Day 4: Tasks & activities

Matrices and matrix algebra, exploring and summarizing data

1. A Leslie matrix example (small groups)

A population of fish we’re interested in has four life stages: eggs (E), fry (F), juvenile (J), breeding adult (A). You are given the following:

  • Each breeding adult will produce, on average, 600 eggs
  • 25% of eggs will survive to become fry
  • 10% of fry will survive to become juveniles
  • 40% of juveniles will survive to become adults
  • Adult survival rate year to year is 80%
  1. With your group, draw the Leslie matrix model for this population structure.
  2. With your group, given an initial population (Year 0) that has 0 eggs, 40,000 fry, 600 juveniles, and 450 adults, by hand project the population structure (i.e. the count in each life stage) in Year 1.

2. Fork & clone a repo to check your Leslie matrix, and make projections

  1. Fork and clone this repo, which contains the Leslie matrix for the example above.
  • Go to the link above. Press Fork in upper right, then Create Fork.
  • Once in your fork, press the green ‘Code’ button
  • Copy the URL to your clipboard
  • Back in RStudio, create a new project (with version control)
  • Where prompted, paste the URL & choose where you’ll save your directory
  • Create project
  • Open the .qmd to explore & run Leslie Matrix code
  1. Explore the code and outputs. Does the Year 1 population projection align with what you calculated?
  2. Add code to the .qmd to expand the projections to years 4, 5, and 6 (it current projects through year 3)
  3. Using the command line: Save, stage, commit, then push your changes.

3. Data exploration & summarizing in R

  1. Create a new Project
  2. Add a new Quarto document in your project, save as r-data-exploration.qmd
  3. Set up your local and remote git repo by running usethis::use_git() and then usethis::use_github()
  4. Attach the {tidyverse}, {skimr}, and {GGally} packages in the setup code chunk
  5. Run View(diamonds) in the Console to look at the built-in diamonds data set in R
  6. Explore the data set using the functions names(), dim(), summary(), head(), tail(), and skimr::skim()
  7. Create a pairs plot using ggpairs()
  8. Create a basic ggplot scatterplot of diamond price (price) as a function of size (carat)
  9. Create a histogram showing the distribution of values in the carat column (recall: a histogram only requires a single variable, e.g. aes(x = carat))
  10. Save, stage, commit, pull, then push your changes back to your repo in RStudio using the GUI interface (buttons)
  11. Create a boxplot (see: geom_boxplot) of diamond clarity (on the x-axis) and price (y-axis).
  12. In the command line, stage, commit, & push changes


End Activity Session (Day 4)