Count the frequency of letters in some famous books

most_common_letters.R

library(dplyr)
library(tibble)
library(gutenbergr)

# List authors in Project Gutenberg, by number of works (descending)
gutenberg_works() %>% 
  group_by(author) %>%
  summarize(count = n()) %>%
  arrange(desc(count))

gutenberg_works(author == 'Twain, Mark') # List Mark Twain's works in Project Gutenberg
tom <- gutenberg_download(74) # The Adventures of Tom Sawyer
huck <- gutenberg_download(76) # Adventures of Huckleberry Finn
yank <- gutenberg_download(86) # A Connecticut Yankee in King Arthur's Court
miss <- gutenberg_download(245) # Life on the Mississippi

# Combine all books and chapters into a single character vector, split by letter, all lower case
text <- paste(c(huck$text, tom$text, yank$text, miss$text), collapse = ' ') %>%
  tolower() %>% 
  strsplit('', useBytes=TRUE)

# Count number of occurrences of each letter, list count in descending order
letters <- as_tibble(cbind(char = unlist(text))) %>%
  filter(char != ' ') %>%
  group_by(char) %>%
  summarize(count = n()) %>%
  arrange(desc(count))