def test_mergeds():
data0 = Dataset.from_wizard(np.ones((5, 5)), targets=1)
data0.fa['one'] = np.ones(5)
data1 = Dataset.from_wizard(np.ones((5, 5)), targets=1, chunks=1)
data1.fa['one'] = np.zeros(5)
data2 = Dataset.from_wizard(np.ones((3, 5)), targets=2, chunks=1)
data3 = Dataset.from_wizard(np.ones((4, 5)), targets=2)
data4 = Dataset.from_wizard(np.ones((2, 5)), targets=3, chunks=2)
data4.fa['test'] = np.arange(5)
# cannot merge if there are attributes missing in one of the datasets
assert_raises(DatasetError, data1.append, data0)
merged = data1.copy()
merged.append(data2)
ok_( merged.nfeatures == 5 )
l12 = [1]*5 + [2]*3
l1 = [1]*8
ok_((merged.targets == l12).all())
ok_((merged.chunks == l1).all())
data_append = data1.copy()
data_append.append(data2)
ok_(data_append.nfeatures == 5)
ok_((data_append.targets == l12).all())
ok_((data_append.chunks == l1).all())
#
# appending
#
# we need the same samples attributes in both datasets
assert_raises(DatasetError, data2.append, data3)
#
# vstacking
#
if __debug__:
# tested only in __debug__
assert_raises(ValueError, vstack, (data0, data1, data2, data3))
datasets = (data1, data2, data4)
merged = vstack(datasets)
assert_equal(merged.shape,
(np.sum([len(ds) for ds in datasets]), data1.nfeatures))
assert_true('test' in merged.fa)
assert_array_equal(merged.sa.targets, [1]*5 + [2]*3 + [3]*2)
#
# hstacking
#
assert_raises(ValueError, hstack, datasets)
datasets = (data0, data1)
merged = hstack(datasets)
assert_equal(merged.shape,
(len(data1), np.sum([ds.nfeatures for ds in datasets])))
assert_true('chunks' in merged.sa)
assert_array_equal(merged.fa.one, [1]*5 + [0]*5)
def test_hstack():
"""Additional tests for hstacking of datasets
"""
ds3d = datasets['3dsmall']
nf1 = ds3d.nfeatures
nf3 = 3 * nf1
ds3dstacked = hstack((ds3d, ds3d, ds3d))
ok_(ds3dstacked.nfeatures == nf3)
for fav in ds3dstacked.fa.itervalues():
v = fav.value
ok_(len(v) == nf3)
assert_array_equal(v[:nf1], v[nf1:2*nf1])
assert_array_equal(v[2*nf1:], v[nf1:2*nf1])