问文本挖掘软件包.入门级

EN

library(tidytext)
library(dplyr)

somewords <- "the lorem ipsum text with some common words.. very common words can be found quite often. these are often commonly used words enmeshed with lorem ipsum."

tibble(somewords) %>%
  unnest_tokens(word, somewords) %>%
  group_by(word) %>%
  count() %>%
  arrange(desc(n))

tibble(somewords) %>%
  unnest_tokens(word, somewords) %>%
  filter(!word %in% stop_words$word)

bigrams <- tibble(somewords) %>%
  unnest_tokens(bigram, somewords, token = "ngrams", n = 2)

bigrams <- bigrams %>%
  count(bigram, sort = TRUE)