Add files for package data

Author: koheiw

R/data.R

@@ -0,0 +1,10 @@
+#' Yahoo News summaries from 2014
+#'
+#' A corpus object containing 2,000 news summaries collected from Yahoo News via
+#' RSS feeds in 2014.
+#' @name data_corpus_news2014
+#' @references Watanabe, K. (2018). Newsmap: A semi-supervised approach to
+#' geographical news classification. Digital Journalism, 6(3), 294–309.
+#' https://doi.org/10.1080/21670811.2017.1293487
+#' @source <https://www.yahoo.com/news/>
+"data_corpus_news2014"

inst/data.R

@@ -0,0 +1,11 @@
+library(quanteda)
+
+dat <- readRDS('~/yahoo-news.RDS')
+dat$text <- paste0(dat$head, ". ", dat$body)
+dat$body <- NULL
+corp <- corpus(dat, text_field = 'text')
+
+set.seed(1234)
+data_corpus_news2014 <- corpus_sample(corp, 20000)
+
+usethis::use_data(data_corpus_news2014)