library(tidyverse)
top_albums <- read_csv("http://jamessuleiman.com/teaching/datasets/Rolling_Stones_Top_500_Albums.csv",
locale = locale(encoding = "ISO-8859-2",
asciify = TRUE))
str(top_albums)
## spc_tbl_ [500 × 6] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
## $ Number : num [1:500] 1 2 3 4 5 6 7 8 9 10 ...
## $ Year : num [1:500] 1967 1966 1966 1965 1965 ...
## $ Album : chr [1:500] "Sgt. Pepper's Lonely Hearts Club Band" "Pet Sounds" "Revolver" "Highway 61 Revisited" ...
## $ Artist : chr [1:500] "The Beatles" "The Beach Boys" "The Beatles" "Bob Dylan" ...
## $ Genre : chr [1:500] "Rock" "Rock" "Rock" "Rock" ...
## $ Subgenre: chr [1:500] "Rock & Roll, Psychedelic Rock" "Pop Rock, Psychedelic Rock" "Psychedelic Rock, Pop Rock" "Folk Rock, Blues Rock" ...
## - attr(*, "spec")=
## .. cols(
## .. Number = col_double(),
## .. Year = col_double(),
## .. Album = col_character(),
## .. Artist = col_character(),
## .. Genre = col_character(),
## .. Subgenre = col_character()
## .. )
## - attr(*, "problems")=<externalptr>
top_albums %>% distinct(Artist)
## # A tibble: 289 × 1
## Artist
## <chr>
## 1 The Beatles
## 2 The Beach Boys
## 3 Bob Dylan
## 4 Marvin Gaye
## 5 The Rolling Stones
## 6 The Clash
## 7 Elvis Presley
## 8 Miles Davis
## 9 The Velvet Underground
## 10 The Jimi Hendrix Experience
## # ℹ 279 more rows
top_albums %>% distinct(Genre)
## # A tibble: 63 × 1
## Genre
## <chr>
## 1 Rock
## 2 Rock, Pop
## 3 Funk / Soul
## 4 Rock, Blues
## 5 Jazz
## 6 Jazz, Rock, Blues, Folk, World, & Country
## 7 Funk / Soul, Pop
## 8 Blues
## 9 Pop
## 10 Rock, Folk, World, & Country
## # ℹ 53 more rows
top_albums %>% distinct(Artist, Genre)
## # A tibble: 342 × 2
## Artist Genre
## <chr> <chr>
## 1 The Beatles Rock
## 2 The Beach Boys Rock
## 3 Bob Dylan Rock
## 4 The Beatles Rock, Pop
## 5 Marvin Gaye Funk / Soul
## 6 The Rolling Stones Rock
## 7 The Clash Rock
## 8 Bob Dylan Rock, Blues
## 9 Elvis Presley Rock
## 10 Miles Davis Jazz
## # ℹ 332 more rows
artist_genre <- top_albums %>% group_by(Artist, Genre) %>% mutate(count_album=n()) %>% select(Genre, Artist, count_album) %>% distinct(Genre, Artist, count_album) %>%
ungroup() %>% slice_max(order_by = count_album, n = 15, with_ties = FALSE)
artist_genre2 <- top_albums %>% group_by(Artist, Genre) %>% mutate(count_album=n()) %>% select(Genre, Artist, count_album) %>% distinct(Genre, Artist, count_album) %>%
ungroup()
artist_genre3 <- inner_join(artist_genre, artist_genre2, by="Artist") %>% rename(Genre = Genre.y, count_album = count_album.y) %>% select(Genre, Artist, count_album)
artist_genre3 %>%
mutate(Artist = fct_reorder(Artist, count_album, .fun='sum')) %>%
ggplot(aes(x = Artist, y = count_album, colour = Genre)) + geom_point(size = 3, pch = 16, position = position_dodge(width = 0.5))+
scale_colour_brewer(palette = "Paired") +
scale_y_discrete(name ="Number of Albums on top 500 list",
limits=c("1","2", "3", "4", "5", "6", "7", "8", "9", "10")) +
theme_minimal() +
labs(title="Artists with the Most Number of Albums on Top 500 (by Album Genre)") + theme(plot.title = element_text(hjust = 0.5)) +
coord_flip()
