---
title: "NYC Flights - data wrangling II"
author: "YOUR NAME HERE"
date: "`r Sys.Date()`"
format: 
  html:
    self-contained: true
    toc: true
    toc_float: true
    number_section: false
    highlight: "tango"
    theme: "cosmo"
editor: visual
editor_options: 
  chunk_output_type: console
---

We will again work with data from the `nycflights13` package.

```{r}
#| label: load-packages
#| message: false
library(nycflights13)
library(tidyverse)
```

## Exercise 1

Examine the documentation for the datasets `airports`, `flights`, and `planes`. What are the dimensions of each? How are these datasets related?

> YOUR ANSWER HERE

## EXAMPLE

Suppose you wanted to make a map of the route of every flight. What variables would you need from which datasets? You need the geographic location of the airports (from `airports`) and the path of flights (i.e., which airports were involved) from `flights`.

We want to join flights to airports. Note these two datasets have no variables in common so we will have to specify the variable to join by using `by =`. Check out the documentation for more information.

```{r}
flights |> 
  left_join(airports, by = c("dest" = "faa"))
```

## Exercise 2

Which airports are in `flights` but not in `airports`? Google to find out what these airports are.

```{r}

```

> YOUR ANSWER HERE

Which airports are in `airports` but not in `flights`? What does this tell us about these airports (at least in 2013)?

```{r}

```

> YOUR ANSWER HERE

## Exercise 3

Starting with the `flights` dataset, create a new dataset `dest_delays` with the median arrival delay for each destination. *Note, this question does not require you to use joins. Make sure to add na.rm = TRUE when computing the median. Check: `dest_delays` should have dimensions 105 x 2.*

```{r}

```

## Exercise 4

Join the columns in `airports` to `dest_delays` (preserving all rows in `dest_delays`. *Check: `delays_by_airport`* *should have dimensions 105 x 9.*

```{r}

```

Based on your answer to Exercise 2, how many rows in `delays_by_airport` do you expect to be missing latitude and longitude information?

> YOUR ANSWER HERE

## Exercise 5

***Is there a relationship between the age of a plane and its delays?*** The plane tail number is given in the `tailnum` variable in the `flights` dataset. The year the plane was manufactured is given in the `year` variable in the `planes` dataset.

Start by finding the median arrival delay for each plane and store the resulting dataset in `plane_delays`. *Check: `plane_delays`* *should have dimensions 4044 x 2*

```{r}

```

Join `plane_delays` to the `planes` data using an appropriate join and then use `mutate` to create an `age` variable. Note this data is from 2013.

```{r}

```

Finally, create an effective visualization of the data to investigate if there a relationship between the age of a plane and its delays. Comment on your conclusions.

```{r}

```

## (FOR LATER) Extra mapping fun

Try re-creating the visualization below and/or exploring other ways to visualized the flights data spatially. *Note, to view the image in your html, download the "flights_map.png" file and place it in the images subfolder of your STAT_7500 folder.*

![](images/flights_map.png)

Some starter code is provided below for creating a basic US map.

```{r}
#| warning: false
#| message: false
library(maps)
library(mapdata)

state <- map_data("state")

ggplot() + 
  geom_polygon(data = state, 
               aes(x = long, y = lat, group = group),
               fill = 'lightblue', color = "white") +
  theme_void() +
  coord_fixed(1.3)
```

Adding on the flight trajectories will require some creative data wrangling. You can use a `geom_curve()` layer to create the flight curves; the above plot has `curvature = 0.2`. Note, you can use different datasets and aesthetic mappings in different `geom` layers (see `geom_polygon()` layer above).

```{r}

```