Hello. This week I am going to cover the post by Benjamin Nowak describing the outcome of the UTMB 2021 running race. His plot clearly shows that most people had to spend more than 35 hours to finish the race in spite of the record being as little as ~20 hours. Ten times less women than men participated in the event, and yet it seems that the overall distribution of finishing time was similar for both men and women. I really liked the choice of colour the graph, which was made with colorblindness in mind (e.g., orange instead of red).
The code looks similar to what we have been using. Tidyverse package was used and we see familiar to us functions such as read_csv() for inputting the data from file, mutate() and filter() for data manipulation, and finally ggplot() for making plots. I like how the author assigned separate "art packages" for the plot to different variables and then combined it together in the end to create a final product: p+tit+plot_layout(design=layout), where p is the plot itself, tit is the title designing, and plot_layot is the layout. This is something we have been taught in class too. The new packages used include waffle, ggtext, glue, showtext, camcorder, patchwork, and ggrepel.
Something I might recommend is expanding the analysis to include how the finishing time depended on age, weight or other parameters.
Hello. This week I am going to cover the post by Benjamin Nowak describing the outcome of the UTMB 2021 running race. His plot clearly shows that most people had to spend more than 35 hours to finish the race in spite of the record being as little as ~20 hours. Ten times less women than men participated in the event, and yet it seems that the overall distribution of finishing time was similar for both men and women. I really liked the choice of colour the graph, which was made with colorblindness in mind (e.g., orange instead of red).
The code looks similar to what we have been using. Tidyverse package was used and we see familiar to us functions such as
read_csv()for inputting the data from file,mutate()andfilter()for data manipulation, and finallyggplot()for making plots. I like how the author assigned separate "art packages" for the plot to different variables and then combined it together in the end to create a final product:p+tit+plot_layout(design=layout), wherepis the plot itself,titis the title designing, andplot_layotis the layout. This is something we have been taught in class too. The new packages used includewaffle,ggtext,glue,showtext,camcorder,patchwork, andggrepel.Something I might recommend is expanding the analysis to include how the finishing time depended on age, weight or other parameters.