Import data
# csv file
data <- read_csv("../00_data/myData.csv")
## New names:
## Rows: 691 Columns: 22
## ── Column specification
## ──────────────────────────────────────────────────────── Delimiter: "," chr
## (8): sort_name, clean_name, album, genre, type, spotify_url, artist_gen... dbl
## (14): ...1, rank_2003, rank_2012, rank_2020, differential, release_year,...
## ℹ Use `spec()` to retrieve the full column specification for this data. ℹ
## Specify the column types or set `show_col_types = FALSE` to quiet this message.
## • `` -> `...1`
data
## # A tibble: 691 × 22
## ...1 sort_name clean_name album rank_2003 rank_2012 rank_2020 differential
## <dbl> <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl>
## 1 1 Sinatra, F… Frank Sin… "In … 100 101 282 -182
## 2 2 Diddley, Bo Bo Diddley "Bo … 214 216 455 -241
## 3 3 Presley, E… Elvis Pre… "Elv… 55 56 332 -277
## 4 4 Sinatra, F… Frank Sin… "Son… 306 308 NA -195
## 5 5 Little Ric… Little Ri… "Her… 50 50 227 -177
## 6 6 Beyonce Beyonce "Lem… NA NA 32 469
## 7 7 Winehouse,… Amy Wineh… "Bac… NA 451 33 468
## 8 8 Crickets Buddy Hol… "The… 421 420 NA -80
## 9 9 Bush, Kate Kate Bush "Hou… NA NA 68 433
## 10 10 Davis, Mil… Miles Dav… "Kin… 12 12 31 -19
## # ℹ 681 more rows
## # ℹ 14 more variables: release_year <dbl>, genre <chr>, type <chr>,
## # weeks_on_billboard <dbl>, peak_billboard_position <dbl>,
## # spotify_popularity <dbl>, spotify_url <chr>, artist_member_count <dbl>,
## # artist_gender <chr>, artist_birth_year_sum <dbl>,
## # debut_album_release_year <dbl>, ave_age_at_top_500 <dbl>,
## # years_between <dbl>, album_id <chr>
Plot data
data %>%
ggplot(aes(genre)) +
geom_bar()
