Read 20 Newsgroups data in R as a datatable (dataframe)

read_20newsgroups.R

# Read 20newsgroups data as a datatable (dataframe)
# Author: Srikanth KS
# license: GPL-3
#
# download data from here:
# https://archive.ics.uci.edu/ml/machine-learning-databases/20newsgroups-mld/20_newsgroups.tar.gz
# extract it and provide its location to `baseDir` on line 9

baseDir        = "Downloads/20_newsgroups"
newsGroupNames = list.files(baseDir, full.names = TRUE)

readText = function(directory) {
  textFileNames = list.files(directory, full.names = TRUE)
  text          = vapply(textFileNames
                         , function(x) paste(readLines(x), collapse = " ")
                         , character(1)
                         )

  data.table::data.table(newsgroup  = basename(directory)
                         , fileName = basename(textFileNames)
                         , text     = text
                         )
}

news20 = data.table::rbindlist(lapply(newsGroupNames, readText))
# to convert news20 into a dataframe, run: `data.table::setDF(news20)`