mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 11:29:13 +03:00
8fc0efc502
* adding unit test for spacy.load with disable/exclude string arg * allow pure strings in from_config * update docs * upstream type adjustements * docs update * make docstring more consistent * Update spacy/language.py Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> * two more cleanups * fix type in internal method Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
83 lines
2.9 KiB
Python
83 lines
2.9 KiB
Python
from typing import Union, Iterable, Dict, Any
|
|
from pathlib import Path
|
|
import sys
|
|
|
|
# set library-specific custom warning handling before doing anything else
|
|
from .errors import setup_default_warnings
|
|
|
|
setup_default_warnings() # noqa: E402
|
|
|
|
# These are imported as part of the API
|
|
from thinc.api import prefer_gpu, require_gpu, require_cpu # noqa: F401
|
|
from thinc.api import Config
|
|
|
|
from . import pipeline # noqa: F401
|
|
from .cli.info import info # noqa: F401
|
|
from .glossary import explain # noqa: F401
|
|
from .about import __version__ # noqa: F401
|
|
from .util import registry, logger # noqa: F401
|
|
|
|
from .errors import Errors
|
|
from .language import Language
|
|
from .vocab import Vocab
|
|
from . import util
|
|
|
|
|
|
if sys.maxunicode == 65535:
|
|
raise SystemError(Errors.E130)
|
|
|
|
|
|
def load(
|
|
name: Union[str, Path],
|
|
*,
|
|
vocab: Union[Vocab, bool] = True,
|
|
disable: Union[str, Iterable[str]] = util.SimpleFrozenList(),
|
|
enable: Union[str, Iterable[str]] = util.SimpleFrozenList(),
|
|
exclude: Union[str, Iterable[str]] = util.SimpleFrozenList(),
|
|
config: Union[Dict[str, Any], Config] = util.SimpleFrozenDict(),
|
|
) -> Language:
|
|
"""Load a spaCy model from an installed package or a local path.
|
|
|
|
name (str): Package name or model path.
|
|
vocab (Vocab): A Vocab object. If True, a vocab is created.
|
|
disable (Union[str, Iterable[str]]): Name(s) of pipeline component(s) to disable. Disabled
|
|
pipes will be loaded but they won't be run unless you explicitly
|
|
enable them by calling nlp.enable_pipe.
|
|
enable (Union[str, Iterable[str]]): Name(s) of pipeline component(s) to enable. All other
|
|
pipes will be disabled (but can be enabled later using nlp.enable_pipe).
|
|
exclude (Union[str, Iterable[str]]): Name(s) of pipeline component(s) to exclude. Excluded
|
|
components won't be loaded.
|
|
config (Dict[str, Any] / Config): Config overrides as nested dict or dict
|
|
keyed by section values in dot notation.
|
|
RETURNS (Language): The loaded nlp object.
|
|
"""
|
|
return util.load_model(
|
|
name,
|
|
vocab=vocab,
|
|
disable=disable,
|
|
enable=enable,
|
|
exclude=exclude,
|
|
config=config,
|
|
)
|
|
|
|
|
|
def blank(
|
|
name: str,
|
|
*,
|
|
vocab: Union[Vocab, bool] = True,
|
|
config: Union[Dict[str, Any], Config] = util.SimpleFrozenDict(),
|
|
meta: Dict[str, Any] = util.SimpleFrozenDict(),
|
|
) -> Language:
|
|
"""Create a blank nlp object for a given language code.
|
|
|
|
name (str): The language code, e.g. "en".
|
|
vocab (Vocab): A Vocab object. If True, a vocab is created.
|
|
config (Dict[str, Any] / Config): Optional config overrides.
|
|
meta (Dict[str, Any]): Overrides for nlp.meta.
|
|
RETURNS (Language): The nlp object.
|
|
"""
|
|
LangClass = util.get_lang_class(name)
|
|
# We should accept both dot notation and nested dict here for consistency
|
|
config = util.dot_to_dict(config)
|
|
return LangClass.from_config(config, vocab=vocab, meta=meta)
|