Tidy Tuesday 10-25-2022: Great British Bakeoff

bakers <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2022/2022-10-25/bakers.csv')

challenges <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2022/2022-10-25/challenges.csv')
ratings <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2022/2022-10-25/ratings.csv')

episodes <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2022/2022-10-25/episodes.csv')

df <- left_join(bakers, challenges, by = c("series", "baker")) %>%
  drop_na(result) %>%
  select(-first_date_us, -last_date_us,-baker_first,-baker_last)

ch_1 <- challenges %>%
  filter(result == "OUT") %>%
  unnest_tokens(word, signature) %>%
  select(-showstopper) %>%
  rename(sig_word = word)

ch_2 <- challenges %>%
  filter(result == "OUT") %>%
  unnest_tokens(word, showstopper) %>%
  select(-signature) %>%
  rename(showstopper_word = word)

df <- left_join(ch_1, ch_2, by = c("series", "episode","baker")) %>%
  filter(!(sig_word %in% stop_words$word)) %>%
  filter(!(showstopper_word %in% stop_words$word))

word_count_1 <- df %>%
  count(sig_word) %>%
  arrange(desc(n)) %>%
  rename(word = sig_word) %>%
  mutate(dish_type = "Signature")

word_count_2 <- df %>%
  count(showstopper_word) %>%
  arrange(desc(n)) %>%
  rename(word = showstopper_word) %>%
  mutate(dish_type = "Showstopper")

words <- rbind(word_count_1, word_count_2)

final_df <- words %>%
  group_by(dish_type) %>%
  slice_max(n = 15, order_by = n)

final_df %>%
  ggplot(aes(area = n, label = word))+
  geom_treemap(aes(fill = word))+
  geom_treemap_text(color = "gray97", min.size = 0, fontface = "bold", place = "center")+
  facet_wrap(~dish_type)+
  theme(legend.position = "none", strip.background = element_rect(fill = "peachpuff3"), plot.background = element_rect(fill = "antiquewhite2"), plot.title = element_text(hjust = 0.5, color = "black", face = "bold.italic", size = 15), strip.text = element_text(face = "bold", size = 15))+
  ggtitle("Which Words are Most Common in Eliminated Dishes on \nThe Great British Bake-off?\n")+
  labs(caption = "Tidy Tuesday 10-25-2022 | Github: @scolando")