Package: grafzahl 0.0.12

Chung-hong Chan

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>.

Authors:Chung-hong Chan [aut, cre]

grafzahl_0.0.12.tar.gz
grafzahl_0.0.12.zip(r-4.7)grafzahl_0.0.12.zip(r-4.6)grafzahl_0.0.12.zip(r-4.5)
grafzahl_0.0.12.tgz(r-4.6-any)grafzahl_0.0.12.tgz(r-4.5-any)
grafzahl_0.0.12.tar.gz(r-4.7-any)grafzahl_0.0.12.tar.gz(r-4.6-any)
grafzahl_0.0.12.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION
card.svg |card.png
grafzahl/json (API)

# Install 'grafzahl' in R:

install.packages('grafzahl', repos = c('https://gesistsa.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/gesistsa/grafzahl/issues

Pkgdown/docs site:https://gesistsa.github.io

Datasets:

ecosent - A Corpus Of Dutch News Headlines
supported_model_types - Supported model types
unciviltweets - A Corpus Of Tweets With Incivility Labels

On CRAN:

6.24 score 43 stars 5 scripts 176 downloads 8 exports 46 dependencies

Last updated from:9040661931. Checks:9 OK. Indexed: yes.

Target	Result	Time
linux-devel-x86_64	OK	183
source / vignettes	OK	196
linux-release-x86_64	OK	164
macos-release-arm64	OK	129
macos-oldrel-arm64	OK	110
windows-devel	OK	122
windows-release	OK	77
windows-oldrel	OK	97
wasm-release	OK	121

Exports:detect_conda detect_cuda get_amharic_data grafzahl hydrate setup_grafzahl textmodel_transformer use_nonconda

Dependencies:assertthat cli codetools cpp11 farver fastmatch foreach ggplot2 glmnet glue gower gtable here isoband ISOcodes iterators jsonlite labeling lattice lifecycle lime magrittr Matrix png quanteda R6 rappdirs RColorBrewer Rcpp RcppEigen RcppTOML reticulate rlang rprojroot S7 scales shape SnowballC stopwords stringi survival vctrs viridisLite withr xml2 yaml

Setup Guide

Rendered fromgrafzahl.Rmdusingknitr::rmarkdown

Last update: 2024-03-25
Started: 2024-03-25

Citation

Development and contributors

Readme and manuals

Help Manual

Help page	Topics
Detecting Miniconda And Cuda	detect_conda detect_cuda
A Corpus Of Dutch News Headlines	ecosent
Download The Amharic News Text Classification Dataset	get_amharic_data
Fine tune a pretrained Transformer model for texts	grafzahl grafzahl.character grafzahl.corpus grafzahl.default textmodel_transformer
Create a grafzahl S3 object from the output_dir	hydrate
Prediction from a fine-tuned grafzahl object	predict.grafzahl
Setup grafzahl	setup_grafzahl
Supported model types	supported_model_types
A Corpus Of Tweets With Incivility Labels	unciviltweets
Set up grafzahl to be used on Google Colab or similar environments	use_nonconda