class ActiveLearner:
def __init__(self, email, password, api_endpoint, project_id):
kauth = KiliAuth(email, password, api_endpoint=api_endpoint)
self.playground = Playground(kauth)
self.project_id = project_id
def get_assets_to_evaluate(self):
assets = self.playground.assets(project_id=self.project_id)
assets_to_evaluate = []
for asset in assets:
if len(asset['labels']) == 0:
assets_to_evaluate.append(asset)
return assets_to_evaluate
def prioritize_assets(self, assets, scorer, *args, **kwargs):
assets_score = [scorer(asset, *args, **kwargs) for asset in assets]
ranked_assets_with_score = sorted(list(zip(assets, assets_score)),
key=lambda x: x[1],
reverse=True)
ranked_assets = [
asset_with_score[0]
for asset_with_score in ranked_assets_with_score
]
return ranked_assets
def update_assets_priority(self, assets):
for i, asset in enumerate(tqdm(assets)):
asset_id = asset['id']
self.playground.update_properties_in_asset(asset_id=asset_id,
priority=i)
return True
def main(api_endpoint):
email = input('Enter email: ')
password = getpass.getpass()
project_id = input('Enter project id: ')
with open('./conf/new_assets.yml', 'r') as f:
configuration = yaml.safe_load(f)
assets = configuration['assets']
kauth = KiliAuth(email, password, api_endpoint)
playground = Playground(kauth)
project = playground.get_project(project_id=project_id)
roles = get(project, 'roles')
for asset in tqdm(assets):
external_id = get(asset, 'externalId')
to_be_labeled_by = [
get(user, 'email') for user in get(asset, 'toBeLabeledBy')
]
asset = get_asset_by_external_id(playground, project_id, external_id)
asset_id = get(asset, 'id')
playground.update_properties_in_asset(
asset_id=asset_id, to_be_labeled_by=to_be_labeled_by)
for name in files
]
kauth = KiliAuth(email=email, password=password)
playground = Playground(kauth)
for filepath in tqdm(only_files[:MAX_NUMBER_OF_ASSET]):
with open(filepath, 'r') as f:
content = f.read()
external_id = filepath
# Insert asset
playground.append_to_dataset(project_id=project_id,
content=escape_content(content),
external_id=external_id)
asset = playground.get_assets_(project_id=project_id,
external_id_contains=[external_id])
asset_id = asset[0]['id']
# Prioritize assets
playground.update_properties_in_asset(asset_id=asset_id, priority=1)
# Insert pre-annotations
response = analyze_entities(content)
entities = [
e for e in response['entities']
if isinstance(e['type'], str) and e['type'] != 'OTHER'
]
json_response = {'entities': add_id_to_entities(entities)}
playground.create_prediction(asset_id=asset_id,
json_response=json_response)
