spaCy/spacy/__init__.py
Sofie Van Landeghem ff91e6dac7
Show warning if entity_ruler runs without patterns (#7807)
* Show warning if entity_ruler runs without patterns

* Show warning if matcher runs without patterns

* fix wording

* unit test for warning once (WIP)

* warn W036 only once

* cleanup

* create filter_warning helper
2021-05-31 18:20:27 +10:00

74 lines
2.5 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()
# 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: Iterable[str] = util.SimpleFrozenList(),
exclude: 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 (Iterable[str]): Names of pipeline components to disable. Disabled
pipes will be loaded but they won't be run unless you explicitly
enable them by calling nlp.enable_pipe.
exclude (Iterable[str]): Names of pipeline components 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, 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)