imdb-character-importance.R

  # define character count function
  get_character_counts = function(df, show_name, character_name) {
    total_episodes = df %>% filter(show == show_name) %>% nrow()
    character_episodes = df %>% 
      filter(show == show_name) %>% filter(str_detect(description, character_name)) %>% nrow()
    result = tibble(show = show_name, character_name = character_name, 
                    total_episodes = total_episodes, character_episodes = character_episodes)
    return(result)
  }

  # define looping function
  get_all_character_counts = function(df, show_name, character_names) {
    datalist = list()
    for (i in 1:length(character_names)) {
      datalist[[i]] = get_character_counts(all_shows, show_name, character_names[i])
    }
    raw = do.call(rbind, datalist)
    return(raw)
  }

  # the office
  names = c('Michael', 'Dwight', 'Jim', 'Pam', 'Ryan', 'Andy', 'Oscar', 'Stanley', 'Kevin', 'Meredith', 'Angela', 'Phyllis', 'Toby', 'Kelly', 'Darryl')
  the_office = get_all_character_counts(all_shows, 'The Office', names)