Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Add read_labels

This commit is contained in:
Matthew Honnibal 2020-09-30 16:52:27 +02:00
parent bc61691f6f
commit e58dca3028
1 changed files with 9 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
spacy/training/corpus.py
View File

@ -43,6 +43,15 @@ def create_jsonl_reader(
return JsonlTexts(path, min_length=min_length, max_length=max_length, limit=limit) return JsonlTexts(path, min_length=min_length, max_length=max_length, limit=limit)
@util.registry.readers("spacy.read_labels.v1")
def read_labels(path: Path, *, require: bool=False):
# I decided not to give this a generic name, because I don't want people to
# use it for arbitrary stuff, as I want this require arg with default False.
if not require and not path.exists():
return None
return srsly.read_json(path)
def walk_corpus(path: Union[str, Path], file_type) -> List[Path]: def walk_corpus(path: Union[str, Path], file_type) -> List[Path]:
path = util.ensure_path(path) path = util.ensure_path(path)
if not path.is_dir() and path.parts[-1].endswith(file_type): if not path.is_dir() and path.parts[-1].endswith(file_type):