|> or %>%) for data wranglingSet up a new GitHub repo in your GitHub workspace called “exercise-03” and clone that down your computer as a new RStudio project. The instructions outlined as Method 1 in Module 6 will be helpful.
Load the “data-wrangling.csv” dataset from this URL as a tabular data structure named d and look at the variables it contains, which are a subset of those in the Kamilar and Cooper dataset on primate ecology, behavior, and life history that we have used previously.
HINT: You can use the
names()function to see a list of variable names in the dataset
Create a new Quarto document called “exercise-3.qmd” within the project and use it to complete the following challenges. Be sure to include both descriptive text about what you are doing and code blocks – i.e., follow a “literate programming” approach to be sure that a reader understands what you are doing. For the plots, feel free to use either {base} R graphics or {ggplot2}, as you prefer. You should use descriptive text to answer the specific questions asked below.
Create a new variable named BSD (body size dimorphism) which is the ratio of average male to female body mass.
Create a new variable named sex_ratio, which is the ratio of the number of adult females to adult males in a typical group.
Create a new variable named DI (for “defensibility index”), which is the ratio of day range length to the diameter of the home range.
HINT: You will need to calculate the latter for each species from the size of its home range! For the purposes of this assignment, presume that the home range is a circle and use the formula for the area of a circle: \(AREA = \pi \times r^2\). The variable pi (note, without parentheses!) will return the value of \(\pi\) as a constant built-in to R, and the function
sqrt()can be used to calculate the square root (\(\sqrt{}\))
Plot the relationship between day range length (y axis) and time spent moving (x axis), for these primate species overall and by family (i.e., a different plot for each family, e.g., by using faceting: + facet_wrap()). Do species that spend more time moving travel farther overall? How about within any particular primate family? Should you transform either of these variables? Why or why not?
Plot the relationship between day range length (y axis) and group size (x axis), overall and by family. Do species that live in larger groups travel farther, overall, in a day? How about within any particular primate family? Should you transform either of these variables?
Plot the relationship between canine size dimorphism (y axis) and body size dimorphism (x axis) overall and by family. Do taxa with greater size dimorphism also show greater canine dimorphism?
Create a new variable named diet_strategy that is “frugivore” if fruits make up >50% of the diet, “folivore” if leaves make up >50% of the diet, and “omnivore” if diet data are available but neither of these is true (i.e., these values are not NA). Then, create boxplots of group size for species with different dietary strategies, omitting the category NA from your plot. Do frugivores live in larger groups than folivores?
HINT: To create this new variable, try combining
mutate()withifelse()orcase_when()statements… check out the notes on “Conditional Expressions” in Module 11. Take a peak at the code snippets below if you get stuck!
mutate(d, "diet_strategy" = ifelse(
Fruit >= 50,
"frugivore",
ifelse(
Leaves >= 50,
"folivore",
ifelse(Fruit < 50 & Leaves < 50, "omnivore", NA)
)
))
mutate(
d,
"diet_strategy" = case_when(
Fruit >= 50 ~ "frugivore",
Leaves >= 50 ~ "folivore",
Fruit < 50 & Leaves < 50 ~ "omnivore",
TRUE ~ NA
)
)|> or %>%) operator, do the following:na.rm = TRUE)…Load in a dataset of your own and write R code to do the following: