def get_cluster_sizes(ds, cluster_counter=None):
"""Compute cluster sizes from all samples in a boolean dataset.
Individually for each sample, in the input dataset, clusters of non-zero
values will be determined after reverse-applying any transformation of the
dataset's mapper (if any).
Parameters
----------
ds : dataset or array
A dataset with boolean samples.
cluster_counter : list or None
If not None, given list is extended with the cluster sizes computed
from the present input dataset. Otherwise, a new list is generated.
Returns
-------
list
Unsorted list of cluster sizes from all samples in the input dataset
(optionally appended to any values passed via ``cluster_counter``).
"""
# XXX input needs to be boolean for the cluster size calculation to work
if cluster_counter is None:
cluster_counter = Counter()
mapper = IdentityMapper()
data = np.asanyarray(ds)
if hasattr(ds, 'a') and 'mapper' in ds.a:
mapper = ds.a.mapper
for i in xrange(len(ds)):
osamp = _verified_reverse1(mapper, data[i])
m_clusters = _get_map_cluster_sizes(osamp)
cluster_counter.update(m_clusters)
return cluster_counter
def test_identity_mapper(s):
idm = IdentityMapper()
# doesn't matter what you throw at it
assert_true(idm.forward(s) is s)
assert_true(idm.forward1(s) is s)
assert_true(idm.reverse(s) is s)
assert_true(idm.reverse1(s) is s)
# even like this it should work, but type conversion
# can happen
assert_array_equal(_verified_reverse1(idm, s), s)
assert_array_equal(idm.reverse1(s), s)
def _reverse_dataset(self, dataset):
# invoke super class _reverse_dataset, this calls, _reverse_dataset
# and this calles _reverse_data in this class
mds = super(FlattenMapper, self)._reverse_dataset(dataset)
# attribute collection needs to have a new length check
mds.fa.set_length_check(mds.nfeatures)
# now unflatten all feature attributes
inspace = self.get_space()
for k in mds.fa:
# reverse map all attributes, but not the inspace indices, since the
# did not come through this mapper and make not sense in inspace
if k != inspace:
mds.fa[k] = _verified_reverse1(self, mds.fa[k].value)
# wipe out the inspace attribute -- needs to be done after the loop to
# not change the size of the dict
if inspace and inspace in mds.fa:
del mds.fa[inspace]
return mds
def _reverse_dataset(self, dataset):
# invoke super class _reverse_dataset, this calls, _reverse_dataset
# and this calles _reverse_data in this class
mds = super(FlattenMapper, self)._reverse_dataset(dataset)
# attribute collection needs to have a new length check
mds.fa.set_length_check(mds.nfeatures)
# now unflatten all feature attributes
inspace = self.get_space()
for k in mds.fa:
# reverse map all attributes, but not the inspace indices, since the
# did not come through this mapper and make not sense in inspace
if k != inspace:
mds.fa[k] = _verified_reverse1(self, mds.fa[k].value)
# wipe out the inspace attribute -- needs to be done after the loop to
# not change the size of the dict
if inspace and inspace in mds.fa:
del mds.fa[inspace]
return mds
def test_flatten():
samples_shape = (2, 2, 4)
data_shape = (4,) + samples_shape
data = np.arange(np.prod(data_shape)).reshape(data_shape).view(myarray)
pristinedata = data.copy()
target = [[ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15],
[16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31],
[32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47],
[48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63]]
target = np.array(target).view(myarray)
index_target = np.array([[0, 0, 0], [0, 0, 1], [0, 0, 2], [0, 0, 3],
[0, 1, 0], [0, 1, 1], [0, 1, 2], [0, 1, 3],
[1, 0, 0], [1, 0, 1], [1, 0, 2], [1, 0, 3],
[1, 1, 0], [1, 1, 1], [1, 1, 2], [1, 1, 3]])
# test only flattening the first two dimensions
fm_max = FlattenMapper(maxdims=2)
fm_max.train(data)
assert_equal(fm_max(data).shape, (4, 4, 4))
# array subclass survives
ok_(isinstance(data, myarray))
# actually, there should be no difference between a plain FlattenMapper and
# a chain that only has a FlattenMapper as the one element
for fm in [FlattenMapper(space='voxel'),
ChainMapper([FlattenMapper(space='voxel'),
StaticFeatureSelection(slice(None))])]:
# not working if untrained
assert_raises(RuntimeError,
fm.forward1,
np.arange(np.sum(samples_shape) + 1))
fm.train(data)
ok_(isinstance(fm.forward(data), myarray))
ok_(isinstance(fm.forward1(data[2]), myarray))
assert_array_equal(fm.forward(data), target)
assert_array_equal(fm.forward1(data[2]), target[2])
assert_raises(ValueError, fm.forward, np.arange(4))
# all of that leaves that data unmodified
assert_array_equal(data, pristinedata)
# reverse mapping
ok_(isinstance(fm.reverse(target), myarray))
ok_(isinstance(fm.reverse1(target[0]), myarray))
ok_(isinstance(fm.reverse(target[1:2]), myarray))
assert_array_equal(fm.reverse(target), data)
assert_array_equal(fm.reverse1(target[0]), data[0])
assert_array_equal(fm.reverse1(target[0]),
_verified_reverse1(fm, target[0]))
assert_array_equal(fm.reverse(target[1:2]), data[1:2])
assert_raises(ValueError, fm.reverse, np.arange(14))
# check one dimensional data, treated as scalar samples
oned = np.arange(5)
fm.train(Dataset(oned))
# needs 2D
assert_raises(ValueError, fm.forward, oned)
# doesn't match mapper, since Dataset turns `oned` into (5,1)
assert_raises(ValueError, fm.forward, oned)
assert_equal(Dataset(oned).nfeatures, 1)
# try dataset mode, with some feature attribute
fattr = np.arange(np.prod(samples_shape)).reshape(samples_shape)
ds = Dataset(data, fa={'awesome': fattr.copy()})
assert_equal(ds.samples.shape, data_shape)
fm.train(ds)
dsflat = fm.forward(ds)
ok_(isinstance(dsflat, Dataset))
ok_(isinstance(dsflat.samples, myarray))
assert_array_equal(dsflat.samples, target)
assert_array_equal(dsflat.fa.awesome, np.arange(np.prod(samples_shape)))
assert_true(isinstance(dsflat.fa['awesome'], ArrayCollectable))
# test index creation
assert_array_equal(index_target, dsflat.fa.voxel)
# and back
revds = fm.reverse(dsflat)
ok_(isinstance(revds, Dataset))
ok_(isinstance(revds.samples, myarray))
assert_array_equal(revds.samples, data)
assert_array_equal(revds.fa.awesome, fattr)
assert_true(isinstance(revds.fa['awesome'], ArrayCollectable))
assert_false('voxel' in revds.fa)
def _call(self, ds):
if len(ds) > 1:
# average all samples into one, assuming we got something like one
# sample per subject as input
avgr = mean_sample()
ds = avgr(ds)
# threshold input; at this point we only have one sample left
thrd = ds.samples[0] > self._thrmap
# mapper default
mapper = IdentityMapper()
# overwrite if possible
if hasattr(ds, 'a') and 'mapper' in ds.a:
mapper = ds.a.mapper
# reverse-map input
othrd = _verified_reverse1(mapper, thrd)
# TODO: what is your purpose in life osamp? ;-)
osamp = _verified_reverse1(mapper, ds.samples[0])
# prep output dataset
outds = ds.copy(deep=False)
outds.fa['featurewise_thresh'] = self._thrmap
# determine clusters
labels, num = measurements.label(othrd,structure=np.ones([3,3,3]))
area = measurements.sum(othrd,
labels,
index=np.arange(1, num + 1)).astype(int)
com = measurements.center_of_mass(
osamp, labels=labels, index=np.arange(1, num + 1))
maxpos = measurements.maximum_position(
osamp, labels=labels, index=np.arange(1, num + 1))
# for the rest we need the labels flattened
labels = mapper.forward1(labels)
# relabel clusters starting with the biggest and increase index with
# decreasing size
ordered_labels = np.zeros(labels.shape, dtype=int)
ordered_area = np.zeros(area.shape, dtype=int)
ordered_com = np.zeros((num, len(osamp.shape)), dtype=float)
ordered_maxpos = np.zeros((num, len(osamp.shape)), dtype=float)
for i, idx in enumerate(np.argsort(area)):
ordered_labels[labels == idx + 1] = num - i
# kinda ugly, but we are looping anyway
ordered_area[i] = area[idx]
ordered_com[i] = com[idx]
ordered_maxpos[i] = maxpos[idx]
labels = ordered_labels
area = ordered_area[::-1]
com = ordered_com[::-1]
maxpos = ordered_maxpos[::-1]
del ordered_labels # this one can be big
# store cluster labels after forward-mapping
outds.fa['clusters_featurewise_thresh'] = labels.copy()
# location info
outds.a['clusterlocations'] = \
np.rec.fromarrays(
[com, maxpos], names=('center_of_mass', 'max'))
# update cluster size histogram with the actual result to get a
# proper lower bound for p-values
# this will make a copy, because the original matrix is int
cluster_probs_raw = _transform_to_pvals(
area, self._null_cluster_sizes.astype('float'))
clusterstats = (
[area, cluster_probs_raw],
['size', 'prob_raw']
)
# evaluate a bunch of stats for all clusters
morestats = {}
for cid in xrange(len(area)):
# keep clusters on outer loop, because selection is more expensive
clvals = ds.samples[0, labels == cid + 1]
for id_, fx in (
('mean', np.mean),
('median', np.median),
('min', np.min),
('max', np.max),
('std', np.std)):
stats = morestats.get(id_, [])
stats.append(fx(clvals))
morestats[id_] = stats
for k, v in morestats.items():
clusterstats[0].append(v)
clusterstats[1].append(k)
if self.params.multicomp_correction is not None:
# do a local import as only this tiny portion needs statsmodels
import statsmodels.stats.multitest as smm
rej, probs_corr = smm.multipletests(
cluster_probs_raw,
alpha=self.params.fwe_rate,
method=self.params.multicomp_correction)[:2]
# store corrected per-cluster probabilities
clusterstats[0].append(probs_corr)
clusterstats[1].append('prob_corrected')
# remove cluster labels that did not pass the FWE threshold
for i, r in enumerate(rej):
if not r:
labels[labels == i + 1] = 0
outds.fa['clusters_fwe_thresh'] = labels
outds.a['clusterstats'] = \
np.rec.fromarrays(clusterstats[0], names=clusterstats[1])
return outds