Beyonce-Words

tidyTuesday beyonce_lyrics

Load the data.

beyonce_lyrics <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2020/2020-09-29/beyonce_lyrics.csv')

## 
## ── Column specification ────────────────────────────────────────────────────────
## cols(
##   line = col_character(),
##   song_id = col_double(),
##   song_name = col_character(),
##   artist_id = col_double(),
##   artist_name = col_character(),
##   song_line = col_double()
## )

str(beyonce_lyrics)

## spec_tbl_df [22,616 × 6] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
##  $ line       : chr [1:22616] "If I ain't got nothing, I got you" "If I ain't got something, I don't give a damn" "'Cause I got it with you" "I don't know much about algebra, but I know 1+1 equals 2" ...
##  $ song_id    : num [1:22616] 50396 50396 50396 50396 50396 ...
##  $ song_name  : chr [1:22616] "1+1" "1+1" "1+1" "1+1" ...
##  $ artist_id  : num [1:22616] 498 498 498 498 498 498 498 498 498 498 ...
##  $ artist_name: chr [1:22616] "Beyoncé" "Beyoncé" "Beyoncé" "Beyoncé" ...
##  $ song_line  : num [1:22616] 1 2 3 4 5 6 7 8 9 10 ...
##  - attr(*, "spec")=
##   .. cols(
##   ..   line = col_character(),
##   ..   song_id = col_double(),
##   ..   song_name = col_character(),
##   ..   artist_id = col_double(),
##   ..   artist_name = col_character(),
##   ..   song_line = col_double()
##   .. )

Beyonce’s Favorite Lyric Words

beyonce_lyrics %>% 
  unnest_tokens(word, line) %>%   # Parse the lyric lines to tidy: one word per row.
  anti_join(., stop_words) %>%    # Remove the stop words
  group_by(word) %>%              # Group them by word
  summarise(Count = n()) %>%      # How common is the word?
  top_n(25) %>%                   # Keep the top 25
  ggplot() + 
  aes(x=fct_reorder(word, Count), y=Count) + 
  geom_col() + 
  coord_flip() + 
  labs(x="Word", title="Beyonce's Top Words in Lyrics")

## Joining, by = "word"

## Selecting by Count

Beyonce’s Cloud

library(wordcloud2)
beyonce_lyrics %>% 
  unnest_tokens(word, line) %>%   # Parse the lyric lines to tidy: one word per row.
  anti_join(., stop_words) %>%    # Remove the stop words
  group_by(word) %>%              # Group them by word
  summarise(Count = n()) %>%      # How common is the word?
  wordcloud2::wordcloud2(size = 0.7, shuffle = TRUE) -> WC111

## Joining, by = "word"

# htmlwidgets::saveWidget(widgetframe::frameWidget(WC111), file='widgets/wcbey.html')
# MyWC
# widgetframe::frameWidget(WC111)
WC111

library(wordcloud2)
MyDat <- beyonce_lyrics %>% 
  unnest_tokens(word, line) %>%   # Parse the lyric lines to tidy: one word per row.
  anti_join(., stop_words) %>%    # Remove the stop words
  group_by(word) %>%              # Group them by word
  summarise(freq = n()) %>%      # How common is the word?
  arrange(desc(freq))
MyWC <- wordcloud2::letterCloud(MyDat, word="Most Popular \n Words in \n Beyonce \n Lyrics", wordSize = 1.75, backgroundColor="lightblue", color='random-dark', size=0.8)
htmlwidgets::saveWidget(widgetframe::frameWidget(MyWC), file='widgets/beyonce.html')
# MyWC
# widgetframe::frameWidget(MyWC)

Something about this does not seem to work now.