Metadata-Version: 2.1
Name: loanpy
Version: 1.0.1
Summary: Python framework for detecting old loanwords
Home-page: UNKNOWN
Author: Viktor Martinović
Author-email: viktor.gmx@gmx.at
License: UNKNOWN
Project-URL: Documentation, https://martino-vic.github.io/loanpy/index.html
Project-URL: Citation, https://zenodo.org/record/4716940#.YISSF5D7SLQ
Project-URL: Git, https://github.com/martino-vic/loanpy
Project-URL: Twitter, https://twitter.com/martino_vic
Keywords: historical computational linguistics,automated borrowing-detection,loanwords,language contact,Hungarian,Gothic,Uralistics
Platform: UNKNOWN
Classifier: Development Status :: 5 - Production/Stable
Classifier: Operating System :: Microsoft :: Windows :: Windows 10
Classifier: Intended Audience :: Science/Research
Classifier: Natural Language :: English
Classifier: Natural Language :: Hungarian
Classifier: Programming Language :: Python :: 3.9
Classifier: License :: OSI Approved :: Academic Free License (AFL)
Classifier: Topic :: Database
Classifier: Topic :: Scientific/Engineering :: Information Analysis
Requires-Python: >=3.9
Description-Content-Type: text/x-rst
Requires-Dist: et-xmlfile (==1.0.1)
Requires-Dist: gensim (==4.0.1)
Requires-Dist: ipatok (==0.2.0)
Requires-Dist: numpy (==1.20.2)
Requires-Dist: openpyxl (==3.0.7)
Requires-Dist: pandas (==1.2.4)
Requires-Dist: python-dateutil (==2.8.1)
Requires-Dist: python-Levenshtein (==0.12.2)
Requires-Dist: pytz (==2021.1)
Requires-Dist: scipy (==1.6.2)
Requires-Dist: six (==1.15.0)
Requires-Dist: smart-open (==5.0.0)

============
Installation
============

::

    $ python -m pip install loanpy


================
Documentation
================


.. image:: https://raw.githubusercontent.com/martino-vic/loanpy/master/white_logo_dark_background.jpg
   :target: https://martino-vic.github.io/loanpy/index.html


====================
Citation
====================

.. image:: https://zenodo.org/badge/259611202.svg
   :target: https://zenodo.org/badge/latestdoi/259611202

============
Description
============

loanpy is a toolkit for historical linguists.
It extracts sound changes from an etymological dictionary.
It reconstructs hypothetical roots of modern L1 words.
It creates hypothetical adaptions of L2 words into proto-L1.
It searches for potential loanwords by first finding phonetic matches
and then calculating their semantic similarity.


Data Sources
~~~~~~~~~~~~~~~~~~~~~~~

- **dfhun_zaicz_backup.csv**: data frame based on the `Hungarian etymological dictionary (Zaicz 2006) <https://regi.tankonyvtar.hu/hu/tartalom/tinta/TAMOP-4_2_5-09_Etimologiai_szotar/adatok.html>`__

- **dfgot_wikiling_backup.csv**: data frame based on `Wikiling <https://koeblergerhard.de/wikiling/?f=got>`__

- **dfgot_wiktionary_backup.csv**: data frame based on `Wiktionary <https://en.wiktionary.org/wiki/Category:Gothic_lemmas>`__

- **dfuralonet.csv**: data frame based on `Uralonet <http://uralonet.nytud.hu>`__

- **substi.csv**: Sound substitutions based on `Information-theoretic causal inference of lexical flow (Dellert 2017)  <https://langsci-press.org/catalog/book/233>`__

- **wordvectornames.xlsx**: Names of pretrained word vector models from `gensim-data  <https://github.com/RaRe-Technologies/gensim-data>`__


Dependencies
~~~~~~~~~~~~~~~~~~~

- `gensim  <https://pypi.org/project/gensim/>`__

- `ipatok  <https://pypi.org/project/ipatok/>`__

- `python-Levenshtein <https://pypi.org/project/python-Levenshtein>`__

- `pandas <https://pypi.org/project/pandas/>`__

- see also requirements.txt


License
~~~~~~~~~~~~~~~~

Academic Free License (AFL)



=======
Git
=======

.. image:: https://raw.githubusercontent.com/martino-vic/loanpy/master/Octocat.png
   :target: https://github.com/martino-vic/loanpy
   :scale: 30%

