explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-08-07 13:44:55 +03:00
Code Issues Packages Projects Releases Wiki Activity

store user data and rename cmd arg

Browse Source
This commit is contained in:
kadarakos 2022-11-23 11:00:39 +00:00
parent b5e08e24bd
commit 74140f5145
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
spacy/cli/apply.py
View File

@ -76,7 +76,7 @@ def apply_cli(
data_path: Path = Arg(..., help=path_help, exists=True), data_path: Path = Arg(..., help=path_help, exists=True),
output_file: Path = Arg(..., help=out_help, dir_okay=False), output_file: Path = Arg(..., help=out_help, dir_okay=False),
code_path: Optional[Path] = Opt(None, "--code", "-c", help=code_help), code_path: Optional[Path] = Opt(None, "--code", "-c", help=code_help),
json_field: str = Opt("text", "--field", "-f", help="Field to grab from .jsonl"), json_field: str = Opt("text", "--json-field", "-jf", help="Field to grab from .jsonl"),
force_overwrite: bool = Opt(False, "--force", "-F", help="Force overwriting the output file"), force_overwrite: bool = Opt(False, "--force", "-F", help="Force overwriting the output file"),
use_gpu: int = Opt(-1, "--gpu-id", "-g", help="GPU ID or -1 for CPU."), use_gpu: int = Opt(-1, "--gpu-id", "-g", help="GPU ID or -1 for CPU."),
batch_size: int = Opt(1, "--batch-size", "-b", help="Batch size."), batch_size: int = Opt(1, "--batch-size", "-b", help="Batch size."),
@ -116,7 +116,7 @@ def apply(
nlp = load_model(model) nlp = load_model(model)
msg.good(f"Loaded model {model}") msg.good(f"Loaded model {model}")
vocab = nlp.vocab vocab = nlp.vocab
docbin = DocBin() docbin = DocBin(store_user_data=True)
paths = walk_directory(data_path) paths = walk_directory(data_path)
streams: List[DocOrStrStream] = [] streams: List[DocOrStrStream] = []
text_files = [] text_files = []