def test_sensitivity_based_feature_selection(self, clf):
# sensitivity analyser and transfer error quantifier use the SAME clf!
sens_ana = clf.get_sensitivity_analyzer(postproc=maxofabs_sample())
# of features to remove
Nremove = 2
# because the clf is already trained when computing the sensitivity
# map, prevent retraining for transfer error calculation
# Use absolute of the svm weights as sensitivity
fe = SensitivityBasedFeatureSelection(
sens_ana,
feature_selector=FixedNElementTailSelector(2),
enable_ca=["sensitivity", "selected_ids"])
data = self.get_data()
data_nfeatures = data.nfeatures
fe.train(data)
resds = fe(data)
# fail if orig datasets are changed
self.assertTrue(data.nfeatures == data_nfeatures)
# silly check if nfeatures got a single one removed
self.assertEqual(data.nfeatures,
resds.nfeatures + Nremove,
msg="We had to remove just a single feature")
self.assertEqual(
fe.ca.sensitivity.nfeatures,
data_nfeatures,
msg="Sensitivity have to have # of features equal to original")
def test_sensitivity_based_feature_selection(self, clf):
# sensitivity analyser and transfer error quantifier use the SAME clf!
sens_ana = clf.get_sensitivity_analyzer(postproc=maxofabs_sample())
# of features to remove
Nremove = 2
# because the clf is already trained when computing the sensitivity
# map, prevent retraining for transfer error calculation
# Use absolute of the svm weights as sensitivity
fe = SensitivityBasedFeatureSelection(sens_ana,
feature_selector=FixedNElementTailSelector(2),
enable_ca=["sensitivity", "selected_ids"])
data = self.get_data()
data_nfeatures = data.nfeatures
fe.train(data)
resds = fe(data)
# fail if orig datasets are changed
self.assertTrue(data.nfeatures == data_nfeatures)
# silly check if nfeatures got a single one removed
self.assertEqual(data.nfeatures, resds.nfeatures+Nremove,
msg="We had to remove just a single feature")
self.assertEqual(fe.ca.sensitivity.nfeatures, data_nfeatures,
msg="Sensitivity have to have # of features equal to original")
def test_custom_combined_selectors(self):
"""Test combination of the selectors in a single function
"""
def custom_tail_selector(seq):
seq1 = FractionTailSelector(0.01, mode='discard',
tail='upper')(seq)
seq2 = FractionTailSelector(0.05, mode='select', tail='upper')(seq)
return list(set(seq1).intersection(seq2))
seq = np.arange(100)
seq_ = custom_tail_selector(seq)
assert_array_equal(sorted(seq_), [95, 96, 97, 98])
# verify that this function could be used in place of the selector
fs = SensitivityBasedFeatureSelection(OneWayAnova(),
custom_tail_selector)
ds = datasets['3dsmall']
fs.train(ds) # XXX: why needs to be trained here explicitly?
ds_ = fs(ds)
assert_equal(ds_.nfeatures, int(ds.nfeatures * 0.04))
def test_custom_combined_selectors(self):
"""Test combination of the selectors in a single function
"""
def custom_tail_selector(seq):
seq1 = FractionTailSelector(0.01, mode='discard', tail='upper')(seq)
seq2 = FractionTailSelector(0.05, mode='select', tail='upper')(seq)
return list(set(seq1).intersection(seq2))
seq = np.arange(100)
seq_ = custom_tail_selector(seq)
assert_array_equal(sorted(seq_), [95, 96, 97, 98])
# verify that this function could be used in place of the selector
fs = SensitivityBasedFeatureSelection(
OneWayAnova(),
custom_tail_selector)
ds = datasets['3dsmall']
fs.train(ds) # XXX: why needs to be trained here explicitly?
ds_ = fs(ds)
assert_equal(ds_.nfeatures, int(ds.nfeatures * 0.04))
data = np.concatenate(data)
labels = np.concatenate(labels)
return data, labels.astype(np.int)
rois = ['aSTG', 'HG', 'pSTG']
for sub_id in range(1, 21):
data = []
for roi in rois:
data_path = os.path.join(data_dir, roi)
tmp_data, label = load_data(data_path, sub_id)
data.append(tmp_data)
data = np.concatenate(data, axis=1)
data = np.concatenate([data[i,:,:].T for i in range(len(data))])
ds = Dataset(data)
ds.sa['time_coords'] = np.linspace(0, len(ds)-1, len(ds))
events = [{'onset': i*5, 'duration': 5, 'targets':label[i], 'chunks':i+1} for i in range(int(len(ds)/5))]
hrf_estimates = fit_event_hrf_model(ds, events, time_attr='time_coords', condition_attr=('targets', 'chunks'),
design_kwargs=dict(drift_model='blank'), glmfit_kwargs=dict(model='ols'),
return_model=True)
fsel = SensitivityBasedFeatureSelection(OneWayAnova(), FixedNElementTailSelector(5000, mode='select', tail='upper'))
fsel.train(hrf_estimates)
ds_p = fsel(hrf_estimates)
np.save('feat_sub{:03d}'.format(sub_id), ds_p.samples)
