emend0.1.0 package

Cleaning Text Data with an AI Assistant

emend-package

emend: Cleaning Text Data with an AI Assistant

get_default_chat

Get or create the default chat object

emend_what_language

Identify the language in the text.

emend_clean_address

Standardise address format

emend_clean_date

Standardise date format

emend_fct_match

Match input factor to specified levels.

emend_fct_reorder

Reorder the levels of the input factor in a meaningful way.

emend_lvl_match

Match the input factor to supplied levels.

emend_lvl_unique

Get the unique levels of messy categorical data

emend_translate

Translate text from one language to another.

Download source packageRead PDF manual

Provides functions to clean and standardize messy data, including textual categories and free-text addresses, using Large Language Models. The package corrects typos, expands abbreviations, and maps inconsistent entries to standardized values. Ideal for Bioinformatics, business, and general data cleaning tasks.

  • Maintainer: Jiajia Li
  • License: MIT + file LICENSE
  • Last published: 2025-04-01

Useful links