PA 2: Using Data Visualization to Find the Penguins

Download the .qmd template and save it in a reasonable location.

Today you will be exploring different types of visualizations to uncover which species of penguins reside on different islands.

Some advice:

Note

Make sure to give your plots reader friendly axes labels!

Note

Make sure your final report does not display any warnings or messages from RStudio!

Getting Started

We will be creating visualizations using the ggplot2 package.

For this activity, we will be exploring the penguins data from the palmerpenguins package, which has fantastic documentation with really awesome artwork. So, you will need to install the palmerpenguins package.

install.packages("palmerpenguins")

install.packages() in the console NOT in your .qmd file!

You should type this into your console and NOT include it in a code chunk in your .qmd file. Recall that we only have to install a package once, but load it each time we open R. Each time you render your .qmd file, ALLthe code chunks are run. Therefore, installing a package in a code chunk would cause R to unnecessarily install the package over and over again. Not good.

Creating a Setup Code Chunk

  1. Insert a code chunk at the beginning of your document (directly under the YAML).
  2. Name the code chunk setup.
  3. Use the hashpipe #| to specify a code chunk option that prevents any messages (e.g., from loading in packages) from appearing.
  4. Load in the tidyverse or ggplot2 package.
  5. Load in the palmerpenguins package.
Code chunk name: setup

Naming your code chunk “setup” has special properties in a .qmd - specifically, this code chunk will run automatically when you try to run a subsequent code chunk. This ensures all packages and any other specifications for your document are loaded and will not cause you errors or messages.

Dataset: penguins

I like to start by seeing the dataset I will be working with, so I am going to pull the penguins data into my R environment. Do you see it in the top right Environment tab?

data(penguins)

You may notice that a dataset called penquins_raw also loaded. We will ignore this and focus on the penguins dataset.

  1. Get to know your data. What are the variables and what units are they measured in? What does each row represent?

Exploring the Penguins Data

Step 1: Barchart

  1. Create a plot of the frequency of each penguin species in the data.

  1. Use https://excalidraw.com/ (or pen and paper, a tablet, etc.) to create a sketch for this plot. Label the aesthetics that will be needed.

  2. Use ggplot2 to create the plot you sketched above.

Step 2: Histogram or Density Curve

  1. Use ggplot2 to plot the distribution of bill lengths for the penguins included in the dataset.

Step 3: Scatterplot

  1. Use ggplot2 to plot the relationship between the length of a penguin’s bill (bill_length_mm) and the depth of their bill (bill_depth_mm).

Step 4: Add a Trend Line

  1. Add a linear trend line to the scatterplot you made above!

Step 5: Adding A Categorical Variable

  1. Building off of the plot you made in Step 4, add an aesthetic to differentiate the species of the penguins in the scatterplot by color for both the points and the trend line.
  1. Edit your plot in (11) above so that the points are colored by species, but there is only one overall linear trend line.
  1. Building on your code from (11), add the location of the penguins (island) to your visualization. There is more than one method to address this, however, one method will more easiliy allow you to address the quesitons below.

Canvas Quiz

Working as a team, use the plots you created to answer the following questions on Canvas.

  1. Which species of penguins is represented least in the Palmer Penguins data set?

  2. Which species had the weakest relationship between bill length and bill depth?

  3. Which species of penguins are found on every island?

  4. Which species of penguins are found only on Dream Island?

  5. Which species of penguins are found only on Biscoe Island?