Springsteen Setlist Similarity

springsteen_sets.R

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

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

download.file(url = 'https://blog.ticketmaster.com/wp-content/uploads/BruceSpringsteen_Blog.jpg',
              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)
  }
}

map(1:3, function(x) {
  paste0('https://www.setlist.fm/setlists/bruce-springsteen-2bd6dcce.html?page=',
         x) %>%
    read_html %>%
    html_nodes('a') %>%
    html_attr('href') %>%
    str_squish %>%
    .[grepl('setlist/bruce-springsteen/2023/', .)] %>%
    sub("..", "", .) %>%
    paste0('https://www.setlist.fm/', .)
}) %>%
  unlist -> boss_set

map_dfr(boss_set, function(x) {
  Sys.sleep(5)
  print(x)
  read_html(x) -> web
  
  tibble(
    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("Bruce Springsteen Setlist at ", "", .),
    songs = web %>%
      html_nodes('.songPart') %>%
      html_text %>%
      str_squish,
    set_length = web %>%
      html_nodes('.hiddenCollapsed') %>%
      html_text %>%
      str_squish %>%
      unique %>%
      .[grepl("End", .)] %>%
      sub(".*[A-Z][M]", "", .) %>%
      sub(" long", "", .)
  ) %>%
    mutate(
      song_number = row_number(),
      set_hrs = sub("[h].*", "", set_length) %>% as.numeric,
      set_mins = sub(".*[h] ", "", set_length) %>%
        sub("m", "", .) %>%
        as.numeric
    )
}) %>%
  group_by(date, location, set_length, set_hrs, set_mins) %>%
  mutate(show_id = cur_group_id()) %>%
  ungroup %>%
  select(8,
         1:2,
         4,
         6:7,
         5:3) -> boss_songs

boss_songs %>%
  group_by(show = sub(", USA", "", location) %>%
             sub(", ", " (", .) %>%
             paste0(., ")"),
           show_id) %>%
  summarize(songs = paste(songs %>% sort, collapse = '| ')) %>%
  ungroup %>%
  select(-show_id) -> boss_sum

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

theme_gtm <- function(base_size = 14,
                      base_family = "Tahoma") {
  (
    theme_foundation(base_size = base_size, base_family = base_family)
    + theme(
      plot.title = element_text(
        face = "bold",
        size = rel(1.2),
        hjust = 0.5
      ),
      text = element_text(),
      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),
      legend.position = "bottom",
      legend.direction = "horizontal",
      legend.key.size = unit(0.2, "cm"),
      legend.spacing = unit(0, "cm"),
      legend.title = element_text(face = "bold"),
      plot.margin = unit(c(15, 5, 5, 5), "mm"),
      plot.subtitle = element_text(hjust = 0.5),
      plot.caption = element_text(hjust = 0.5),
      strip.background = element_rect(colour = "#f0f0f0", fill = "#f0f0f0"),
      strip.text = element_text(face = "bold")
    )
  )
  
}

boss_sum %>%
  select(-songs) %>%
  bind_cols(map_dfc(1:nrow(boss_sum), function(x) {
    boss_sum %>%
      mutate(sim = jarowinkler(songs, songs[x])) %>%
      select(sim) %>%
      setNames(boss_sum[1][x, ])
  })) %>%
  gather(comp, similarity,-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 = 3) +
  scale_fill_gradient(low = '#FFFFFF',
                      high = '#f44c3c',
                      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 = "Bruce Springsteen 2023 Tour Setlist Similarity",
    subtitle = NULL,
    caption = "Chart: Benjamin Robinson (@benj_robinson) | Data: SetList.FM, 2023."
  )

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

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

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