def test_loader_nonexistent():
text_file = 'this/doesnt/exist.txt'
with pytest.raises(IOError):
stims = load_stims(text_file)
audio_file = 'no/audio/here.wav'
with pytest.raises(IOError):
stims = load_stims([text_file, audio_file])
text_file = join(get_test_data_path(), 'text', 'sample_text.txt')
stims = load_stims([text_file, audio_file], fail_silently=True)
assert len(stims) == 1
with pytest.raises(IOError):
stims = load_stims(audio_file, fail_silently=True)
def clean_transcript(input_transcript, input_media, onset=None, offset=None):
stim = load_stims([input_media])[0]
if not isinstance(stim, AudioStim):
conv = VideoToAudioConverter()
stim = conv.transform(stim)
input_media = '/tmp/input_audio.wav'
stim.save(input_media)
_, extension = splitext(input_transcript)
clean_transcript = '/tmp/clean_transcript.txt'
with open(clean_transcript, 'w') as new_file:
if extension == 'srt':
txt = ComplexTextStim(input_transcript)
for el in txt.elements:
_clean_save(el.text, new_file, el.onset, el.duration)
else: # Treat as a singe block of text
if onset is None or offset is None:
raise Exception("Onset and offset must be declared")
txt = TextStim(input_transcript)
_clean_save(txt.text, new_file, onset, stim.duration - offset)
return clean_transcript, input_media
def hash_stim(stim, blocksize=65536):
""" Hash a pliers stimulus """
if isinstance(stim, Path):
stim = stim.as_posix()
if isinstance(stim, str):
from pliers.stimuli import load_stims
from os.path import isfile
assert isfile(stim)
stim = load_stims(stim)
hasher = hashlib.sha1()
if hasattr(stim, "data"):
return hash_data(stim.data)
else:
filename = stim.history.source_file \
if stim.history \
else stim.filename
with open(filename, 'rb') as afile:
buf = afile.read(blocksize)
while len(buf) > 0:
hasher.update(buf)
buf = afile.read(blocksize)
return hasher.hexdigest()
def test_magic_loader():
text_file = join(get_test_data_path(), 'text', 'sample_text.txt')
audio_file = join(get_test_data_path(), 'audio', 'barber.wav')
video_file = join(get_test_data_path(), 'video', 'small.mp4')
stim_files = [text_file, audio_file, video_file]
stims = load_stims(stim_files)
assert len(stims) == 3
assert round(stims[1].duration) == 57
assert isinstance(stims[0].text, string_types)
assert stims[2].width == 560
def test_magic_loader2():
text_file = join(get_test_data_path(), 'text', 'sample_text.txt')
video_url = 'http://www.obamadownloads.com/videos/iran-deal-speech.mp4'
audio_url = 'http://www.bobainsworth.com/wav/simpsons/themodyn.wav'
image_url = 'https://www.whitehouse.gov/sites/whitehouse.gov/files/images/twitter_cards_potus.jpg'
text_url = 'https://github.com/tyarkoni/pliers/blob/master/README.md'
stims = load_stims([text_file, video_url, audio_url, image_url, text_url])
assert len(stims) == 5
assert stims[1].fps == 12
assert stims[3].data.shape == (240, 240, 3)
def test_magic_loader2():
text_file = join(get_test_data_path(), 'text', 'sample_text.txt')
video_url = 'https://archive.org/download/DisneyCastletest/Disney_Castle_512kb.mp4'
audio_url = 'https://archive.org/download/999WavFiles/TANKEN.WAV'
image_url = 'https://archive.org/download/NIX-C-1987-11903/1987_11903L.jpg'
text_url = 'https://github.com/psychoinformaticslab/pliers/blob/master/README.rst'
stims = load_stims([text_file, video_url, audio_url, image_url, text_url])
assert len(stims) == 5
assert stims[1].fps == 30.0
assert stims[3].data.shape == (288, 360, 3)
def _load_stim_models(dataset_name, task_name):
""" Given a dataset and task, load all available stimuli as Pliers
stimuli, and pair them with original database stim object. """
stim_models = Stimulus.query.filter_by(
active=True).join(RunStimulus).join(Run).join(Task).filter_by(
name=task_name).join(Dataset).filter_by(name=dataset_name)
stims = []
print("Loading stim models...")
for stim_model in progressbar(stim_models):
if stim_model.path is None:
# Load both ways for Text stimuli
stims.append(
(stim_model, ComplexTextStim(text=stim_model.content)))
stims.append((stim_model, TextStim(text=stims[-1][1].data)))
else:
stims.append((stim_model, load_stims(stim_model.path)))
return stims
def check_updates(transformers, datastore=None, stimuli=None):
""" Run transformers through a battery of stimuli, and check if output has
changed. Store results in csv file for comparison.
Args:
transformers (list): A list of tuples of transformer names and
dictionary of parameters to instantiate with (or empty dict).
datastore (str): Filepath of CSV file with results. Stored in home dir
by default.
stimuli (list): List of stimuli file paths to extract from. If None,
use test data.
"""
# Find datastore file
datastore = datastore or expanduser('~/.pliers_updates')
prior_data = pd.read_csv(datastore) if exists(datastore) else None
# Load stimuli
stimuli = stimuli or glob.glob(
join(dirname(realpath(__file__)), '../tests/data/image/CC0/*'))
stimuli = load_stims(stimuli)
# Get transformers
loaded_transformers = {
get_transformer(name, **params): (name, params)
for name, params in transformers
}
# Transform stimuli
results = pd.DataFrame({'time_extracted': [datetime.datetime.now()]})
for trans in loaded_transformers.keys():
for stim in stimuli:
if trans._stim_matches_input_types(stim):
res = trans.transform(stim)
try: # Add iterable
res = [res._data for r in res]
except TypeError:
res = res._data
res = hash_data(res) if isinstance(trans,
(Converter,
Filter)) else res[0][0]
results["{}.{}".format(trans.__hash__(), stim.name)] = [res]
# Check for mismatches
mismatches = []
if prior_data is not None:
last = prior_data[
prior_data.time_extracted == prior_data.time_extracted.max()]. \
iloc[0].drop('time_extracted')
for label, value in results.iteritems():
old = last.get(label)
new = value.values[0]
if old is not None:
if isinstance(new, str):
if new != old:
mismatches.append(label)
elif not np.isclose(old, new):
mismatches.append(label)
results = prior_data.append(results)
results.to_csv(datastore, index=False)
# Get corresponding transformer name and parameters
def get_trans(hash_tr):
for obj, attr in loaded_transformers.items():
if str(obj.__hash__()) == hash_tr:
return attr
delta_t = set([m.split('.')[0] for m in mismatches])
delta_t = [get_trans(dt) for dt in delta_t]
return {'transformers': delta_t, 'mismatches': mismatches}
def convert_stimuli(dataset_name, task_name, converters):
""" Convert stimuli to different modality using pliers.
Args:
dataset_name - dataset name
task_name - task name
converters - dictionary of converter names to parameters
Output:
list of db ids of converted stimuli
"""
print("Converting stimuli")
dataset_id = Dataset.query.filter_by(name=dataset_name).one().id
converters = [get_transformer(n, **p) for n, p in converters]
# Load all active original stimuli for task
stim_objects = Stimulus.query.filter_by(active=True, parent_id=None).join(
RunStimulus).join(Run).join(Task).filter_by(name=task_name).join(
Dataset).filter_by(name=dataset_name)
total_new_stims = []
# Extract new stimuli from original stimuli
for stim in stim_objects:
new_stims = []
# Re-create new RS associations with newly created stims
rs_orig = RunStimulus.query.filter_by(stimulus_id=stim.id).join(
Run).join(Task).filter_by(name=task_name)
loaded_stim = load_stims(stim.path)
# Extract for each converter
for conv in converters:
results = []
# Extract and flatten results (to a single unit)
if conv._stim_matches_input_types(loaded_stim):
cstim = conv.transform(loaded_stim)
try: # Add iterable
results += cstim
except TypeError:
if hasattr(cstim, 'elements'):
results += cstim.elements
else:
results.append(cstim)
results = [res for res in results
if hasattr(res, 'data') and res.data != '']
new_stims += create_new_stimuli(
dataset_id, task_name, stim.id, results, rs_orig,
transformer=cstim.history.transformer_class,
transformer_params=cstim.history.transformer_params)
# De-activate previously generated stimuli from these converters.
update = Stimulus.query.filter_by(parent_id=stim.id).filter(
Stimulus.id.notin_(new_stims),
Stimulus.converter_name == cstim.history.transformer_class,
Stimulus.converter_parameters == cstim.history.transformer_params)
if update.count():
update.update(dict(active=False), synchronize_session='fetch')
db.session.commit()
total_new_stims += new_stims
return total_new_stims
def check_updates(transformers, datastore=None, stimuli=None):
""" Run transformers through a battery of stimuli, and check if output has
changed. Store results in csv file for comparison.
Args:
transformers (list): A list of tuples of transformer names and
dictionary of parameters to instantiate with (or empty dict).
datastore (str): Filepath of CSV file with results. Stored in home dir
by default.
stimuli (list): List of stimuli file paths to extract from. If None,
use test data.
"""
# Find datastore file
datastore = datastore or expanduser('~/.pliers_updates')
prior_data = pd.read_csv(datastore) if exists(datastore) else None
# Load stimuli
stimuli = stimuli or glob.glob(
join(dirname(realpath(__file__)), '../tests/data/image/CC0/*'))
stimuli = load_stims(stimuli)
# Get transformers
loaded_transformers = {get_transformer(name, **params): (name, params)
for name, params in transformers}
# Transform stimuli
results = pd.DataFrame({'time_extracted': [datetime.datetime.now()]})
for trans in loaded_transformers.keys():
for stim in stimuli:
if trans._stim_matches_input_types(stim):
res = trans.transform(stim)
try: # Add iterable
res = [getattr(res, '_data', res.data) for r in res]
except TypeError:
res = getattr(res, '_data', res.data)
res = hash_data(res)
results["{}.{}".format(trans.__hash__(), stim.name)] = [res]
# Check for mismatches
mismatches = []
if prior_data is not None:
last = prior_data[
prior_data.time_extracted == prior_data.time_extracted.max()]. \
iloc[0].drop('time_extracted')
for label, value in results.iteritems():
old = last.get(label)
new = value.values[0]
if old is not None:
if isinstance(new, str):
if new != old:
mismatches.append(label)
elif not np.isclose(old, new):
mismatches.append(label)
results = prior_data.append(results)
results.to_csv(datastore, index=False)
# Get corresponding transformer name and parameters
def get_trans(hash_tr):
for obj, attr in loaded_transformers.items():
if str(obj.__hash__()) == hash_tr:
return attr
delta_t = set([m.split('.')[0] for m in mismatches])
delta_t = [get_trans(dt) for dt in delta_t]
return {'transformers': delta_t, 'mismatches': mismatches}
