load data
df <- read_csv("playlist - data_clean.csv")
## Rows: 144 Columns: 3
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (3): genre, artist, title
##
## 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.
genreCount <- df %>% count(genre)
genreCount
## # A tibble: 6 × 2
## genre n
## <chr> <int>
## 1 Genre 1 - hiphop/rap 26
## 2 Genre 2 - pop/kpop/Latin 22
## 3 Genre 3 - house/ska 5
## 4 Genre 4 - rnb/soul 43
## 5 Genre 5 - alt/indie/folk 34
## 6 Genre 6 - country/rock 14
genreCount %>% mutate(probability = n / 144*100)
## # A tibble: 6 × 3
## genre n probability
## <chr> <int> <dbl>
## 1 Genre 1 - hiphop/rap 26 18.1
## 2 Genre 2 - pop/kpop/Latin 22 15.3
## 3 Genre 3 - house/ska 5 3.47
## 4 Genre 4 - rnb/soul 43 29.9
## 5 Genre 5 - alt/indie/folk 34 23.6
## 6 Genre 6 - country/rock 14 9.72
head(genreCount)
## # A tibble: 6 × 2
## genre n
## <chr> <int>
## 1 Genre 1 - hiphop/rap 26
## 2 Genre 2 - pop/kpop/Latin 22
## 3 Genre 3 - house/ska 5
## 4 Genre 4 - rnb/soul 43
## 5 Genre 5 - alt/indie/folk 34
## 6 Genre 6 - country/rock 14
ten <- sample_n(df, 10)
ten
## # A tibble: 10 × 3
## genre artist title
## <chr> <chr> <chr>
## 1 Genre 5 - alt/indie/folk Fleetwood Mac Landslide
## 2 Genre 4 - rnb/soul sza snooze
## 3 Genre 5 - alt/indie/folk Taylor Swift Peace
## 4 Genre 1 - hiphop/rap Outkast Hey Ya
## 5 Genre 1 - hiphop/rap Ken carson Murda musik
## 6 Genre 5 - alt/indie/folk The Shins New Slang
## 7 Genre 4 - rnb/soul Jhene Aiko Stranger
## 8 Genre 2 - pop/kpop/Latin ariana grande honeymoon avenue
## 9 Genre 5 - alt/indie/folk The Weather Machine Back O'er Oregon
## 10 Genre 4 - rnb/soul Thee sacred souls For now
six <- sample_n(df, 6)
seven <- sample_n(df, 7)
nine <- sample_n(df, 9)