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. 📙📗📘