mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 03:19:13 +03:00
f9946154d9
* Draft spancat model
* Add spancat model
* Add test for extract_spans
* Add extract_spans layer
* Upd extract_spans
* Add spancat model
* Add test for spancat model
* Upd spancat model
* Update spancat component
* Upd spancat
* Update spancat model
* Add quick spancat test
* Import SpanCategorizer
* Fix SpanCategorizer component
* Import SpanGroup
* Fix span extraction
* Fix import
* Fix import
* Upd model
* Update spancat models
* Add scoring, update defaults
* Update and add docs
* Fix type
* Update spacy/ml/extract_spans.py
* Auto-format and fix import
* Fix comment
* Fix type
* Fix type
* Update website/docs/api/spancategorizer.md
* Fix comment
Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
* Better defense
Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
* Fix labels list
Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
* Update spacy/ml/extract_spans.py
Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
* Update spacy/pipeline/spancat.py
Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
* Set annotations during update
* Set annotations in spancat
* fix imports in test
* Update spacy/pipeline/spancat.py
* replace MaxoutLogistic with LinearLogistic
* fix config
* various small fixes
* remove set_annotations parameter in update
* use our beloved tupley format with recent support for doc.spans
* bugfix to allow renaming the default span_key (scores weren't showing up)
* use different key in docs example
* change defaults to better-working parameters from project (WIP)
* register spacy.extract_spans.v1 for legacy purposes
* Upd dev version so can build wheel
* layers instead of architectures for smaller building blocks
* Update website/docs/api/spancategorizer.md
Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
* Update website/docs/api/spancategorizer.md
Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
* Include additional scores from overrides in combined score weights
* Parameterize spans key in scoring
Parameterize the `SpanCategorizer` `spans_key` for scoring purposes so
that it's possible to evaluate multiple `spancat` components in the same
pipeline.
* Use the (intentionally very short) default spans key `sc` in the
`SpanCategorizer`
* Adjust the default score weights to include the default key
* Adjust the scorer to use `spans_{spans_key}` as the prefix for the
returned score
* Revert addition of `attr_name` argument to `score_spans` and adjust
the key in the `getter` instead.
Note that for `spancat` components with a custom `span_key`, the score
weights currently need to be modified manually in
`[training.score_weights]` for them to be available during training. To
suppress the default score weights `spans_sc_p/r/f` during training, set
them to `null` in `[training.score_weights]`.
* Update website/docs/api/scorer.md
* Fix scorer for spans key containing underscore
* Increment version
* Add Spans to Evaluate CLI (#8439)
* Add Spans to Evaluate CLI
* Change to spans_key
* Add spans per_type output
Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
* Fix spancat GPU issues (#8455)
* Fix GPU issues
* Require thinc >=8.0.6
* Switch to glorot_uniform_init
* Fix and test ngram suggester
* Include final ngram in doc for all sizes
* Fix ngrams for docs of the same length as ngram size
* Handle batches of docs that result in no ngrams
* Add tests
Co-authored-by: Ines Montani <ines@ines.io>
Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com>
Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
Co-authored-by: Nirant <NirantK@users.noreply.github.com>
131 lines
3.1 KiB
INI
131 lines
3.1 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
|
|
Programming Language :: Python :: 3.9
|
|
Topic :: Scientific/Engineering
|
|
project_urls =
|
|
Release notes = https://github.com/explosion/spaCy/releases
|
|
Source = https://github.com/explosion/spaCy
|
|
|
|
[options]
|
|
zip_safe = false
|
|
include_package_data = true
|
|
python_requires = >=3.6
|
|
setup_requires =
|
|
cython>=0.25,<3.0
|
|
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>=8.0.6,<8.1.0
|
|
install_requires =
|
|
# Our libraries
|
|
spacy-legacy>=3.0.6,<3.1.0
|
|
murmurhash>=0.28.0,<1.1.0
|
|
cymem>=2.0.2,<2.1.0
|
|
preshed>=3.0.2,<3.1.0
|
|
thinc>=8.0.6,<8.1.0
|
|
blis>=0.4.0,<0.8.0
|
|
wasabi>=0.8.1,<1.1.0
|
|
srsly>=2.4.1,<3.0.0
|
|
catalogue>=2.0.4,<2.1.0
|
|
typer>=0.3.0,<0.4.0
|
|
pathy>=0.3.5
|
|
# Third-party dependencies
|
|
tqdm>=4.38.0,<5.0.0
|
|
numpy>=1.15.0
|
|
requests>=2.13.0,<3.0.0
|
|
pydantic>=1.7.4,!=1.8,!=1.8.1,<1.9.0
|
|
jinja2
|
|
# Official Python utilities
|
|
setuptools
|
|
packaging>=20.0
|
|
typing_extensions>=3.7.4,<4.0.0.0; python_version < "3.8"
|
|
|
|
[options.entry_points]
|
|
console_scripts =
|
|
spacy = spacy.cli:setup_cli
|
|
|
|
[options.extras_require]
|
|
lookups =
|
|
spacy_lookups_data>=1.0.2,<1.1.0
|
|
transformers =
|
|
spacy_transformers>=1.0.1,<1.1.0
|
|
ray =
|
|
spacy_ray>=0.1.0,<1.0.0
|
|
cuda =
|
|
cupy>=5.0.0b4,<10.0.0
|
|
cuda80 =
|
|
cupy-cuda80>=5.0.0b4,<10.0.0
|
|
cuda90 =
|
|
cupy-cuda90>=5.0.0b4,<10.0.0
|
|
cuda91 =
|
|
cupy-cuda91>=5.0.0b4,<10.0.0
|
|
cuda92 =
|
|
cupy-cuda92>=5.0.0b4,<10.0.0
|
|
cuda100 =
|
|
cupy-cuda100>=5.0.0b4,<10.0.0
|
|
cuda101 =
|
|
cupy-cuda101>=5.0.0b4,<10.0.0
|
|
cuda102 =
|
|
cupy-cuda102>=5.0.0b4,<10.0.0
|
|
cuda110 =
|
|
cupy-cuda110>=5.0.0b4,<10.0.0
|
|
cuda111 =
|
|
cupy-cuda111>=5.0.0b4,<10.0.0
|
|
cuda112 =
|
|
cupy-cuda112>=5.0.0b4,<10.0.0
|
|
# Language tokenizers with external dependencies
|
|
ja =
|
|
sudachipy>=0.4.9
|
|
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, E741
|
|
max-line-length = 80
|
|
select = B,C,E,F,W,T4,B9
|
|
exclude =
|
|
.env,
|
|
.git,
|
|
__pycache__,
|
|
_tokenizer_exceptions_list.py,
|
|
|
|
[tool:pytest]
|
|
markers =
|
|
slow
|
|
|
|
[mypy]
|
|
ignore_missing_imports = True
|
|
no_implicit_optional = True
|
|
plugins = pydantic.mypy, thinc.mypy
|