def test_largest_cc_img():
""" Check the extraction of the largest connected component, for niftis
Similiar to smooth_img tests for largest connected_component_img, here also
only the added features for largest_connected_component are tested.
"""
# Test whether dimension of 3Dimg and list of 3Dimgs are kept.
shapes = ((10, 11, 12), (13, 14, 15))
regions = [1, 3]
img1 = testing.generate_labeled_regions(shape=shapes[0],
n_regions=regions[0])
img2 = testing.generate_labeled_regions(shape=shapes[1],
n_regions=regions[1])
for create_files in (False, True):
with testing.write_tmp_imgs(img1, img2,
create_files=create_files) as imgs:
# List of images as input
out = largest_connected_component_img(imgs)
assert_true(isinstance(out, list))
assert_true(len(out) == 2)
for o, s in zip(out, shapes):
assert_true(o.shape == (s))
# Single image as input
out = largest_connected_component_img(imgs[0])
assert_true(isinstance(out, Nifti1Image))
assert_true(out.shape == (shapes[0]))
# Test whether 4D Nifti throws the right error.
img_4D = testing.generate_fake_fmri(shapes[0], length=17)
assert_raises(DimensionError, largest_connected_component_img, img_4D)
def test_generate_labeled_regions():
"""Minimal testing of generate_labeled_regions"""
shape = (3, 4, 5)
n_regions = 10
regions = generate_labeled_regions(shape, n_regions)
assert_true(regions.shape == shape)
assert (len(np.unique(regions.get_data())) == n_regions + 1)
def test_generate_labeled_regions():
"""Minimal testing of generate_labeled_regions"""
shape = (3, 4, 5)
n_regions = 10
regions = generate_labeled_regions(shape, n_regions)
assert_true(regions.shape == shape)
assert (len(np.unique(regions.get_data())) == n_regions + 1)
def test_error_messages_connected_label_regions():
shape = (13, 11, 12)
affine = np.eye(4)
n_regions = 2
labels_img = testing.generate_labeled_regions(shape, affine=affine,
n_regions=n_regions)
assert_raises_regex(ValueError,
"Expected 'min_size' to be specified as integer.",
connected_label_regions,
labels_img=labels_img, min_size='a')
assert_raises_regex(ValueError,
"'connect_diag' must be specified as True or False.",
connected_label_regions,
labels_img=labels_img, connect_diag=None)
def test_error_messages_connected_label_regions():
shape = (13, 11, 12)
affine = np.eye(4)
n_regions = 2
labels_img = testing.generate_labeled_regions(shape, affine=affine,
n_regions=n_regions)
assert_raises_regex(ValueError,
"Expected 'min_size' to be specified as integer.",
connected_label_regions,
labels_img=labels_img, min_size='a')
assert_raises_regex(ValueError,
"'connect_diag' must be specified as True or False.",
connected_label_regions,
labels_img=labels_img, connect_diag=None)
def test_largest_cc():
""" Check the extraction of the largest connected component.
"""
a = np.zeros((6, 6, 6))
assert_raises(ValueError, largest_connected_component, a)
a[1:3, 1:3, 1:3] = 1
np.testing.assert_equal(a, largest_connected_component(a))
b = a.copy()
b[5, 5, 5] = 1
np.testing.assert_equal(a, largest_connected_component(b))
# Tests for correct errors, when an image or string are passed.
img = testing.generate_labeled_regions(shape=(10, 11, 12),
n_regions=2)
assert_raises(ValueError, largest_connected_component, img)
assert_raises(ValueError, largest_connected_component, "Test String")
def test_nifti_labels_masker_with_nans_and_infs():
length = 3
n_regions = 9
fmri_img, mask_img = generate_random_img((13, 11, 12),
affine=np.eye(4), length=length)
labels_img = testing.generate_labeled_regions((13, 11, 12),
affine=np.eye(4),
n_regions=n_regions)
# nans
mask_data = mask_img.get_data()
mask_data[:, :, 7] = np.nan
mask_data[:, :, 4] = np.inf
mask_img = nibabel.Nifti1Image(mask_data, np.eye(4))
masker = NiftiLabelsMasker(labels_img, mask_img=mask_img)
sig = masker.fit_transform(fmri_img)
assert_equal(sig.shape, (length, n_regions))
assert_true(np.all(np.isfinite(sig)))
def test_nifti_labels_masker_with_nans_and_infs():
length = 3
n_regions = 9
fmri_img, mask_img = generate_random_img((13, 11, 12),
affine=np.eye(4),
length=length)
labels_img = testing.generate_labeled_regions((13, 11, 12),
affine=np.eye(4),
n_regions=n_regions)
# nans
mask_data = mask_img.get_data()
mask_data[:, :, 7] = np.nan
mask_data[:, :, 4] = np.inf
mask_img = nibabel.Nifti1Image(mask_data, np.eye(4))
masker = NiftiLabelsMasker(labels_img, mask_img=mask_img)
sig = masker.fit_transform(fmri_img)
assert_equal(sig.shape, (length, n_regions))
assert_true(np.all(np.isfinite(sig)))
def test_largest_cc():
""" Check the extraction of the largest connected component.
"""
a = np.zeros((6, 6, 6))
assert_raises(ValueError, largest_connected_component, a)
a[1:3, 1:3, 1:3] = 1
np.testing.assert_equal(a, largest_connected_component(a))
# A simple test with non-native dtype
a_change_type = a.astype('>f8')
np.testing.assert_equal(a, largest_connected_component(a_change_type))
b = a.copy()
b[5, 5, 5] = 1
np.testing.assert_equal(a, largest_connected_component(b))
# A simple test with non-native dtype
b_change_type = b.astype('>f8')
np.testing.assert_equal(a, largest_connected_component(b_change_type))
# Tests for correct errors, when an image or string are passed.
img = testing.generate_labeled_regions(shape=(10, 11, 12),
n_regions=2)
assert_raises(ValueError, largest_connected_component, img)
assert_raises(ValueError, largest_connected_component, "Test String")
def test_connected_label_regions():
shape = (13, 11, 12)
affine = np.eye(4)
n_regions = 9
labels_img = testing.generate_labeled_regions(shape, affine=affine,
n_regions=n_regions)
labels_data = labels_img.get_data()
n_labels_wo_reg_ext = len(np.unique(labels_data))
# region extraction without specifying min_size
extracted_regions_on_labels_img = connected_label_regions(labels_img)
extracted_regions_labels_data = extracted_regions_on_labels_img.get_data()
n_labels_wo_min = len(np.unique(extracted_regions_labels_data))
assert_true(n_labels_wo_reg_ext < n_labels_wo_min)
# with specifying min_size
extracted_regions_with_min = connected_label_regions(labels_img,
min_size=100)
extracted_regions_with_min_data = extracted_regions_with_min.get_data()
n_labels_with_min = len(np.unique(extracted_regions_with_min_data))
assert_true(n_labels_wo_min > n_labels_with_min)
# Test connect_diag=False
ext_reg_without_connect_diag = connected_label_regions(labels_img,
connect_diag=False)
data_wo_connect_diag = ext_reg_without_connect_diag.get_data()
n_labels_wo_connect_diag = len(np.unique(data_wo_connect_diag))
assert_true(n_labels_wo_connect_diag > n_labels_wo_reg_ext)
# If min_size is large and if all the regions are removed then empty image
# will be returned
extract_reg_min_size_large = connected_label_regions(labels_img,
min_size=500)
assert_true(np.unique(extract_reg_min_size_large.get_data()) == 0)
# Test the names of the brain regions given in labels.
# Test labels for 9 regions in n_regions
labels = ['region_a', 'region_b', 'region_c', 'region_d', 'region_e',
'region_f', 'region_g', 'region_h', 'region_i']
# If labels are provided, first return will contain extracted labels image
# and second return will contain list of new names generated based on same
# name with assigned on both hemispheres for example.
extracted_reg, new_labels = connected_label_regions(labels_img,
min_size=100,
labels=labels)
# The length of new_labels returned can differ depending upon min_size. If
# min_size given is more small regions can be removed therefore newly
# generated labels can be less than original size of labels. Or if min_size
# is less then newly generated labels can be more.
# We test here whether labels returned are empty or not.
assert_not_equal(new_labels, '')
assert_true(len(new_labels) <= len(labels))
# labels given in numpy array
labels = np.asarray(labels)
extracted_reg2, new_labels2 = connected_label_regions(labels_img,
labels=labels)
assert_not_equal(new_labels, '')
# By default min_size is less, so newly generated labels can be more.
assert_true(len(new_labels2) >= len(labels))
# If number of labels provided are wrong (which means less than number of
# unique labels in labels_img), then we raise an error
# Test whether error raises
unique_labels = set(np.unique(np.asarray(labels_img.get_data())))
unique_labels.remove(0)
# labels given are less than n_regions=9
provided_labels = ['region_a', 'region_c', 'region_f',
'region_g', 'region_h', 'region_i']
assert_true(len(provided_labels) < len(unique_labels))
np.testing.assert_raises(ValueError, connected_label_regions,
labels_img, labels=provided_labels)
# Test if unknown/negative integers are provided as labels in labels_img,
# we raise an error and test the same whether error is raised.
labels_data = np.zeros(shape, dtype=np.int)
h0 = shape[0] // 2
h1 = shape[1] // 2
h2 = shape[2] // 2
labels_data[:h0, :h1, :h2] = 1
labels_data[:h0, :h1, h2:] = 2
labels_data[:h0, h1:, :h2] = 3
labels_data[:h0, h1:, h2:] = 4
labels_data[h0:, :h1, :h2] = 5
labels_data[h0:, :h1, h2:] = 6
labels_data[h0:, h1:, :h2] = np.nan
labels_data[h0:, h1:, h2:] = np.inf
neg_labels_img = nibabel.Nifti1Image(labels_data, affine)
np.testing.assert_raises(ValueError, connected_label_regions,
labels_img=neg_labels_img)
# If labels_img provided is 4D Nifti image, then test whether error is
# raised or not. Since this function accepts only 3D image.
labels_4d_data = np.zeros((shape) + (2, ))
labels_data[h0:, h1:, :h2] = 0
labels_data[h0:, h1:, h2:] = 0
labels_4d_data[..., 0] = labels_data
labels_4d_data[..., 1] = labels_data
labels_img_4d = nibabel.Nifti1Image(labels_4d_data, np.eye(4))
np.testing.assert_raises(DimensionError, connected_label_regions,
labels_img=labels_img_4d)
# Test if labels (or names to regions) given is a string without a list.
# Then, we expect it to be split to regions extracted and returned as list.
labels_in_str = 'region_a'
labels_img_in_str = testing.generate_labeled_regions(shape, affine=affine,
n_regions=1)
extract_regions, new_labels = connected_label_regions(labels_img_in_str,
labels=labels_in_str)
assert_true(isinstance(new_labels, list))
# If user has provided combination of labels, then function passes without
# breaking and new labels are returned based upon given labels and should
# be equal or more based on regions extracted
combined_labels = ['region_a', '1', 'region_b', '2', 'region_c', '3',
'region_d', '4', 'region_e']
ext_reg, new_labels = connected_label_regions(labels_img,
labels=combined_labels)
assert_true(len(new_labels) >= len(combined_labels))
def test_largest_cc_img():
""" Check the extraction of the largest connected component, for niftis
Similiar to smooth_img tests for largest connected_component_img, here also
only the added features for largest_connected_component are tested.
"""
# Test whether dimension of 3Dimg and list of 3Dimgs are kept.
shapes = ((10, 11, 12), (13, 14, 15))
regions = [1, 3]
img1 = testing.generate_labeled_regions(shape=shapes[0],
n_regions=regions[0])
img2 = testing.generate_labeled_regions(shape=shapes[1],
n_regions=regions[1])
for create_files in (False, True):
with testing.write_tmp_imgs(img1, img2,
create_files=create_files) as imgs:
# List of images as input
out = largest_connected_component_img(imgs)
assert_true(isinstance(out, list))
assert_true(len(out) == 2)
for o, s in zip(out, shapes):
assert_true(o.shape == (s))
# Single image as input
out = largest_connected_component_img(imgs[0])
assert_true(isinstance(out, Nifti1Image))
assert_true(out.shape == (shapes[0]))
# Test whether 4D Nifti throws the right error.
img_4D = testing.generate_fake_fmri(shapes[0], length=17)
assert_raises(DimensionError, largest_connected_component_img, img_4D)
# tests adapted to non-native endian data dtype
img1_change_dtype = nibabel.Nifti1Image(img1.get_data().astype('>f8'),
affine=img1.affine)
img2_change_dtype = nibabel.Nifti1Image(img2.get_data().astype('>f8'),
affine=img2.affine)
for create_files in (False, True):
with testing.write_tmp_imgs(img1_change_dtype,
img2_change_dtype,
create_files=create_files) as imgs:
# List of images as input
out = largest_connected_component_img(imgs)
assert_true(isinstance(out, list))
assert_true(len(out) == 2)
for o, s in zip(out, shapes):
assert_true(o.shape == (s))
# Single image as input
out = largest_connected_component_img(imgs[0])
assert_true(isinstance(out, Nifti1Image))
assert_true(out.shape == (shapes[0]))
# Test the output with native and without native
out_native = largest_connected_component_img(img1)
out_non_native = largest_connected_component_img(img1_change_dtype)
np.testing.assert_equal(out_native.get_data(), out_non_native.get_data())
def test_nifti_labels_masker_resampling():
# Test resampling in NiftiLabelsMasker
shape1 = (10, 11, 12)
affine = np.eye(4)
# mask
shape2 = (16, 17, 18)
# labels
shape3 = (13, 14, 15)
n_regions = 9
length = 3
# With data of the same affine
fmri11_img, _ = generate_random_img(shape1, affine=affine, length=length)
_, mask22_img = generate_random_img(shape2, affine=affine, length=length)
labels33_img = testing.generate_labeled_regions(shape3,
n_regions,
affine=affine)
# Test error checking
assert_raises(ValueError,
NiftiLabelsMasker,
labels33_img,
resampling_target="mask")
assert_raises(ValueError,
NiftiLabelsMasker,
labels33_img,
resampling_target="invalid")
# Target: labels
masker = NiftiLabelsMasker(labels33_img,
mask_img=mask22_img,
resampling_target="labels")
masker.fit()
np.testing.assert_almost_equal(masker.labels_img_.affine,
labels33_img.affine)
assert_equal(masker.labels_img_.shape, labels33_img.shape)
np.testing.assert_almost_equal(masker.mask_img_.affine,
masker.labels_img_.affine)
assert_equal(masker.mask_img_.shape, masker.labels_img_.shape[:3])
transformed = masker.transform(fmri11_img)
assert_equal(transformed.shape, (length, n_regions))
fmri11_img_r = masker.inverse_transform(transformed)
np.testing.assert_almost_equal(fmri11_img_r.affine,
masker.labels_img_.affine)
assert_equal(fmri11_img_r.shape,
(masker.labels_img_.shape[:3] + (length, )))
# Test with clipped labels: mask does not contain all labels.
# Shapes do matter in that case, because there is some resampling
# taking place.
shape1 = (10, 11, 12) # fmri
shape2 = (8, 9, 10) # mask
shape3 = (16, 18, 20) # maps
n_regions = 9
length = 21
fmri11_img, _ = generate_random_img(shape1, affine=affine, length=length)
_, mask22_img = generate_random_img(shape2, affine=affine, length=length)
# Target: labels
labels33_img = testing.generate_labeled_regions(shape3,
n_regions,
affine=affine)
masker = NiftiLabelsMasker(labels33_img,
mask_img=mask22_img,
resampling_target="labels")
masker.fit()
np.testing.assert_almost_equal(masker.labels_img_.affine,
labels33_img.affine)
assert_equal(masker.labels_img_.shape, labels33_img.shape)
np.testing.assert_almost_equal(masker.mask_img_.affine,
masker.labels_img_.affine)
assert_equal(masker.mask_img_.shape, masker.labels_img_.shape[:3])
uniq_labels = np.unique(masker.labels_img_.get_data())
assert_equal(uniq_labels[0], 0)
assert_equal(len(uniq_labels) - 1, n_regions)
transformed = masker.transform(fmri11_img)
assert_equal(transformed.shape, (length, n_regions))
# Some regions have been clipped. Resulting signal must be zero
assert_less((transformed.var(axis=0) == 0).sum(), n_regions)
fmri11_img_r = masker.inverse_transform(transformed)
np.testing.assert_almost_equal(fmri11_img_r.affine,
masker.labels_img_.affine)
assert_equal(fmri11_img_r.shape,
(masker.labels_img_.shape[:3] + (length, )))
# Test with data and atlas of different shape: the atlas should be
# resampled to the data
shape22 = (5, 5, 6)
affine2 = 2 * np.eye(4)
affine2[-1, -1] = 1
fmri22_img, _ = generate_random_img(shape22, affine=affine2, length=length)
masker = NiftiLabelsMasker(labels33_img, mask_img=mask22_img)
masker.fit_transform(fmri22_img)
np.testing.assert_array_equal(masker._resampled_labels_img_.affine,
affine2)
# Test with filenames
with testing.write_tmp_imgs(fmri22_img) as filename:
masker = NiftiLabelsMasker(labels33_img, resampling_target='data')
masker.fit_transform(filename)
# test labels masker with resampling target in 'data', 'labels' to return
# resampled labels having number of labels equal with transformed shape of
# 2nd dimension. This tests are added based on issue #1673 in Nilearn
shape = (13, 11, 12)
affine = np.eye(4) * 2
fmri_img, _ = generate_random_img(shape, affine=affine, length=21)
labels_img = testing.generate_labeled_regions((9, 8, 6),
affine=np.eye(4),
n_regions=10)
for resampling_target in ['data', 'labels']:
masker = NiftiLabelsMasker(labels_img=labels_img,
resampling_target=resampling_target)
transformed = masker.fit_transform(fmri_img)
resampled_labels_img = masker._resampled_labels_img_
n_resampled_labels = len(np.unique(resampled_labels_img.get_data()))
assert_equal(n_resampled_labels - 1, transformed.shape[1])
# inverse transform
compressed_img = masker.inverse_transform(transformed)
# Test that compressing the image a second time should yield an image
# with the same data as compressed_img.
transformed2 = masker.fit_transform(fmri_img)
# inverse transform again
compressed_img2 = masker.inverse_transform(transformed2)
np.testing.assert_array_equal(compressed_img.get_data(),
compressed_img2.get_data())
def test_signal_extraction_with_maps_and_labels():
shape = (4, 5, 6)
n_regions = 7
length = 8
# Generate labels
labels = list(range(n_regions + 1)) # 0 is background
labels_img = generate_labeled_regions(shape, n_regions, labels=labels)
labels_data = labels_img.get_data()
# Convert to maps
maps_data = np.zeros(shape + (n_regions, ))
for n, l in enumerate(labels):
if n == 0:
continue
maps_data[labels_data == l, n - 1] = 1
maps_img = nibabel.Nifti1Image(maps_data, labels_img.get_affine())
# Generate fake data
fmri_img, _ = generate_fake_fmri(shape=shape,
length=length,
affine=labels_img.get_affine())
# Extract signals from maps and labels: results must be identical.
maps_signals, maps_labels = region.img_to_signals_maps(fmri_img, maps_img)
labels_signals, labels_labels =\
region.img_to_signals_labels(fmri_img, labels_img)
np.testing.assert_almost_equal(maps_signals, labels_signals)
## Same thing with a mask, containing only 3 regions.
mask_data = (labels_data == 1) + (labels_data == 2) + (labels_data == 5)
mask_img = nibabel.Nifti1Image(mask_data.astype(np.int8),
labels_img.get_affine())
labels_signals, labels_labels =\
region.img_to_signals_labels(fmri_img, labels_img,
mask_img=mask_img)
maps_signals, maps_labels = \
region.img_to_signals_maps(fmri_img, maps_img,
mask_img=mask_img)
np.testing.assert_almost_equal(maps_signals, labels_signals)
assert_true(maps_signals.shape[1] == n_regions)
assert_true(maps_labels == list(range(len(maps_labels))))
assert_true(labels_signals.shape == (length, n_regions))
assert_true(labels_labels == labels[1:])
# Inverse operation (mostly smoke test)
labels_img_r = region.signals_to_img_labels(labels_signals,
labels_img,
mask_img=mask_img)
assert_true(labels_img_r.shape == shape + (length, ))
maps_img_r = region.signals_to_img_maps(maps_signals,
maps_img,
mask_img=mask_img)
assert_true(maps_img_r.shape == shape + (length, ))
## Check that NaNs in regions inside mask are preserved
region1 = labels_data == 2
indices = [ind[:1] for ind in np.where(region1)]
fmri_img.get_data()[indices + [slice(None)]] = float('nan')
labels_signals, labels_labels =\
region.img_to_signals_labels(fmri_img, labels_img,
mask_img=mask_img)
assert_true(np.all(np.isnan(labels_signals[:, labels_labels.index(2)])))
def test_signal_extraction_with_maps_and_labels():
shape = (4, 5, 6)
n_regions = 7
length = 8
# Generate labels
labels = list(range(n_regions + 1)) # 0 is background
labels_img = generate_labeled_regions(shape, n_regions, labels=labels)
labels_data = labels_img.get_data()
# Convert to maps
maps_data = np.zeros(shape + (n_regions,))
for n, l in enumerate(labels):
if n == 0:
continue
maps_data[labels_data == l, n - 1] = 1
maps_img = nibabel.Nifti1Image(maps_data, labels_img.affine)
# Generate fake data
fmri_img, _ = generate_fake_fmri(shape=shape, length=length,
affine=labels_img.affine)
# Extract signals from maps and labels: results must be identical.
maps_signals, maps_labels = signal_extraction.img_to_signals_maps(
fmri_img, maps_img)
labels_signals, labels_labels = signal_extraction.img_to_signals_labels(
fmri_img, labels_img)
np.testing.assert_almost_equal(maps_signals, labels_signals)
# Same thing with a mask, containing only 3 regions.
mask_data = (labels_data == 1) + (labels_data == 2) + (labels_data == 5)
mask_img = nibabel.Nifti1Image(mask_data.astype(np.int8),
labels_img.affine)
labels_signals, labels_labels = signal_extraction.img_to_signals_labels(
fmri_img, labels_img, mask_img=mask_img)
maps_signals, maps_labels = signal_extraction.img_to_signals_maps(
fmri_img, maps_img, mask_img=mask_img)
np.testing.assert_almost_equal(maps_signals, labels_signals)
assert_true(maps_signals.shape[1] == n_regions)
assert_true(maps_labels == list(range(len(maps_labels))))
assert_true(labels_signals.shape == (length, n_regions))
assert_true(labels_labels == labels[1:])
# Inverse operation (mostly smoke test)
labels_img_r = signal_extraction.signals_to_img_labels(
labels_signals, labels_img, mask_img=mask_img)
assert_true(labels_img_r.shape == shape + (length,))
maps_img_r = signal_extraction.signals_to_img_maps(
maps_signals, maps_img, mask_img=mask_img)
assert_true(maps_img_r.shape == shape + (length,))
# Check that NaNs in regions inside mask are preserved
region1 = labels_data == 2
indices = [ind[:1] for ind in np.where(region1)]
fmri_img.get_data()[indices + [slice(None)]] = float('nan')
labels_signals, labels_labels = signal_extraction.img_to_signals_labels(
fmri_img, labels_img, mask_img=mask_img)
assert_true(np.all(np.isnan(labels_signals[:, labels_labels.index(2)])))
def test_nifti_labels_masker():
# Check working of shape/affine checks
shape1 = (13, 11, 12)
affine1 = np.eye(4)
shape2 = (12, 10, 14)
affine2 = np.diag((1, 2, 3, 1))
n_regions = 9
length = 3
fmri11_img, mask11_img = generate_random_img(shape1, affine=affine1,
length=length)
fmri12_img, mask12_img = generate_random_img(shape1, affine=affine2,
length=length)
fmri21_img, mask21_img = generate_random_img(shape2, affine=affine1,
length=length)
labels11_img = testing.generate_labeled_regions(shape1, affine=affine1,
n_regions=n_regions)
mask_img_4d = nibabel.Nifti1Image(np.ones((2, 2, 2, 2), dtype=np.int8),
affine=np.diag((4, 4, 4, 1)))
# verify that 4D mask arguments are refused
masker = NiftiLabelsMasker(labels11_img, mask_img=mask_img_4d)
testing.assert_raises_regex(DimensionError, "Data must be a 3D",
masker.fit)
# check exception when transform() called without prior fit()
masker11 = NiftiLabelsMasker(labels11_img, resampling_target=None)
testing.assert_raises_regex(
ValueError, 'has not been fitted. ', masker11.transform, fmri11_img)
# No exception raised here
signals11 = masker11.fit().transform(fmri11_img)
assert_equal(signals11.shape, (length, n_regions))
masker11 = NiftiLabelsMasker(labels11_img, mask_img=mask11_img,
resampling_target=None)
signals11 = masker11.fit().transform(fmri11_img)
assert_equal(signals11.shape, (length, n_regions))
# Test all kinds of mismatch between shapes and between affines
masker11 = NiftiLabelsMasker(labels11_img, resampling_target=None)
masker11.fit()
assert_raises(ValueError, masker11.transform, fmri12_img)
assert_raises(ValueError, masker11.transform, fmri21_img)
masker11 = NiftiLabelsMasker(labels11_img, mask_img=mask12_img,
resampling_target=None)
assert_raises(ValueError, masker11.fit)
masker11 = NiftiLabelsMasker(labels11_img, mask_img=mask21_img,
resampling_target=None)
assert_raises(ValueError, masker11.fit)
# Transform, with smoothing (smoke test)
masker11 = NiftiLabelsMasker(labels11_img, smoothing_fwhm=3,
resampling_target=None)
signals11 = masker11.fit().transform(fmri11_img)
assert_equal(signals11.shape, (length, n_regions))
masker11 = NiftiLabelsMasker(labels11_img, smoothing_fwhm=3,
resampling_target=None)
signals11 = masker11.fit_transform(fmri11_img)
assert_equal(signals11.shape, (length, n_regions))
testing.assert_raises_regex(
ValueError, 'has not been fitted. ',
NiftiLabelsMasker(labels11_img).inverse_transform, signals11)
# Call inverse transform (smoke test)
fmri11_img_r = masker11.inverse_transform(signals11)
assert_equal(fmri11_img_r.shape, fmri11_img.shape)
np.testing.assert_almost_equal(fmri11_img_r.get_affine(),
fmri11_img.get_affine())
def test_largest_cc_img():
""" Check the extraction of the largest connected component, for niftis
Similiar to smooth_img tests for largest connected_component_img, here also
only the added features for largest_connected_component are tested.
"""
# Test whether dimension of 3Dimg and list of 3Dimgs are kept.
shapes = ((10, 11, 12), (13, 14, 15))
regions = [1, 3]
img1 = testing.generate_labeled_regions(shape=shapes[0],
n_regions=regions[0])
img2 = testing.generate_labeled_regions(shape=shapes[1],
n_regions=regions[1])
for create_files in (False, True):
with testing.write_tmp_imgs(img1, img2,
create_files=create_files) as imgs:
# List of images as input
out = largest_connected_component_img(imgs)
assert_true(isinstance(out, list))
assert_true(len(out) == 2)
for o, s in zip(out, shapes):
assert_true(o.shape == (s))
# Single image as input
out = largest_connected_component_img(imgs[0])
assert_true(isinstance(out, Nifti1Image))
assert_true(out.shape == (shapes[0]))
# Test whether 4D Nifti throws the right error.
img_4D = testing.generate_fake_fmri(shapes[0], length=17)
assert_raises(DimensionError, largest_connected_component_img, img_4D)
# tests adapted to non-native endian data dtype
img1_change_dtype = nibabel.Nifti1Image(img1.get_data().astype('>f8'),
affine=img1.affine)
img2_change_dtype = nibabel.Nifti1Image(img2.get_data().astype('>f8'),
affine=img2.affine)
for create_files in (False, True):
with testing.write_tmp_imgs(img1_change_dtype, img2_change_dtype,
create_files=create_files) as imgs:
# List of images as input
out = largest_connected_component_img(imgs)
assert_true(isinstance(out, list))
assert_true(len(out) == 2)
for o, s in zip(out, shapes):
assert_true(o.shape == (s))
# Single image as input
out = largest_connected_component_img(imgs[0])
assert_true(isinstance(out, Nifti1Image))
assert_true(out.shape == (shapes[0]))
# Test the output with native and without native
out_native = largest_connected_component_img(img1)
out_non_native = largest_connected_component_img(img1_change_dtype)
np.testing.assert_equal(out_native.get_data(), out_non_native.get_data())
def test_nifti_labels_masker_resampling():
# Test resampling in NiftiLabelsMasker
shape1 = (10, 11, 12)
affine = np.eye(4)
# mask
shape2 = (16, 17, 18)
# labels
shape3 = (13, 14, 15)
n_regions = 9
length = 3
# With data of the same affine
fmri11_img, _ = generate_random_img(shape1, affine=affine, length=length)
_, mask22_img = generate_random_img(shape2, affine=affine, length=length)
labels33_img = testing.generate_labeled_regions(shape3,
n_regions,
affine=affine)
# Test error checking
assert_raises(ValueError,
NiftiLabelsMasker,
labels33_img,
resampling_target="mask")
assert_raises(ValueError,
NiftiLabelsMasker,
labels33_img,
resampling_target="invalid")
# Target: labels
masker = NiftiLabelsMasker(labels33_img,
mask_img=mask22_img,
resampling_target="labels")
masker.fit()
np.testing.assert_almost_equal(get_affine(masker.labels_img_),
get_affine(labels33_img))
assert_equal(masker.labels_img_.shape, labels33_img.shape)
np.testing.assert_almost_equal(get_affine(masker.mask_img_),
get_affine(masker.labels_img_))
assert_equal(masker.mask_img_.shape, masker.labels_img_.shape[:3])
transformed = masker.transform(fmri11_img)
assert_equal(transformed.shape, (length, n_regions))
fmri11_img_r = masker.inverse_transform(transformed)
np.testing.assert_almost_equal(get_affine(fmri11_img_r),
get_affine(masker.labels_img_))
assert_equal(fmri11_img_r.shape,
(masker.labels_img_.shape[:3] + (length, )))
# Test with clipped labels: mask does not contain all labels.
# Shapes do matter in that case, because there is some resampling
# taking place.
shape1 = (10, 11, 12) # fmri
shape2 = (8, 9, 10) # mask
shape3 = (16, 18, 20) # maps
n_regions = 9
length = 21
fmri11_img, _ = generate_random_img(shape1, affine=affine, length=length)
_, mask22_img = generate_random_img(shape2, affine=affine, length=length)
# Target: labels
labels33_img = testing.generate_labeled_regions(shape3,
n_regions,
affine=affine)
masker = NiftiLabelsMasker(labels33_img,
mask_img=mask22_img,
resampling_target="labels")
masker.fit()
np.testing.assert_almost_equal(get_affine(masker.labels_img_),
get_affine(labels33_img))
assert_equal(masker.labels_img_.shape, labels33_img.shape)
np.testing.assert_almost_equal(get_affine(masker.mask_img_),
get_affine(masker.labels_img_))
assert_equal(masker.mask_img_.shape, masker.labels_img_.shape[:3])
uniq_labels = np.unique(masker.labels_img_.get_data())
assert_equal(uniq_labels[0], 0)
assert_equal(len(uniq_labels) - 1, n_regions)
transformed = masker.transform(fmri11_img)
assert_equal(transformed.shape, (length, n_regions))
# Some regions have been clipped. Resulting signal must be zero
assert_less((transformed.var(axis=0) == 0).sum(), n_regions)
fmri11_img_r = masker.inverse_transform(transformed)
np.testing.assert_almost_equal(get_affine(fmri11_img_r),
get_affine(masker.labels_img_))
assert_equal(fmri11_img_r.shape,
(masker.labels_img_.shape[:3] + (length, )))
# Test with data and atlas of different shape: the atlas should be
# resampled to the data
shape22 = (5, 5, 6)
affine2 = 2 * np.eye(4)
affine2[-1, -1] = 1
fmri22_img, _ = generate_random_img(shape22, affine=affine2, length=length)
masker = NiftiLabelsMasker(labels33_img, mask_img=mask22_img)
masker.fit_transform(fmri22_img)
np.testing.assert_array_equal(get_affine(masker._resampled_labels_img_),
affine2)
# Test with filenames
with testing.write_tmp_imgs(fmri22_img) as filename:
masker = NiftiLabelsMasker(labels33_img, resampling_target='data')
masker.fit_transform(filename)
def test_connected_label_regions():
shape = (13, 11, 12)
affine = np.eye(4)
n_regions = 9
labels_img = testing.generate_labeled_regions(shape, affine=affine,
n_regions=n_regions)
labels_data = labels_img.get_data()
n_labels_wo_reg_ext = len(np.unique(labels_data))
# region extraction without specifying min_size
extracted_regions_on_labels_img = connected_label_regions(labels_img)
extracted_regions_labels_data = extracted_regions_on_labels_img.get_data()
n_labels_wo_min = len(np.unique(extracted_regions_labels_data))
assert_true(n_labels_wo_reg_ext < n_labels_wo_min)
# with specifying min_size
extracted_regions_with_min = connected_label_regions(labels_img,
min_size=100)
extracted_regions_with_min_data = extracted_regions_with_min.get_data()
n_labels_with_min = len(np.unique(extracted_regions_with_min_data))
assert_true(n_labels_wo_min > n_labels_with_min)
# Test connect_diag=False
ext_reg_without_connect_diag = connected_label_regions(labels_img,
connect_diag=False)
data_wo_connect_diag = ext_reg_without_connect_diag.get_data()
n_labels_wo_connect_diag = len(np.unique(data_wo_connect_diag))
assert_true(n_labels_wo_connect_diag > n_labels_wo_reg_ext)
# If min_size is large and if all the regions are removed then empty image
# will be returned
extract_reg_min_size_large = connected_label_regions(labels_img,
min_size=500)
assert_true(np.unique(extract_reg_min_size_large.get_data()) == 0)
# Test the names of the brain regions given in labels.
# Test labels for 9 regions in n_regions
labels = ['region_a', 'region_b', 'region_c', 'region_d', 'region_e',
'region_f', 'region_g', 'region_h', 'region_i']
# If labels are provided, first return will contain extracted labels image
# and second return will contain list of new names generated based on same
# name with assigned on both hemispheres for example.
extracted_reg, new_labels = connected_label_regions(labels_img,
min_size=100,
labels=labels)
# The length of new_labels returned can differ depending upon min_size. If
# min_size given is more small regions can be removed therefore newly
# generated labels can be less than original size of labels. Or if min_size
# is less then newly generated labels can be more.
# We test here whether labels returned are empty or not.
assert_not_equal(new_labels, '')
assert_true(len(new_labels) <= len(labels))
# labels given in numpy array
labels = np.asarray(labels)
extracted_reg2, new_labels2 = connected_label_regions(labels_img,
labels=labels)
assert_not_equal(new_labels, '')
# By default min_size is less, so newly generated labels can be more.
assert_true(len(new_labels2) >= len(labels))
# If number of labels provided are wrong (which means less than number of
# unique labels in labels_img), then we raise an error
# Test whether error raises
unique_labels = set(np.unique(np.asarray(labels_img.get_data())))
unique_labels.remove(0)
# labels given are less than n_regions=9
provided_labels = ['region_a', 'region_c', 'region_f',
'region_g', 'region_h', 'region_i']
assert_true(len(provided_labels) < len(unique_labels))
np.testing.assert_raises(ValueError, connected_label_regions,
labels_img, labels=provided_labels)
# Test if unknown/negative integers are provided as labels in labels_img,
# we raise an error and test the same whether error is raised.
labels_data = np.zeros(shape, dtype=np.int)
h0 = shape[0] // 2
h1 = shape[1] // 2
h2 = shape[2] // 2
labels_data[:h0, :h1, :h2] = 1
labels_data[:h0, :h1, h2:] = 2
labels_data[:h0, h1:, :h2] = 3
labels_data[:h0, h1:, h2:] = 4
labels_data[h0:, :h1, :h2] = 5
labels_data[h0:, :h1, h2:] = 6
labels_data[h0:, h1:, :h2] = np.nan
labels_data[h0:, h1:, h2:] = np.inf
neg_labels_img = nibabel.Nifti1Image(labels_data, affine)
np.testing.assert_raises(ValueError, connected_label_regions,
labels_img=neg_labels_img)
# If labels_img provided is 4D Nifti image, then test whether error is
# raised or not. Since this function accepts only 3D image.
labels_4d_data = np.zeros((shape) + (2, ))
labels_data[h0:, h1:, :h2] = 0
labels_data[h0:, h1:, h2:] = 0
labels_4d_data[..., 0] = labels_data
labels_4d_data[..., 1] = labels_data
labels_img_4d = nibabel.Nifti1Image(labels_4d_data, np.eye(4))
np.testing.assert_raises(DimensionError, connected_label_regions,
labels_img=labels_img_4d)
# Test if labels (or names to regions) given is a string without a list.
# Then, we expect it to be split to regions extracted and returned as list.
labels_in_str = 'region_a'
labels_img_in_str = testing.generate_labeled_regions(shape, affine=affine,
n_regions=1)
extract_regions, new_labels = connected_label_regions(labels_img_in_str,
labels=labels_in_str)
assert_true(isinstance(new_labels, list))
# If user has provided combination of labels, then function passes without
# breaking and new labels are returned based upon given labels and should
# be equal or more based on regions extracted
combined_labels = ['region_a', '1', 'region_b', '2', 'region_c', '3',
'region_d', '4', 'region_e']
ext_reg, new_labels = connected_label_regions(labels_img,
labels=combined_labels)
assert_true(len(new_labels) >= len(combined_labels))
def test_nifti_labels_masker():
# Check working of shape/affine checks
shape1 = (13, 11, 12)
affine1 = np.eye(4)
shape2 = (12, 10, 14)
affine2 = np.diag((1, 2, 3, 1))
n_regions = 9
length = 3
fmri11_img, mask11_img = generate_random_img(shape1,
affine=affine1,
length=length)
fmri12_img, mask12_img = generate_random_img(shape1,
affine=affine2,
length=length)
fmri21_img, mask21_img = generate_random_img(shape2,
affine=affine1,
length=length)
labels11_img = testing.generate_labeled_regions(shape1,
affine=affine1,
n_regions=n_regions)
mask_img_4d = nibabel.Nifti1Image(np.ones((2, 2, 2, 2), dtype=np.int8),
affine=np.diag((4, 4, 4, 1)))
# verify that 4D mask arguments are refused
masker = NiftiLabelsMasker(labels11_img, mask_img=mask_img_4d)
testing.assert_raises_regex(
DimensionError, "Input data has incompatible dimensionality: "
"Expected dimension is 3D and you provided "
"a 4D image.", masker.fit)
# check exception when transform() called without prior fit()
masker11 = NiftiLabelsMasker(labels11_img, resampling_target=None)
testing.assert_raises_regex(ValueError, 'has not been fitted. ',
masker11.transform, fmri11_img)
# No exception raised here
signals11 = masker11.fit().transform(fmri11_img)
assert_equal(signals11.shape, (length, n_regions))
masker11 = NiftiLabelsMasker(labels11_img,
mask_img=mask11_img,
resampling_target=None)
signals11 = masker11.fit().transform(fmri11_img)
assert_equal(signals11.shape, (length, n_regions))
# Test all kinds of mismatch between shapes and between affines
masker11 = NiftiLabelsMasker(labels11_img, resampling_target=None)
masker11.fit()
assert_raises(ValueError, masker11.transform, fmri12_img)
assert_raises(ValueError, masker11.transform, fmri21_img)
masker11 = NiftiLabelsMasker(labels11_img,
mask_img=mask12_img,
resampling_target=None)
assert_raises(ValueError, masker11.fit)
masker11 = NiftiLabelsMasker(labels11_img,
mask_img=mask21_img,
resampling_target=None)
assert_raises(ValueError, masker11.fit)
# Transform, with smoothing (smoke test)
masker11 = NiftiLabelsMasker(labels11_img,
smoothing_fwhm=3,
resampling_target=None)
signals11 = masker11.fit().transform(fmri11_img)
assert_equal(signals11.shape, (length, n_regions))
masker11 = NiftiLabelsMasker(labels11_img,
smoothing_fwhm=3,
resampling_target=None)
signals11 = masker11.fit_transform(fmri11_img)
assert_equal(signals11.shape, (length, n_regions))
testing.assert_raises_regex(
ValueError, 'has not been fitted. ',
NiftiLabelsMasker(labels11_img).inverse_transform, signals11)
# Call inverse transform (smoke test)
fmri11_img_r = masker11.inverse_transform(signals11)
assert_equal(fmri11_img_r.shape, fmri11_img.shape)
np.testing.assert_almost_equal(get_affine(fmri11_img_r),
get_affine(fmri11_img))
def test_nifti_labels_masker_resampling():
# Test resampling in NiftiLabelsMasker
shape1 = (10, 11, 12)
affine = np.eye(4)
# mask
shape2 = (16, 17, 18)
# labels
shape3 = (13, 14, 15)
n_regions = 9
length = 3
# With data of the same affine
fmri11_img, _ = generate_random_img(shape1, affine=affine,
length=length)
_, mask22_img = generate_random_img(shape2, affine=affine,
length=length)
labels33_img = testing.generate_labeled_regions(shape3, n_regions,
affine=affine)
# Test error checking
assert_raises(ValueError, NiftiLabelsMasker, labels33_img,
resampling_target="mask")
assert_raises(ValueError, NiftiLabelsMasker, labels33_img,
resampling_target="invalid")
# Target: labels
masker = NiftiLabelsMasker(labels33_img, mask_img=mask22_img,
resampling_target="labels")
masker.fit()
np.testing.assert_almost_equal(masker.labels_img_.get_affine(),
labels33_img.get_affine())
assert_equal(masker.labels_img_.shape, labels33_img.shape)
np.testing.assert_almost_equal(masker.mask_img_.get_affine(),
masker.labels_img_.get_affine())
assert_equal(masker.mask_img_.shape, masker.labels_img_.shape[:3])
transformed = masker.transform(fmri11_img)
assert_equal(transformed.shape, (length, n_regions))
fmri11_img_r = masker.inverse_transform(transformed)
np.testing.assert_almost_equal(fmri11_img_r.get_affine(),
masker.labels_img_.get_affine())
assert_equal(fmri11_img_r.shape,
(masker.labels_img_.shape[:3] + (length,)))
# Test with clipped labels: mask does not contain all labels.
# Shapes do matter in that case, because there is some resampling
# taking place.
shape1 = (10, 11, 12) # fmri
shape2 = (8, 9, 10) # mask
shape3 = (16, 18, 20) # maps
n_regions = 9
length = 21
fmri11_img, _ = generate_random_img(shape1, affine=affine,
length=length)
_, mask22_img = generate_random_img(shape2, affine=affine,
length=length)
# Target: labels
labels33_img = testing.generate_labeled_regions(shape3, n_regions,
affine=affine)
masker = NiftiLabelsMasker(labels33_img, mask_img=mask22_img,
resampling_target="labels")
masker.fit()
np.testing.assert_almost_equal(masker.labels_img_.get_affine(),
labels33_img.get_affine())
assert_equal(masker.labels_img_.shape, labels33_img.shape)
np.testing.assert_almost_equal(masker.mask_img_.get_affine(),
masker.labels_img_.get_affine())
assert_equal(masker.mask_img_.shape, masker.labels_img_.shape[:3])
uniq_labels = np.unique(masker.labels_img_.get_data())
assert_equal(uniq_labels[0], 0)
assert_equal(len(uniq_labels) - 1, n_regions)
transformed = masker.transform(fmri11_img)
assert_equal(transformed.shape, (length, n_regions))
# Some regions have been clipped. Resulting signal must be zero
assert_less((transformed.var(axis=0) == 0).sum(), n_regions)
fmri11_img_r = masker.inverse_transform(transformed)
np.testing.assert_almost_equal(fmri11_img_r.get_affine(),
masker.labels_img_.get_affine())
assert_equal(fmri11_img_r.shape,
(masker.labels_img_.shape[:3] + (length,)))
# Test with data and atlas of different shape: the atlas should be
# resampled to the data
shape22 = (5, 5, 6)
affine2 = 2 * np.eye(4)
affine2[-1, -1] = 1
fmri22_img, _ = generate_random_img(shape22, affine=affine2,
length=length)
masker = NiftiLabelsMasker(labels33_img, mask_img=mask22_img)
masker.fit_transform(fmri22_img)
np.testing.assert_array_equal(
masker._resampled_labels_img_.get_affine(),
affine2)
# Test with filenames
with testing.write_tmp_imgs(fmri22_img) as filename:
masker = NiftiLabelsMasker(labels33_img, resampling_target='data')
masker.fit_transform(filename)
