grafzahl: Supervised Machine Learning for Textual Data Using Transformers and 'Quanteda'

Duct tape the 'quanteda' ecosystem (Benoit et al., 2018) <doi:10.21105/joss.00774> to modern Transformer-based text classification models (Wolf et al., 2020) <doi:10.18653/v1/2020.emnlp-demos.6>, in order to facilitate supervised machine learning for textual data. This package mimics the behaviors of 'quanteda.textmodels' and provides a function to setup the 'Python' environment to use the pretrained models from 'Hugging Face' <https://huggingface.co/>. More information: <doi:10.5117/CCR2023.1.003.CHAN>.

Version: 0.0.8
Depends: R (≥ 3.5)
Imports: jsonlite, lime, quanteda, reticulate, utils, stats
Suggests: quanteda.textmodels, testthat (≥ 3.0.0), withr
Published: 2023-04-12
Author: Chung-hong Chan ORCID iD [aut, cre]
Maintainer: Chung-hong Chan <chainsawtiney at gmail.com>
BugReports: https://github.com/chainsawriot/grafzahl/issues
License: GPL (≥ 3)
URL: https://github.com/chainsawriot/grafzahl
NeedsCompilation: no
Citation: grafzahl citation info
CRAN checks: grafzahl results

Documentation:

Reference manual: grafzahl.pdf

Downloads:

Package source: grafzahl_0.0.8.tar.gz
Windows binaries: r-devel: grafzahl_0.0.8.zip, r-release: grafzahl_0.0.8.zip, r-oldrel: grafzahl_0.0.8.zip
macOS binaries: r-release (arm64): grafzahl_0.0.8.tgz, r-oldrel (arm64): grafzahl_0.0.8.tgz, r-release (x86_64): grafzahl_0.0.8.tgz
Old sources: grafzahl archive

Linking:

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