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 save_lifespans(self):
util.dump(self.out_dir / 'evaluations.pickle',
last_alive_indices=self.last_alive_indices,
well_index=self.well_index)
lifespans = estimate_lifespans.last_alive_indices_to_lifespans(self.last_alive_indices, self.ages)
lifespans_out = [('well name', 'lifespan')] + [(wn, str(ls)) for wn, ls in zip(self.well_names, lifespans)]
util.dump_csv(lifespans_out, self.out_dir/'evaluated_lifespans.csv')
def save_status(self):
util.dump(self.out_dir / 'statuses.pickle',
statuses=self.statuses,
well_names=self.well_names,
status_codes=self.status_codes,
well_index=self.well_index)
status_out = [('well name', 'status')] + [(wn, self.status_codes[i]) for wn, i in zip(self.well_names, self.statuses)]
util.dump_csv(status_out, self.out_dir/'evaluated_statuses.csv')
def calculate_lifespans(scored_dir, training_data):
"""Once well images have been scored, estimate worm lifespans.
Parameters:
scored_dir: corresponds to out_dir parameter to process_image_dir() --
the parent directory of all of the extracted and scored images.
training_data: paths to one or more training data files with calibration information.
"""
scored_dir = pathlib.Path(scored_dir)
data = load_data(scored_dir)
training = load_training_data(training_data)
states = estimate_lifespans.simple_hmm(data.scores, data.ages,
training.lifespans, training.ages, training.scores, training.states,
lifespan_sigma=6)[0]
# states = estimate_lifespans.estimate_lifespans(data.scores, data.ages, training.states, training.scores, training.ages)
lifespans = estimate_lifespans.states_to_lifespans(states, data.ages)
last_alive_indices = estimate_lifespans.states_to_last_alive_indices(states)
lifespans_out = [('well name', 'lifespan')]+[(well_name, str(lifespan)) for well_name, lifespan in zip(data.well_names, lifespans)]
util.dump_csv(lifespans_out, scored_dir/'lifespans.csv')
util.dump(scored_dir/'lifespans.pickle', well_names=data.well_names, ages=data.ages, states=states,
lifespans=lifespans, last_alive_indices=last_alive_indices)