NYC Flights

We will use some flight data in this problem. To access it$,$ remember to load the tidyverse,

mdsr$,$ and nycflights$13$ packages. If you've never used the mdsr package, remember to run

install.packages$("$mdsr$")$ in your console $($just once, and this shouldn't be in your $.$Rmd$,$ but

rather in your console$)$ and THEN run library$($mdsr$)($put this in the setup chunk$).$ Do the same for the

nycflights$13$ package.

Load the flights dataset. Calculate, for each month, the average distance flown. Arrange from longest

to shortest. Call this new dataset avg$\_$d$.$ IInt: to load in data from a package, use the function data$()$

and set the argument to the name of the dataset.

Load the airlines dataset $($from the nycflights$13$ package$).$ Join this dataset with the flights

dataset so that no rows are dropped. Keep the flight, carrier, and name columns. Call this new

dataset flightsJoined. Use the head$()$ function to preview the first $5$ rows of this dataset

Now, create a new dataset flightsJoined$2$ that:

creates a new variable, distance$\_km,$ which is distance in kilometers $($note that $1$ mile is about $1\mathrm{.}6$

kilometers$)$

keeps only the variables: name, flight, arr$\_$delay, and distance$\_$km

keeps only observations where distance is less than $500$ kilometers

orders the observtaions from highest to lowest arr$\_$delay

Display the first $10$ observations of this dataset. Comment on what you see.

Hint: start again by joining the flights and airlines datasets as in $(2).$

Lastly, compute the number of flights $($call this N$),$ the average arrival delay $($call this avg$\_$arr$\_$delay$),$

and the average distance in kilometers $($call this avg$\_$dist$\_$km$)$ among these flights with distances less

than $500km($i$.$e$.$ working off of flightsJoined$2)$ grouping by the carrier $($aka airline$)$ name. Sort the

results in descending order based on avg$\_$arr$\_$delay. Show your results.

Getting NAs for avg$\_$arr$\_$delay? That happens when some observations are missing that data. Before

grouping and summarizing, add a line to exclude observations with missing arrival delay information using

filter$($

is$.$na$($arr$\_$delay$)==$ FALSE$).$