def load_time_meta():
data_dir = neural_data_dir / 'StoriesData_Dec2018' / 'stories_textgridsbyJeanne'
files = data_dir.glob("*TextGrid*")
time_to_words = []
for file in files:
textgrid = TextGrid.load(file)
words = [tier for tier in textgrid.tiers if tier.nameid == 'words'][0]
rows = defaultdict(list)
for (time_start, time_end, word) in words.simple_transcript:
rows['time_start'].append(float(time_start))
rows['time_end'].append(float(time_end))
rows['word'].append(word)
story_index = int(file.stem)
story = stories_meta.sel(number=story_index).values
story = next(iter(set(story))) # Boar was read twice
rows = DataArray(rows['word'],
coords={
'filepath':
('time_bin', [file.name] * len(rows['word'])),
'story':
('time_bin', [story] * len(rows['word'])),
'time_start': ('time_bin', rows['time_start']),
'time_end': ('time_bin', rows['time_end']),
},
dims=['time_bin'])
gather_indexes(rows)
time_to_words.append(rows)
time_to_words = merge_data_arrays(time_to_words)
return time_to_words
def _merge_voxel_meta(data, meta, bold_shift_seconds):
data_missing = set(meta['story'].values) - set(data['story'].values)
if data_missing:
warnings.warn(f"Stories missing from the data: {data_missing}")
meta_missing = set(data['story'].values) - set(meta['story'].values)
if meta_missing:
warnings.warn(f"Stories missing from the meta: {meta_missing}")
ignored_words = [None, '', '<s>', '</s>', '<s']
annotated_data = []
for story in tqdm(ordered_set(data['story'].values), desc='merge meta'):
if story not in meta['story'].values:
continue
story_meta = meta.sel(story=story)
story_meta = story_meta.sortby('time_end')
story_data = data.sel(story=story).stack(timepoint=['timepoint_value'])
story_data = story_data.sortby('timepoint_value')
timepoints = story_data['timepoint_value'].values.tolist()
assert is_sorted(timepoints)
timepoints = [
timepoint - bold_shift_seconds for timepoint in timepoints
]
sentences = []
last_timepoint = -np.inf
for timepoint in timepoints:
if last_timepoint >= max(story_meta['time_end'].values):
break
if timepoint <= 0:
sentences.append(None)
continue # ignore fixation period
timebin_meta = [
last_timepoint < end <= timepoint
for end in story_meta['time_end'].values
]
timebin_meta = story_meta[{'time_bin': timebin_meta}]
sentence = ' '.join(word.strip() for word in timebin_meta.values
if word not in ignored_words)
sentence = sentence.lower().strip()
# quick-fixes
if story == 'Boar' and sentence == 'interactions the the': # Boar duplicate
sentence = 'interactions the'
if story == 'KingOfBirds' and sentence == 'the fact that the larger': # missing word in TextGrid
sentence = 'earth ' + sentence
if story == 'MrSticky' and sentence == 'worry don\'t worry i went extra slowly since it\'s':
sentence = 'don\'t worry i went extra slowly since it\'s'
sentences.append(sentence)
last_timepoint = timebin_meta['time_end'].values[-1]
sentence_index = [
i for i, sentence in enumerate(sentences) if sentence
]
sentences = np.array(sentences)[sentence_index]
if story not in ['Boar', 'KingOfBirds',
'MrSticky']: # ignore quick-fixes
annotated_sentence = ' '.join(sentences)
meta_sentence = ' '.join(word.strip() for word in story_meta.values if word not in ignored_words) \
.lower().strip()
assert annotated_sentence == meta_sentence
# re-interpret timepoints as stimuli
coords = {}
for coord_name, dims, coord_value in walk_coords(story_data):
dims = [
dim if not dim.startswith('timepoint') else 'presentation'
for dim in dims
]
# discard the timepoints for which the stimulus did not change (empty word)
coord_value = coord_value if not array_is_element(
dims, 'presentation') else coord_value[sentence_index]
coords[coord_name] = dims, coord_value
coords = {
**coords,
**{
'stimulus_sentence': ('presentation', sentences)
}
}
story_data = story_data[{
dim: slice(None) if dim != 'timepoint' else sentence_index
for dim in story_data.dims
}]
dims = [
dim if not dim.startswith('timepoint') else 'presentation'
for dim in story_data.dims
]
story_data = xr.DataArray(story_data.values, coords=coords, dims=dims)
story_data['story'] = 'presentation', [story] * len(
story_data['presentation'])
gather_indexes(story_data)
annotated_data.append(story_data)
annotated_data = merge_data_arrays(annotated_data)
return annotated_data
def load_voxel_data(bold_shift_seconds=4):
data = load_filtered_voxel_timepoints()
gather_indexes(data)
meta = load_time_meta()
annotated_data = _merge_voxel_meta(data, meta, bold_shift_seconds)
return annotated_data
def load_filtered_voxel_timepoints():
data = load_voxel_timepoints()
data = data.sel(threshold='from90to100')
gather_indexes(data)
data = data.sel(subject_nStories=8)
return data
'time_with_fixation':
('story', [338, 318, 394, 396, 302, 410, 348, 394, 388, 422, 338]),
'time_without_fixation': ('story', [
5 * 60 + 6, 4 * 60 + 46, 6 * 60 + 2, 6 * 60 + 4, 4 * 60 + 30,
6 * 60 + 18, 5 * 60 + 16, 6 * 60 + 2, 5 * 60 + 56, 6 * 60 + 30,
5 * 60 + 6
]),
'recording_timepoints':
('story', [169, 159, 197, 198, 151, 205, 174, 197, 194, 211, 169])
},
dims=['story'])
stories_meta['story_index'] = 'story', [
".".join([str(value) for value in values]) for values in zip(
*[stories_meta[coord].values for coord in ['story_name', 'reader']])
]
gather_indexes(stories_meta)
def _merge_voxel_meta(data, meta, bold_shift_seconds):
data_missing = set(meta['story'].values) - set(data['story'].values)
if data_missing:
warnings.warn(f"Stories missing from the data: {data_missing}")
meta_missing = set(data['story'].values) - set(meta['story'].values)
if meta_missing:
warnings.warn(f"Stories missing from the meta: {meta_missing}")
ignored_words = [None, '', '<s>', '</s>', '<s']
annotated_data = []
for story in tqdm(ordered_set(data['story'].values), desc='merge meta'):
if story not in meta['story'].values:
continue