[BUG] -- Arguments `enable` and `disable` not working as expected in `spacy.load`
it176131 opened this issue · 0 comments
it176131 commented
How to reproduce the behaviour
The problem
This raises error E1042.
import spacy
spacy.load("en_core_web_sm", enable=["senter"])---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
Cell In[4], line 2
1 # Error E1042.
----> 2 nlp = spacy.load("en_core_web_sm", enable=["senter"])
File ~\ADO\ml_kg\env\Lib\site-packages\spacy\__init__.py:51, in load(name, vocab, disable, enable, exclude, config)
27 def load(
28 name: Union[str, Path],
29 *,
(...)
34 config: Union[Dict[str, Any], Config] = util.SimpleFrozenDict(),
35 ) -> Language:
36 """Load a spaCy model from an installed package or a local path.
37
38 name (str): Package name or model path.
(...)
49 RETURNS (Language): The loaded nlp object.
50 """
---> 51 return util.load_model(
52 name,
53 vocab=vocab,
54 disable=disable,
55 enable=enable,
56 exclude=exclude,
57 config=config,
58 )
File ~\ADO\ml_kg\env\Lib\site-packages\spacy\util.py:465, in load_model(name, vocab, disable, enable, exclude, config)
463 return get_lang_class(name.replace("blank:", ""))()
464 if is_package(name): # installed as package
--> 465 return load_model_from_package(name, **kwargs) # type: ignore[arg-type]
466 if Path(name).exists(): # path to model data directory
467 return load_model_from_path(Path(name), **kwargs) # type: ignore[arg-type]
File ~\ADO\ml_kg\env\Lib\site-packages\spacy\util.py:501, in load_model_from_package(name, vocab, disable, enable, exclude, config)
484 """Load a model from an installed package.
485
486 name (str): The package name.
(...)
498 RETURNS (Language): The loaded nlp object.
499 """
500 cls = importlib.import_module(name)
--> 501 return cls.load(vocab=vocab, disable=disable, enable=enable, exclude=exclude, config=config)
File ~\ADO\ml_kg\env\Lib\site-packages\en_core_web_sm\__init__.py:10, in load(**overrides)
9 def load(**overrides):
---> 10 return load_model_from_init_py(__file__, **overrides)
File ~\ADO\ml_kg\env\Lib\site-packages\spacy\util.py:682, in load_model_from_init_py(init_file, vocab, disable, enable, exclude, config)
680 if not model_path.exists():
681 raise IOError(Errors.E052.format(path=data_path))
--> 682 return load_model_from_path(
683 data_path,
684 vocab=vocab,
685 meta=meta,
686 disable=disable,
687 enable=enable,
688 exclude=exclude,
689 config=config,
690 )
File ~\ADO\ml_kg\env\Lib\site-packages\spacy\util.py:539, in load_model_from_path(model_path, meta, vocab, disable, enable, exclude, config)
537 overrides = dict_to_dot(config, for_overrides=True)
538 config = load_config(config_path, overrides=overrides)
--> 539 nlp = load_model_from_config(
540 config,
541 vocab=vocab,
542 disable=disable,
543 enable=enable,
544 exclude=exclude,
545 meta=meta,
546 )
547 return nlp.from_disk(model_path, exclude=exclude, overrides=overrides)
File ~\ADO\ml_kg\env\Lib\site-packages\spacy\util.py:587, in load_model_from_config(config, meta, vocab, disable, enable, exclude, auto_fill, validate)
584 # This will automatically handle all codes registered via the languages
585 # registry, including custom subclasses provided via entry points
586 lang_cls = get_lang_class(nlp_config["lang"])
--> 587 nlp = lang_cls.from_config(
588 config,
589 vocab=vocab,
590 disable=disable,
591 enable=enable,
592 exclude=exclude,
593 auto_fill=auto_fill,
594 validate=validate,
595 meta=meta,
596 )
597 return nlp
File ~\ADO\ml_kg\env\Lib\site-packages\spacy\language.py:1973, in Language.from_config(cls, config, vocab, disable, enable, exclude, meta, auto_fill, validate)
1965 warnings.warn(
1966 Warnings.W123.format(
1967 enable=enable,
1968 enabled=enabled,
1969 )
1970 )
1972 # Ensure sets of disabled/enabled pipe names are not contradictory.
-> 1973 disabled_pipes = cls._resolve_component_status(
1974 list({*disable, *config["nlp"].get("disabled", [])}),
1975 enable,
1976 config["nlp"]["pipeline"],
1977 )
1978 nlp._disabled = set(p for p in disabled_pipes if p not in exclude)
1980 nlp.batch_size = config["nlp"]["batch_size"]
File ~\ADO\ml_kg\env\Lib\site-packages\spacy\language.py:2153, in Language._resolve_component_status(disable, enable, pipe_names)
2151 # If any pipe to be enabled is in to_disable, the specification is inconsistent.
2152 if len(set(enable) & to_disable):
-> 2153 raise ValueError(Errors.E1042.format(enable=enable, disable=disable))
2155 return tuple(to_disable)
ValueError: [E1042] `enable=['senter']` and `disable=['senter']` are inconsistent with each other.
If you only passed one of `enable` or `disable`, the other argument is specified in your pipeline's configuration.
In that case pass an empty list for the previously not specified argument to avoid this error.Based on the error message I tried setting the disable argument to an empty list, but this raises the same error:
# Another error E1042.
nlp = spacy.load("en_core_web_sm", enable=["senter"], disable=[])ValueError: [E1042] `enable=['senter']` and `disable=['senter']` are inconsistent with each other.
If you only passed one of `enable` or `disable`, the other argument is specified in your pipeline's configuration.
In that case pass an empty list for the previously not specified argument to avoid this error.This lead me to believe that something is wrong with the disable argument.
# Runs, but does not return as expected.
nlp = spacy.load("en_core_web_sm", disable=[])
nlp.disabled # ['senter']Hacky solutions
I've found at least two ways to get around it.
- Bypass the
enable/disablearguments and supply a dictionary to theconfigargument:
# Runs and returns as expected.
nlp = spacy.load("en_core_web_sm", config={"nlp": {"disabled": []}})
nlp.disabled # []
"senter" in nlp.pipe_names # True- Or load the model as-is and enable the component after-the-fact:
# Runs and returns as expected.
nlp = spacy.load("en_core_web_sm")
nlp.enable_pipe("senter")
nlp.disabled # []
"senter" in nlp.pipe_names # TrueThoughts?
I don't really like either of the hacky solutions as I'd expect the enable/disable arguments to handle this. I'd be willing to submit a PR if this is indeed a bug.
Your Environment
- Operating System: Windows 10
- Python Version Used: 3.12.4
- spaCy Version Used: 3.7.5
- Environment Information: Results of
pip list
Package Version Editable project location
-------------------------- -------------- ---------------------------
aiofiles 24.1.0
annotated-types 0.7.0
anyio 4.4.0
argon2-cffi 23.1.0
argon2-cffi-bindings 21.2.0
arrow 1.3.0
asttokens 2.4.1
async-lru 2.0.4
attrs 23.2.0
Babel 2.15.0
beautifulsoup4 4.12.3
black 24.4.2
bleach 6.1.0
blis 0.7.11
cachetools 5.4.0
catalogue 2.0.10
certifi 2024.7.4
cffi 1.16.0
cfgv 3.4.0
charset-normalizer 3.3.2
click 8.1.7
cloudpathlib 0.18.1
colorama 0.4.6
comm 0.2.2
confection 0.1.5
contourpy 1.2.1
curated-tokenizers 0.0.9
curated-transformers 0.1.1
cycler 0.12.1
cymem 2.0.8
debugpy 1.8.2
decorator 5.1.1
defusedxml 0.7.1
distlib 0.3.8
en-core-web-lg 3.7.1
en-core-web-md 3.7.1
en-core-web-sm 3.7.1
en-core-web-trf 3.7.3
executing 2.0.1
fastapi 0.110.3
fastjsonschema 2.20.0
filelock 3.15.4
fonttools 4.53.1
fqdn 1.5.1
fsspec 2024.6.1
h11 0.14.0
httpcore 1.0.5
httpx 0.27.0
huggingface-hub 0.24.5
identify 2.6.0
idna 3.7
ipykernel 6.29.5
ipython 8.26.0
ipython-genutils 0.2.0
ipywidgets 8.1.3
isoduration 20.11.0
isort 5.13.2
jedi 0.19.1
Jinja2 3.1.4
json5 0.9.25
jsonpointer 3.0.0
jsonschema 4.23.0
jsonschema-specifications 2023.12.1
jupyter 1.0.0
jupyter_client 8.6.2
jupyter-console 6.6.3
jupyter_core 5.7.2
jupyter-events 0.10.0
jupyter-lsp 2.2.5
jupyter_server 2.14.2
jupyter_server_terminals 0.5.3
jupyterlab 4.2.4
jupyterlab_pygments 0.3.0
jupyterlab_server 2.27.3
jupyterlab_widgets 3.0.11
kiwisolver 1.4.5
langcodes 3.4.0
language_data 1.2.0
marisa-trie 1.2.0
markdown-it-py 3.0.0
MarkupSafe 2.1.5
matplotlib 3.9.1
matplotlib-inline 0.1.7
mdurl 0.1.2
mistune 3.0.2
mpmath 1.3.0
murmurhash 1.0.10
mypy 1.10.1
mypy-extensions 1.0.0
nbclassic 1.1.0
nbclient 0.10.0
nbconvert 7.16.4
nbformat 5.10.4
neo4j 5.22.0
nest-asyncio 1.6.0
networkx 3.3
nodeenv 1.9.1
notebook 7.2.1
notebook_shim 0.2.4
numpy 1.26.4
overrides 7.7.0
packaging 24.1
pandocfilters 1.5.1
parso 0.8.4
pathspec 0.12.1
peewee 3.16.3
pillow 10.4.0
pip 24.2
pip-system-certs 4.0
platformdirs 4.2.2
pre-commit 3.7.1
preshed 3.0.9
prodigy 1.15.6
prodigy_pdf 0.2.2
prometheus_client 0.20.0
prompt_toolkit 3.0.47
psutil 6.0.0
pure_eval 0.2.3
pycparser 2.22
pydantic 2.8.2
pydantic_core 2.20.1
Pygments 2.18.0
PyJWT 2.8.0
pyparsing 3.1.2
pypdfium2 4.20.0
pytesseract 0.3.10
python-dateutil 2.9.0.post0
python-dotenv 1.0.1
python-json-logger 2.0.7
pytz 2024.1
pywin32 306
pywinpty 2.0.13
PyYAML 6.0.1
pyzmq 26.0.3
qtconsole 5.5.2
QtPy 2.4.1
radicli 0.0.25
referencing 0.35.1
regex 2024.7.24
requests 2.32.3
rfc3339-validator 0.1.4
rfc3986-validator 0.1.1
rich 13.7.1
rpds-py 0.19.0
ruff 0.5.2
safetensors 0.4.3
Send2Trash 1.8.3
setuptools 70.3.0
shellingham 1.5.4
six 1.16.0
smart-open 7.0.4
sniffio 1.3.1
soupsieve 2.5
spacy 3.7.5
spacy-alignments 0.9.1
spacy-curated-transformers 0.2.2
spacy-legacy 3.0.12
spacy-llm 0.7.2
spacy-loggers 1.0.5
spacy-lookups-data 1.0.5
spacy-transformers 1.3.5
srsly 2.4.8
stack-data 0.6.3
starlette 0.37.2
sympy 1.13.1
terminado 0.18.1
thinc 8.2.5
tinycss2 1.3.0
tokenizers 0.15.2
toolz 0.12.1
torch 2.4.0
tornado 6.4.1
tqdm 4.66.4
traitlets 5.14.3
transformers 4.36.2
typeguard 3.0.2
typer 0.12.3
types-python-dateutil 2.9.0.20240316
typing_extensions 4.12.2
uri-template 1.3.0
urllib3 2.2.2
uvicorn 0.26.0
virtualenv 20.26.3
wasabi 1.1.3
wcwidth 0.2.13
weasel 0.4.1
webcolors 24.6.0
webencodings 0.5.1
websocket-client 1.8.0
widgetsnbextension 4.0.11
wrapt 1.16.0