thedoors.R

library(geniusR)
library(tidyverse)
library(tidytext)

album_texty <- genius_album(artist = "The Doors", album = "The Doors")

tidy_album <- album_texty %>%
  unnest_tokens(word,lyric) %>%
  anti_join(stop_words)

song_words <- tidy_album %>%
  count(track_title, word, sort = TRUE) %>%
  ungroup()

song_words <- song_words %>%
  bind_tf_idf(word, track_title, n) %>%
  arrange(desc(tf_idf))

top <- song_words %>%
  arrange(desc(tf_idf)) %>%
  mutate(text = factor(word, levels = rev(unique(word)))) %>% 
  group_by(track_title) %>% 
  top_n(5) %>% 
  ungroup

top %>%
  mutate(word = factor(word, levels = rev(unique(word)))) %>%
  group_by(track_title) %>%
  top_n(5) %>%
  ungroup() %>%
  ggplot(aes(word, tf_idf, fill = track_title)) +
  geom_col(show.legend = FALSE) +
  labs(x = NULL, y = "tf-idf") +
  facet_wrap(~track_title, ncol = 2, scales = "free") +
  coord_flip()