Skip to main content

A Python implementation of the ConText algorithm

Project description

pyConTextNLP
============

This code has been validated using the included notebooks on Python v 3.7.2. Python 2.x is no longer supported.

pyConTextNLP is a Python implementation/extension/modification of the
ConText algorithm described in `CITE <>`__ which is itself a
generalization of the NegEx algorithm described in `CITE <>`__.

The package is maintained by Brian Chapman at the University of Utah.
Other active and past developers include:

- Wendy W. Chapman
- Glenn Dayton
- Danielle Mowery

Introduction
------------

pyConTextNLP is a partial implementation of the ConText algorithm using
Python. The original description of pyConTextNLP was provided in Chapman
BE, Lee S, Kang HP, Chapman WW, "Document-level classification of CT
pulmonary angiography reports based on an extension of the ConText
algorithm." `J Biomed Inform. 2011
Oct;44(5):728-37 <http://www.sciencedirect.com/science/article/pii/S1532046411000621>`__

Other publications/presentations based on pyConText include: \* Wilson
RA, et al. "Automated ancillary cancer history classification for
mesothelioma patients from free-text clinical reports." J Pathol Inform.
2010 Oct 11;1:24. \* Chapman BE, Lee S, Kang HP, Chapman WW. "Using
ConText to Identify Candidate Pulmonary Embolism Subjects Based on
Dictated Radiology Reports." (Presented at AMIA Clinical Research
Informatics Summit 2011) \* Wilson RA, Chapman WW, DeFries SJ, Becich
MJ, Chapman BE. "Identifying History of Ancillary Cancers in
Mesothelioma Patients from Free-Text Clinical Reports." (Presented at
AMIA 2010).

Note: we changed the package name from pyConText to pyConTextNLP because
of a name conflict on pypi.

Installation
------------

Latest Version
~~~~~~~~~~~~~~

The latest version of pyConTextNLP is available on [github](https://github.com/chapmanbe/pyConTextNLP).
The package can be installed by either cloning the repository and running `python setup.py install`.
Alternatively or by
.. code:: shell
pip install git+https://github.com/chapmanbe/pyConTextNLP.git

PyPi
~~~~~

pyConTextNLP is also available via the Python Package Index and can be installed via

.. code:: shell

pip install pyConTextNLP

Dependencies include

* networkx
* PyYAML


Tutorials
---------

See the `notebooks folder <./notebooks>`__ for a series of walkthroughs
demonstrating pyConTextNLP core concepts with example data.


How to Use
----------

I am working on improving the documentation and (hopefully) adding some
testing to the code.

Some preliminary comments:

- pyConTextNLP works marks up text on a sentence by sentence level.
- pyConTextNLP assumes the sentence is a string not a list of words
- Our preferred way to represent knowledge is now with YAML files rather than TSV files.



Project details


Download files

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

Source Distribution

pyConTextNLP-0.7.0.1.tar.gz (21.4 kB view details)

Uploaded Source

Built Distribution

pyConTextNLP-0.7.0.1-py2.py3-none-any.whl (74.7 kB view details)

Uploaded Python 2Python 3

File details

Details for the file pyConTextNLP-0.7.0.1.tar.gz.

File metadata

  • Download URL: pyConTextNLP-0.7.0.1.tar.gz
  • Upload date:
  • Size: 21.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/1.12.1 pkginfo/1.5.0.1 requests/2.21.0 setuptools/40.6.3 requests-toolbelt/0.9.1 tqdm/4.30.0 CPython/3.7.2

File hashes

Hashes for pyConTextNLP-0.7.0.1.tar.gz
Algorithm Hash digest
SHA256 4e63d57adb1629af1bbf2fdd6661bc2a7a1f6660412ee33965030aa8c74bce5a
MD5 f6e31a0270ab8f5c56ff4bcc03c1274f
BLAKE2b-256 4fa57d1cffb15a0d5021bf0dfdf768189bb6a36bf669f2510ee8ea91047d7465

See more details on using hashes here.

File details

Details for the file pyConTextNLP-0.7.0.1-py2.py3-none-any.whl.

File metadata

  • Download URL: pyConTextNLP-0.7.0.1-py2.py3-none-any.whl
  • Upload date:
  • Size: 74.7 kB
  • Tags: Python 2, Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/1.12.1 pkginfo/1.5.0.1 requests/2.21.0 setuptools/40.6.3 requests-toolbelt/0.9.1 tqdm/4.30.0 CPython/3.7.2

File hashes

Hashes for pyConTextNLP-0.7.0.1-py2.py3-none-any.whl
Algorithm Hash digest
SHA256 83d70476b8587200287428e0a312cb8c903dda9129f3726c34f75d14f2e2878e
MD5 a99f800aae06ea1be31ac1944fd5e469
BLAKE2b-256 294fe76ef634f4ba7466585af7c1f0cfbce788ee8926a926ae33ae8101e131d9

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page