/usr/share/pyshared/mvpa2/measures/searchlight.py is in python-mvpa2 2.1.0-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 | # emacs: -*- mode: python; py-indent-offset: 4; indent-tabs-mode: nil -*-
# vi: set ft=python sts=4 ts=4 sw=4 et:
### ### ### ### ### ### ### ### ### ### ### ### ### ### ### ### ### ### ### ##
#
# See COPYING file distributed along with the PyMVPA package for the
# copyright and license terms.
#
### ### ### ### ### ### ### ### ### ### ### ### ### ### ### ### ### ### ### ##
"""Implementation of the Searchlight algorithm"""
__docformat__ = 'restructuredtext'
if __debug__:
from mvpa2.base import debug
import numpy as np
from mvpa2.base import externals, warning
from mvpa2.base.dochelpers import borrowkwargs, _repr_attrs
from mvpa2.base.types import is_datasetlike
from mvpa2.datasets import hstack, Dataset
from mvpa2.support import copy
from mvpa2.featsel.base import StaticFeatureSelection
from mvpa2.measures.base import Measure
from mvpa2.base.state import ConditionalAttribute
from mvpa2.misc.neighborhood import IndexQueryEngine, Sphere
class BaseSearchlight(Measure):
"""Base class for searchlights.
The idea for a searchlight algorithm stems from a paper by
:ref:`Kriegeskorte et al. (2006) <KGB06>`.
"""
roi_sizes = ConditionalAttribute(enabled=False,
doc="Number of features in each ROI.")
roi_feature_ids = ConditionalAttribute(enabled=False,
doc="Feature IDs for all generated ROIs.")
is_trained = True
"""Indicate that this measure is always trained."""
def __init__(self, queryengine, roi_ids=None, nproc=None, **kwargs):
"""
Parameters
----------
queryengine : QueryEngine
Engine to use to discover the "neighborhood" of each feature.
See :class:`~mvpa2.misc.neighborhood.QueryEngine`.
roi_ids : None or list(int) or str
List of feature ids (not coordinates) the shall serve as ROI seeds
(e.g. sphere centers). Alternatively, this can be the name of a
feature attribute of the input dataset, whose non-zero values
determine the feature ids. By default all features will be used.
nproc : None or int
How many processes to use for computation. Requires `pprocess`
external module. If None -- all available cores will be used.
**kwargs
In addition this class supports all keyword arguments of its
base-class :class:`~mvpa2.measures.base.Measure`.
"""
Measure.__init__(self, **kwargs)
if nproc > 1 and not externals.exists('pprocess'):
raise RuntimeError("The 'pprocess' module is required for "
"multiprocess searchlights. Please either "
"install python-pprocess, or reduce `nproc` "
"to 1 (got nproc=%i)" % nproc)
self._queryengine = queryengine
if roi_ids is not None and not isinstance(roi_ids, str) \
and not len(roi_ids):
raise ValueError, \
"Cannot run searchlight on an empty list of roi_ids"
self.__roi_ids = roi_ids
self.nproc = nproc
def __repr__(self, prefixes=[]):
"""String representation of a `Measure`
Includes only arguments which differ from default ones
"""
return super(BaseSearchlight, self).__repr__(
prefixes=prefixes
+ _repr_attrs(self, ['queryengine', 'roi_ids', 'nproc']))
def _call(self, dataset):
"""Perform the ROI search.
"""
# local binding
nproc = self.nproc
if nproc is None and externals.exists('pprocess'):
import pprocess
try:
nproc = pprocess.get_number_of_cores() or 1
except AttributeError:
warning("pprocess version %s has no API to figure out maximal "
"number of cores. Using 1"
% externals.versions['pprocess'])
nproc = 1
# train the queryengine
self._queryengine.train(dataset)
# decide whether to run on all possible center coords or just a provided
# subset
if isinstance(self.__roi_ids, str):
roi_ids = dataset.fa[self.__roi_ids].value.nonzero()[0]
elif self.__roi_ids is not None:
roi_ids = self.__roi_ids
# safeguard against stupidity
if __debug__:
if max(roi_ids) >= dataset.nfeatures:
raise IndexError, \
"Maximal center_id found is %s whenever given " \
"dataset has only %d features" \
% (max(roi_ids), dataset.nfeatures)
else:
roi_ids = np.arange(dataset.nfeatures)
# pass to subclass
results, roi_sizes = self._sl_call(dataset, roi_ids, nproc)
if not roi_sizes is None:
self.ca.roi_sizes = roi_sizes
if 'mapper' in dataset.a:
# since we know the space we can stick the original mapper into the
# results as well
if self.__roi_ids is None:
results.a['mapper'] = copy.copy(dataset.a.mapper)
else:
# there is an additional selection step that needs to be
# expressed by another mapper
mapper = copy.copy(dataset.a.mapper)
mapper.append(StaticFeatureSelection(roi_ids,
dshape=dataset.shape[1:]))
results.a['mapper'] = mapper
# charge state
self.ca.raw_results = results
# return raw results, base-class will take care of transformations
return results
def _sl_call(self, dataset, roi_ids, nproc):
"""Classical generic searchlight implementation
"""
raise NotImplementedError("Must be implemented in the derived classes")
queryengine = property(fget=lambda self: self._queryengine)
roi_ids = property(fget=lambda self: self.__roi_ids)
class Searchlight(BaseSearchlight):
"""The implementation of a generic searchlight measure.
The idea for a searchlight algorithm stems from a paper by
:ref:`Kriegeskorte et al. (2006) <KGB06>`. As a result it
produces a map of measures given a `datameasure` instance of
interest, which is ran at each spatial location.
"""
def __init__(self, datameasure, queryengine, add_center_fa=False, **kwargs):
"""
Parameters
----------
datameasure : callable
Any object that takes a :class:`~mvpa2.datasets.base.Dataset`
and returns some measure when called.
add_center_fa : bool or str
If True or a string, each searchlight ROI dataset will have a boolean
vector as a feature attribute that indicates the feature that is the
seed (e.g. sphere center) for the respective ROI. If True, the
attribute is named 'roi_seed', the provided string is used as the name
otherwise.
**kwargs
In addition this class supports all keyword arguments of its
base-class :class:`~mvpa2.measures.searchlight.BaseSearchlight`.
"""
BaseSearchlight.__init__(self, queryengine, **kwargs)
self.datameasure = datameasure
if isinstance(add_center_fa, str):
self.__add_center_fa = add_center_fa
elif add_center_fa:
self.__add_center_fa = 'roi_seed'
else:
self.__add_center_fa = False
def __repr__(self, prefixes=[]):
return super(Searchlight, self).__repr__(
prefixes=prefixes
+ _repr_attrs(self, ['datameasure'])
+ _repr_attrs(self, ['add_center_fa'], default=False)
)
def _sl_call(self, dataset, roi_ids, nproc):
"""Classical generic searchlight implementation
"""
# compute
if nproc > 1:
# split all target ROIs centers into `nproc` equally sized blocks
nproc_needed = min(len(roi_ids), nproc)
roi_blocks = np.array_split(roi_ids, nproc_needed)
# the next block sets up the infrastructure for parallel computing
# this can easily be changed into a ParallelPython loop, if we
# decide to have a PP job server in PyMVPA
import pprocess
p_results = pprocess.Map(limit=nproc_needed)
if __debug__:
debug('SLC', "Starting off child processes for nproc=%i"
% nproc_needed)
compute = p_results.manage(
pprocess.MakeParallel(self._proc_block))
for block in roi_blocks:
# should we maybe deepcopy the measure to have a unique and
# independent one per process?
compute(block, dataset, copy.copy(self.__datameasure))
# collect results
results = []
if self.ca.is_enabled('roi_sizes'):
roi_sizes = []
else:
roi_sizes = None
for r, rsizes in p_results:
results += r
if not roi_sizes is None:
roi_sizes += rsizes
else:
# otherwise collect the results in a list
results, roi_sizes = \
self._proc_block(roi_ids, dataset, self.__datameasure)
if __debug__ and 'SLC' in debug.active:
debug('SLC', '') # just newline
resshape = len(results) and np.asanyarray(results[0]).shape or 'N/A'
debug('SLC', ' hstacking %d results of shape %s'
% (len(results), resshape))
# but be careful: this call also serves as conversion from parallel maps
# to regular lists!
# this uses the Dataset-hstack
result_ds = hstack(results)
if self.ca.is_enabled('roi_feature_ids'):
self.ca.roi_feature_ids = [r.a.roi_feature_ids for r in results]
if __debug__:
debug('SLC', " hstacked shape %s" % (result_ds.shape,))
return result_ds, roi_sizes
def _proc_block(self, block, ds, measure):
"""Little helper to capture the parts of the computation that can be
parallelized
"""
if __debug__:
debug_slc_ = 'SLC_' in debug.active
debug('SLC',
"Starting computing block for %i elements" % len(block))
if self.ca.is_enabled('roi_sizes'):
roi_sizes = []
else:
roi_sizes = None
results = []
# put rois around all features in the dataset and compute the
# measure within them
for i, f in enumerate(block):
# retrieve the feature ids of all features in the ROI from the query
# engine
roi_fids = self._queryengine[f]
if __debug__ and debug_slc_:
debug('SLC_', 'For %r query returned ids %r' % (f, roi_fids))
# slice the dataset
roi = ds[:, roi_fids]
if self.__add_center_fa:
# add fa to indicate ROI seed if requested
roi_seed = np.zeros(roi.nfeatures, dtype='bool')
roi_seed[roi_fids.index(f)] = True
roi.fa[self.__add_center_fa] = roi_seed
# compute the datameasure and store in results
res = measure(roi)
if self.ca.is_enabled('roi_feature_ids'):
if not is_datasetlike(res):
res = Dataset(np.atleast_1d(res))
# add roi feature ids to intermediate result dataset for later
# aggregation
res.a['roi_feature_ids'] = roi_fids
results.append(res)
# store the size of the roi dataset
if not roi_sizes is None:
roi_sizes.append(roi.nfeatures)
if __debug__:
debug('SLC', "Doing %i ROIs: %i (%i features) [%i%%]" \
% (len(block),
f+1,
roi.nfeatures,
float(i+1)/len(block)*100,), cr=True)
return results, roi_sizes
def __set_datameasure(self, datameasure):
"""Set the datameasure"""
self.untrain()
self.__datameasure = datameasure
datameasure = property(fget=lambda self: self.__datameasure,
fset=__set_datameasure)
add_center_fa = property(fget=lambda self: self.__add_center_fa)
@borrowkwargs(Searchlight, '__init__', exclude=['roi_ids'])
def sphere_searchlight(datameasure, radius=1, center_ids=None,
space='voxel_indices', **kwargs):
"""Creates a `Searchlight` to run a scalar `Measure` on
all possible spheres of a certain size within a dataset.
The idea for a searchlight algorithm stems from a paper by
:ref:`Kriegeskorte et al. (2006) <KGB06>`.
Parameters
----------
datameasure : callable
Any object that takes a :class:`~mvpa2.datasets.base.Dataset`
and returns some measure when called.
radius : int
All features within this radius around the center will be part
of a sphere. Radius is in grid-indices, i.e. ``1`` corresponds
to all immediate neighbors, regardless of the physical distance.
center_ids : list of int
List of feature ids (not coordinates) the shall serve as sphere
centers. Alternatively, this can be the name of a feature attribute
of the input dataset, whose non-zero values determine the feature
ids. By default all features will be used (it is passed as ``roi_ids``
argument of Searchlight).
space : str
Name of a feature attribute of the input dataset that defines the spatial
coordinates of all features.
**kwargs
In addition this class supports all keyword arguments of its
base-class :class:`~mvpa2.measures.base.Measure`.
Notes
-----
If `Searchlight` is used as `SensitivityAnalyzer` one has to make
sure that the specified scalar `Measure` returns large
(absolute) values for high sensitivities and small (absolute) values
for low sensitivities. Especially when using error functions usually
low values imply high performance and therefore high sensitivity.
This would in turn result in sensitivity maps that have low
(absolute) values indicating high sensitivities and this conflicts
with the intended behavior of a `SensitivityAnalyzer`.
"""
# build a matching query engine from the arguments
kwa = {space: Sphere(radius)}
qe = IndexQueryEngine(**kwa)
# init the searchlight with the queryengine
return Searchlight(datameasure, queryengine=qe, roi_ids=center_ids,
**kwargs)
#class OptimalSearchlight( object ):
# def __init__( self,
# searchlight,
# test_radii,
# verbose=False,
# **kwargs ):
# """
# """
# # results will end up here
# self.__perfmeans = []
# self.__perfvars = []
# self.__chisquares = []
# self.__chanceprobs = []
# self.__spheresizes = []
#
# # run searchligh for all radii in the list
# for radius in test_radii:
# if verbose:
# print 'Using searchlight with radius:', radius
# # compute the results
# searchlight( radius, **(kwargs) )
#
# self.__perfmeans.append( searchlight.perfmean )
# self.__perfvars.append( searchlight.perfvar )
# self.__chisquares.append( searchlight.chisquare )
# self.__chanceprobs.append( searchlight.chanceprob )
# self.__spheresizes.append( searchlight.spheresize )
#
#
# # now determine the best classification accuracy
# best = np.array(self.__perfmeans).argmax( axis=0 )
#
# # select the corresponding values of the best classification
# # in all data tables
# self.perfmean = best.choose(*(self.__perfmeans))
# self.perfvar = best.choose(*(self.__perfvars))
# self.chisquare = best.choose(*(self.__chisquares))
# self.chanceprob = best.choose(*(self.__chanceprobs))
# self.spheresize = best.choose(*(self.__spheresizes))
#
# # store the best performing radius
# self.bestradius = np.zeros( self.perfmean.shape, dtype='uint' )
# self.bestradius[searchlight.mask==True] = \
# best.choose( test_radii )[searchlight.mask==True]
#
#
#
#def makeSphericalROIMask( mask, radius, elementsize=None ):
# """
# """
# # use default elementsize if none is supplied
# if not elementsize:
# elementsize = [ 1 for i in range( len(mask.shape) ) ]
# else:
# if len( elementsize ) != len( mask.shape ):
# raise ValueError, 'elementsize does not match mask dimensions.'
#
# # rois will be drawn into this mask
# roi_mask = np.zeros( mask.shape, dtype='int32' )
#
# # while increase with every ROI
# roi_id_counter = 1
#
# # build spheres around every non-zero value in the mask
# for center, spheremask in \
# algorithms.SpheresInMask( mask,
# radius,
# elementsize,
# forcesphere = True ):
#
# # set all elements that match the current spheremask to the
# # current ROI index value
# roi_mask[spheremask] = roi_id_counter
#
# # increase ROI counter
# roi_id_counter += 1
#
# return roi_mask
|