Skip to content

A Python package for automatically cleaning the short text present in maintenance work orders and strategies.

License

Notifications You must be signed in to change notification settings

nlp-tlp/mudlark

Repository files navigation

Mudlark

Pytest Status Coverage Status Pylint Status

This library is designed to provide utilities for cleaning CSV datasets that contain technical language. Mudlark has three main purposes:

  • Rapid and easy preprocessing of CSV datasets that have a text column.
  • Exporting a CSV dataset to a JSON file that can be readily imported into QuickGraph, so that you can annotate the textual portion of your CSV dataset.
  • Normalising a single piece of text which involves replacing any words appearing in a predefined "corrections dictionary" with suitable replacements. You can view this dictionary here.

Note that at this stage, the pipeline-based normalisation method that we use is designed for maintenance work orders, but it is also applicable to other domains featuring similar technical language.

📘📗📙 Full README and code documentation available on ReadtheDocs. 📙📗📘

About

A Python package for automatically cleaning the short text present in maintenance work orders and strategies.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 4

  •  
  •  
  •  
  •  

Languages