text2vec_windows_crash.R

library(devtools)
library(magrittr)
install_github("dselivanov/text2vec")
data("movie_review")
# this works fine:
dtm <- create_dict_corpus(src = movie_review[['review']][1:100],
                   preprocess_fun = tolower,
                   tokenizer = regexp_tokenizer,
                   batch_size = 100,
                   progress = F) %>% 
  get_dtm(corpus = corp, type = "dgCMatrix")
dim(dtm)
#but this crashes:
corp <- create_dict_corpus(src = movie_review[['review']][1:100],
                   preprocess_fun = tolower,
                   tokenizer = regexp_tokenizer,
                   batch_size = 100,
                   progress = F)
str(corp)