def _migrate_tasks(project_path, project):
""" Migrate tasks from json file to database objects"""
tasks_path = project_path / 'tasks.json'
with io.open(os.path.abspath(tasks_path)) as t:
tasks_data = json.load(t)
for task_id, task_data in tasks_data.items():
task = Task.objects.create(data=task_data.get('data', {}),
project=project)
# migrate annotations
annotations_path = project_path / 'completions' / '{}.json'.format(
task_id)
if annotations_path.exists():
with io.open(os.path.abspath(annotations_path)) as c:
annotations_data = json.load(c)
for annotation in annotations_data['completions']:
task_annotation = Annotation(
result=annotation['result'],
task=task,
lead_time=annotation['lead_time'],
was_cancelled=annotation.get(
'was_cancelled', False),
completed_by=project.created_by,
)
with suppress_autotime(task_annotation,
['created_at']):
task_annotation.created_at = datetime.datetime.fromtimestamp(
annotation['created_at'],
tz=datetime.datetime.now().astimezone().tzinfo)
task_annotation.save()
# migrate predictions
predictions_path = project_path / 'predictions' / '{}.json'.format(
task_id)
if predictions_path.exists():
with io.open(os.path.abspath(predictions_path)) as c:
predictions_data = json.load(c)
for prediction in predictions_data['predictions']:
task_prediction = Prediction(
result=prediction['result'], task=task)
with suppress_autotime(task_prediction,
['created_at']):
task_prediction.created_at = datetime.datetime.fromtimestamp(
prediction['created_at'],
tz=datetime.datetime.now().astimezone().tzinfo)
task_prediction.save()
def create(self, request, *args, **kwargs):
# check project permissions
project = self.get_object()
tasks_ids = set(Task.objects.filter(project=project).values_list('id', flat=True))
logger.debug(f'Importing {len(self.request.data)} predictions to project {project} with {len(tasks_ids)} tasks')
predictions = []
for item in self.request.data:
if item.get('task') not in tasks_ids:
raise LabelStudioValidationErrorSentryIgnored(
f'{item} contains invalid "task" field: corresponding task ID couldn\'t be retrieved '
f'from project {project} tasks')
predictions.append(Prediction(
task_id=item['task'],
result=Prediction.prepare_prediction_result(item.get('result'), project),
score=item.get('score'),
model_version=item.get('model_version', 'undefined')
))
predictions_obj = Prediction.objects.bulk_create(predictions, batch_size=settings.BATCH_SIZE)
return Response({'created': len(predictions_obj)}, status=status.HTTP_201_CREATED)
def create(self, validated_data):
""" Create Tasks and Annotations in bulk
"""
db_tasks, db_annotations, db_predictions, validated_tasks = [], [], [], validated_data
logging.info(
f'Try to serialize tasks with annotations, data len = {len(validated_data)}'
)
user = self.context.get('user', None)
project = self.context.get('project')
# to be sure we add tasks with annotations at the same time
with transaction.atomic():
# extract annotations and predictions
task_annotations, task_predictions = [], []
for task in validated_tasks:
task_annotations.append(task.pop('annotations', []))
task_predictions.append(task.pop('predictions', []))
# check annotator permissions for completed by
organization = user.active_organization \
if not project.created_by.active_organization else project.created_by.active_organization
project_user_ids = organization.members.values_list('user__id',
flat=True)
annotator_ids = set()
for annotations in task_annotations:
for annotation in annotations:
annotator_ids.add(self.get_completed_by_id(annotation))
for i in annotator_ids:
if i not in project_user_ids and i is not None:
raise ValidationError(
f'Annotations with "completed_by"={i} are produced by annotator '
f'who is not allowed for this project as invited annotator or team member'
)
# add tasks first
for task in validated_tasks:
t = Task(project=project,
data=task['data'],
meta=task.get('meta', {}),
overlap=project.maximum_annotations,
file_upload_id=task.get('file_upload_id'))
db_tasks.append(t)
if settings.DJANGO_DB == settings.DJANGO_DB_SQLITE:
self.db_tasks = []
try:
last_task = Task.objects.latest('id')
current_id = last_task.id + 1
except Task.DoesNotExist:
current_id = 1
for task in db_tasks:
task.id = current_id
current_id += 1
self.db_tasks = Task.objects.bulk_create(
db_tasks, batch_size=settings.BATCH_SIZE)
else:
self.db_tasks = Task.objects.bulk_create(
db_tasks, batch_size=settings.BATCH_SIZE)
logging.info(
f'Tasks serialization success, len = {len(self.db_tasks)}')
# add annotations
for i, annotations in enumerate(task_annotations):
for annotation in annotations:
# support both "ground_truth" and "ground_truth"
ground_truth = annotation.pop('ground_truth', True)
if 'ground_truth' in annotation:
ground_truth = annotation.pop('ground_truth', True)
# get user id
completed_by_id = self.get_completed_by_id(
annotation, default=user.id if user else None)
annotation.pop('completed_by', None)
db_annotations.append(
Annotation(task=self.db_tasks[i],
ground_truth=ground_truth,
completed_by_id=completed_by_id,
result=annotation['result']))
# add predictions
last_model_version = None
for i, predictions in enumerate(task_predictions):
for prediction in predictions:
prediction_score = prediction.get('score')
if prediction_score is not None:
try:
prediction_score = float(prediction_score)
except ValueError as exc:
logger.error(
f'Can\'t upload prediction score: should be in float format. Reason: {exc}.'
f'Fallback to score=None',
exc_info=True)
prediction_score = None
last_model_version = prediction.get(
'model_version', 'undefined')
db_predictions.append(
Prediction(task=self.db_tasks[i],
result=prediction['result'],
score=prediction_score,
model_version=last_model_version))
# annotations: DB bulk create
if settings.DJANGO_DB == settings.DJANGO_DB_SQLITE:
self.db_annotations = []
try:
last_annotation = Annotation.objects.latest('id')
current_id = last_annotation.id + 1
except Annotation.DoesNotExist:
current_id = 1
for annotation in db_annotations:
annotation.id = current_id
current_id += 1
self.db_annotations = Annotation.objects.bulk_create(
db_annotations, batch_size=settings.BATCH_SIZE)
else:
self.db_annotations = Annotation.objects.bulk_create(
db_annotations, batch_size=settings.BATCH_SIZE)
logging.info(
f'Annotations serialization success, len = {len(self.db_annotations)}'
)
# predictions: DB bulk create
self.db_predictions = Prediction.objects.bulk_create(
db_predictions, batch_size=settings.BATCH_SIZE)
logging.info(
f'Predictions serialization success, len = {len(self.db_predictions)}'
)
# renew project model version if it's empty
if not project.model_version and last_model_version is not None:
project.model_version = last_model_version
project.save()
return db_tasks
def create(self, validated_data):
""" Create Tasks and Annotations in bulk
"""
db_tasks, db_annotations, db_predictions, validated_tasks = [], [], [], validated_data
logging.info(
f'Try to serialize tasks with annotations, data len = {len(validated_data)}'
)
user = self.context.get('user', None)
project = self.context.get('project')
organization = user.active_organization \
if not project.created_by.active_organization else project.created_by.active_organization
members_email_to_id = dict(
organization.members.values_list('user__email', 'user__id'))
members_ids = set(members_email_to_id.values())
logger.debug(
f"{len(members_email_to_id)} members found in organization {organization}"
)
# to be sure we add tasks with annotations at the same time
with transaction.atomic():
# extract annotations and predictions
task_annotations, task_predictions = [], []
for task in validated_tasks:
annotations = task.pop('annotations', [])
# insert a valid "completed_by_id" by existing member
self._insert_valid_completed_by_id_or_raise(
annotations, members_email_to_id, members_ids, user
or project.created_by)
predictions = task.pop('predictions', [])
task_annotations.append(annotations)
task_predictions.append(predictions)
# add tasks first
for task in validated_tasks:
t = Task(project=project,
data=task['data'],
meta=task.get('meta', {}),
overlap=project.maximum_annotations,
file_upload_id=task.get('file_upload_id'))
db_tasks.append(t)
# deprecated meta warning
if 'meta' in task:
logger.warning(
'You task data has field "meta" which is deprecated and it will be removed in future'
)
if settings.DJANGO_DB == settings.DJANGO_DB_SQLITE:
self.db_tasks = []
try:
last_task = Task.objects.latest('id')
current_id = last_task.id + 1
except Task.DoesNotExist:
current_id = 1
for task in db_tasks:
task.id = current_id
current_id += 1
self.db_tasks = Task.objects.bulk_create(
db_tasks, batch_size=settings.BATCH_SIZE)
else:
self.db_tasks = Task.objects.bulk_create(
db_tasks, batch_size=settings.BATCH_SIZE)
logging.info(
f'Tasks serialization success, len = {len(self.db_tasks)}')
# add annotations
for i, annotations in enumerate(task_annotations):
for annotation in annotations:
# support both "ground_truth" and "ground_truth"
ground_truth = annotation.pop('ground_truth', True)
was_cancelled = annotation.pop('was_cancelled', False)
db_annotations.append(
Annotation(
task=self.db_tasks[i],
ground_truth=ground_truth,
was_cancelled=was_cancelled,
completed_by_id=annotation['completed_by_id'],
result=annotation['result']))
# add predictions
last_model_version = None
for i, predictions in enumerate(task_predictions):
for prediction in predictions:
prediction_score = prediction.get('score')
if prediction_score is not None:
try:
prediction_score = float(prediction_score)
except ValueError as exc:
logger.error(
f'Can\'t upload prediction score: should be in float format. Reason: {exc}.'
f'Fallback to score=None',
exc_info=True)
prediction_score = None
last_model_version = prediction.get(
'model_version', 'undefined')
db_predictions.append(
Prediction(task=self.db_tasks[i],
result=prediction['result'],
score=prediction_score,
model_version=last_model_version))
# annotations: DB bulk create
if settings.DJANGO_DB == settings.DJANGO_DB_SQLITE:
self.db_annotations = []
try:
last_annotation = Annotation.objects.latest('id')
current_id = last_annotation.id + 1
except Annotation.DoesNotExist:
current_id = 1
for annotation in db_annotations:
annotation.id = current_id
current_id += 1
self.db_annotations = Annotation.objects.bulk_create(
db_annotations, batch_size=settings.BATCH_SIZE)
else:
self.db_annotations = Annotation.objects.bulk_create(
db_annotations, batch_size=settings.BATCH_SIZE)
logging.info(
f'Annotations serialization success, len = {len(self.db_annotations)}'
)
# predictions: DB bulk create
self.db_predictions = Prediction.objects.bulk_create(
db_predictions, batch_size=settings.BATCH_SIZE)
logging.info(
f'Predictions serialization success, len = {len(self.db_predictions)}'
)
# renew project model version if it's empty
if not project.model_version and last_model_version is not None:
project.model_version = last_model_version
project.save()
return db_tasks
def create(self, validated_data):
""" Create Tasks and Annotations in bulk
"""
db_tasks, db_annotations, db_predictions, validated_tasks = [], [], [], validated_data
logging.info(f'Try to serialize tasks with annotations, data len = {len(validated_data)}')
user = self.context.get('user', None)
organization = user.active_organization \
if not self.project.created_by.active_organization else self.project.created_by.active_organization
members_email_to_id = dict(organization.members.values_list('user__email', 'user__id'))
members_ids = set(members_email_to_id.values())
logger.debug(f"{len(members_email_to_id)} members found in organization {organization}")
# to be sure we add tasks with annotations at the same time
with transaction.atomic():
# extract annotations and predictions
task_annotations, task_predictions = [], []
for task in validated_tasks:
annotations = task.pop('annotations', [])
# insert a valid "completed_by_id" by existing member
self._insert_valid_completed_by_id_or_raise(
annotations, members_email_to_id, members_ids, user or self.project.created_by)
predictions = task.pop('predictions', [])
task_annotations.append(annotations)
task_predictions.append(predictions)
# add tasks first
max_overlap = self.project.maximum_annotations
# identify max inner id
tasks = Task.objects.filter(project=self.project)
max_inner_id = (tasks.order_by("-inner_id")[0].inner_id + 1) if tasks else 1
for i, task in enumerate(validated_tasks):
t = Task(
project=self.project,
data=task['data'],
meta=task.get('meta', {}),
overlap=max_overlap,
is_labeled=len(task_annotations[i]) >= max_overlap,
file_upload_id=task.get('file_upload_id'),
inner_id=max_inner_id + i
)
db_tasks.append(t)
if settings.DJANGO_DB == settings.DJANGO_DB_SQLITE:
self.db_tasks = []
try:
last_task = Task.objects.latest('id')
current_id = last_task.id + 1
except Task.DoesNotExist:
current_id = 1
for task in db_tasks:
task.id = current_id
current_id += 1
self.db_tasks = Task.objects.bulk_create(db_tasks, batch_size=settings.BATCH_SIZE)
else:
self.db_tasks = Task.objects.bulk_create(db_tasks, batch_size=settings.BATCH_SIZE)
logging.info(f'Tasks serialization success, len = {len(self.db_tasks)}')
# add annotations
for i, annotations in enumerate(task_annotations):
for annotation in annotations:
if not isinstance(annotation, dict):
continue
# support both "ground_truth" and "ground_truth"
ground_truth = annotation.pop('ground_truth', True)
was_cancelled = annotation.pop('was_cancelled', False)
lead_time = annotation.pop('lead_time', None)
db_annotations.append(Annotation(task=self.db_tasks[i],
ground_truth=ground_truth,
was_cancelled=was_cancelled,
completed_by_id=annotation['completed_by_id'],
result=annotation['result'],
lead_time=lead_time))
# add predictions
last_model_version = None
for i, predictions in enumerate(task_predictions):
for prediction in predictions:
if not isinstance(prediction, dict):
continue
# we need to call result normalizer here since "bulk_create" doesn't call save() method
result = Prediction.prepare_prediction_result(prediction['result'], self.project)
prediction_score = prediction.get('score')
if prediction_score is not None:
try:
prediction_score = float(prediction_score)
except ValueError as exc:
logger.error(
f'Can\'t upload prediction score: should be in float format. Reason: {exc}.'
f'Fallback to score=None', exc_info=True)
prediction_score = None
last_model_version = prediction.get('model_version', 'undefined')
db_predictions.append(Prediction(task=self.db_tasks[i],
result=result,
score=prediction_score,
model_version=last_model_version))
# annotations: DB bulk create
if settings.DJANGO_DB == settings.DJANGO_DB_SQLITE:
self.db_annotations = []
try:
last_annotation = Annotation.objects.latest('id')
current_id = last_annotation.id + 1
except Annotation.DoesNotExist:
current_id = 1
for annotation in db_annotations:
annotation.id = current_id
current_id += 1
self.db_annotations = Annotation.objects.bulk_create(db_annotations, batch_size=settings.BATCH_SIZE)
else:
self.db_annotations = Annotation.objects.bulk_create(db_annotations, batch_size=settings.BATCH_SIZE)
logging.info(f'Annotations serialization success, len = {len(self.db_annotations)}')
# predictions: DB bulk create
self.db_predictions = Prediction.objects.bulk_create(db_predictions, batch_size=settings.BATCH_SIZE)
logging.info(f'Predictions serialization success, len = {len(self.db_predictions)}')
# renew project model version if it's empty
if not self.project.model_version and last_model_version is not None:
self.project.model_version = last_model_version
self.project.save()
self.post_process_annotations(self.db_annotations)
return db_tasks