core.py", line 85, in setup return old_setup(**new_attr) File "/usr/ra/pyssg/Python-2.4.2/lib/python2.4/distutils/core.py", line 149, in setup dist.run_commands() File "/usr/ra/pyssg/Python-2.4.2/lib/python2.4/distutils/dist.py", line 946, in run_commands self.run_command(cmd) File "/usr/ra/pyssg/Python-2.4.2/lib/python2.4/distutils/dist.py", line 966, in run_command cmd_obj.run() File "/usr/ra/pyssg/Python-2.4.2/lib/python2.4/distutils/command/build.py", line 112, in run self.run_command(cmd_name) File "/usr/ra/pyssg/Python-2.4.2/lib/python2.4/distutils/cmd.py", line 333, in run_command self.distribution.run_command(command) File "/usr/ra/pyssg/Python-2.4.2/lib/python2.4/distutils/dist.py", line 966, in run_command cmd_obj.run() File "/data/basil5/numpy/numpy/distutils/command/build_src.py", line 84, in run self.build_sources() File "/data/basil5/numpy/numpy/distutils/command/build_src.py", line 99, in build_sources self.build_extension_sources(ext) File "/data/basil5/numpy/numpy/distutils/command/build_src.py", line 209, in build_extension_sources sources = self.generate_sources(sources, ext) File "/data/basil5/numpy/numpy/distutils/command/build_src.py", line 267, in generate_sources source = func(extension, build_dir) File "numpy/core/setup.py", line 35, in generate_config_h library_dirs = default_lib_dirs) File "/usr/ra/pyssg/Python-2.4.2/lib/python2.4/distutils/command/config.py", line 278, in try_run self._check_compiler() File "/data/basil5/numpy/numpy/distutils/command/config.py", line 35, in _check_compiler self.fcompiler.customize(self.distribution) File "/data/basil5/numpy/numpy/distutils/fcompiler/__init__.py", line 281, in customize (conf,'f77flags')) File "/data/basil5/numpy/numpy/distutils/fcompiler/__init__.py", line 511, in __get_flags var = command() File "/data/basil5/numpy/numpy/distutils/fcompiler/sun.py", line 27, in get_flags_f77 if (self.get_version() or '') >= '7': File "/data/basil5/numpy/numpy/distutils/ccompiler.py", line 256, in CCompiler_get_version raise ValueError("compiler version not matched (%r)" % (version,)) ValueError: compiler version not matched (None)

3 3

complex comparisons
by Tim Hochberg 20 Mar '06

20 Mar '06

I just noticed that complex arrays can be compared using [<, <=, > and >=]. Do we really want this? I'd prefer to follow numarray's lead here and only support [==, !=] on complex arrays. -tim

6 6

gentoo numpy/scipy
by Sebastien Fabbro 20 Mar '06

20 Mar '06

Hello all, For those interested, I try to maintain recent versions of numpy, scipy and some other science related python packages for Gentoo Linux in http://gentooscience.org. All of these packages will end up in the standard Gentoo tree at some point. They are experimental to test recent features or can't wait for gentoo stabilization process. On a related subject, the numpy/scipy building process could really benefit some up-to-date, documentation package maintainer friendly, e.g. a site.cfg commented example. Regards, Sebastien

1 0

NumPy 0.9.6-r1?
by Ed Schofield 20 Mar '06

20 Mar '06

Hi Travis, I've re-built NumPy 0.9.6 for Win32 / Py2.4 after disabling the block in testing/utils.py that requires win32all. Let me know if you'd like me to upload it to the Wiki as NumPy 0.9.6-r1. It's 66kb smaller than your .exe file, which I don't quite understand, but otherwise seems to work fine. I've built it against ATLAS-3.6.0-PII from http://old.scipy.org. -- Ed

1 0

Rationale behind behaviour of atleast_3d in Numpy
by Zdeněk Hurák 20 Mar '06

20 Mar '06

Hello, As a newcommer, I am trying not only to learn to use Numpy, but also to understand it. I think I need some help with function atleast_3d. When applied to 2d array, its behaviour is different then when applied to 1d array (it is a documented feature): a = array([1,2,3]) A = array([[1,2,3],[4,5,6]]) a3d = atleast_3d(a) print a3d.shape ---> (1, 3, 1) A3d = atleast_3d(A) print A3d.shape ---> (2, 3, 1) What is the rationale behind this in my opinion unintuitive inconsistency? I especially don't understand the behaviour for 1d arrays. But even with 2d arrays, I am inclined to think (with my beginner-level of mastering Python and Numpy) that a more natural result of shape function would be (1,2,3). Thank you very much for some explanation, Zdenek Hurak

1 0

Fw:
by vzkezlxdkhy 19 Mar '06

19 Mar '06

----- Original Message ----- From: Herman Augustus To: dmqztgjn(a)nate.com Sent: Monday, March 13, 2006 11:16 PM Subject: numpy-discussion

1 0

NumPy 0.9.6 and win32pdh
by Ed Schofield 19 Mar '06

19 Mar '06

Hi all, I'm trying to compile Win32 binaries for a new release of SciPy. I'm getting a warning message upon import after installing numpy-0.9.6-win32-py2.4.exe: import testing -> failed: No module named win32pdh and I'm unable to run any of NumPy's unit tests unless I manually comment out the block if os.name=='nt': ... in testing\utils.py. Has anyone else seen this? Does anyone know if the win32pdh module is supposed to be installed with the python-2.4.2.msi installer from python.org? The Python 2.3 installer, numpy-0.9.6-win32-py2.3.exe, works fine, because the corresponding if statement has an additional condition (" and sys.version[:3] > '2.3'"), so the import is never attempted. -- Ed

3 2

gcc-4.1
by Darren Dale 18 Mar '06

18 Mar '06

Has anyone been able to build numpy with gcc-4.1? I upgraded gcc on my home computer this weekend from glibc-2.3.6 and gcc-3.4.5 to glibc-2.4 and gcc-4.1. When I try to build numpy I get warnings like "warning: build_ext: fcompiler=gnu is not available." I tried forcing numpy to use gfortran with "python setup.py config_fc --fcompiler=gnu95 build", and got the same warning for fcompiler=gnu95. Here is the output of "gfortran --version": GNU Fortran 95 (GCC) 4.1.0 (Gentoo 4.1.0) Copyright (C) 2006 Free Software Foundation, Inc. GNU Fortran comes with NO WARRANTY, to the extent permitted by law. You may redistribute copies of GNU Fortran under the terms of the GNU General Public License. For more information about these matters, see the file named COPYING And here is the output of "python setup.py config_fc --help-fcompiler": Running from numpy source directory. running config_fc customize CompaqFCompiler customize NoneFCompiler customize AbsoftFCompiler Could not locate executable ifort Could not locate executable ifc Could not locate executable ifort Could not locate executable efort Could not locate executable efc customize IntelFCompiler Could not locate executable g77 Could not locate executable f77 Could not locate executable f95 customize GnuFCompiler customize SunFCompiler customize VastFCompiler customize GnuFCompiler customize IbmFCompiler customize Gnu95FCompiler customize IntelVisualFCompiler customize G95FCompiler customize IntelItaniumFCompiler customize PGroupFCompiler customize LaheyFCompiler customize CompaqVisualFCompiler customize MipsFCompiler customize HPUXFCompiler customize IntelItaniumVisualFCompiler customize NAGFCompiler List of available Fortran compilers: List of unavailable Fortran compilers: --fcompiler=absoft Absoft Corp Fortran Compiler --fcompiler=compaq Compaq Fortran Compiler --fcompiler=compaqv DIGITAL|Compaq Visual Fortran Compiler --fcompiler=g95 GNU Fortran 95 Compiler --fcompiler=gnu GNU Fortran Compiler --fcompiler=gnu95 GNU 95 Fortran Compiler --fcompiler=hpux HP Fortran 90 Compiler --fcompiler=ibm IBM XL Fortran Compiler --fcompiler=intel Intel Fortran Compiler for 32-bit apps --fcompiler=intele Intel Fortran Compiler for Itanium apps --fcompiler=intelev Intel Visual Fortran Compiler for Itanium apps --fcompiler=intelv Intel Visual Fortran Compiler for 32-bit apps --fcompiler=lahey Lahey/Fujitsu Fortran 95 Compiler --fcompiler=mips MIPSpro Fortran Compiler --fcompiler=nag NAGWare Fortran 95 Compiler --fcompiler=none Fake Fortran compiler --fcompiler=pg Portland Group Fortran Compiler --fcompiler=sun Sun|Forte Fortran 95 Compiler --fcompiler=vast Pacific-Sierra Research Fortran 90 Compiler List of unimplemented Fortran compilers: --fcompiler=f Fortran Company/NAG F Compiler For compiler details, run 'config_fc --verbose' setup command. Thanks, Darren

3 5

Array scalar math ideas
by Travis Oliphant 17 Mar '06

17 Mar '06

I'm starting to write the remaining array scalar math tables (so that we can speed up scalar*scalar arithmetic). Right now, all operations involving scalars are converted to 0-d arrays - use the ufunc machinery - and are converted back to scalars after the operation. The scalarmathmodule.c.src file is being written to fix this and insert type-appropriate operations for each of the (number-type) array scalars. My general strategy for the binary operations is going to be the following. I wanted to bounce it off the list to see what other ideas people had: Code outline: Convert inputs so that self is the array scalar of some type and other is the other object if (other is an array scalar of the same data-type as self) arg3 = other else if (other is an array scalar of a different data-type as self) arg3 = convert_other_to_self_data_type(other) else if (other is a Python scalar) arg3 = convert_Python_scalar_to_array_scalar(other) else if (other is a 0-d array) arg3 = convert_other_to_self_data_type_from_0-d_array(other) else return (use ufunc to calculate result). return (operation using self and arg3) if an error condition is encountered, then only at that point, the proper way to handle it will be determined by looking in the local / global / builtin scope for the error-handling variable. Tthis avoids the overhead of looking up what to do to the case of an error actually occurring --- I need to change the ufuncobject.c code to also do this and save the overhead there too --- right now what to do is looked up every time, rather than waiting until an error is actually detected.) What do people think? -Travis

3 4

numexpr update
by Tim Hochberg 17 Mar '06

17 Mar '06

I just committed a whole slow of changes to numexpr for your enjoyment. First the good news. It now handles integers as well as floats and the framework is in place for adding complex numbers as well (it can actually add complex numbers, but nothing else yet). It should be pretty simple to add complex at this point, so that'll probably happen soon. Otherwise things are more or less the same, although I expect to modifying the interface a little bit here soon to better support typing of input values. Now the bad news: somewhere along the way I introduced some sort of memory bug and it occasionally segfaults on me. I'm not sure if it's reference counting or I'm scribbling outside my allocated block of memory somehow, but I'll continue hunting it down. More minor issues include int**int is a little bit bogus and I've turned off the aggressive power optimizations for the moment pending some improvements to the compiler. -tim

1 0