In-class exercise ggplot2

In [1]:

#install.packages(c("maps", "mapproj"))
library(tidyverse)
library(xtable)
library(nycflights23)

Instructions

Data set

Recall the nycflights23 package, which provides the following data frames (tibbles):

• airlines
• airports
• flights
• planes
• weather

Plots

Create plots with ggplot2 for the following prompts/questions.

1. How many flights took place each hour, broken down by origin airport and month?

2. What carrier has the largest proportion of cancelled flights?

3. For the top-3 carriers (total number of flights) across all 3 origin airports in the summer (July-September), show the relationship between departure and arrival delay (use color coding and faceting where appropriate).

4. For the top-10 destinations across all 3 origin airports, add a circle (or bubble) to the map. Make the circle size proportionate to the total number of flights to that destination. (Use color coding where appropriate).

ggplot(map_data("state"), aes(long, lat, group=group)) +
geom_polygon(fill="white", color="black") +
theme_bw()

5. Create a plot of your own choice and design. (Please state the question your plot is trying to answer.)