a linguistic toolkit for detecting old loanwords by predicting, evaluating and applying changes in horizontal and vertical lexical transfers


Keywords
linguistics, loanwords, language-contact, sound-change-applier
License
MIT
Install
pip install loanpy==0.0.6

Documentation

the DOI continuous integration status code coverage status Documentation Status PyPI Latest Version

Intro

LoanPy is a linguistic toolkit developed during the course of my PhD thesis at the University of Vienna, providing solutions for various tasks in historical and contact linguistics, such as:

  • Mining correspondence patterns from etymological data on the level of phonology and phonotactics
  • Predicting loanword adaptation (lateral/horizontal transfers) based on heuristics and etymological data
  • Historical reconstruction of words (vertical transfers) based on etymological data
  • Evaluating the quality of the predictive models
  • Searching for potential (old) loanwords between two languages

This toolkit has been designed with ease of use and compatibility in mind, offering a standalone, easy-to-setup, and cross-platform solution that works with Python 3.7 or higher.

Installation

Latest stable version:

$ pip install loanpy

Development version:

$ pip install git+https://github.com/martino-vic/loanpy.git@main

Documentation

Citation

If you use loanpy 3 in your research or project, please cite the following:

@misc{martinovic2023,
  author       = {Viktor Martinovi{\'c}},
  title        = {LoanpyDataHub/loanpy: Third stable release},
  month        = may,
  year         = 2023,
  publisher    = {Zenodo},
  version      = {3.0.0},
  doi          = {10.5281/zenodo.7893906},
  url          = {https://doi.org/10.5281/zenodo.7893906}
}

License

LoanPy is released under the MIT License.

Compatible Input Data

LoanPy supports the following datasets:

Main Changes Compared to Version 2

  • Standalone: No external dependencies needed.
  • Easy setup: Just download or clone the repository and start using it.
  • Cross-platform: Works on any platform that supports Python.
  • Python Compatibility: Works with Python 3.7 or higher.
  • CLDF Integration: Fully compatible with CLDF data standards.