def run(args):
if not args.store is None and args.output is None:
raise ValueError("--output is require for result storage")
if not args.data is None:
dss = [arg2ds(d) for d in args.data]
if len(dss):
# convenience short-cut
ds = dss[0]
try:
import nose.tools as nt
except ImportError:
pass
for expr in args.eval:
if expr == '-':
exec sys.stdin
elif os.path.isfile(expr):
execfile(expr, globals(), locals())
else:
exec expr
if not args.store is None:
out = {}
for var in args.store:
try:
out[var] = locals()[var]
except KeyError:
warning("'%s' not found in local name space -- skipped." % var)
if len(out):
ds2hdf5(out, args.output, compression=args.hdf5_compression)
def run(args):
if args.store is not None and args.output is None:
raise ValueError("--output is require for result storage")
if args.data is not None:
dss = [arg2ds(d) for d in args.data]
if len(dss):
# convenience short-cut
ds = dss[0]
try:
import nose.tools as nt
except ImportError:
pass
for expr in args.eval:
if expr == '-':
exec sys.stdin
elif os.path.isfile(expr):
execfile(expr, globals(), locals())
else:
exec expr
if args.store is not None:
out = {}
for var in args.store:
try:
out[var] = locals()[var]
except KeyError:
warning("'%s' not found in local name space -- skipped." % var)
if len(out):
ds2hdf5(out, args.output, compression=args.hdf5_compression)
def run(args):
dss = hdf2ds(args.data)
verbose(3, 'Loaded %i dataset(s)' % len(dss))
ds = vstack(dss)
verbose(3, 'Concatenation yielded %i samples with %i features' % ds.shape)
# slicing
sliceme = {'samples': slice(None), 'features': slice(None)}
# indices
for opt, col, which in ((args.samples_by_index, ds.sa, 'samples'),
(args.features_by_index, ds.fa, 'features')):
if opt is None:
continue
if len(opt) == 1 and opt[0].count(':'):
# slice spec
arg = opt[0].split(':')
spec = []
for a in arg:
if not len(a):
spec.append(None)
else:
spec.append(int(a))
sliceme[which] = slice(*spec)
else:
# actual indices
sliceme[which] = [int(o) for o in opt]
# attribute evaluation
for opt, col, which in ((args.samples_by_attr, ds.sa, 'samples'),
(args.features_by_attr, ds.fa, 'features')):
if opt is None:
continue
sliceme[which] = _eval_attr_expr(opt, col)
# apply selection
ds = ds.__getitem__((sliceme['samples'], sliceme['features']))
verbose(1, 'Selected %i samples with %i features' % ds.shape)
# strip attributes
for attrarg, col, descr in ((args.strip_sa, ds.sa, 'sample '),
(args.strip_fa, ds.fa, 'feature '),
(args.strip_da, ds.a, '')):
if not attrarg is None:
for attr in attrarg:
try:
del col[attr]
except KeyError:
warning("dataset has no %sattribute '%s' to remove"
% (descr, attr))
# and store
ds2hdf5(ds, args.output, compression=args.hdf5_compression)
return ds
def run(args):
dss = hdf2ds(args.data)
verbose(3, 'Loaded %i dataset(s)' % len(dss))
ds = vstack(dss)
verbose(3, 'Concatenation yielded %i samples with %i features' % ds.shape)
# get CV instance
cv = get_crossvalidation_instance(args.learner, args.partitioner,
args.errorfx, args.sampling_repetitions,
args.learner_space,
args.balance_training, args.permutations,
args.avg_datafold_results,
args.prob_tail)
res = cv(ds)
# some meaningful output
# XXX make condition on classification analysis only?
print cv.ca.stats
print 'Results\n-------'
if args.permutations > 0:
nprob = cv.ca.null_prob.samples
if res.shape[1] == 1:
# simple result structure
if args.permutations > 0:
p = ', p-value (%s tail)' % args.prob_tail
else:
p = ''
print 'Fold, Result%s' % p
for i in xrange(len(res)):
if args.permutations > 0:
p = ', %f' % nprob[i, 0]
else:
p = ''
print '%s, %f%s' % (res.sa.cvfolds[i], res.samples[i, 0], p)
# and store
ds2hdf5(res, args.output, compression=args.hdf5_compression)
if args.permutations > 0:
if args.output.endswith('.hdf5'):
args.output = args.output[:-5]
ds2hdf5(cv.ca.null_prob,
'%s_nullprob' % args.output,
compression=args.hdf5_compression)
return res
def run(args):
dss = hdf2ds(args.data)
verbose(3, 'Loaded %i dataset(s)' % len(dss))
ds = vstack(dss)
verbose(3, 'Concatenation yielded %i samples with %i features' % ds.shape)
# get CV instance
cv = get_crossvalidation_instance(
args.learner, args.partitioner, args.errorfx, args.sampling_repetitions,
args.learner_space, args.balance_training, args.permutations,
args.avg_datafold_results, args.prob_tail)
res = cv(ds)
# some meaningful output
# XXX make condition on classification analysis only?
print cv.ca.stats
print 'Results\n-------'
if args.permutations > 0:
nprob = cv.ca.null_prob.samples
if res.shape[1] == 1:
# simple result structure
if args.permutations > 0:
p=', p-value (%s tail)' % args.prob_tail
else:
p=''
print 'Fold, Result%s' % p
for i in xrange(len(res)):
if args.permutations > 0:
p = ', %f' % nprob[i, 0]
else:
p = ''
print '%s, %f%s' % (res.sa.cvfolds[i], res.samples[i, 0], p)
# and store
ds2hdf5(res, args.output, compression=args.hdf5_compression)
if args.permutations > 0:
if args.output.endswith('.hdf5'):
args.output = args.output[:-5]
ds2hdf5(cv.ca.null_prob, '%s_nullprob' % args.output,
compression=args.hdf5_compression)
return res
def run(args):
ds = arg2ds(args.data)
verbose(3, 'Concatenation yielded %i samples with %i features' % ds.shape)
# build list of events
events = []
timebased_events = False
if args.event_attrs is not None:
def_attrs = dict([(k, ds.sa[k].value) for k in args.event_attrs])
events = find_events(**def_attrs)
elif args.csv_events is not None:
if args.csv_events == '-':
csv = sys.stdin.read()
import cStringIO
csv = cStringIO.StringIO(csv)
else:
csv = open(args.csv_events, 'rU')
csvt = _load_csv_table(csv)
if not len(csvt):
raise ValueError("no CSV columns found")
if args.onset_column:
csvt['onset'] = csvt[args.onset_column]
nevents = len(csvt[csvt.keys()[0]])
events = []
for ev in xrange(nevents):
events.append(dict([(k, v[ev]) for k, v in csvt.iteritems()]))
elif args.onsets is not None:
if not len(args.onsets):
args.onsets = [i for i in sys.stdin]
# time or sample-based?
if args.time_attr is None:
oconv = int
else:
oconv = float
events = [{'onset': oconv(o)} for o in args.onsets]
elif args.fsl_ev3 is not None:
timebased_events = True
from mvpa2.misc.fsl import FslEV3
events = []
for evsrc in args.fsl_ev3:
events.extend(FslEV3(evsrc).to_events())
if not len(events):
raise ValueError("no events defined")
verbose(2, 'Extracting %i events' % len(events))
if args.event_compression is None:
evmap = None
elif args.event_compression == 'mean':
evmap = FxMapper('features', np.mean, attrfx=merge2first)
elif args.event_compression == 'median':
evmap = FxMapper('features', np.median, attrfx=merge2first)
elif args.event_compression == 'min':
evmap = FxMapper('features', np.min, attrfx=merge2first)
elif args.event_compression == 'max':
evmap = FxMapper('features', np.max, attrfx=merge2first)
# convert to event-related ds
evds = eventrelated_dataset(ds,
events,
time_attr=args.time_attr,
match=args.match_strategy,
event_offset=args.offset,
event_duration=args.duration,
event_mapper=evmap)
# act on all attribute options
evds = process_common_dsattr_opts(evds, args)
# and store
ds2hdf5(evds, args.output, compression=args.hdf5_compression)
return evds
def run(args):
ds = arg2ds(args.data)
verbose(3, 'Concatenation yielded %i samples with %i features' % ds.shape)
# build list of events
events = []
timebased_events = False
if args.event_attrs is not None:
def_attrs = dict([(k, ds.sa[k].value) for k in args.event_attrs])
events = find_events(**def_attrs)
elif args.csv_events is not None:
if args.csv_events == '-':
csv = sys.stdin.read()
import cStringIO
csv = cStringIO.StringIO(csv)
else:
csv = open(args.csv_events, 'rU')
csvt = _load_csv_table(csv)
if not len(csvt):
raise ValueError("no CSV columns found")
if args.onset_column:
csvt['onset'] = csvt[args.onset_column]
nevents = len(csvt[csvt.keys()[0]])
events = []
for ev in xrange(nevents):
events.append(dict([(k, v[ev]) for k, v in csvt.iteritems()]))
elif args.onsets is not None:
if not len(args.onsets):
args.onsets = [i for i in sys.stdin]
# time or sample-based?
if args.time_attr is None:
oconv = int
else:
oconv = float
events = [{'onset': oconv(o)} for o in args.onsets]
elif args.fsl_ev3 is not None:
timebased_events = True
from mvpa2.misc.fsl import FslEV3
events = []
for evsrc in args.fsl_ev3:
events.extend(FslEV3(evsrc).to_events())
if not len(events):
raise ValueError("no events defined")
verbose(2, 'Extracting %i events' % len(events))
if args.event_compression is None:
evmap = None
elif args.event_compression == 'mean':
evmap = FxMapper('features', np.mean, attrfx=merge2first)
elif args.event_compression == 'median':
evmap = FxMapper('features', np.median, attrfx=merge2first)
elif args.event_compression == 'min':
evmap = FxMapper('features', np.min, attrfx=merge2first)
elif args.event_compression == 'max':
evmap = FxMapper('features', np.max, attrfx=merge2first)
# convert to event-related ds
evds = eventrelated_dataset(ds, events, time_attr=args.time_attr,
match=args.match_strategy,
event_offset=args.offset,
event_duration=args.duration,
event_mapper=evmap)
# act on all attribute options
evds = process_common_dsattr_opts(evds, args)
# and store
ds2hdf5(evds, args.output, compression=args.hdf5_compression)
return evds
def run(args):
if not args.chunks is None:
# apply global "chunks" setting
for cattr in ('detrend_chunks', 'zscore_chunks'):
if getattr(args, cattr) is None:
# only overwrite if individual option is not given
args.__setattr__(cattr, args.chunks)
ds = arg2ds(args.data)
if not args.poly_detrend is None:
if not args.detrend_chunks is None \
and not args.detrend_chunks in ds.sa:
raise ValueError(
"--detrend-chunks attribute '%s' not found in dataset" %
args.detrend_chunks)
from mvpa2.mappers.detrend import poly_detrend
verbose(1, "Detrend")
poly_detrend(ds,
polyord=args.poly_detrend,
chunks_attr=args.detrend_chunks,
opt_regs=args.detrend_regrs,
space=args.detrend_coords)
if args.filter_passband is not None:
from mvpa2.mappers.filters import iir_filter
from scipy.signal import butter, buttord
if args.sampling_rate is None or args.filter_stopband is None:
raise ValueError("spectral filtering requires specification of "
"--filter-stopband and --sampling-rate")
# determine filter type
nyquist = args.sampling_rate / 2.0
if len(args.filter_passband) > 1:
btype = 'bandpass'
if not len(args.filter_passband) == len(args.filter_stopband):
raise ValueError(
"passband and stopband specifications have to "
"match in size")
wp = [v / nyquist for v in args.filter_passband]
ws = [v / nyquist for v in args.filter_stopband]
elif args.filter_passband[0] < args.filter_stopband[0]:
btype = 'lowpass'
wp = args.filter_passband[0] / nyquist
ws = args.filter_stopband[0] / nyquist
elif args.filter_passband[0] > args.filter_stopband[0]:
btype = 'highpass'
wp = args.filter_passband[0] / nyquist
ws = args.filter_stopband[0] / nyquist
else:
raise ValueError("invalid specification of Butterworth filter")
# create filter
verbose(1, "Spectral filtering (%s)" % (btype, ))
try:
ord, wn = buttord(wp,
ws,
args.filter_passloss,
args.filter_stopattenuation,
analog=False)
b, a = butter(ord, wn, btype=btype)
except OverflowError:
raise ValueError(
"cannot contruct Butterworth filter for the given "
"specification")
ds = iir_filter(ds, b, a)
if args.zscore:
from mvpa2.mappers.zscore import zscore
verbose(1, "Z-score")
zscore(ds, chunks_attr=args.zscore_chunks, params=args.zscore_params)
verbose(3, "Dataset summary %s" % (ds.summary()))
# invariants?
if not args.strip_invariant_features is None:
from mvpa2.datasets.miscfx import remove_invariant_features
ds = remove_invariant_features(ds)
# and store
ds2hdf5(ds, args.output, compression=args.hdf5_compression)
return ds
def run(args):
if os.path.isfile(args.payload) and args.payload.endswith('.py'):
measure = script2obj(args.payload)
elif args.payload == 'cv':
if args.cv_learner is None or args.cv_partitioner is None:
raise ValueError('cross-validation payload requires --learner and --partitioner')
# get CV instance
measure = get_crossvalidation_instance(
args.cv_learner, args.cv_partitioner, args.cv_errorfx,
args.cv_sampling_repetitions, args.cv_learner_space,
args.cv_balance_training, args.cv_permutations,
args.cv_avg_datafold_results, args.cv_prob_tail)
else:
raise RuntimeError("this should not happen")
ds = arg2ds(args.data)
if args.ds_preproc_fx is not None:
ds = args.ds_preproc_fx(ds)
# setup neighborhood
# XXX add big switch to allow for setting up surface-based neighborhoods
from mvpa2.misc.neighborhood import IndexQueryEngine
qe = IndexQueryEngine(**dict(args.neighbors))
# determine ROIs
rids = None # all by default
aggregate_fx = args.aggregate_fx
if args.roi_attr is not None:
# first figure out which roi features should be processed
if len(args.roi_attr) == 1 and args.roi_attr[0] in ds.fa.keys():
# name of an attribute -> pull non-zeroes
rids = ds.fa[args.roi_attr[0]].value.nonzero()[0]
else:
# an expression?
from .cmd_select import _eval_attr_expr
rids = _eval_attr_expr(args.roi_attr, ds.fa).nonzero()[0]
seed_ids = None
if args.scatter_rois is not None:
# scatter_neighborhoods among available ids if was requested
from mvpa2.misc.neighborhood import scatter_neighborhoods
attr, nb = args.scatter_rois
coords = ds.fa[attr].value
if rids is not None:
# select only those which were chosen by ROI
coords = coords[rids]
_, seed_ids = scatter_neighborhoods(nb, coords)
if aggregate_fx is None:
# no custom one given -> use default "fill in" function
aggregate_fx = _fill_in_scattered_results
if args.enable_ca is None:
args.enable_ca = ['roi_feature_ids']
elif 'roi_feature_ids' not in args.enable_ca:
args.enable_ca += ['roi_feature_ids']
if seed_ids is None:
roi_ids = rids
else:
if rids is not None:
# we had to sub-select by scatterring among available rids
# so we would need to get original ids
roi_ids = rids[seed_ids]
else:
# scattering happened on entire feature-set
roi_ids = seed_ids
verbose(3, 'Attempting %i ROI analyses'
% ((roi_ids is None) and ds.nfeatures or len(roi_ids)))
from mvpa2.measures.searchlight import Searchlight
sl = Searchlight(measure,
queryengine=qe,
roi_ids=roi_ids,
nproc=args.nproc,
results_backend=args.multiproc_backend,
results_fx=aggregate_fx,
enable_ca=args.enable_ca,
disable_ca=args.disable_ca)
# XXX support me too!
# add_center_fa
# tmp_prefix
# nblocks
# null_dist
# run
res = sl(ds)
if (seed_ids is not None) and ('mapper' in res.a):
# strip the last mapper link in the chain, which would be the seed ID selection
res.a['mapper'] = res.a.mapper[:-1]
# XXX create more output
# and store
ds2hdf5(res, args.output, compression=args.hdf5_compression)
return res
def run(args):
if os.path.isfile(args.payload) and args.payload.endswith('.py'):
measure = script2obj(args.payload)
elif args.payload == 'cv':
if args.cv_learner is None or args.cv_partitioner is None:
raise ValueError(
'cross-validation payload requires --learner and --partitioner'
)
# get CV instance
measure = get_crossvalidation_instance(
args.cv_learner, args.cv_partitioner, args.cv_errorfx,
args.cv_sampling_repetitions, args.cv_learner_space,
args.cv_balance_training, args.cv_permutations,
args.cv_avg_datafold_results, args.cv_prob_tail)
else:
raise RuntimeError("this should not happen")
ds = arg2ds(args.data)
if not args.ds_preproc_fx is None:
ds = args.ds_preproc_fx(ds)
# setup neighborhood
# XXX add big switch to allow for setting up surface-based neighborhoods
from mvpa2.misc.neighborhood import IndexQueryEngine
qe = IndexQueryEngine(**dict(args.neighbors))
# determine ROIs
rids = None # all by default
aggregate_fx = args.aggregate_fx
if args.roi_attr is not None:
# first figure out which roi features should be processed
if len(args.roi_attr) == 1 and args.roi_attr[0] in ds.fa.keys():
# name of an attribute -> pull non-zeroes
rids = ds.fa[args.roi_attr[0]].value.nonzero()[0]
else:
# an expression?
from .cmd_select import _eval_attr_expr
rids = _eval_attr_expr(args.roi_attr, ds.fa).nonzero()[0]
seed_ids = None
if args.scatter_rois is not None:
# scatter_neighborhoods among available ids if was requested
from mvpa2.misc.neighborhood import scatter_neighborhoods
attr, nb = args.scatter_rois
coords = ds.fa[attr].value
if rids is not None:
# select only those which were chosen by ROI
coords = coords[rids]
_, seed_ids = scatter_neighborhoods(nb, coords)
if aggregate_fx is None:
# no custom one given -> use default "fill in" function
aggregate_fx = _fill_in_scattered_results
if args.enable_ca is None:
args.enable_ca = ['roi_feature_ids']
elif 'roi_feature_ids' not in args.enable_ca:
args.enable_ca += ['roi_feature_ids']
if seed_ids is None:
roi_ids = rids
else:
if rids is not None:
# we had to sub-select by scatterring among available rids
# so we would need to get original ids
roi_ids = rids[seed_ids]
else:
# scattering happened on entire feature-set
roi_ids = seed_ids
verbose(
3, 'Attempting %i ROI analyses' %
((roi_ids is None) and ds.nfeatures or len(roi_ids)))
from mvpa2.measures.searchlight import Searchlight
sl = Searchlight(measure,
queryengine=qe,
roi_ids=roi_ids,
nproc=args.nproc,
results_backend=args.multiproc_backend,
results_fx=aggregate_fx,
enable_ca=args.enable_ca,
disable_ca=args.disable_ca)
# XXX support me too!
# add_center_fa
# tmp_prefix
# nblocks
# null_dist
# run
res = sl(ds)
if (seed_ids is not None) and ('mapper' in res.a):
# strip the last mapper link in the chain, which would be the seed ID selection
res.a['mapper'] = res.a.mapper[:-1]
# XXX create more output
# and store
ds2hdf5(res, args.output, compression=args.hdf5_compression)
return res
def run(args):
if args.chunks is not None:
# apply global "chunks" setting
for cattr in ("detrend_chunks", "zscore_chunks"):
if getattr(args, cattr) is None:
# only overwrite if individual option is not given
args.__setattr__(cattr, args.chunks)
ds = arg2ds(args.data)
if args.poly_detrend is not None:
if args.detrend_chunks is not None and not args.detrend_chunks in ds.sa:
raise ValueError("--detrend-chunks attribute '%s' not found in dataset" % args.detrend_chunks)
from mvpa2.mappers.detrend import poly_detrend
verbose(1, "Detrend")
poly_detrend(
ds,
polyord=args.poly_detrend,
chunks_attr=args.detrend_chunks,
opt_regs=args.detrend_regrs,
space=args.detrend_coords,
)
if args.filter_passband is not None:
from mvpa2.mappers.filters import iir_filter
from scipy.signal import butter, buttord
if args.sampling_rate is None or args.filter_stopband is None:
raise ValueError("spectral filtering requires specification of " "--filter-stopband and --sampling-rate")
# determine filter type
nyquist = args.sampling_rate / 2.0
if len(args.filter_passband) > 1:
btype = "bandpass"
if not len(args.filter_passband) == len(args.filter_stopband):
raise ValueError("passband and stopband specifications have to " "match in size")
wp = [v / nyquist for v in args.filter_passband]
ws = [v / nyquist for v in args.filter_stopband]
elif args.filter_passband[0] < args.filter_stopband[0]:
btype = "lowpass"
wp = args.filter_passband[0] / nyquist
ws = args.filter_stopband[0] / nyquist
elif args.filter_passband[0] > args.filter_stopband[0]:
btype = "highpass"
wp = args.filter_passband[0] / nyquist
ws = args.filter_stopband[0] / nyquist
else:
raise ValueError("invalid specification of Butterworth filter")
# create filter
verbose(1, "Spectral filtering (%s)" % (btype,))
try:
ord, wn = buttord(wp, ws, args.filter_passloss, args.filter_stopattenuation, analog=False)
b, a = butter(ord, wn, btype=btype)
except OverflowError:
raise ValueError("cannot contruct Butterworth filter for the given " "specification")
ds = iir_filter(ds, b, a)
if args.zscore:
from mvpa2.mappers.zscore import zscore
verbose(1, "Z-score")
zscore(ds, chunks_attr=args.zscore_chunks, params=args.zscore_params)
verbose(3, "Dataset summary %s" % (ds.summary()))
# invariants?
if args.strip_invariant_features is not None:
from mvpa2.datasets.miscfx import remove_invariant_features
ds = remove_invariant_features(ds)
# and store
ds2hdf5(ds, args.output, compression=args.hdf5_compression)
return ds
