def test__smooth_array():
"""Test smoothing of images: _smooth_array()"""
# Impulse in 3D
data = np.zeros((40, 41, 42))
data[20, 20, 20] = 1
# fwhm divided by any test affine must be odd. Otherwise assertion below
# will fail. ( 9 / 0.6 = 15 is fine)
fwhm = 9
test_affines = (np.eye(4), np.diag((1, 1, -1, 1)), np.diag((.6, 1, .6, 1)))
for affine in test_affines:
filtered = image._smooth_array(data, affine, fwhm=fwhm, copy=True)
assert_false(np.may_share_memory(filtered, data))
# We are expecting a full-width at half maximum of
# fwhm / voxel_size:
vmax = filtered.max()
above_half_max = filtered > .5 * vmax
for axis in (0, 1, 2):
proj = np.any(np.any(np.rollaxis(above_half_max, axis=axis),
axis=-1),
axis=-1)
np.testing.assert_equal(proj.sum(),
fwhm / np.abs(affine[axis, axis]))
# Check that NaNs in the data do not propagate
data[10, 10, 10] = np.NaN
filtered = image._smooth_array(data,
affine,
fwhm=fwhm,
ensure_finite=True,
copy=True)
assert_true(np.all(np.isfinite(filtered)))
# Check copy=False.
for affine in test_affines:
data = np.zeros((40, 41, 42))
data[20, 20, 20] = 1
image._smooth_array(data, affine, fwhm=fwhm, copy=False)
# We are expecting a full-width at half maximum of
# fwhm / voxel_size:
vmax = data.max()
above_half_max = data > .5 * vmax
for axis in (0, 1, 2):
proj = np.any(np.any(np.rollaxis(above_half_max, axis=axis),
axis=-1),
axis=-1)
np.testing.assert_equal(proj.sum(),
fwhm / np.abs(affine[axis, axis]))
# Check fwhm='fast'
for affine in test_affines:
np.testing.assert_equal(image._smooth_array(data, affine, fwhm='fast'),
image._fast_smooth_array(data))
def test__smooth_array():
"""Test smoothing of images: _smooth_array()"""
# Impulse in 3D
data = np.zeros((40, 41, 42))
data[20, 20, 20] = 1
# fwhm divided by any test affine must be odd. Otherwise assertion below
# will fail. ( 9 / 0.6 = 15 is fine)
fwhm = 9
test_affines = (np.eye(4), np.diag((1, 1, -1, 1)),
np.diag((.6, 1, .6, 1)))
for affine in test_affines:
filtered = image._smooth_array(data, affine,
fwhm=fwhm, copy=True)
assert_false(np.may_share_memory(filtered, data))
# We are expecting a full-width at half maximum of
# fwhm / voxel_size:
vmax = filtered.max()
above_half_max = filtered > .5 * vmax
for axis in (0, 1, 2):
proj = np.any(np.any(np.rollaxis(above_half_max,
axis=axis), axis=-1), axis=-1)
np.testing.assert_equal(proj.sum(),
fwhm / np.abs(affine[axis, axis]))
# Check that NaNs in the data do not propagate
data[10, 10, 10] = np.NaN
filtered = image._smooth_array(data, affine, fwhm=fwhm,
ensure_finite=True, copy=True)
assert_true(np.all(np.isfinite(filtered)))
# Check copy=False.
for affine in test_affines:
data = np.zeros((40, 41, 42))
data[20, 20, 20] = 1
image._smooth_array(data, affine, fwhm=fwhm, copy=False)
# We are expecting a full-width at half maximum of
# fwhm / voxel_size:
vmax = data.max()
above_half_max = data > .5 * vmax
for axis in (0, 1, 2):
proj = np.any(np.any(np.rollaxis(above_half_max,
axis=axis), axis=-1), axis=-1)
np.testing.assert_equal(proj.sum(),
fwhm / np.abs(affine[axis, axis]))
# Check fwhm='fast'
for affine in test_affines:
np.testing.assert_equal(image._smooth_array(data, affine, fwhm='fast'),
image._fast_smooth_array(data))
def plot_contour_atlas(niimgs, labels, cut_coords=None,
title=None, percentile=99):
legend_lines = []
slicer = plot_bg(cut_coords, title)
atlas = np.vstack([niimg.get_data()[np.newaxis] for niimg in niimgs])
# atlas = StandardScaler().fit_transform(atlas.T).T
affine = niimgs[0].get_affine()
for i, (label, data) in enumerate(zip(labels, atlas)):
data = np.array(_smooth_array(data, affine, 5), copy=True)
data[data < 0] = 0
color = np.array(pl.cm.Set1(float(i) / (len(labels) - 1)))
# data, affine = niimg.get_data(), niimg.get_affine()
# affine = niimg.get_affine()
level = scoreatpercentile(data.ravel(), percentile)
slicer.contour_map(data, affine, levels=(level, ),
linewidth=2.5, colors=(color, ))
slicer.plot_map(data, affine, threshold=level,
cmap=alpha_cmap(color))
legend_lines.append(pl.Line2D([0, 0], [0, 0],
color=color, linewidth=4))
ax = slicer.axes['z'].ax.get_figure().add_axes([.80, .1, .15, .8])
pl.axis('off')
ax.legend(legend_lines, labels, loc='center right',
prop=dict(size=4), title='Labels',
borderaxespad=0,
bbox_to_anchor=(1 / .85, .5))
atlas = np.rollaxis(atlas, 0, 4)
return nb.Nifti1Image(atlas, affine=affine)
