24.3 Stop words and Frequencies

tidy_books %>%
  count(word, sort = TRUE) 
## # A tibble: 14,520 x 2
##    word      n
##    <chr> <int>
##  1 the   26351
##  2 to    24044
##  3 and   22515
##  4 of    21178
##  5 a     13408
##  6 her   13055
##  7 i     12006
##  8 in    11217
##  9 was   11204
## 10 it    10234
## # ... with 14,510 more rows

data(stop_words)

tidy_books <- tidy_books %>%
  anti_join(stop_words)
## Joining, by = "word"

tidy_books %>%
  count(word, sort = TRUE) 
## # A tibble: 13,914 x 2
##    word       n
##    <chr>  <int>
##  1 miss    1855
##  2 time    1337
##  3 fanny    862
##  4 dear     822
##  5 lady     817
##  6 sir      806
##  7 day      797
##  8 emma     787
##  9 sister   727
## 10 house    699
## # ... with 13,904 more rows

library(ggplot2)

tidy_books %>%
  count(word, sort = TRUE) %>%
  filter(n > 600) %>%
  mutate(word = reorder(word, n)) %>%
  ggplot(aes(word, n)) +
  geom_col() +
  xlab(NULL) +
  coord_flip()