tidylo-example.R

library(dplyr)
library(janeaustenr)
library(tidytext)
library(tidylo)
library(ggplot2)

tidy_bigrams <- austen_books() %>%
  unnest_tokens(bigram, text, token = "ngrams", n = 2)

# bigrams across books
tidy_bigrams

bigram_counts <- tidy_bigrams %>%
  count(book, bigram, sort = TRUE)

bigram_counts

bigram_log_odds <- bigram_counts %>%
  bind_log_odds(book, bigram, n)

bigram_log_odds

bigram_log_odds %>%
  group_by(book) %>%
  slice_max(log_odds_weighted, n = 10) %>%
  ungroup() %>%
  mutate(bigram = reorder(bigram, log_odds_weighted)) %>%
  ggplot(aes(bigram, log_odds_weighted, fill = book)) +
  geom_col(show.legend = FALSE) + 
  facet_wrap(~book, scales = "free") +
  coord_flip() +
  labs(x = NULL)