def decode_voxels():
assembly = load_voxels()
cross_validation = CrossValidationSingle(splits=1,
split_coord='stimulus_id',
stratification_coord='story')
subjects = list(sorted(set(assembly['subject_UID'].values)))
scores = []
for subject in subjects:
subject_index = [
subject == coord_subject
for coord_subject in assembly['subject_UID'].values
]
subject_assembly = assembly[{'neuroid': subject_index}]
subject_score = cross_validation(subject_assembly, apply=fit_decode)
subject_score = subject_score.sel(
aggregation='center') # since we're only doing one split
print(
f"subject {subject}: "
f"{subject_score.sel(accuracy_aggregation='center', train_test='train').values:.2f} train, "
f"{subject_score.sel(accuracy_aggregation='center', train_test='test').values:.2f} test"
)
subject_score = subject_score.expand_dims('subject')
subject_score['subject'] = [subject]
scores.append(subject_score)
scores = Score.merge(*scores)
return scores
def fROI_correlation():
assembly = load_voxels()
stories = list(sorted(set(assembly['story'].values)))
subjects = list(sorted(set(assembly['subject_UID'].values)))
split_scores = []
correlate = pearsonr_correlation(xarray_kwargs=dict(correlation_coord='stimulus_id', neuroid_coord='fROI_area'))
cross_stories_subjects = list(itertools.product(stories, subjects))
for story, heldout_subject in tqdm(cross_stories_subjects, desc='cross-{story,subject}'):
story_assembly = assembly[{'presentation': [coord_story == story for coord_story in assembly['story'].values]}]
subject_pool = story_assembly[{'neuroid': [subject != heldout_subject
for subject in story_assembly['subject_UID'].values]}]
subject_pool = average_subregions(subject_pool)
heldout = story_assembly[{'neuroid': [subject == heldout_subject
for subject in story_assembly['subject_UID'].values]}]
heldout = average_subregions(heldout)
split_score = correlate(subject_pool, heldout)
split_score = type(split_score)(split_score.values, coords={
coord: (dims, values) for coord, dims, values in walk_coords(split_score)
if not coord.startswith('subject_') and coord != 'neuroid_id'}, dims=split_score.dims)
split_score = split_score.expand_dims('heldout_subject').expand_dims('story')
split_score['heldout_subject'], split_score['story'] = [heldout_subject], [story]
split_scores.append(split_score)
correlation = Score.merge(*split_scores)
correlation = apply_aggregate(lambda scores: scores.mean('neuroid').mean('story'), correlation)
center = correlation.mean('heldout_subject')
error = correlation.std('heldout_subject')
score = Score([center, error], coords={**{'aggregation': ['center', 'error']},
**{coord: (dims, values) for coord, dims, values in walk_coords(center)}},
dims=('aggregation',) + center.dims)
score.attrs[Score.RAW_VALUES_KEY] = correlation.attrs[Score.RAW_VALUES_KEY]
return score
def decode_fROI():
assembly = load_voxels()
assembly = average_subregions(assembly)
cross_validation = CrossValidationSingle(splits=10,
split_coord='stimulus_id',
stratification_coord='story')
score = cross_validation(assembly, apply=fit_decode)
return score
def _load_assembly(self, bold_shift):
assembly = load_voxels(bold_shift_seconds=bold_shift)
return assembly