Modular, fast NLP framework, compatible with Pytorch and spaCy, offering tailored support for French clinical notes.

These details have not been verified by PyPI

Project links

Project description

Tests

EDS-NLP

EDS-NLP is a collaborative NLP framework that aims primarily at extracting information from French clinical notes. At its core, it is a collection of components or pipes, either rule-based functions or deep learning modules. These components are organized into a novel efficient and modular pipeline system, built for hybrid and multitask models. We use spaCy to represent documents and their annotations, and Pytorch as a deep-learning backend for trainable components.

EDS-NLP is versatile and can be used on any textual document. The rule-based components are fully compatible with spaCy's components, and vice versa. This library is a product of collaborative effort, and we encourage further contributions to enhance its capabilities.

Check out our interactive demo !

Features

Rule-based components for French clinical notes
Trainable components: NER, Span classification
Support for multitask deep-learning models with weights sharing
Fast inference, with multi-GPU support out of the box
Easy to use, with a spaCy-like API
Compatible with rule-based spaCy components
Support for various io formats like BRAT, JSON, Parquet, Pandas or Spark

Quick start

Installation

You can install EDS-NLP via pip. We recommend pinning the library version in your projects, or use a strict package manager like Poetry.

pip install edsnlp

or if you want to use the trainable components (using pytorch)

pip install "edsnlp[ml]"

A first pipeline

Once you've installed the library, let's begin with a very simple example that extracts mentions of COVID19 in a text, and detects whether they are negated.

import edsnlp

nlp = edsnlp.blank("eds")

terms = dict(
    covid=["covid", "coronavirus"],
)

# Split the documents into sentences, this isneeded for negation detection
nlp.add_pipe("eds.sentences")
# Matcher component
nlp.add_pipe("eds.matcher", config=dict(terms=terms))
# Negation detection
nlp.add_pipe("eds.negation")

# Process your text in one call !
doc = nlp("Le patient n'est pas atteint de covid")

doc.ents
# Out: (covid,)

doc.ents[0]._.negation
# Out: True

Documentation & Tutorials

Go to the documentation for more information.

Disclaimer

The performances of an extraction pipeline may depend on the population and documents that are considered.

Contributing to EDS-NLP

We welcome contributions ! Fork the project and propose a pull request. Take a look at the dedicated page for detail.

Citation

If you use EDS-NLP, please cite us as below.

@misc{edsnlp,
  author = {Wajsburt, Perceval and Petit-Jean, Thomas and Dura, Basile and Cohen, Ariel and Jean, Charline and Bey, Romain},
  doi    = {10.5281/zenodo.6424993},
  title  = {EDS-NLP: efficient information extraction from French clinical notes},
  url    = {https://aphp.github.io/edsnlp}
}

Acknowledgement

We would like to thank Assistance Publique – Hôpitaux de Paris, AP-HP Foundation and Inria for funding this project.

Project details

These details have not been verified by PyPI

Project links

Release history Release notifications | RSS feed

0.13.1

Oct 10, 2024

0.13.0

Jul 22, 2024

0.12.3

Jun 17, 2024

0.12.2

Jun 17, 2024

0.12.1

Jun 5, 2024

0.12.0

May 22, 2024

0.11.2

Apr 10, 2024

0.11.1

Apr 2, 2024

0.11.0

Mar 29, 2024

0.10.7

Mar 12, 2024

0.10.6

Feb 24, 2024

0.10.5

Jan 29, 2024

0.10.4

Jan 19, 2024

0.10.3

Jan 11, 2024

0.10.2

Dec 20, 2023

This version

0.10.1

Dec 15, 2023

0.10.0

Dec 4, 2023

0.10.0b1 pre-release

Oct 16, 2023

0.9.1

Sep 22, 2023

0.9.0

Sep 15, 2023

0.8.1

May 31, 2023

0.8.0

May 25, 2023

0.7.4

Dec 12, 2022

0.7.3 yanked

Nov 25, 2022

Reason this release was yanked:

Problem with UMLS dependency: tries to write on protected path

0.7.2

Oct 26, 2022

0.7.1

Oct 13, 2022

0.7.0

Sep 6, 2022

0.6.2

Aug 2, 2022

0.6.1

Jul 11, 2022

0.6.0

Jun 17, 2022

0.5.3

May 4, 2022

0.5.2

Apr 29, 2022

0.5.1

Apr 11, 2022

0.5.0 yanked

Apr 8, 2022

Reason this release was yanked:

Issue with the PhraseMatcher

0.4.4

Mar 31, 2022

0.4.3

Mar 18, 2022

0.4.2

Mar 16, 2022

0.4.1

Mar 14, 2022

0.4.0

Mar 8, 2022

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

edsnlp-0.10.1.tar.gz (1.5 MB view details)

Uploaded Dec 15, 2023 Source

Built Distributions

edsnlp-0.10.1-cp311-cp311-win_amd64.whl (1.8 MB view details)

Uploaded Dec 15, 2023 CPython 3.11 Windows x86-64

edsnlp-0.10.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (2.7 MB view details)

Uploaded Dec 15, 2023 CPython 3.11 manylinux: glibc 2.17+ x86-64

edsnlp-0.10.1-cp311-cp311-macosx_11_0_arm64.whl (1.8 MB view details)

Uploaded Dec 15, 2023 CPython 3.11 macOS 11.0+ ARM64

edsnlp-0.10.1-cp311-cp311-macosx_10_9_x86_64.whl (1.8 MB view details)

Uploaded Dec 15, 2023 CPython 3.11 macOS 10.9+ x86-64

edsnlp-0.10.1-cp310-cp310-win_amd64.whl (1.8 MB view details)

Uploaded Dec 15, 2023 CPython 3.10 Windows x86-64

edsnlp-0.10.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (2.7 MB view details)

Uploaded Dec 15, 2023 CPython 3.10 manylinux: glibc 2.17+ x86-64

edsnlp-0.10.1-cp310-cp310-macosx_11_0_arm64.whl (1.8 MB view details)

Uploaded Dec 15, 2023 CPython 3.10 macOS 11.0+ ARM64

edsnlp-0.10.1-cp310-cp310-macosx_10_9_x86_64.whl (1.8 MB view details)

Uploaded Dec 15, 2023 CPython 3.10 macOS 10.9+ x86-64

edsnlp-0.10.1-cp39-cp39-win_amd64.whl (1.8 MB view details)

Uploaded Dec 15, 2023 CPython 3.9 Windows x86-64

edsnlp-0.10.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (2.7 MB view details)

Uploaded Dec 15, 2023 CPython 3.9 manylinux: glibc 2.17+ x86-64

edsnlp-0.10.1-cp39-cp39-macosx_11_0_arm64.whl (1.8 MB view details)

Uploaded Dec 15, 2023 CPython 3.9 macOS 11.0+ ARM64

edsnlp-0.10.1-cp39-cp39-macosx_10_9_x86_64.whl (1.8 MB view details)

Uploaded Dec 15, 2023 CPython 3.9 macOS 10.9+ x86-64

edsnlp-0.10.1-cp38-cp38-win_amd64.whl (1.8 MB view details)

Uploaded Dec 15, 2023 CPython 3.8 Windows x86-64

edsnlp-0.10.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (2.7 MB view details)

Uploaded Dec 15, 2023 CPython 3.8 manylinux: glibc 2.17+ x86-64

edsnlp-0.10.1-cp38-cp38-macosx_11_0_arm64.whl (1.8 MB view details)

Uploaded Dec 15, 2023 CPython 3.8 macOS 11.0+ ARM64

edsnlp-0.10.1-cp38-cp38-macosx_10_9_x86_64.whl (1.8 MB view details)

Uploaded Dec 15, 2023 CPython 3.8 macOS 10.9+ x86-64

edsnlp-0.10.1-cp37-cp37m-win_amd64.whl (1.8 MB view details)

Uploaded Dec 15, 2023 CPython 3.7m Windows x86-64

edsnlp-0.10.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (2.6 MB view details)

Uploaded Dec 15, 2023 CPython 3.7m manylinux: glibc 2.17+ x86-64

edsnlp-0.10.1-cp37-cp37m-macosx_10_9_x86_64.whl (1.8 MB view details)

Uploaded Dec 15, 2023 CPython 3.7m macOS 10.9+ x86-64

File details

Details for the file edsnlp-0.10.1.tar.gz.

File metadata

Download URL: edsnlp-0.10.1.tar.gz
Upload date: Dec 15, 2023
Size: 1.5 MB
Tags: Source
Uploaded using Trusted Publishing? No
Uploaded via: twine/4.0.2 CPython/3.9.18

File hashes

Hashes for edsnlp-0.10.1.tar.gz
Algorithm	Hash digest
SHA256	`f50d76398e750b753759b56ca03f459b926f4ddde29f8d564ad6e5b72566cad6`
MD5	`179c1bccb0ea8c93684ded9d4645f9b3`
BLAKE2b-256	`d85432f936a70c3ddf32cff299602684337c61e79b1f0558ba4b28bfc4a526d1`

Algorithm	Hash digest
SHA256	`49ed9bcac52a4c6e608511e9c19f48781a80e847cd4f85c7565ed385e8c24100`
MD5	`25d35acc47c18da50d07d1d127a178ad`
BLAKE2b-256	`b3092359f2f933caa0fbd7e04289a1c0e8b46eb390a96e0f1e8b38d1703edd9c`

Algorithm	Hash digest
SHA256	`4e3ff5cc0d41d392a6fb326db5b317c3a8bec06f8b02abe45bdd55958058b02e`
MD5	`e24a3ece448494045453ce69eb164b07`
BLAKE2b-256	`fa72ab6d40aad2e4ad042262640b6ff8f6b062a75e017a8f244a66ec715f95ef`

Algorithm	Hash digest
SHA256	`de0553c6a9be80400be085105dc6f47a990958a793f8d89b614b4ce8431be7b7`
MD5	`9e15748ab627d36225cd69242016a229`
BLAKE2b-256	`af6434bfe7e7953d7637041d8ca86929c5dd96364a91698458c7b57b07046f40`

Algorithm	Hash digest
SHA256	`f3bf83b33f89146ee88bd48ac14175faee3c0643e489ccbf96f48ae78e434d7a`
MD5	`17c6fc6d32c35270f01e3c78a9066378`
BLAKE2b-256	`4f8a92dff65ccd2ee618f8b56b0f7d47b0fc781b45e739a9070224af8f9dde2d`

Algorithm	Hash digest
SHA256	`7c28352af9aebbf656bcee508d56385952a020b437cf1ea101963f361be04e44`
MD5	`88aaf76f4c38050f917f5247a1f18430`
BLAKE2b-256	`21a9edf70b0bbb2e3b20ec4479c6589c64f32f2516a51fa64a86a06d908a785a`

Algorithm	Hash digest
SHA256	`160645dc2cb8fdf485fb337634f46f4485b8aaaba791a39d7a73ea7d43857584`
MD5	`1d5a8397c5d2d11249e4b8dcb453267e`
BLAKE2b-256	`5878743b0977a002ddfaf67d9f10cd40a3f34f4326a6f9f7e4d06d7f8e05ec55`

Algorithm	Hash digest
SHA256	`68bb9710021956fbc00d7dd5712df93dc953117f83259c6b178daf86b917dd34`
MD5	`9c7c252f55b0de000bd3ad387a543c2b`
BLAKE2b-256	`4b221f4e5d50ab1b6f4a0273c54c267d8225c62b21b2b8644e9a5ba553741338`

Algorithm	Hash digest
SHA256	`e9b6cfaa19ba88c9b4e20a6f2ad740c3ec610641289cc4de2be3801c28a043ba`
MD5	`38de5007f4eedab00bf9be4c0235c508`
BLAKE2b-256	`89373ff7e047ac350bfb32855b482c7fe42e7dee918a8026a4b38b0a9fd89f9a`

Algorithm	Hash digest
SHA256	`8497eb833ea16c9ef7f0979eb7ad97c72464a29d4ca657dbc6c3c99b5568f6f6`
MD5	`fd2c233ae245e96bc23a97d3c487e3ba`
BLAKE2b-256	`27bff8aac416abdeebe7ae857e94bd9ad683ae829fa02d7a4bbf605b27094e45`

Algorithm	Hash digest
SHA256	`1edb2b1ff0f53256a0d2eebf3a7276502883c346f78ba214b6d15def4a9f0ca3`
MD5	`c5921833ece4dba869d6578e8262a8f0`
BLAKE2b-256	`005c2bc482c4d8b35518da52b053a1548413428d8190521b50fdf9a6dab26701`

Algorithm	Hash digest
SHA256	`e11f67fde6e3d0acb45207bbf9b01a1249dae8dc2404e6868a23c5d1b51eb404`
MD5	`5e4208bf28412a8c22dcf1dda7a74ff8`
BLAKE2b-256	`fbff63eb4d42de841df068cbfc81dd4b78e98f39efbfcfbba0000797bdcedd17`

Algorithm	Hash digest
SHA256	`c86a47a8a87627dadcf5954b362e68166f663f0797e389ea1433e13bac2e008a`
MD5	`3e43ff217848e19ed209d32574ae24f0`
BLAKE2b-256	`08649d5318bc7d709cc0a58853b86025d9f4cb20fbb19efc64186e0a15413162`

Algorithm	Hash digest
SHA256	`daf4f74ebf900bd03e8aa97e9af1748c3da4640663f853de1392211b146f8e76`
MD5	`7b52ab8e1ab3421eb519ec08c882d0ac`
BLAKE2b-256	`ab7aab3fe54845e092849c914ed5be0af49fca82c7a603d81edb525320eb86c4`

Algorithm	Hash digest
SHA256	`455b60321203efb23e4cf9d027e871c4ed14a39e27ee3595f8b9be97c6296b25`
MD5	`09e6fbb55e7a882e2ff8b122e14b7a35`
BLAKE2b-256	`7717621c603ffdce3d66b84039dfb3f5fdb193364f8bf81720b8423cd30240a2`

Algorithm	Hash digest
SHA256	`f46cc74306f24f48bdab1b88525f5ce72a41070590cdce826fb0af5399f2a689`
MD5	`d93b2e982162bd1204fce962088281e3`
BLAKE2b-256	`6986793abfa6b3bfd95292a069926ba497289989a005786b06f51aeaeffe0b6d`

Algorithm	Hash digest
SHA256	`c0d4a67971da1f172d8b9099925d32f168a516b64e54d95e826d9f3149147369`
MD5	`8c37dcf89bdcdd81ba339032135de8d2`
BLAKE2b-256	`d844b5d1c2b849357e67eb35f9b3ef6061e8392754f68ab4e5a98a45d735c6bd`

Algorithm	Hash digest
SHA256	`178aa03f17aef2d8f9be92fe3c9a7d647a1aea0dd61c23aae45cba54bc34c96c`
MD5	`1e297fbd877cf4950012c45f10d82579`
BLAKE2b-256	`7dbf9b76972caef0bea353ef79476f2a43df36899ade1d9bdf9a3d4b37bc7693`

Algorithm	Hash digest
SHA256	`97bb2c15f6ab4cf98fc1f6884a6773bcc8acec94485eef1b20e5ff6614cd95b9`
MD5	`b9fa6a05a26cf578d523dfdaeac33d26`
BLAKE2b-256	`ea15e621a40da436542956eb7358ebb6d30ce5267196c5724f3a60bcec305bf9`

Algorithm	Hash digest
SHA256	`1e08f0f807725587847b925d84ca40ef0b3c2c2c61534ef0eda0f912ceccc2a0`
MD5	`eff9156a5b8f1f4c54a40aa9a54689ed`
BLAKE2b-256	`345ff8291f6333eadfd118cc9e8946a6e2386d0a2fc6a303a2cc9fc0c6887386`

edsnlp 0.10.1

Navigation

Verified details

Maintainers

Unverified details

Project links

Meta

Project description

EDS-NLP

Features

Quick start

Installation

A first pipeline

Documentation & Tutorials

Disclaimer

Contributing to EDS-NLP

Citation

Acknowledgement

Project details

Verified details

Maintainers

Unverified details

Project links

Meta

Release history Release notifications | RSS feed

Download files

Source Distribution

Built Distributions

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details