def train_model_for_dirty_field(task: ExtendedTask, dirty_field_id: Any) -> None:
dirty_field = DocumentField.objects.get(pk=dirty_field_id)
if dirty_field.can_retrain():
dirty_field.dirty = False
dirty_field.save()
train_docs_count = field_detection_utils.get_approved_documents_number(dirty_field, None)
if train_docs_count >= dirty_field.trained_after_documents_number:
new_model = field_detection.train_document_field_detector_model(CeleryTaskLogger(task),
dirty_field,
None)
if new_model:
ClassifierModel.objects.filter(document_field=dirty_field).delete()
new_model.save()
def train_model_for_dirty_field(task: ExtendedTask, dirty_field_id: Any) -> None:
dirty_field = DocumentTypeField.objects \
.filter(pk=dirty_field_id) \
.prefetch_related('document_type', 'document_field')[0]
if dirty_field.can_retrain():
dirty_field.dirty = False
dirty_field.save()
document_type = dirty_field.document_type
field = dirty_field.document_field
train_docs_count = field_detection_utils.get_approved_documents_number(document_type, field, None)
if train_docs_count >= settings.ML_TRAIN_DATA_SET_GROUP_LEN:
new_model = field_detection.train_document_field_detector_model(CeleryTaskLogger(task),
document_type, field, None)
if new_model:
ClassifierModel.objects.filter(document_type=document_type, document_field=field).delete()
new_model.save()