if (FALSE) {
require(quanteda)
corpus <- data_corpus_inaugural
corpus <- head(corpus, n = 10)
corpus <- split_segments(corpus)
tok <- tokens(corpus, remove_punct = TRUE)
tok <- tokens_remove(tok, stopwords("en"))
dtm <- dfm(tok, tolower = TRUE)
dtm <- dfm_trim(dtm, min_docfreq = 3)
res <- rainette(dtm, k = 3, min_segment_size = 15)
rainette_explor(res, dtm, corpus)
}
Run the code above in your browser using DataLab