def _check_memory(memory, verbose=0):
"""Function to ensure an instance of a joblib.Memory object.
Parameters
----------
memory: None or instance of joblib.Memory or str
Used to cache the masking process.
If a str is given, it is the path to the caching directory.
verbose : int, optional (default 0)
Verbosity level.
Returns
-------
instance of joblib.Memory.
"""
if memory is None:
memory = Memory(cachedir=None, verbose=verbose)
if isinstance(memory, _basestring):
cache_dir = memory
if nilearn.EXPAND_PATH_WILDCARDS:
cache_dir = os.path.expanduser(cache_dir)
# Perform some verifications on given path.
split_cache_dir = os.path.split(cache_dir)
if (len(split_cache_dir) > 1 and
(not os.path.exists(split_cache_dir[0]) and
split_cache_dir[0] != '')):
if (not nilearn.EXPAND_PATH_WILDCARDS and
cache_dir.startswith("~")):
# Maybe the user want to enable expanded user path.
error_msg = ("Given cache path parent directory doesn't "
"exists, you gave '{0}'. Enabling "
"nilearn.EXPAND_PATH_WILDCARDS could solve "
"this issue.".format(split_cache_dir[0]))
elif memory.startswith("~"):
# Path built on top of expanded user path doesn't exist.
error_msg = ("Given cache path parent directory doesn't "
"exists, you gave '{0}' which was expanded "
"as '{1}' but doesn't exist either. Use "
"nilearn.EXPAND_PATH_WILDCARDS to deactivate "
"auto expand user path (~) behavior."
.format(split_cache_dir[0],
os.path.dirname(memory)))
else:
# The given cache base path doesn't exist.
error_msg = ("Given cache path parent directory doesn't "
"exists, you gave '{0}'."
.format(split_cache_dir[0]))
raise ValueError(error_msg)
memory = Memory(cachedir=cache_dir, verbose=verbose)
return memory
def test_cache_memory_level():
with tempfile.TemporaryDirectory() as temp_dir:
joblib_dir = Path(temp_dir, 'joblib', 'nilearn', 'tests',
'test_cache_mixin', 'f')
mem = Memory(cachedir=temp_dir, verbose=0)
cache_mixin.cache(f, mem, func_memory_level=2, memory_level=1)(2)
assert_equal(len(_get_subdirs(joblib_dir)), 0)
cache_mixin.cache(f, Memory(cachedir=None))(2)
assert_equal(len(_get_subdirs(joblib_dir)), 0)
cache_mixin.cache(f, mem, func_memory_level=2, memory_level=3)(2)
assert_equal(len(_get_subdirs(joblib_dir)), 1)
cache_mixin.cache(f, mem)(3)
assert_equal(len(_get_subdirs(joblib_dir)), 2)
def test_cache_memory_level():
temp_dir = tempfile.mkdtemp()
job_glob = os.path.join(temp_dir, 'joblib', 'nilearn', 'tests',
'test_cache_mixin', 'f', '*')
mem = Memory(cachedir=temp_dir, verbose=0)
cache_mixin.cache(f, mem, func_memory_level=2, memory_level=1)(2)
assert_equal(len(glob.glob(job_glob)), 0)
cache_mixin.cache(f, Memory(cachedir=None))(2)
assert_equal(len(glob.glob(job_glob)), 0)
cache_mixin.cache(f, mem, func_memory_level=2, memory_level=3)(2)
assert_equal(len(glob.glob(job_glob)), 2)
cache_mixin.cache(f, mem)(3)
assert_equal(len(glob.glob(job_glob)), 3)
def test_shelving():
mask_img = Nifti1Image(np.ones((2, 2, 2), dtype=np.int8),
affine=np.diag((4, 4, 4, 1)))
epi_img1 = Nifti1Image(np.ones((2, 2, 2)), affine=np.diag((4, 4, 4, 1)))
epi_img2 = Nifti1Image(np.ones((2, 2, 2)), affine=np.diag((2, 2, 2, 1)))
cachedir = mkdtemp()
try:
masker_shelved = MultiNiftiMasker(mask_img=mask_img,
memory=Memory(cachedir=cachedir,
mmap_mode='r',
verbose=0))
masker_shelved._shelving = True
masker = MultiNiftiMasker(mask_img=mask_img)
epis_shelved = masker_shelved.fit_transform([epi_img1, epi_img2])
epis = masker.fit_transform([epi_img1, epi_img2])
for epi_shelved, epi in zip(epis_shelved, epis):
epi_shelved = epi_shelved.get()
assert_array_equal(epi_shelved, epi)
epi = masker.fit_transform(epi_img1)
epi_shelved = masker_shelved.fit_transform(epi_img1)
epi_shelved = epi_shelved.get()
assert_array_equal(epi_shelved, epi)
finally:
# enables to delete "filename" on windows
del masker
shutil.rmtree(cachedir, ignore_errors=True)
def __init__(self, n_components=20,
mask=None,
smoothing_fwhm=None,
do_cca=True,
random_state=None,
standardize=False, detrend=False,
low_pass=None, high_pass=None, t_r=None,
target_affine=None, target_shape=None,
mask_strategy='epi', mask_args=None,
memory=Memory(cachedir=None), memory_level=0,
n_jobs=1,
verbose=0
):
self.n_components = n_components
self.do_cca = do_cca
BaseDecomposition.__init__(self, n_components=n_components,
random_state=random_state,
mask=mask,
smoothing_fwhm=smoothing_fwhm,
standardize=standardize,
detrend=detrend,
low_pass=low_pass,
high_pass=high_pass, t_r=t_r,
target_affine=target_affine,
target_shape=target_shape,
mask_strategy=mask_strategy,
mask_args=mask_args,
memory=memory,
memory_level=memory_level,
n_jobs=n_jobs,
verbose=verbose)
def __init__(self, labels_img, background_label=0, mask_img=None,
smoothing_fwhm=None, standardize=False, detrend=False,
low_pass=None, high_pass=None, t_r=None, dtype=None,
resampling_target="data",
memory=Memory(cachedir=None, verbose=0), memory_level=1,
verbose=0):
self.labels_img = labels_img
self.background_label = background_label
self.mask_img = mask_img
# Parameters for _smooth_array
self.smoothing_fwhm = smoothing_fwhm
# Parameters for clean()
self.standardize = standardize
self.detrend = detrend
self.low_pass = low_pass
self.high_pass = high_pass
self.t_r = t_r
self.dtype = dtype
# Parameters for resampling
self.resampling_target = resampling_target
# Parameters for joblib
self.memory = memory
self.memory_level = memory_level
self.verbose = verbose
if resampling_target not in ("labels", "data", None):
raise ValueError("invalid value for 'resampling_target' "
"parameter: " + str(resampling_target))
def test_joblib_cache():
from nilearn._utils.compat import hash, Memory
mask = np.zeros((40, 40, 40))
mask[20, 20, 20] = 1
mask_img = Nifti1Image(mask, np.eye(4))
with testing.write_tmp_imgs(mask_img, create_files=True) as filename:
masker = NiftiMasker(mask_img=filename)
masker.fit()
mask_hash = hash(masker.mask_img_)
get_data(masker.mask_img_)
assert_true(mask_hash == hash(masker.mask_img_))
# Test a tricky issue with memmapped joblib.memory that makes
# imgs return by inverse_transform impossible to save
cachedir = mkdtemp()
try:
masker.memory = Memory(cachedir=cachedir, mmap_mode='r', verbose=0)
X = masker.transform(mask_img)
# inverse_transform a first time, so that the result is cached
out_img = masker.inverse_transform(X)
out_img = masker.inverse_transform(X)
out_img.to_filename(os.path.join(cachedir, 'test.nii'))
finally:
# enables to delete "filename" on windows
del masker
shutil.rmtree(cachedir, ignore_errors=True)
def __init__(self, model, mask=None, n_cluster=40, n_components=20, group=True, sub_num=1, smoothing_fwhm=6,
do_cca=True,
threshold='auto',
n_init=10,
random_state=None,
standardize=True, detrend=True,
low_pass=None, high_pass=None, t_r=None,
target_affine=None, target_shape=None,
mask_strategy='epi', mask_args=None,
memory=Memory(cachedir=None), memory_level=0,
n_jobs=1, verbose=0):
super(ClusterProcess, self).__init__(
n_components=n_components,
do_cca=do_cca,
random_state=random_state,
# feature_compression=feature_compression,
mask=mask, smoothing_fwhm=smoothing_fwhm,
standardize=standardize, detrend=detrend,
low_pass=low_pass, high_pass=high_pass, t_r=t_r,
target_affine=target_affine, target_shape=target_shape,
mask_strategy=mask_strategy, mask_args=mask_args,
memory=memory, memory_level=memory_level,
n_jobs=n_jobs, verbose=verbose)
self.n_cluster = n_cluster
self.model_ = model
self.group = group
self.sub_num = sub_num
self.train_data = None
self.model = None
def __init__(self,
maps_img,
mask_img=None,
min_region_size=1350,
threshold=1.,
thresholding_strategy='ratio_n_voxels',
extractor='local_regions',
smoothing_fwhm=6,
standardize=False,
detrend=False,
low_pass=None,
high_pass=None,
t_r=None,
memory=Memory(cachedir=None),
memory_level=0,
verbose=0):
super(RegionExtractor, self).__init__(maps_img=maps_img,
mask_img=mask_img,
smoothing_fwhm=smoothing_fwhm,
standardize=standardize,
detrend=detrend,
low_pass=low_pass,
high_pass=high_pass,
t_r=t_r,
memory=memory,
memory_level=memory_level,
verbose=verbose)
self.maps_img = maps_img
self.min_region_size = min_region_size
self.thresholding_strategy = thresholding_strategy
self.threshold = threshold
self.extractor = extractor
self.smoothing_fwhm = smoothing_fwhm
def __init__(self, mask=None, smoothing_fwhm=None,
standardize=False, detrend=False,
low_pass=None, high_pass=None, t_r=None,
target_affine=None, target_shape=None,
mask_strategy='background', mask_args=None,
memory=Memory(cachedir=None), memory_level=0,
n_jobs=1, verbose=0,
dummy=None):
self.mask = mask
self.smoothing_fwhm = smoothing_fwhm
self.standardize = standardize
self.detrend = detrend
self.low_pass = low_pass
self.high_pass = high_pass
self.t_r = t_r
self.target_affine = target_affine
self.target_shape = target_shape
self.mask_strategy = mask_strategy
self.mask_args = mask_args
self.memory = memory
self.memory_level = memory_level
self.n_jobs = n_jobs
self.verbose = verbose
self.dummy = dummy
def filter_and_mask(imgs, mask_img_, parameters,
memory_level=0, memory=Memory(cachedir=None),
verbose=0,
confounds=None,
copy=True,
dtype=None):
imgs = _utils.check_niimg(imgs, atleast_4d=True, ensure_ndim=4)
# Check whether resampling is truly necessary. If so, crop mask
# as small as possible in order to speed up the process
if not _check_same_fov(imgs, mask_img_):
parameters = copy_object(parameters)
# now we can crop
mask_img_ = image.crop_img(mask_img_, copy=False)
parameters['target_shape'] = mask_img_.shape
parameters['target_affine'] = mask_img_.affine
data, affine = filter_and_extract(imgs, _ExtractionFunctor(mask_img_),
parameters,
memory_level=memory_level,
memory=memory,
verbose=verbose,
confounds=confounds, copy=copy,
dtype=dtype)
# For _later_: missing value removal or imputing of missing data
# (i.e. we want to get rid of NaNs, if smoothing must be done
# earlier)
# Optionally: 'doctor_nan', remove voxels with NaNs, other option
# for later: some form of imputation
return data
def test__safe_cache_flush():
# Test the _safe_cache function that is supposed to flush the
# cache if the nibabel version changes
with tempfile.TemporaryDirectory() as temp_dir:
mem = Memory(cachedir=temp_dir)
version_file = os.path.join(temp_dir, 'joblib', 'module_versions.json')
# Create an mock version_file with old module versions
with open(version_file, 'w') as f:
json.dump({"nibabel": [0, 0]}, f)
# Create some store structure
nibabel_dir = os.path.join(temp_dir, 'joblib', 'nibabel_')
os.makedirs(nibabel_dir)
# First turn off version checking
nilearn.CHECK_CACHE_VERSION = False
cache_mixin._safe_cache(mem, f)
assert_true(os.path.exists(nibabel_dir))
# Second turn on version checking
nilearn.CHECK_CACHE_VERSION = True
# Make sure that the check will run again
cache_mixin.__CACHE_CHECKED = {}
with open(version_file, 'w') as f:
json.dump({"nibabel": [0, 0]}, f)
cache_mixin._safe_cache(mem, f)
assert_true(os.path.exists(version_file))
assert_false(os.path.exists(nibabel_dir))
def test_check_memory():
# Test if _check_memory returns a memory object with the cachedir equal to
# input path
with tempfile.TemporaryDirectory() as temp_dir:
mem_none = Memory(cachedir=None)
mem_temp = Memory(cachedir=temp_dir)
for mem in [None, mem_none]:
memory = cache_mixin._check_memory(mem, verbose=False)
assert_true(memory, Memory)
assert_equal(memory.cachedir, mem_none.cachedir)
for mem in [temp_dir, mem_temp]:
memory = cache_mixin._check_memory(mem, verbose=False)
assert_equal(memory.cachedir, mem_temp.cachedir)
assert_true(memory, Memory)
def __init__(self, alpha=0.1, tol=1e-3, max_iter=10, verbose=0,
memory=Memory(cachedir=None), memory_level=0):
self.alpha = alpha
self.tol = tol
self.max_iter = max_iter
self.memory = memory
self.memory_level = memory_level
self.verbose = verbose
def test_cache_shelving():
with tempfile.TemporaryDirectory() as temp_dir:
joblib_dir = Path(temp_dir, 'joblib', 'nilearn', 'tests',
'test_cache_mixin', 'f')
mem = Memory(cachedir=temp_dir, verbose=0)
res = cache_mixin.cache(f, mem, shelve=True)(2)
assert_equal(res.get(), 2)
assert_equal(len(_get_subdirs(joblib_dir)), 1)
res = cache_mixin.cache(f, mem, shelve=True)(2)
assert_equal(res.get(), 2)
assert_equal(len(_get_subdirs(joblib_dir)), 1)
def __init__(self,
labels_img,
background_label=0,
mask_img=None,
smoothing_fwhm=None,
standardize=False,
detrend=False,
low_pass=None,
high_pass=None,
t_r=None,
dtype=None,
resampling_target="data",
memory=Memory(cachedir=None, verbose=0),
memory_level=1,
verbose=0,
strategy="mean"):
self.labels_img = labels_img
self.background_label = background_label
self.mask_img = mask_img
# Parameters for _smooth_array
self.smoothing_fwhm = smoothing_fwhm
# Parameters for clean()
self.standardize = standardize
self.detrend = detrend
self.low_pass = low_pass
self.high_pass = high_pass
self.t_r = t_r
self.dtype = dtype
# Parameters for resampling
self.resampling_target = resampling_target
# Parameters for joblib
self.memory = memory
self.memory_level = memory_level
self.verbose = verbose
available_reduction_strategies = {
'mean', 'median', 'sum', 'minimum', 'maximum',
'standard_deviation', 'variance'
}
if strategy not in available_reduction_strategies:
raise ValueError(
str.format("Invalid strategy '{}'. Valid strategies are {}.",
strategy, available_reduction_strategies))
self.strategy = strategy
if resampling_target not in ("labels", "data", None):
raise ValueError("invalid value for 'resampling_target' "
"parameter: " + str(resampling_target))
def test_check_memory():
# Test if _check_memory returns a memory object with the cachedir equal to
# input path
try:
temp_dir = tempfile.mkdtemp()
mem_none = Memory(cachedir=None)
mem_temp = Memory(cachedir=temp_dir)
for mem in [None, mem_none]:
memory = cache_mixin._check_memory(mem, verbose=False)
assert_true(memory, Memory)
assert_equal(memory.cachedir, mem_none.cachedir)
for mem in [temp_dir, mem_temp]:
memory = cache_mixin._check_memory(mem, verbose=False)
assert_equal(memory.cachedir, mem_temp.cachedir)
assert_true(memory, Memory)
finally:
if os.path.exists(temp_dir):
shutil.rmtree(temp_dir)
def __init__(self,
mask=None,
n_components=20,
smoothing_fwhm=6,
do_cca=True,
threshold='auto',
n_init=10,
random_state=None,
standardize=True,
detrend=True,
low_pass=None,
high_pass=None,
t_r=None,
target_affine=None,
target_shape=None,
mask_strategy='epi',
mask_args=None,
memory=Memory(cachedir=None),
memory_level=0,
n_jobs=1,
verbose=0):
super(CanICA, self).__init__(
n_components=n_components,
do_cca=do_cca,
random_state=random_state,
# feature_compression=feature_compression,
mask=mask,
smoothing_fwhm=smoothing_fwhm,
standardize=standardize,
detrend=detrend,
low_pass=low_pass,
high_pass=high_pass,
t_r=t_r,
target_affine=target_affine,
target_shape=target_shape,
mask_strategy=mask_strategy,
mask_args=mask_args,
memory=memory,
memory_level=memory_level,
n_jobs=n_jobs,
verbose=verbose)
if isinstance(threshold, float) and threshold > n_components:
raise ValueError("Threshold must not be higher than number "
"of maps. "
"Number of maps is %s and you provided "
"threshold=%s" %
(str(n_components), str(threshold)))
self.threshold = threshold
self.n_init = n_init
def __init__(
self,
mask_img=None,
sessions=None,
smoothing_fwhm=None,
standardize=False,
detrend=False,
low_pass=None,
high_pass=None,
t_r=None,
target_affine=None,
target_shape=None,
mask_strategy='background',
mask_args=None,
sample_mask=None,
dtype=None,
memory_level=1,
memory=Memory(cachedir=None),
verbose=0,
reports=True,
):
# Mask is provided or computed
self.mask_img = mask_img
self.sessions = sessions
self.smoothing_fwhm = smoothing_fwhm
self.standardize = standardize
self.detrend = detrend
self.low_pass = low_pass
self.high_pass = high_pass
self.t_r = t_r
self.target_affine = target_affine
self.target_shape = target_shape
self.mask_strategy = mask_strategy
self.mask_args = mask_args
self.sample_mask = sample_mask
self.dtype = dtype
self.memory = memory
self.memory_level = memory_level
self.verbose = verbose
self.reports = reports
self._report_description = ('This report shows the input Nifti '
'image overlaid with the outlines of the '
'mask (in green). We recommend to inspect '
'the report for the overlap between the '
'mask and its input image. ')
self._overlay_text = ('\n To see the input Nifti image before '
'resampling, hover over the displayed image.')
self._shelving = False
def _cache(self, func, func_memory_level=1, shelve=False, **kwargs):
"""Return a joblib.Memory object.
The memory_level determines the level above which the wrapped
function output is cached. By specifying a numeric value for
this level, the user can to control the amount of cache memory
used. This function will cache the function call or not
depending on the cache level.
Parameters
----------
func: function
The function the output of which is to be cached.
memory_level: int
The memory_level from which caching must be enabled for the wrapped
function.
shelve: bool
Whether to return a joblib MemorizedResult, callable by a .get()
method, instead of the return value of func
Returns
-------
mem: joblib.MemorizedFunc, wrapped in _ShelvedFunc if shelving
Object that wraps the function func to cache its further call.
This object may be a no-op, if the requested level is lower
than the value given to _cache()).
For consistency, a callable object is always returned.
"""
verbose = getattr(self, 'verbose', 0)
# Creates attributes if they don't exist
# This is to make creating them in __init__() optional.
if not hasattr(self, "memory_level"):
self.memory_level = 0
if not hasattr(self, "memory"):
self.memory = Memory(cachedir=None, verbose=verbose)
self.memory = _check_memory(self.memory, verbose=verbose)
# If cache level is 0 but a memory object has been provided, set
# memory_level to 1 with a warning.
if self.memory_level == 0 and self.memory.cachedir is not None:
warnings.warn("memory_level is currently set to 0 but "
"a Memory object has been provided. "
"Setting memory_level to 1.")
self.memory_level = 1
return cache(func, self.memory, func_memory_level=func_memory_level,
memory_level=self.memory_level, shelve=shelve,
**kwargs)
def test__safe_cache_dir_creation():
# Test the _safe_cache function that is supposed to flush the
# cache if the nibabel version changes
with tempfile.TemporaryDirectory() as temp_dir:
mem = Memory(cachedir=temp_dir)
version_file = os.path.join(temp_dir, 'joblib', 'module_versions.json')
assert_false(os.path.exists(version_file))
# First test that a version file get created
cache_mixin._safe_cache(mem, f)
assert_true(os.path.exists(version_file))
# Test that it does not get recreated during the same session
os.unlink(version_file)
cache_mixin._safe_cache(mem, f)
assert_false(os.path.exists(version_file))
def __init__(self,
maps_img,
mask_img=None,
allow_overlap=True,
smoothing_fwhm=None,
standardize=False,
detrend=False,
low_pass=None,
high_pass=None,
t_r=None,
dtype=None,
resampling_target="data",
memory=Memory(cachedir=None, verbose=0),
memory_level=0,
verbose=0):
self.maps_img = maps_img
self.mask_img = mask_img
# Maps Masker parameter
self.allow_overlap = allow_overlap
# Parameters for image.smooth
self.smoothing_fwhm = smoothing_fwhm
# Parameters for clean()
self.standardize = standardize
self.detrend = detrend
self.low_pass = low_pass
self.high_pass = high_pass
self.t_r = t_r
self.dtype = dtype
# Parameters for resampling
self.resampling_target = resampling_target
# Parameters for joblib
self.memory = memory
self.memory_level = memory_level
self.verbose = verbose
if resampling_target not in ("mask", "maps", "data", None):
raise ValueError("invalid value for 'resampling_target'"
" parameter: " + str(resampling_target))
if self.mask_img is None and resampling_target == "mask":
raise ValueError(
"resampling_target has been set to 'mask' but no mask "
"has been provided.\nSet resampling_target to something else"
" or provide a mask.")
def test_cache_shelving():
try:
temp_dir = tempfile.mkdtemp()
job_glob = os.path.join(temp_dir, 'joblib', 'nilearn', 'tests',
'test_cache_mixin', 'f', '*')
mem = Memory(cachedir=temp_dir, verbose=0)
res = cache_mixin.cache(f, mem, shelve=True)(2)
assert_equal(res.get(), 2)
assert_equal(len(glob.glob(job_glob)), 1)
res = cache_mixin.cache(f, mem, shelve=True)(2)
assert_equal(res.get(), 2)
assert_equal(len(glob.glob(job_glob)), 1)
finally:
del mem
shutil.rmtree(temp_dir, ignore_errors=True)
def __init__(self,
n_components=20,
n_epochs=1,
alpha=10,
reduction_ratio='auto',
dict_init=None,
random_state=None,
batch_size=20,
method="cd",
mask=None,
smoothing_fwhm=4,
standardize=True,
detrend=True,
low_pass=None,
high_pass=None,
t_r=None,
target_affine=None,
target_shape=None,
mask_strategy='epi',
mask_args=None,
n_jobs=1,
verbose=0,
memory=Memory(cachedir=None),
memory_level=0):
BaseDecomposition.__init__(self,
n_components=n_components,
random_state=random_state,
mask=mask,
smoothing_fwhm=smoothing_fwhm,
standardize=standardize,
detrend=detrend,
low_pass=low_pass,
high_pass=high_pass,
t_r=t_r,
target_affine=target_affine,
target_shape=target_shape,
mask_strategy=mask_strategy,
mask_args=mask_args,
memory=memory,
memory_level=memory_level,
n_jobs=n_jobs,
verbose=verbose)
self.n_epochs = n_epochs
self.batch_size = batch_size
self.method = method
self.alpha = alpha
self.reduction_ratio = reduction_ratio
self.dict_init = dict_init
def __init__(self,
method,
n_parcels=50,
random_state=0,
mask=None,
smoothing_fwhm=4.,
standardize=False,
detrend=False,
low_pass=None,
high_pass=None,
t_r=None,
target_affine=None,
target_shape=None,
mask_strategy='epi',
mask_args=None,
scaling=False,
n_iter=10,
memory=Memory(cachedir=None),
memory_level=0,
n_jobs=1,
verbose=1):
self.method = method
self.n_parcels = n_parcels
self.scaling = scaling
self.n_iter = n_iter
MultiPCA.__init__(self,
n_components=200,
random_state=random_state,
mask=mask,
memory=memory,
smoothing_fwhm=smoothing_fwhm,
standardize=standardize,
detrend=detrend,
low_pass=low_pass,
high_pass=high_pass,
t_r=t_r,
target_affine=target_affine,
target_shape=target_shape,
mask_strategy=mask_strategy,
mask_args=mask_args,
memory_level=memory_level,
n_jobs=n_jobs,
verbose=verbose)
def __init__(self,
mask_img=None,
sessions=None,
smoothing_fwhm=None,
standardize=False,
detrend=False,
low_pass=None,
high_pass=None,
t_r=None,
target_affine=None,
target_shape=None,
mask_strategy='background',
mask_args=None,
sample_mask=None,
dtype=None,
memory_level=1,
memory=Memory(cachedir=None),
verbose=0):
# Mask is provided or computed
self.mask_img = mask_img
self.sessions = sessions
self.smoothing_fwhm = smoothing_fwhm
self.standardize = standardize
self.detrend = detrend
self.low_pass = low_pass
self.high_pass = high_pass
self.t_r = t_r
self.target_affine = target_affine
self.target_shape = target_shape
self.mask_strategy = mask_strategy
self.mask_args = mask_args
self.sample_mask = sample_mask
self.dtype = dtype
self.memory = memory
self.memory_level = memory_level
self.verbose = verbose
self._shelving = False
def test_rena_clustering():
data_img, mask_img = generate_fake_fmri(shape=(10, 11, 12), length=5)
data = get_data(data_img)
mask = get_data(mask_img)
X = np.empty((data.shape[3], int(mask.sum())))
for i in range(data.shape[3]):
X[i, :] = np.copy(data[:, :, :, i])[get_data(mask_img) != 0]
nifti_masker = NiftiMasker(mask_img=mask_img).fit()
n_voxels = nifti_masker.transform(data_img).shape[1]
rena = ReNA(mask_img, n_clusters=10)
X_red = rena.fit_transform(X)
X_compress = rena.inverse_transform(X_red)
assert 10 == rena.n_clusters_
assert X.shape == X_compress.shape
memory = Memory(cachedir=None)
rena = ReNA(mask_img, n_clusters=-2, memory=memory)
pytest.raises(ValueError, rena.fit, X)
rena = ReNA(mask_img, n_clusters=10, scaling=True)
X_red = rena.fit_transform(X)
X_compress = rena.inverse_transform(X_red)
for n_iter in [-2, 0]:
rena = ReNA(mask_img, n_iter=n_iter, memory=memory)
pytest.raises(ValueError, rena.fit, X)
for n_clusters in [1, 2, 4, 8]:
rena = ReNA(mask_img, n_clusters=n_clusters, n_iter=1,
memory=memory).fit(X)
assert n_clusters != rena.n_clusters_
del n_voxels, X_red, X_compress
def __init__(self,
n_components=20,
random_state=None,
mask=None,
smoothing_fwhm=None,
standardize=True,
detrend=True,
low_pass=None,
high_pass=None,
t_r=None,
target_affine=None,
target_shape=None,
mask_strategy='epi',
mask_args=None,
memory=Memory(cachedir=None),
memory_level=0,
n_jobs=1,
verbose=0):
self.n_components = n_components
self.random_state = random_state
self.mask = mask
self.smoothing_fwhm = smoothing_fwhm
self.standardize = standardize
self.detrend = detrend
self.low_pass = low_pass
self.high_pass = high_pass
self.t_r = t_r
self.target_affine = target_affine
self.target_shape = target_shape
self.mask_strategy = mask_strategy
self.mask_args = mask_args
self.memory = memory
self.memory_level = memory_level
self.n_jobs = n_jobs
self.verbose = verbose
def __init__(self,
seeds,
radius=None,
mask_img=None,
allow_overlap=False,
smoothing_fwhm=None,
standardize=False,
detrend=False,
low_pass=None,
high_pass=None,
t_r=None,
dtype=None,
memory=Memory(cachedir=None, verbose=0),
memory_level=1,
verbose=0):
self.seeds = seeds
self.mask_img = mask_img
self.radius = radius
self.allow_overlap = allow_overlap
# Parameters for _smooth_array
self.smoothing_fwhm = smoothing_fwhm
# Parameters for clean()
self.standardize = standardize
self.detrend = detrend
self.low_pass = low_pass
self.high_pass = high_pass
self.t_r = t_r
self.dtype = dtype
# Parameters for joblib
self.memory = memory
self.memory_level = memory_level
self.verbose = verbose
def _iter_check_niimg(niimgs, ensure_ndim=None, atleast_4d=False,
target_fov=None, dtype=None,
memory=Memory(cachedir=None),
memory_level=0, verbose=0):
"""Iterate over a list of niimgs and do sanity checks and resampling
Parameters
----------
niimgs: list of niimg or glob pattern
Image to iterate over
ensure_ndim: integer, optional
If specified, an error is raised if the data does not have the
required dimension.
atleast_4d: boolean, optional
If True, any 3D image is converted to a 4D single scan.
target_fov: tuple of affine and shape
If specified, images are resampled to this field of view
dtype: {dtype, "auto"}
Data type toward which the data should be converted. If "auto", the
data will be converted to int32 if dtype is discrete and float32 if it
is continuous.
See also
--------
check_niimg, check_niimg_3d, check_niimg_4d
"""
# If niimgs is a string, use glob to expand it to the matching filenames.
niimgs = _resolve_globbing(niimgs)
ref_fov = None
resample_to_first_img = False
ndim_minus_one = ensure_ndim - 1 if ensure_ndim is not None else None
if target_fov is not None and target_fov != "first":
ref_fov = target_fov
i = -1
for i, niimg in enumerate(niimgs):
try:
niimg = check_niimg(
niimg, ensure_ndim=ndim_minus_one, atleast_4d=atleast_4d,
dtype=dtype)
if i == 0:
ndim_minus_one = len(niimg.shape)
if ref_fov is None:
ref_fov = (niimg.affine, niimg.shape[:3])
resample_to_first_img = True
if not _check_fov(niimg, ref_fov[0], ref_fov[1]):
if target_fov is not None:
from nilearn import image # we avoid a circular import
if resample_to_first_img:
warnings.warn('Affine is different across subjects.'
' Realignement on first subject '
'affine forced')
niimg = cache(image.resample_img, memory,
func_memory_level=2,
memory_level=memory_level)(
niimg, target_affine=ref_fov[0],
target_shape=ref_fov[1])
else:
raise ValueError(
"Field of view of image #%d is different from "
"reference FOV.\n"
"Reference affine:\n%r\nImage affine:\n%r\n"
"Reference shape:\n%r\nImage shape:\n%r\n"
% (i, ref_fov[0], niimg.affine, ref_fov[1],
niimg.shape))
yield niimg
except DimensionError as exc:
# Keep track of the additional dimension in the error
exc.increment_stack_counter()
raise
except TypeError as exc:
img_name = ''
if isinstance(niimg, _basestring):
img_name = " (%s) " % niimg
exc.args = (('Error encountered while loading image #%d%s'
% (i, img_name),) + exc.args)
raise
# Raising an error if input generator is empty.
if i == -1:
raise ValueError("Input niimgs list is empty.")
