mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-10 19:57:17 +03:00
43b960c01b
* Update with WIP * Update with WIP * Update with pipeline serialization * Update types and pipe factories * Add deep merge, tidy up and add tests * Fix pipe creation from config * Don't validate default configs on load * Update spacy/language.py Co-authored-by: Ines Montani <ines@ines.io> * Adjust factory/component meta error * Clean up factory args and remove defaults * Add test for failing empty dict defaults * Update pipeline handling and methods * provide KB as registry function instead of as object * small change in test to make functionality more clear * update example script for EL configuration * Fix typo * Simplify test * Simplify test * splitting pipes.pyx into separate files * moving default configs to each component file * fix batch_size type * removing default values from component constructors where possible (TODO: test 4725) * skip instead of xfail * Add test for config -> nlp with multiple instances * pipeline.pipes -> pipeline.pipe * Tidy up, document, remove kwargs * small cleanup/generalization for Tok2VecListener * use DEFAULT_UPSTREAM field * revert to avoid circular imports * Fix tests * Replace deprecated arg * Make model dirs require config * fix pickling of keyword-only arguments in constructor * WIP: clean up and integrate full config * Add helper to handle function args more reliably Now also includes keyword-only args * Fix config composition and serialization * Improve config debugging and add visual diff * Remove unused defaults and fix type * Remove pipeline and factories from meta * Update spacy/default_config.cfg Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/default_config.cfg * small UX edits * avoid printing stack trace for debug CLI commands * Add support for language-specific factories * specify the section of the config which holds the model to debug * WIP: add Language.from_config * Update with language data refactor WIP * Auto-format * Add backwards-compat handling for Language.factories * Update morphologizer.pyx * Fix morphologizer * Update and simplify lemmatizers * Fix Japanese tests * Port over tagger changes * Fix Chinese and tests * Update to latest Thinc * WIP: xfail first Russian lemmatizer test * Fix component-specific overrides * fix nO for output layers in debug_model * Fix default value * Fix tests and don't pass objects in config * Fix deep merging * Fix lemma lookup data registry Only load the lookups if an entry is available in the registry (and if spacy-lookups-data is installed) * Add types * Add Vocab.from_config * Fix typo * Fix tests * Make config copying more elegant * Fix pipe analysis * Fix lemmatizers and is_base_form * WIP: move language defaults to config * Fix morphology type * Fix vocab * Remove comment * Update to latest Thinc * Add morph rules to config * Tidy up * Remove set_morphology option from tagger factory * Hack use_gpu * Move [pipeline] to top-level block and make [nlp.pipeline] list Allows separating component blocks from component order – otherwise, ordering the config would mean a changed component order, which is bad. Also allows initial config to define more components and not use all of them * Fix use_gpu and resume in CLI * Auto-format * Remove resume from config * Fix formatting and error * [pipeline] -> [components] * Fix types * Fix tagger test: requires set_morphology? Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com> Co-authored-by: Matthew Honnibal <honnibal+gh@gmail.com>
112 lines
2.5 KiB
INI
112 lines
2.5 KiB
INI
[metadata]
|
|
description = Industrial-strength Natural Language Processing (NLP) in Python
|
|
url = https://spacy.io
|
|
author = Explosion
|
|
author_email = contact@explosion.ai
|
|
license = MIT
|
|
long_description = file: README.md
|
|
long_description_content_type = text/markdown
|
|
classifiers =
|
|
Development Status :: 5 - Production/Stable
|
|
Environment :: Console
|
|
Intended Audience :: Developers
|
|
Intended Audience :: Science/Research
|
|
License :: OSI Approved :: MIT License
|
|
Operating System :: POSIX :: Linux
|
|
Operating System :: MacOS :: MacOS X
|
|
Operating System :: Microsoft :: Windows
|
|
Programming Language :: Cython
|
|
Programming Language :: Python :: 3
|
|
Programming Language :: Python :: 3.6
|
|
Programming Language :: Python :: 3.7
|
|
Programming Language :: Python :: 3.8
|
|
Topic :: Scientific/Engineering
|
|
|
|
[options]
|
|
zip_safe = false
|
|
include_package_data = true
|
|
python_requires = >=3.6
|
|
setup_requires =
|
|
wheel
|
|
cython>=0.25
|
|
numpy>=1.15.0
|
|
# We also need our Cython packages here to compile against
|
|
cymem>=2.0.2,<2.1.0
|
|
preshed>=3.0.2,<3.1.0
|
|
murmurhash>=0.28.0,<1.1.0
|
|
thinc>=8.0.0a19,<8.0.0a30
|
|
install_requires =
|
|
# Our libraries
|
|
murmurhash>=0.28.0,<1.1.0
|
|
cymem>=2.0.2,<2.1.0
|
|
preshed>=3.0.2,<3.1.0
|
|
thinc>=8.0.0a19,<8.0.0a30
|
|
blis>=0.4.0,<0.5.0
|
|
wasabi>=0.7.1,<1.1.0
|
|
srsly>=2.1.0,<3.0.0
|
|
catalogue>=0.0.7,<1.1.0
|
|
typer>=0.3.0,<0.4.0
|
|
# Third-party dependencies
|
|
tqdm>=4.38.0,<5.0.0
|
|
numpy>=1.15.0
|
|
requests>=2.13.0,<3.0.0
|
|
pydantic>=1.3.0,<2.0.0
|
|
pytokenizations
|
|
# Official Python utilities
|
|
setuptools
|
|
packaging
|
|
importlib_metadata>=0.20; python_version < "3.8"
|
|
|
|
[options.entry_points]
|
|
console_scripts =
|
|
spacy = spacy.cli:app
|
|
|
|
[options.extras_require]
|
|
lookups =
|
|
spacy_lookups_data>=0.3.2,<0.4.0
|
|
cuda =
|
|
cupy>=5.0.0b4,<9.0.0
|
|
cuda80 =
|
|
cupy-cuda80>=5.0.0b4,<9.0.0
|
|
cuda90 =
|
|
cupy-cuda90>=5.0.0b4,<9.0.0
|
|
cuda91 =
|
|
cupy-cuda91>=5.0.0b4,<9.0.0
|
|
cuda92 =
|
|
cupy-cuda92>=5.0.0b4,<9.0.0
|
|
cuda100 =
|
|
cupy-cuda100>=5.0.0b4,<9.0.0
|
|
cuda101 =
|
|
cupy-cuda101>=5.0.0b4,<9.0.0
|
|
cuda102 =
|
|
cupy-cuda102>=5.0.0b4,<9.0.0
|
|
# Language tokenizers with external dependencies
|
|
ja =
|
|
sudachipy>=0.4.5
|
|
sudachidict_core>=20200330
|
|
ko =
|
|
natto-py==0.9.0
|
|
th =
|
|
pythainlp>=2.0
|
|
|
|
[bdist_wheel]
|
|
universal = false
|
|
|
|
[sdist]
|
|
formats = gztar
|
|
|
|
[flake8]
|
|
ignore = E203, E266, E501, E731, W503
|
|
max-line-length = 80
|
|
select = B,C,E,F,W,T4,B9
|
|
exclude =
|
|
.env,
|
|
.git,
|
|
__pycache__,
|
|
_tokenizer_exceptions_list.py,
|
|
spacy/__init__.py
|
|
|
|
[tool:pytest]
|
|
markers =
|
|
slow
|