Data Viz + Data Wrangling

Day 3

Dr. Elijah Meyer

Duke University
STA 199 - Summer 2023

May 22nd

Checklist

– Clone ae-03-summer-your-user-name using the SSH key

Note: if you do not see an ae-03 specifically for you, you have not accepted your org invite

Announcements

– AE’s are being graded: We will demo how to turn AE’s in today

– Keep up to date with Slack

Goals for today

– Finish off data visualization

– Introduce dplyr functions

– Continue R practice

Warm up

Identify which plot eachgeom creates

– geom_point()

– geom_density()

– geom_boxplot()

– geom_bar()

Warm Up #2

What is the difference between |> and + ?

Warm Up #3 (Reading Practice)

penguins |>
 ggplot(
 aes(x = body_mass_g, fill = species )) +
 geom_histogram(binwidth = 200, alpha = 0.3)

Types of variables

Types of variables

Type is how an object is stored in memory.

– glimpse is a great way to check data types

– Can also use typeof()

Examples

– glimpse(mtcars)

– typeof(mtcars$mpg)

Types of variables

Some of the types of variables include:

– “logical”

– “integer”

– “double”

– “character”

– “factor”

logical

– logi in glimpse

– The logical data type in R is also known as boolean data type. It can only have two values: TRUE and FALSE.

– as.logical can turn a variable into a logical. False = 0; True everything else

integer

– int in glimpse

– Integers are whole numbers (those numbers without a decimal point)

– as.integer can turn a double into an integer. Forces 22.8 -> 22.

double

– dbl in glimpse

– Real numbers (can include decimals)

– as.doublecan force a column to be a double. Identical to as.numeric.

character

– chr in glimpse

– Character string (text)

– as.character attempts to coerce its argument to character type

factor

– fct in glimpse

– Factor in R is also known as a categorical variable that stores both string and integer data values as levels.

– factor attempts to coerce its argument to factor type

Why this matters

am: Transmission (0 = automatic; 1 = manual)

Why this matters

– Functions

– Plotting

– Summary statistics

General takeaways

– Can you identify variable types

– Often need to turn something into a factor to make it categorical

– Often need to turn something into a double (numeric) to make it quantitative

More on this later

Today’s live coding topic (Data Manipulation)

Data Manipulation

– Want to subset

– Want to manipulate

– Want to create

… from data

Function of the day (saw on lab-0)

Themes are a powerful way to customize the non-data components of your plots: i.e. titles, labels, fonts, background, gridlines, and legends.

theme()

– https://ggplot2.tidyverse.org/reference/theme.html

– I often use it for legend manipulation… but there is so much more!

ae-03

Plot Recreate

Wrap up

– Data types matter. Get in the habit of checking them at the beginning of analysis

– Have the tools to create new variables, calculate summary statistics, etc. that accompany strong visualizations

– Have the tools to manipulate data to be in a more usable format