def nf_select(nf):
fselector = mvpa2.FixedNElementTailSelector(np.round(nf),
tail='upper',
mode='select',
sort=False)
sbfs = mvpa2.SensitivityBasedFeatureSelection(
mvpa2.OneWayAnova(),
fselector,
enable_ca=['sensitivities'],
auto_train=True)
if (optimize == 1):
not_test_ds = ds[ds.chunks != chunk]
train_ds = not_test_ds[not_test_ds.chunks != val_chunk]
sbfs.train(train_ds)
ds2 = sbfs(
not_test_ds
) #optimize nf & include validation set for computing dists
elif (optimize == 0):
train_ds = ds[
ds.chunks !=
chunk] #retrain with all data if not optimizing
sbfs.train(train_ds)
ds2 = sbfs(
ds
) #pick top features with training & use whole dataset for computing dists
return ds2
def nf_select(nf):
fselector = mvpa2.FixedNElementTailSelector(np.round(nf),
tail='upper',
mode='select',
sort=False)
sbfs = mvpa2.SensitivityBasedFeatureSelection(
mvpa2.OneWayAnova(),
fselector,
enable_ca=['sensitivities'],
auto_train=True)
if (optimize >= 1):
not_test_ds = ds[ds.chunks != chunk]
val_ds = not_test_ds[not_test_ds.chunks == val_chunk]
train_ds = not_test_ds[not_test_ds.chunks != val_chunk]
sbfs.train(train_ds)
train_ds = sbfs(train_ds)
val_ds = sbfs(val_ds)
return train_ds, val_ds
elif (optimize == 0):
train_ds = ds[ds.chunks != chunk]
test_ds = ds[ds.chunks == chunk]
sbfs.train(train_ds)
train_ds = sbfs(train_ds)
test_ds = sbfs(test_ds)
return train_ds, test_ds
def nf_select(nf):
#this function is for selecting the number of voxels (i.e., voxels = features)
#probably overkill to wrap twice
fselector = mvpa2.FixedNElementTailSelector(np.round(nf), tail='upper',mode='select', sort=False)
sbfs = mvpa2.SensitivityBasedFeatureSelection(mvpa2.OneWayAnova(), fselector, enable_ca=['sensitivities'], auto_train=True)
if(optimize>=1):
not_test_ds = ds[ds.chunks!=chunk]
val_ds = not_test_ds[not_test_ds.chunks==val_chunk]
train_ds = not_test_ds[not_test_ds.chunks!=val_chunk]
sbfs.train(train_ds)
train_ds = sbfs(train_ds)
val_ds = sbfs(val_ds)
return train_ds, val_ds;
elif(optimize==0):
train_ds = ds[ds.chunks!=chunk]
test_ds = ds[ds.chunks==chunk]
sbfs.train(train_ds)
train_ds = sbfs(train_ds)
test_ds = sbfs(test_ds)
return train_ds, test_ds;
# REDUCE TO CLASS LABELS, AND ONLY KEEP CONDITIONS OF INTEREST (KEEP VS SWITCH)
dataset.targets = [t[0] for t in dataset.targets]
dataset = dataset[N.array([l in ['k', 's'] for l in dataset.sa.targets],
dtype='bool')]
print '... and only', dataset.shape[
0], 'cases of interest (Keep vs Switch Language)'
dataset = M.datasets.miscfx.remove_invariant_features(dataset)
print 'saving as compressed file', trimmedCache
pickleFile = gzip.open(trimmedCache, 'wb', 5)
pickle.dump(dataset, pickleFile)
anovaSelectedSMLR = M.FeatureSelectionClassifier(
M.PLR(),
M.SensitivityBasedFeatureSelection(
M.OneWayAnova(),
M.FixedNElementTailSelector(500, mode='select', tail='upper')),
)
foldwiseCvedAnovaSelectedSMLR = M.CrossValidation(
anovaSelectedSMLR,
M.NFoldPartitioner(),
enable_ca=['samples_error', 'stats', 'calling_time', 'confusion'])
# run classifier
print 'learning on detrended, normalised, averaged, Keep vs Switch ...', datetime.datetime.now(
)
results = foldwiseCvedAnovaSelectedSMLR(dataset)
print '... done', datetime.datetime.now()
print 'accuracy', N.round(100 - N.mean(results) * 100,
1), '%', datetime.datetime.now()
#New lines for out putting the result into a csv file.
precision = N.round(100 - N.mean(results) * 100, 1)