Module 11: Apply it to your data 10

Import your data

taylor_album_songs <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2023/2023-10-17/taylor_album_songs.csv')

## Rows: 194 Columns: 29
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr   (7): album_name, track_name, artist, featuring, key_name, mode_name, k...
## dbl  (14): track_number, danceability, energy, key, loudness, mode, speechin...
## lgl   (4): ep, bonus_track, explicit, lyrics
## date  (4): album_release, promotional_release, single_release, track_release
## 
## 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.

Chapter 15

Create a factor

taylor_album_songs %>%
    count(album_name)

## # A tibble: 10 × 2
##    album_name                      n
##    <chr>                       <int>
##  1 1989                           16
##  2 Fearless (Taylor's Version)    26
##  3 Lover                          18
##  4 Midnights                      23
##  5 Red (Taylor's Version)         30
##  6 Speak Now                      17
##  7 Taylor Swift                   15
##  8 evermore                       17
##  9 folklore                       17
## 10 reputation                     15

x1 <- c("1989", "Fearless (Taylor's Version", "Lover", "Midnights", "Red (Taylor's Version", "Speak Now", "Taylor Swift", "evermore", "folklore", "reputation")
album_name_levels <- c("1989", "Fearless (Taylor's Version", "Lover", "Midnights", "Red (Taylor's Version", "Speak Now", "Taylor Swift", "evermore", "folklore", "reputation")
y1 <- factor(x1, levels = album_name_levels)
y1

##  [1] 1989                       Fearless (Taylor's Version
##  [3] Lover                      Midnights                 
##  [5] Red (Taylor's Version      Speak Now                 
##  [7] Taylor Swift               evermore                  
##  [9] folklore                   reputation                
## 10 Levels: 1989 Fearless (Taylor's Version Lover ... reputation

sort(y1)

##  [1] 1989                       Fearless (Taylor's Version
##  [3] Lover                      Midnights                 
##  [5] Red (Taylor's Version      Speak Now                 
##  [7] Taylor Swift               evermore                  
##  [9] folklore                   reputation                
## 10 Levels: 1989 Fearless (Taylor's Version Lover ... reputation

Modify factor order

Make two bar charts here - one before ordering another after

duration_ms_by_album_name <- taylor_album_songs %>%
    group_by(album_name) %>%
    summarise(
        avg_duration_ms = mean(duration_ms, na.rm = TRUE)
    )
duration_ms_by_album_name

## # A tibble: 10 × 2
##    album_name                  avg_duration_ms
##    <chr>                                 <dbl>
##  1 1989                                229438.
##  2 Fearless (Taylor's Version)         245866.
##  3 Lover                               206188.
##  4 Midnights                           208464.
##  5 Red (Taylor's Version)              261328 
##  6 Speak Now                           280583.
##  7 Taylor Swift                        213972.
##  8 evermore                            243817.
##  9 folklore                            236965.
## 10 reputation                          223020.

# Plot
duration_ms_by_album_name %>%
    ggplot(aes(x = avg_duration_ms, y = album_name)) + geom_point()

duration_ms_by_album_name %>%
    ggplot(aes(x = avg_duration_ms, y = fct_reorder(.f = album_name, .x = avg_duration_ms))) + geom_point() +
    # Labeling 
    labs(y = NULL, x = "Mean Duration Ms")

Modify factor levels

Show examples of three functions:

• fct_recode

taylor_album_songs %>% 
    mutate(album_name = fct_recode(album_name, "Red" = "Red (Taylor's Version)")) %>%
    count(album_name)

## # A tibble: 10 × 2
##    album_name                      n
##    <fct>                       <int>
##  1 1989                           16
##  2 evermore                       17
##  3 Fearless (Taylor's Version)    26
##  4 folklore                       17
##  5 Lover                          18
##  6 Midnights                      23
##  7 Red                            30
##  8 reputation                     15
##  9 Speak Now                      17
## 10 Taylor Swift                   15

• fct_collapse

taylor_album_songs %>%
    mutate(album_name = fct_collapse(album_name,
                                     after2020 = c("Midnights", "evermore", "folklore", "Red (Taylor's Version)", "Fearless (Taylor's Version)"),
                                     before2020 = c("1989", "Lover", "reputation", "Speak Now", "Taylor Swift")
                                     )) %>%
    count(album_name)

## # A tibble: 2 × 2
##   album_name     n
##   <fct>      <int>
## 1 before2020    81
## 2 after2020    113

• fct_lump

taylor_album_songs %>%
    mutate(album_name = fct_lump(album_name, n = 5)) %>%
    count(album_name, sort = TRUE)

## # A tibble: 8 × 2
##   album_name                      n
##   <fct>                       <int>
## 1 Other                          46
## 2 Red (Taylor's Version)         30
## 3 Fearless (Taylor's Version)    26
## 4 Midnights                      23
## 5 Lover                          18
## 6 evermore                       17
## 7 folklore                       17
## 8 Speak Now                      17

Chapter 16

No need to do anything here.