Tidytuesday

Load this week’s Data

ultra_rankings <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-10-26/ultra_rankings.csv')
race <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-10-26/race.csv')

summarizing this week’s data

*Consolidating and some minor cleaning for the two datasets available in this week

consolidated = race %>% 
  left_join(ultra_rankings,by = "race_year_id") %>% 
  mutate(runner = str_to_title(runner),
         country = str_replace(country,"(.+)?(United States)(.+)?","United States"),
         country = str_replace(country,"(.+)?(China)(.+)?","China"),
         country = str_replace(country,"(.+)?(Japan)(.+)?","Japan"),
         year = year(date))

Animating the firt plot

consolidated %>%
  group_by(country, year) %>% 
  filter(!is.na(gender),
         !is.na(country)) %>%
  summarise(total = n(),
            women = sum(gender=="W"),
            ratio_women = 100*(women/total)) %>% 
  arrange(-total) %>% 
  head(40) %>% 
  mutate(country = fct_reorder(country,ratio_women),
         year = as.integer(year)) %>% 
  ggplot(aes(ratio_women,country, fill =country))+
  geom_col()+
  ease_aes()+
#  scale_x_discrete(labels = percent())+
  labs(title = "% of Women Participation in Ultra Trail Running within countries \n with highest # of participants ",
       subtitle = "Year of events = {frame_time}",
       x = "% Women participation",
       caption = "Plot by @Birasafab")+
  transition_time(year)+
#  transition_reveal(along = year)+
  theme(legend.position = "none")