Bayesian Statistics and Computing

---

# Bayesian Statistics and Computing

##  Lecture 4: Data Visualization in R

#### *Yanfei Kang | BSC | 2021 Spring*

---

> "The simple graph has brought more information to the data analyst’s mind than any other device."

> — John Tukey

---
# Objectives

1. basic graphics with **R**

2. elegant graphics with **ggplot2**

---
class: inverse, center, middle
# Basic graphics with R

---
# `mpg` dataframe

`mpg` contains observations collected by the US Environment Protection Agency on 38 models of car. You can see more details via `?mpg`. Among the variables in `mpg` are:

1. `displ`, a car’s engine size, in litres.
2. `hwy`, a car's fuel efficiency on the highway, in miles per gallon (mpg). A car with a low fuel efficiency consumes more fuel than a car with a high fuel efficiency when they travel the same distance.
3. ...

---
# Basic plots

Practice and look at the help document of `plot`.

```r
library(ggplot2)
plot(mpg$displ, mpg$hwy)
abline(lm(hwy ~ displ, data = mpg))
title("Regression of MPG on engine size")
```
]

.pull-right[
<img src="figure/unnamed-chunk-1-1.png" width="504" style="display: block; margin: auto;" />
]

---
# Histograms and density plots

```r
hist(mpg$hwy)
```

<img src="figure/unnamed-chunk-2-1.png" width="504" style="display: block; margin: auto;" />
]

```r
d <- density(mpg$hwy)  ## returns the density data
plot(d)
```

<img src="figure/unnamed-chunk-3-1.png" width="504" style="display: block; margin: auto;" />
]

---
# Piechart

```r
car.table <- table(mpg$manufacturer)
pie(car.table)
```
]

.pull-right[
<img src="figure/unnamed-chunk-4-1.png" width="504" style="display: block; margin: auto;" />
]

---
# Boxplots

```r
## Boxplot of MPG
boxplot(mpg$hwy, main = "Boxplot of MPG")

## Boxplot of MPG by Car Cylinders
boxplot(hwy ~ cyl, data = mpg, main = "Car Milage Data", xlab = "Number of Cylinders", ylab = "Miles Per Gallon")
```

---
# Correlation plot

```r
library(corrplot)
M <- cor(mtcars)
corrplot(M, addCoef.col = "grey")
```
]

.pull-right[
<img src="figure/unnamed-chunk-6-1.png" width="504" style="display: block; margin: auto;" />
]

---
# Time series

```r
plot(AirPassengers)
```

---
# Multiple plots

```r
par(mfrow = c(1, 2))
plot(AirPassengers)
boxplot(ggplot2::mpg$hwy, data = ggplot2::mpg, main = "Boxplot of MPG")
```

---
class: inverse, center, middle
# Elegant graphics with ggplot2

---
# Creating a ggplot

```r
library(ggplot2)
ggplot(data = mpg) + geom_point(mapping = aes(x = displ, y = hwy))
```

---
# Creating a ggplot

``` 
ggplot(data = <DATA>) + 
  <GEOM_FUNCTION>(mapping = aes(<MAPPINGS>))
```

1. With ggplot2, you begin a plot with the function `ggplot()`. `ggplot()` creates a coordinate system that you can add layers to.

2. You complete your graph by adding one or more layers to `ggplot()`. For example, `geom_point()` adds a layer of points to your plot, which creates a scatterplot. You can specify the color, size and shape of these points. Each geom function in ggplot2 takes a `mapping` argument.

---
# Change the color, size and shape of points

```r
ggplot(data = mpg) + geom_point(mapping = aes(x = displ, y = hwy), color = 2, size = 3, shape = 18)
```
]

.pull-right[
<img src="figure/unnamed-chunk-10-1.png" width="504" style="display: block; margin: auto;" />
]
---
# Facets

.pull-left[
- Another way, particularly useful for categorical variables, is to split your plot into facets, subplots that each display one subset of the data.
- To facet your plot by a single variable, use `facet_wrap()`. The first argument should be a formula, which you create with ~ followed by a variable name.

```r
ggplot(data = mpg) + geom_point(mapping = aes(x = displ, y = hwy)) + facet_wrap(~class, nrow = 2)
```
]

.pull-right[
<img src="figure/unnamed-chunk-12-1.png" width="504" style="display: block; margin: auto;" />
]

---
# Facets

.pull-left[
To facet your plot on the combination of two variables, add facet_grid() to your plot call.

```r
ggplot(data = mpg) + geom_point(mapping = aes(x = displ, y = hwy)) + facet_grid(drv ~ cyl)
```
]

.pull-right[
<img src="figure/unnamed-chunk-14-1.png" width="504" style="display: block; margin: auto;" />
]

---
# Pairwise plots

```r
library(GGally)
ggpairs(subset(mtcars, select = c(1, 3, 4, 5, 6)))
```
]
.pull-right[
<img src="figure/unnamed-chunk-15-1.png" width="504" style="display: block; margin: auto;" />
]
---
# Geometric objects

```r
## left
p1 <- ggplot(data = mpg) + geom_point(mapping = aes(x = displ, y = hwy))

## right
p2 <- ggplot(data = mpg) + geom_smooth(mapping = aes(x = displ, y = hwy))

## put the two plots in one row
gridExtra::grid.arrange(p1, p2, ncol = 2)
```

---
# Geometric objects

---
# Geometric objects

- A **geom** is the geometrical object that a plot uses to represent data.

- Bar charts use bar geoms, line charts use line geoms, boxplots use boxplot geoms, and so on.

- You can also add multiple geom functions.

```r
ggplot(data = mpg) + geom_point(mapping = aes(x = displ, y = hwy)) + geom_smooth(mapping = aes(x = displ, y = hwy))
```

---
# Bar chart

.pull-left[
The following chart displays the total number of cars in the `mpg` dataset, grouped by `drv`.

```r
ggplot(data = mpg) + geom_bar(mapping = aes(x = drv, fill = drv))
```
]

.pull-right[
<img src="figure/unnamed-chunk-18-1.png" width="504" style="display: block; margin: auto;" />
]

---
# Histogram
.pull-left[

```r
ggplot(data = mpg) + geom_histogram(mapping = aes(x = hwy))
```
]

.pull-right[
<img src="figure/unnamed-chunk-19-1.png" width="504" style="display: block; margin: auto;" />
]
---
# Boxplots
.pull-left[

```r
ggplot(data = mpg, mapping = aes(x = class, y = hwy)) + geom_boxplot()

```
]

.pull-right[
<img src="figure/unnamed-chunk-20-1.png" width="504" style="display: block; margin: auto;" />
]

---
# Time series

```r
library(ggplot2)
library(forecast)
autoplot(AirPassengers)
```

---
# Summary

- We have seen basic  **R** plots and plots from **ggplot2**.

- In this course, you will also use animated plots (e.g., gifs), interactive plots, etc.

---
# References

[R documentation of **ggplot2**.](https://www.rdocumentation.org/packages/ggplot2/versions/3.2.1)