Taylor Swift Eras Tour Setlist Similarity

swift_sets.R

library(dplyr)
library(rvest)
library(stringr)
library(purrr)
library(tidyr)
library(janitor)
library(RecordLinkage)
library(ggplot2)
library(scales)
library(ggthemes)
library(magick)
library(forcats)

## ENTER LOCAL DIRECTORY WITHOUT QUOTE MARKS ##
dir = readline()

download.file(url = 'https://i.iheart.com/v3/re/new_assets/6372707fb66c34b0905cb19d?ops=gravity(%22north%22),fit(1200,675),quality(65)',
              destfile = paste0(dir, "tour.png"),
              mode = 'wb')

add_logo <- function(plot_path,
                     logo_path,
                     logo_position = 'top left',
                     logo_scale = 5,
                     save = FALSE) {
  if (!logo_position %in% c("top right", "top left", "bottom right", "bottom left")) {
    stop(
      "Error Message: Uh oh! Logo Position not recognized\n  Try: logo_positon = 'top left', 'top right', 'bottom left', or 'bottom right'"
    )
  }
  
  # read in raw images
  plot <- image_read(plot_path)
  logo_raw <- image_read(logo_path)
  
  # get dimensions of plot for scaling
  plot_height <- image_info(plot)$height
  plot_width <- image_info(plot)$width
  
  # default scale to 1/10th width of plot
  # Can change with logo_scale
  logo <-
    image_scale(logo_raw, as.character(plot_width / logo_scale))
  
  # Get width of logo
  logo_width <- image_info(logo)$width
  logo_height <- image_info(logo)$height
  
  # Set position of logo
  # Position starts at 0,0 at top left
  # Using 0.01 for 1% - aesthetic padding
  
  if (logo_position == "top right") {
    x_pos = plot_width - logo_width - 0.01 * plot_width
    y_pos = 0.01 * plot_height
  } else if (logo_position == "top left") {
    x_pos = 0.01 * plot_width
    y_pos = 0.01 * plot_height
  } else if (logo_position == "bottom right") {
    x_pos = plot_width - logo_width - 0.01 * plot_width
    y_pos = plot_height - logo_height - 0.01 * plot_height
  } else if (logo_position == "bottom left") {
    x_pos = 0.01 * plot_width
    y_pos = plot_height - logo_height - 0.01 * plot_height
  }
  
  # Compose the actual overlay
  image_composite(plot, logo, offset = paste0("+", x_pos, "+", y_pos)) -> plot
  
  if (save == TRUE) {
    image_ggplot(plot)
    
    ggsave(
      plot_path,
      height = 8,
      width = 8,
      units = 'in',
      dpi = 'retina'
    )
  } else if (save == FALSE) {
    plot(plot)
  }
}

'https://www.setlist.fm/search?artist=3bd6bc5c&page=2&query=tour:%28The+Eras+Tour%29' %>%
    read_html %>%
    html_nodes('.listPager-lg') %>%
    html_text %>%
    str_squish %>%
    str_split('') %>%
    unlist %>%
    as.numeric %>%
    max -> max_pg

map(1:max_pg, function(x) {
  paste0('https://www.setlist.fm/search?artist=3bd6bc5c&page=', x, '&query=tour:%28The+Eras+Tour%29') %>%
    read_html %>%
    html_nodes('a') %>%
    html_attr('href') %>%
    str_squish %>%
    unique %>%
    .[grepl("setlist/taylor-swift", .)] %>%
    paste0('https://www.setlist.fm/', .)
}) %>%
  unlist -> swift_set

map_dfr(swift_set, function(x) {
  Sys.sleep(5)
  print(x)
  read_html(x) -> web
  
  tibble(
    show_url = x,
    show_id = sub(".*2023/", "", x) %>%
    sub(".html", "", .),
    date = web %>%
      html_nodes('.dateBlock') %>%
      html_text %>%
      str_squish %>%
      as.Date(format = "%b %d %Y"),
    location = web %>%
      html_nodes('.setlistHeadline') %>%
      html_text %>%
      str_squish %>%
      sub(" Edit.*", "", .) %>%
      sub("Taylor Swift Setlist at ", "", .),
    song_name = web %>%
      html_nodes('.songLabel') %>%
      html_text %>%
      str_squish %>%
      unique,
    song_id = web %>%
    html_nodes('.songLabel') %>%
    html_attr('href') %>%
    sub(".*=", "", .) %>%
    unique
  ) %>%
    mutate(
      song_number = row_number()
    )
}) %>% distinct -> swift_songs

swift_songs %>%
    group_by(date,
             show = sub(", USA", "", location) %>%
                 sub(", ", " (", .) %>%
                 paste0(., ")"),
             show_id) %>%
    summarize(songs = paste(song_name %>% sort, collapse = '| ')) %>%
    ungroup %>%
    group_by(show) %>%
    mutate(id = row_number()) %>%
    ungroup %>%
    mutate(show = paste0(show, " - ", id),
           show = forcats::fct_reorder(show, date)) %>%
    select(-id, -show_id, -date) %>%
    arrange(show) -> swift_sum

suppressWarnings(windowsFonts("Tahoma" = windowsFont("Tahoma")))

swift_sum %>%
    select(-songs) %>%
    bind_cols(map_dfc(1:nrow(swift_sum), function(x) {
        swift_sum %>%
            mutate(sim = jarowinkler(songs, songs[x])) %>%
            select(sim) %>%
            setNames(swift_sum$show[x])
    })) %>%
    gather(comp, similarity, -show) %>%
    mutate(comp = factor(comp, levels = swift_sum$show)) %>%
  ggplot(aes(
    x = show,
    y = comp,
    fill = similarity,
    label = percent(similarity, accuracy = 1),
    fontface = ifelse(show == comp, "bold", "plain")
  )) +
  geom_tile(color = 'black') +
  geom_text(size = 2.5) +
  scale_fill_gradient(low = '#FFFFFF',
                      high = '#b8396b',
                      labels = percent) +
  scale_x_discrete(position = "top") +
  theme_foundation(base_size = 14, base_family = 'Tahoma') +
  theme(
    axis.text.x = element_text(angle = 45, hjust = -.05),
    legend.position = 'right',
    legend.direction = 'vertical',
    plot.title = element_text(
      face = "bold",
      size = rel(1.2),
      hjust = 0.5
    ),
    strip.background = element_rect(colour = "#f0f0f0", fill = "#f0f0f0"),
    strip.text = element_text(face = "bold"),
    panel.background = element_rect(colour = NA),
    plot.background = element_rect(colour = NA),
    panel.border = element_rect(colour = NA),
    axis.title = element_text(face = "bold", size = rel(1)),
    axis.title.y = element_text(angle = 90, vjust = 2),
    axis.title.x = element_text(vjust = -0.2),
    axis.text = element_text(),
    axis.line.x = element_line(colour = "black"),
    axis.line.y.left = element_line(colour = "black"),
    axis.line.y.right  = element_blank(),
    axis.ticks = element_line(),
    panel.grid.major = element_line(colour = "#f0f0f0"),
    panel.grid.minor = element_blank(),
    legend.key = element_rect(colour = NA)
  ) +
  labs(
    x = NULL,
    y = NULL,
    fill = 'Jarow-Winkler Score',
    title = "Taylor Swift's Era's Tour Setlist Similarity",
    subtitle = NULL,
    caption = "Chart: Benjamin Robinson (@benj_robinson) | Data: SetList.FM, 2023."
  )

ggsave(
  paste0(dir, "tswift.PNG"),
  height = 7.5,
  width = 15,
  units = 'in',
  dpi = 'retina'
)

add_logo(plot_path = paste0(dir, "tswift.PNG"),
         logo_path = paste0(dir, "tour.PNG"),
         save = TRUE)

image_read(path = paste0(dir, "tswift.PNG")) %>%
  image_trim %>%
  image_write(path = paste0(dir, "tswift.PNG"))