def test_directaccess():
f = tempfile.NamedTemporaryFile()
h5save(f.name, 'test')
assert_equal(h5load(f.name), 'test')
f.close()
f = tempfile.NamedTemporaryFile()
h5save(f.name, datasets['uni4medium'])
assert_array_equal(h5load(f.name).samples, datasets['uni4medium'].samples)
def test_directaccess():
f = tempfile.NamedTemporaryFile()
h5save(f.name, "test")
assert_equal(h5load(f.name), "test")
f.close()
f = tempfile.NamedTemporaryFile()
h5save(f.name, datasets["uni4medium"])
assert_array_equal(h5load(f.name).samples, datasets["uni4medium"].samples)
def test_dataset_without_chunks():
# ValueError: All chunk dimensions must be positive (Invalid arguments to routine: Out of range)
# MH: This is not about Dataset chunks, but about an empty samples array
f = tempfile.NamedTemporaryFile()
ds = AttrDataset([8], a=dict(custom=1))
save(ds, f.name, compression='gzip')
ds_loaded = h5load(f.name)
ok_(ds_loaded.a.custom == ds.a.custom)
def test_dataset_without_chunks():
# ValueError: All chunk dimensions must be positive (Invalid arguments to routine: Out of range)
# MH: This is not about Dataset chunks, but about an empty samples array
f = tempfile.NamedTemporaryFile()
ds = AttrDataset([8], a=dict(custom=1))
save(ds, f.name, compression='gzip')
ds_loaded = h5load(f.name)
ok_(ds_loaded.a.custom == ds.a.custom)
def test_recursion():
obj = range(2)
obj.append(HDFDemo())
obj.append(obj)
f = tempfile.NamedTemporaryFile()
h5save(f.name, obj)
lobj = h5load(f.name)
assert_equal(obj[:2], lobj[:2])
assert_equal(type(obj[2]), type(lobj[2]))
ok_(obj[3] is obj)
ok_(lobj[3] is lobj)
def test_recursion():
obj = range(2)
obj.append(HDFDemo())
obj.append(obj)
f = tempfile.NamedTemporaryFile()
h5save(f.name, obj)
lobj = h5load(f.name)
assert_equal(obj[:2], lobj[:2])
assert_equal(type(obj[2]), type(lobj[2]))
ok_(obj[3] is obj)
ok_(lobj[3] is lobj)
def test_function_ptrs():
ds = load_example_fmri_dataset()
# add a mapper with a function ptr inside
ds = ds.get_mapped(mean_sample())
f = tempfile.NamedTemporaryFile()
h5save(f.name, ds)
ds_loaded = h5load(f.name)
fresh = load_example_fmri_dataset().O
# check that the reconstruction function pointer in the FxMapper points
# to the right one
assert_array_equal(ds_loaded.a.mapper.forward(fresh),
ds.samples)
def test_function_ptrs():
if not externals.exists('nifti') and not externals.exists('nibabel'):
raise SkipTest
ds = load_example_fmri_dataset()
# add a mapper with a function ptr inside
ds = ds.get_mapped(mean_sample())
f = tempfile.NamedTemporaryFile()
h5save(f.name, ds)
ds_loaded = h5load(f.name)
fresh = load_example_fmri_dataset().O
# check that the reconstruction function pointer in the FxMapper points
# to the right one
assert_array_equal(ds_loaded.a.mapper.forward(fresh), ds.samples)
def _test_h5py_clfs():
# YOH: For now just to see which ones work (could be stored/loaded)
# Later on to become a proper valid test
from mvpa.clfs.warehouse import clfswh, regrswh
for lrn in clfswh[:] + regrswh[:]:
print lrn
f = tempfile.NamedTemporaryFile()
try:
h5save(f.name, lrn)
lrn_ = h5load(f.name)
print "ok: %s" % lrn_
except Exception, e:
#raise AssertionError,
print "Failed to store %s due to %r" % (lrn, e)
# lets simply clone it so we could make its all states on
lrn = lrn.clone()
# Lets enable all the states
lrn.ca.enable('all')
f = tempfile.NamedTemporaryFile()
# Store/reload untrained learner
try:
h5save(f.name, lrn)
except Exception, e:
raise AssertionError, \
"Failed to store due to %r" % (e,)
try:
lrn_ = h5load(f.name)
except Exception, e:
raise AssertionError, \
"Failed to load due to %r" % (e,)
ok_(isinstance(lrn_, Classifier))
# Verify that we have the same ca enabled
# XXX FAILS atm!
#ok_(set(lrn.ca.enabled) == set(lrn_.ca.enabled))
# lets choose a dataset
dsname, errorfx = \
{False: ('uni2large', MeanMismatchErrorFx()),
True: ('sin_modulated', CorrErrorFx())}\
['regression' in lrn.__tags__]
ds_train = datasets['%s_train' % dsname]
# lets simply clone it so we could make its all states on
lrn = lrn.clone()
# Lets enable all the states
lrn.ca.enable('all')
f = tempfile.NamedTemporaryFile()
# Store/reload untrained learner
try:
h5save(f.name, lrn)
except Exception, e:
raise AssertionError, \
"Failed to store due to %r" % (e,)
try:
lrn_ = h5load(f.name)
except Exception, e:
raise AssertionError, \
"Failed to load due to %r" % (e,)
ok_(isinstance(lrn_, Classifier))
# Verify that we have the same ca enabled
# XXX FAILS atm!
#ok_(set(lrn.ca.enabled) == set(lrn_.ca.enabled))
# lets choose a dataset
dsname, errorfx = \
{False: ('uni2large', mean_mismatch_error),
True: ('sin_modulated', corr_error)}\
['regression' in lrn.__tags__]
ds = datasets[dsname]
def test_matfile_v73_compat():
mat = h5load(os.path.join(pymvpa_dataroot, 'v73.mat'))
assert_equal(len(mat), 2)
assert_equal(sorted(mat.keys()), ['x', 'y'])
assert_array_equal(mat['x'], np.arange(6)[None].T)
assert_array_equal(mat['y'], np.array([(1, 0, 1)], dtype='uint8').T)
def test_0d_object_ndarray():
f = tempfile.NamedTemporaryFile()
a = np.array(0, dtype=object)
h5save(f.name, a)
a_ = h5load(f.name)
ok_(a == a_)
def test_matfile_v73_compat():
mat = h5load(os.path.join(pymvpa_dataroot, 'v73.mat'))
assert_equal(len(mat), 2)
assert_equal(sorted(mat.keys()), ['x', 'y'])
assert_array_equal(mat['x'], np.arange(6)[None].T)
assert_array_equal(mat['y'], np.array([(1,0,1)], dtype='uint8').T)
def test_0d_object_ndarray():
f = tempfile.NamedTemporaryFile()
a = np.array(0, dtype=object)
h5save(f.name, a)
a_ = h5load(f.name)
ok_(a == a_)
def test_matfile_v73_compat():
mat = h5load(os.path.join(pymvpa_dataroot, "v73.mat"))
assert_equal(len(mat), 2)
assert_equal(sorted(mat.keys()), ["x", "y"])
assert_array_equal(mat["x"], np.arange(6)[None].T)
assert_array_equal(mat["y"], np.array([(1, 0, 1)], dtype="uint8").T)
