text <- c("Because I could not stop for Death -",
          "He kindly stopped for me -",
          "The Carriage held but just Ourselves -",
          "and Immortality")
library(dplyr)
## 
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union
text_df <- tibble(line = 1:4, text = text)
text_df
## # A tibble: 4 × 2
##    line text                                  
##   <int> <chr>                                 
## 1     1 Because I could not stop for Death -  
## 2     2 He kindly stopped for me -            
## 3     3 The Carriage held but just Ourselves -
## 4     4 and Immortality
library(tidytext)

text_df %>%
  unnest_tokens(word, text)
## # A tibble: 20 × 2
##     line word       
##    <int> <chr>      
##  1     1 because    
##  2     1 i          
##  3     1 could      
##  4     1 not        
##  5     1 stop       
##  6     1 for        
##  7     1 death      
##  8     2 he         
##  9     2 kindly     
## 10     2 stopped    
## 11     2 for        
## 12     2 me         
## 13     3 the        
## 14     3 carriage   
## 15     3 held       
## 16     3 but        
## 17     3 just       
## 18     3 ourselves  
## 19     4 and        
## 20     4 immortality
library(janeaustenr)
library(stringr)

original_books <- austen_books() %>%
  group_by(book) %>%
  mutate(linenumber = row_number(),
         chapter = cumsum(str_detect(text, 
                                     regex("^chapter [\\divxlc]",
                                           ignore_case = TRUE)))) %>%
  ungroup()

tidy_books <- original_books %>%
  unnest_tokens(word, text)

data(stop_words)

tidy_books <- tidy_books %>%
  anti_join(stop_words)
## Joining with `by = join_by(word)`
tidy_books %>%
  count(word, sort = TRUE)
## # A tibble: 13,910 × 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
## # ℹ 13,900 more rows
library(ggplot2)

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

## Reference https://www.tidytextmining.com/tidytext