---
title: "Grammar of graphics exercises"
author: "Nicholas Horton (nhorton@amherst.edu)"
date: "August 31, 2017"
output:
  html_document:
    fig_height: 5
    fig_width: 7
  pdf_document:
    fig_height: 5
    fig_width: 7
  word_document:
    fig_height: 3
    fig_width: 5
---

```{r, setup, include=FALSE}
library(mdsr)   # Load additional packages here 
```

## Introduction
These exercises are taken from the grammar of graphics chapter from **Modern Data Science with R**: http://mdsr-book.github.io.  Other materials relevant for instructors (sample activities, overview video) for this chapter can be found there.


## Galton
Using the famous `Galton` data set from the `mosaicData` package:

1. Create a scatterplot of each person's `height` against their father's height
2. Separate your plot into facets by `sex`
3. Add regression lines to all of your facets

Hint: recall that you can find out more about the data set by running the command `?Galton`.


SOLUTION:

```{r}
library(mdsr)
glimpse(Galton)
# solution goes here
```


## Railtrails
Using the `RailTrail` data set from the `mosaicData` package:

1.  Create a scatterplot of the number of crossings per day `volume` against the high temperature that day
2. Separate your plot into facets by `weekday`
3. Add regression lines to the two facets

SOLUTION:

```{r}
library(mdsr)
glimpse(RailTrail)
# solution goes here
```


## Hamilton and Angelica
Angelica Schuyler Church (https://en.wikipedia.org/wiki/Angelica_Schuyler_Church, 1756--1814) was the daughter of New York Governer Philip Schuyler and sister of
Elizabeth Schuyler Hamilton.  Angelica, New York was named after her.  Generate a plot of the reported proportion of babies born
with the name Angelica over time and interpret the figure.

SOLUTION:

```{r}
library(mdsr)
library(babynames)
glimpse(babynames)
# solution goes here
```

## Marriage
The following questions use the `Marriage` data set from the `mosaicData` package.

1.  Create an informative and meaningful data graphic.
2. Identify each of the visual cues that you are using, and describe how they are related to each variable.
3. Create a data graphic with at least *five* variables (either quantitative or categorical). For the purposes of this exercise, do not worry about making your visualization meaningful---just try to encode five variables into one plot.


```{r}
library(mdsr)
glimpse(Marriage)
# solution goes here
```

## MLB teams
The `MLB_teams` data set in the `mdsr` package contains information about Major League Baseball teams in the past four seasons. There are several quantitative and a few categorical variables present. See how many variables you can illustrate on a single plot in R. The current record is 7. (Note: This is *not* good graphical practice---it is merely an exercise to help you understand how to use visual cues and aesthetics!)

```{r}
library(mdsr)
glimpse(MLB_teams)
# solution goes here
```

## Payroll
Use the `MLB_teams` data in the `mdsr` package to create an informative data graphic that illustrates the relationship between winning percentage and payroll in context.

SOLUTION:

```{r}
library(mdsr)
# solution goes here
```


## Dead names
Use the `make_babynames_dist` function in the `mdsr` package to recreate the "Deadest Names" graphic from FiveThirtyEight (http://tinyurl.com/zcbcl9o).

SOLUTION:

```{r}
library(mdsr)
babynames_dist <- make_babynames_dist()
glimpse(babynames_dist)
```

## MacLeish
The `macleish` package contains weather data collected every ten minutes in 2015 from two weather stations in Whately, MA.
Using `ggpplot2` create a data graphic that displays the average temperature over each 10-minute interal (`temperature` as a function of time (`when`).

SOLUTION:

```{r}
library(mdsr)
library(macleish)
glimpse(whately_2015)
# solution goes here
```

## NASA weather
Using data from the `nasaweather` package, create a scatterplot between `wind` and `pressure` with color being used to distinguish the `type` of storm.

SOLUTION:

```{r message=FALSE}
library(mdsr)
library(nasaweather)
glimpse(storms)
# solution goes here
```

## More weather
Using data from the `nasaweather` package, use the `geom_path` function to plot the path of each tropical storm in the `storms` data table. Use color to distinguish the storms from one another, and use facetting to plot each `year` in its own panel.

SOLUTION:

```{r}
library(mdsr)
library(nasaweather)
# solution goes here
```