mirror of https://github.com/doccano/doccano.git
pythonannotation-tooldatasetsactive-learningtext-annotationdatasetnatural-language-processingdata-labelingmachine-learning
You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
39 lines
1.3 KiB
39 lines
1.3 KiB
from typing import Type
|
|
|
|
from projects.models import (
|
|
DOCUMENT_CLASSIFICATION,
|
|
SEQUENCE_LABELING,
|
|
SEQ2SEQ,
|
|
SPEECH2TEXT,
|
|
IMAGE_CLASSIFICATION,
|
|
INTENT_DETECTION_AND_SLOT_FILLING,
|
|
)
|
|
from . import catalog, repositories, writers
|
|
|
|
|
|
def create_repository(project):
|
|
mapping = {
|
|
DOCUMENT_CLASSIFICATION: repositories.TextClassificationRepository,
|
|
SEQUENCE_LABELING: repositories.SequenceLabelingRepository,
|
|
SEQ2SEQ: repositories.Seq2seqRepository,
|
|
IMAGE_CLASSIFICATION: repositories.FileRepository,
|
|
SPEECH2TEXT: repositories.Speech2TextRepository,
|
|
INTENT_DETECTION_AND_SLOT_FILLING: repositories.IntentDetectionSlotFillingRepository,
|
|
}
|
|
if project.project_type not in mapping:
|
|
ValueError(f"Invalid project type: {project.project_type}")
|
|
repository = mapping[project.project_type](project)
|
|
return repository
|
|
|
|
|
|
def create_writer(file_format: str) -> Type[writers.BaseWriter]:
|
|
mapping = {
|
|
catalog.CSV.name: writers.CsvWriter,
|
|
catalog.JSON.name: writers.JSONWriter,
|
|
catalog.JSONL.name: writers.JSONLWriter,
|
|
catalog.FastText.name: writers.FastTextWriter,
|
|
catalog.IntentAndSlot.name: writers.IntentAndSlotWriter,
|
|
}
|
|
if file_format not in mapping:
|
|
ValueError(f"Invalid format: {file_format}")
|
|
return mapping[file_format]
|