def aggregate_scores(out_dir):
"""Once all images have been scored, aggregate the per-image-set (i.e. per-day)
score data to a single file for the whole experiment.
"""
out_dir = pathlib.Path(out_dir)
well_names = None
all_scores = {}
for scorefile in out_dir.glob('*/scores.pickle'): # find all such files below outdir
scores = util.load(scorefile)
data = util.load(scorefile.parent / 'metadata.pickle')
assert data.well_names == scores.well_names
if well_names is None:
well_names = data.well_names
else:
assert well_names == data.well_names
all_scores[data.date] = data.age, scores.well_scores
assert len(all_scores) > 0 # makes sure there are files to score!
dates, ages_and_scores = zip(*sorted(all_scores.items()))
ages, scores = zip(*ages_and_scores)
ages = numpy.array(ages)
scores = numpy.array(scores).T
data_out = [[''] + [d.isoformat() for d in dates]]
data_out += [[''] + [str(a) for a in ages]]
for well_name, score in zip(well_names, scores):
data_out += [[well_name] + [str(s) for s in score]]
util.dump_csv(data_out, out_dir/'scores.csv')
util.dump(out_dir / 'scores.pickle', dates=dates, ages=ages, well_names=well_names, scores=scores)
def score_image_set(out_dir, score_params, ignore_previous=False):
"""Score wells for a single day's scanned images.
Parameters:
out_dir: directory in which well_images directory is found, and to which score
data will be written.
score_params: configuration information for scoring wells for movement.
This must be a parameter dictionary suitable to pass to score_wells.score_wells()
ignore_previous: if False, and stored results already exist, skip processing
"""
out_dir = pathlib.Path(out_dir)
score_file = out_dir / 'scores.pickle'
if score_file.exists() and not ignore_previous:
return
print('scoring images for {}'.format(out_dir))
well_names = util.load(out_dir / 'metadata.pickle').well_names
well_mask = freeimage.read(str(out_dir.parent / 'well_mask.png')) > 0
well_dir = out_dir / 'well_images'
well_images = []
for well_name in well_names:
images = [freeimage.read(str(image)) for image in sorted(well_dir.glob(well_name+'-*.png'))]
well_images.append(images)
well_scores = score_wells.score_wells(well_images, well_mask, **score_params)
util.dump(score_file, well_names=well_names, well_scores=well_scores)
scores_out = [[name, str(score)] for name, score in zip(well_names, well_scores)]
util.dump_csv(scores_out, out_dir / 'scores.csv')
def load(self):
data = util.load(self.out_dir / 'statuses.pickle')
assert self.status_codes == data.status_codes
assert self.well_names == data.well_names
self.statuses = data.statuses
self.well_index = data.well_index
self.set_well(self.well_index)
def load_data(scored_dir):
"""Load score data, and if available, lifespan data, from a processed directory.
Returns a Data object with attributes:
dates
ages
well_names
scores
and if lifespan data are found, also:
states
lifespans
last_alive_indices
If manually-annotated well-statuses from 'statuses.pickle' are found, also:
eval_well_statuses
If manually-annotated lifespans from 'evaluations.pickle' are found, also:
eval_last_alive_indices
"""
scored_dir = pathlib.Path(scored_dir)
data = util.Data()
scores = util.load(scored_dir / 'scores.pickle')
for name in ('dates', 'ages', 'well_names', 'scores'):
setattr(data, name, getattr(scores, name))
lifespan_data = scored_dir / 'lifespans.pickle'
if lifespan_data.exists():
lifespans = util.load(lifespan_data)
assert numpy.all(scores.ages == lifespans.ages) and scores.well_names == lifespans.well_names
for name in ('states', 'lifespans', 'last_alive_indices'):
setattr(data, name, getattr(lifespans, name))
eval_data = scored_dir / 'evaluations.pickle'
if eval_data.exists():
evaluated = util.load(eval_data)
data.eval_last_alive_indices = evaluated.last_alive_indices
data.eval_lifespans = estimate_lifespans.last_alive_indices_to_lifespans(evaluated.last_alive_indices, data.ages)
status_data = scored_dir / 'statuses.pickle'
if status_data.exists():
statuses = util.load(status_data)
status_codes = [statuses.status_codes[i] for i in statuses.statuses]
status_dict = dict(zip(statuses.well_names, status_codes))
all_statuses = []
for well_name in data.well_names:
if well_name in status_dict:
all_statuses.append(status_dict[well_name])
else:
all_statuses.append(statuses.status_codes[0])
data.eval_well_statuses = all_statuses
return data
def load_training_data(training_data_files):
"""Load data from one or more training data files. If multiple files are provided,
merge their data."""
states, scores, ages, lifespans = [], [], [], []
if isinstance(training_data_files, (str, pathlib.Path)):
training_data_files = [training_data_files]
for training_data in training_data_files:
training = util.load(training_data)
# training.states, training.scores are shape-(n_worms, n_timepoints) arrays
# training.ages is n_timepoints long. We want to flatten both into lists
states.extend(training.states.flat)
scores.extend(training.scores.flat)
ages.extend(list(training.ages) * training.states.shape[0])
training_lifespans = estimate_lifespans.states_to_lifespans(training.states, training.ages)
lifespans.extend(estimate_lifespans.cleanup_lifespans(training_lifespans, training.ages))
training_out = util.Data(states=numpy.array(states), scores=numpy.array(scores),
ages=numpy.array(ages), lifespans=numpy.array(lifespans))
return training_out
def load(self):
data = util.load(self.out_dir / 'evaluations.pickle')
self.last_alive_indices = data.last_alive_indices
self.well_index = data.well_index
self.set_well(self.well_index)
