class FeaturePermutationRegression(RegressionAnalysisPipeline):
def run(self):
self.loader = ConnectivityDataLoader()
self.X, self.y = self.loader.setup_analysis(self.path,
self.roi_list,
self.directory,
self.condition_list,
self.subjects).filter(self.filter_).get_data()
X = self.X
y = self.y
X = zscore(X, axis=1) # Sample-wise
y = zscore(np.float_(y))
self.fs = FeatureSelectionIterator().setup_analysis(self.fs_algorithm,
self.fs_ranking_fx)
self.reg = RegressionAnalysis().setup_analysis(self.cv_schema,
self.learner,
self.error_fx,
feature_selection=self.fs)
self.perm = PermutationAnalysis().setup_analysis(self.reg,
n_permutation=self.n_permutations,
dimension='labels')
self.results = []
reg_res = self.reg.run(X, y) # To be selected
perm_res = self.perm.run(X, y)
self.results.append([reg_res, perm_res])
#self.save()
return self.results
class RegressionAnalysisPipeline(Pipeline):
_default_fields = {'path':'/media/robbis/DATA/fmri/monks/',
'roi_list':None,
'directory':None,
'condition_list':None,
'subjects':None,
'filter_':None,
'fs_algorithm':Correlation,
'fs_ranking_fx':ranking_correlation,
'cv_schema':ShuffleSplit(12,
n_iter=250,
test_size=0.25),
'learner':SVR(kernel='linear', C=1),
'error_fx':[mean_squared_error, correlation],
'y_field':None,
'n_permutations':2000
}
def setup_analysis(self, **kwargs):
"""
Fields needed:
path: (e.g. '/media/robbis/DATA/fmri/monks/')
roi_list: (e.g. load '/media/robbis/DATA/fmri/templates_fcmri/findlab_rois.txt')
directory (e.g. '20151030_141350_connectivity_filtered_first_no_gsr_findlab_fmri')
condition_list (e.g. ['Samatha', 'Vipassana'])
subjects (e.g. '/media/robbis/DATA/fmri/monks/attributes_struct.txt')
filter (e.g. {'meditation':'Samatha', 'groups':'E'})
-- filter_keywords were used to build the filter
e.g. meditation: Vipassana will overwrite the filter
fs_algorithm (e.g. mvpa_itab.stats.base.Correlation)
fs_ranking_fx (e.g. mvpa_itab.measures.ranking_correlation)
cv_schema (e.g. ShuffleSplit(num_exp_subjects, n_iter=cv_repetitions, test_size=cv_fraction)
learner (e.g. SVR(kernel='linear', C=1))
error_fx (e.g. [mean_squared_error, correlation])
y_field (e.g. expertise)
n_permutations (e.g. 1000)
"""
self._configuration = dict()
for arg in self._default_fields:
setattr(self, arg, self._default_fields[arg])
self._configuration[arg] = self._default_fields[arg]
for arg in kwargs:
setattr(self, arg, kwargs[arg])
self._configuration[arg] = kwargs[arg]
return self
def update_configuration(self, **kwargs):
for arg in kwargs:
setattr(self, arg, kwargs[arg])
self._configuration[arg] = kwargs[arg]
if arg in self.filter_.keys():
self.filter_[arg] = kwargs[arg]
self._configuration['filter_'][arg] = kwargs[arg]
return self
def run(self):
self.results = []
self.loader = ConnectivityDataLoader()
self.X, self.y = self.loader.setup_analysis(self.path,
self.roi_list,
self.directory,
self.condition_list,
self.subjects).filter(self.filter_).get_data()
X = self.X
y = self.y
X = zscore(X, axis=1) # Sample-wise
y = zscore(np.float_(y))
self.fs = FeatureSelectionIterator()
self.fs.setup_analysis(self.fs_algorithm, self.fs_ranking_fx).run(X, y).select_first(80)
self.reg = RegressionAnalysis().setup_analysis(self.cv_schema,
self.learner,
self.error_fx)
#Speedup stuff
schema = ShuffleSplit(12, n_iter=1, test_size=0.25)
self.perm_reg = RegressionAnalysis().setup_analysis(schema,
self.learner,
self.error_fx)
self.perm = PermutationAnalysis().setup_analysis(self.reg,
n_permutation=self.n_permutations,
dimension='features')
for i,set_ in enumerate(self.fs):
if i > 78:
X_ = X[:,set_]
y_ = y
reg_res = self.reg.run(X_, y_) # To be selected
n_dist = self.perm.run(X_, y_)
p_res = self.perm.pvalues(reg_res)
self.results.append([reg_res, n_dist, p_res])
#self.save()
return self.results