In EmilHvitfeldt/textrecipes: Extra 'Recipes' for Text Processing

#| label: setup
#| include: false
knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  fig.path = "man/figures/README-",
  out.width = "100%"
)

textrecipes

Introduction

textrecipes contain extra steps for the recipes package for preprocessing text data.

Installation

You can install the released version of textrecipes from CRAN with:

#| eval: false
install.packages("textrecipes")

Install the development version from GitHub with:

#| label: installation
#| eval: false
# install.packages("pak")
pak::pak("tidymodels/textrecipes")

Example

In the following example we will go through the steps needed, to convert a character variable to the TF-IDF of its tokenized words after removing stopwords, and, limiting ourself to only the 10 most used words. The preprocessing will be conducted on the variable medium and artist.

#| message: false
library(recipes)
library(textrecipes)
library(modeldata)

data("tate_text")

okc_rec <- recipe(~ medium + artist, data = tate_text) |>
  step_tokenize(medium, artist) |>
  step_stopwords(medium, artist) |>
  step_tokenfilter(medium, artist, max_tokens = 10) |>
  step_tfidf(medium, artist)

okc_obj <- okc_rec |>
  prep()

str(bake(okc_obj, tate_text))

Breaking changes

As of version 0.4.0, step_lda() no longer accepts character variables and instead takes tokenlist variables.

the following recipe

#| eval: false
recipe(~text_var, data = data) |>
  step_lda(text_var)

can be replaced with the following recipe to achive the same results

#| eval: false
lda_tokenizer <- function(x) text2vec::word_tokenizer(tolower(x))
recipe(~text_var, data = data) |>
  step_tokenize(text_var,
    custom_token = lda_tokenizer
  ) |>
  step_lda(text_var)

Contributing

This project is released with a Contributor Code of Conduct. By contributing to this project, you agree to abide by its terms.

For questions and discussions about tidymodels packages, modeling, and machine learning, please post on RStudio Community.
If you think you have encountered a bug, please submit an issue.
Either way, learn how to create and share a reprex (a minimal, reproducible example), to clearly communicate about your code.
Check out further details on contributing guidelines for tidymodels packages and how to get help.