/pylangacq

Language Acquisition Research Tools

Primary LanguagePythonMIT LicenseMIT

PyLangAcq: Language Acquisition Research in Python

Full documentation: https://pylangacq.org


PyPI version Supported Python versions PyPI - Downloads CircleCI Builds

PyLangAcq is a Python library for language acquisition research.

  • Easy access to CHILDES and other TalkBank datasets
  • Intuitive Python data structures for flexible data access and manipulation
  • Standard developmental measures readily available: Mean length of utterance (MLU), type-token ratio (TTR), and index of productive syntax (IPSyn)
  • Direct support and powerful extensions possible for CHAT-formatted conversational datasets more generally

Download and Install

To download and install the most recent version:

$ pip install --upgrade pylangacq

Ready for more? Check out the Quickstart page.

Links

How to Cite

PyLangAcq is authored and maintained by Jackson L. Lee.

Lee, Jackson L., Ross Burkholder, Gallagher B. Flinn, and Emily R. Coppess. 2016. Working with CHAT transcripts in Python. Technical report TR-2016-02, Department of Computer Science, University of Chicago.

@TechReport{lee-et-al-pylangacq:2016,
   Title       = {Working with CHAT transcripts in Python},
   Author      = {Lee, Jackson L. and Burkholder, Ross and Flinn, Gallagher B. and Coppess, Emily R.},
   Institution = {Department of Computer Science, University of Chicago},
   Year        = {2016},
   Number      = {TR-2016-02},
}

License

MIT License. Please see LICENSE.txt in the GitHub source code for details.

The test data files included come from CHILDES, and have a CC BY-NC-SA 3.0 license instead; please also see src/pylangacq/tests/README.md in the GitHub source code for details.

Changelog

Please see CHANGELOG.md.

Setting up a Development Environment

The latest code under development is available on Github at jacksonllee/pylangacq. To obtain this version for experimental features or for development:

$ git clone https://github.com/jacksonllee/pylangacq.git
$ cd pylangacq
$ pip install -e ".[dev]"

To run tests and styling checks:

$ pytest -vv --doctest-modules --cov=pylangacq pylangacq docs/source
$ flake8 pylangacq
$ black --check pylangacq

To build the documentation website files:

$ python docs/source/build_docs.py