emend: Cleaning Text Data with an AI Assistant

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.

Version: 0.1.0
Depends: R (≥ 4.1.0)
Imports: cli, jsonlite, rlang, ellmer
Suggests: rmarkdown, testthat (≥ 3.0.0)
Published: 2025-04-01
DOI: 10.32614/CRAN.package.emend
Author: Emi Tanaka ORCID iD [aut, cph], Jiajia Li ORCID iD [aut, cre]
Maintainer: Jiajia Li <lijia970324 at gmail.com>
BugReports: https://github.com/anuopensci/emend/issues
License: MIT + file LICENSE
URL: https://github.com/anuopensci/emend, https://anuopensci.github.io/emend/
NeedsCompilation: no
Materials: README NEWS
CRAN checks: emend results

Documentation:

Reference manual: emend.pdf

Downloads:

Package source: emend_0.1.0.tar.gz
Windows binaries: r-devel: emend_0.1.0.zip, r-release: emend_0.1.0.zip, r-oldrel: emend_0.1.0.zip
macOS binaries: r-devel (arm64): not available, r-release (arm64): not available, r-oldrel (arm64): not available, r-devel (x86_64): not available, r-release (x86_64): not available, r-oldrel (x86_64): not available

Linking:

Please use the canonical form https://CRAN.R-project.org/package=emend to link to this page.