PPOL670 | Introduction to Data Science for Public Policy Week 5 Data Visualization

# PPOL670 | Introduction to Data Science for Public Policy Week 5 Data Visualization 
###  Prof. Eric Dunford  ◆  Georgetown University  ◆  McCourt School of Public Policy  ◆  <a href="mailto:eric.dunford@georgetown.edu" class="email">eric.dunford@georgetown.edu</a>

---

<div class="slide-footer"> 
PPOL670 | Introduction to Data Science for Public Policy

&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;

Week 5

&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;

Data Visualization

</div>

---

# The Components of Data Visualization

---

### What do you see?

---

### Mapping data to space

---

### Aesthetics

.center[<img src="Figures/common-aesthetics-1.png", width=500>]
 
.center[<img src="Figures/basic-scales-example-1.png", width=500>]

---

### Color as a tool to distinguish

---

### Color as a tool to represent values

---

### Color as a tool to highlight

---

### Presentation as information

---

### Presentation as distortion

---

### The data type drives the visualization decisions

Think carefully about what you're trying to convey and what information you're using to make your point.

| Data Type   | Example |  Scale  |
|-------------|---------|---------|
| Numerical   | `1.3`, `800`, `10e3` | Continuous | 
| Integer     | `1`, `2`, `3` | Discrete | 
| Categorical | `"dog"`, `"Nigeria"`, `"A"` | Discrete |
| Ordered     | `"Small"`, `"Medium"`, `"Large"` | Discrete |
| Dates/Time  | `2009-01-02`, `5:32:33` | Continuous |

]

---

### The data type drives the visualization decisions

.center[
.center[<img src="Figures/amounts-1.png", width=500>]
.center[<img src="Figures/proportions-1.png", width=500>]
.center[<img src="Figures/single-distributions-1.png", width=500>]
.center[<img src="Figures/basic-scatter-1.png", width=500>]
]

---

class:newsection

# Grammar of Graphics

---

.pull-right[
`ggplot2` (a part of the `tidyverse` package) is a power graphics package that offers a flexible and intuitive graphics language capable of building sophisticated graphics.

`ggplot` has a **special syntax** that we'll have to get used to, _but_ once we understand the basics, we'll be able to produce some advanced and sophisticated graphics with ease!
]

---

`ggplot2` is based on a **grammar of graphics**. In essence, you can build every graph from the same components that follow the same intuitive naming conventions.

Every graph is composed of

1. a **dataset**

2. **coordinate system**

2. **mappings** &rarr; the variables we're aiming to visualize

3. **geom**etric expressions of how the data should be projected onto a space

]

---

### (1) data

Let's use the `diamonds` data, which is an example dataset provided by `ggplot` that contains the prices and other attributes of almost 54,000 diamonds.

```r
glimpse(diamonds)
```

```
## Observations: 53,940
## Variables: 10
## $ carat <dbl> 0.23, 0.21, 0.23, 0.29, 0.31, 0.24, 0.24, 0.26, 0.22, 0.…
## $ cut <ord> Ideal, Premium, Good, Premium, Good, Very Good, Very Goo…
## $ color <ord> E, E, E, I, J, J, I, H, E, H, J, J, F, J, E, E, I, J, J,…
## $ clarity <ord> SI2, SI1, VS1, VS2, SI2, VVS2, VVS1, SI1, VS2, VS1, SI1,…
## $ depth <dbl> 61.5, 59.8, 56.9, 62.4, 63.3, 62.8, 62.3, 61.9, 65.1, 59…
## $ table <dbl> 55, 61, 65, 58, 58, 57, 57, 55, 61, 61, 55, 56, 61, 54, …
## $ price <int> 326, 326, 327, 334, 335, 336, 336, 337, 337, 338, 339, 3…
## $ x <dbl> 3.95, 3.89, 4.05, 4.20, 4.34, 3.94, 3.95, 4.07, 3.87, 4.…
## $ y <dbl> 3.98, 3.84, 4.07, 4.23, 4.35, 3.96, 3.98, 4.11, 3.78, 4.…
## $ z <dbl> 2.43, 2.31, 2.31, 2.63, 2.75, 2.48, 2.47, 2.53, 2.49, 2.…
```

---

### (2) coordinate system

Use the `ggplot()` function to establish the coordinate system.

```r
ggplot(data=diamonds)
```

---

### (3) mappings

What variables from the data do we want to map to the projected space?

- What variable makes up the y-axis?
- What variable makes up the x-axis?
- Are there any variables to group by? (More on this later)

Need to use a special function `aes()` (short for "aesthetics") to map variables from the data to the geometric space.

Whenever we want to plot a variable feature, we **_must_** wrap it in the `aes()` function.

---

### (3) mappings

What variables from the data do we want to map to the projected space?

```r
ggplot(data=diamonds,aes(x=price,y=carat))
```

---

### (4) geom &rarr; projection

How should your mappings be projected onto the coordinate space?

```r
ggplot(data=diamonds,aes(x=price,y=carat)) +
* geom_point()
```

---

### (4) geom &rarr; projection

How should your mappings be projected onto the coordinate space?

- `geom_` are aesthetic **layers** that are mapped onto the plot.

- We "add" layers and design preferences `+`.

- We can add as many layers as we want. Layers placed on top of one another in accordance with the order that they are specified.

- Plots can be assigned as objects and rendered later.

]

```r
ggplot(data=diamonds,
       aes(x=price,y=carat)) +
  geom_point() 
```

<img src="lecture-week-05_data-visualization_files/figure-html/unnamed-chunk-11-1.png" style="display: block; margin: auto;" />
]

---

`+`

`<GEOM_FUNCTION>`(mapping = aes(`<MAPPINGS>`))
]

`+`

`<GEOM_FUNCTION>`(mapping = aes(`<MAPPINGS>`))

`+`

`<GEOM_FUNCTION>`(mapping = aes(`<MAPPINGS>`))

`+`

`<GEOM_FUNCTION>`(mapping = aes(`<MAPPINGS>`))

`$$\vdots$$`

]

---

`+`

`<GEOM_FUNCTION>`(mapping = aes(`<MAPPINGS>`))
]

`+`

`<SCALE_FUNCTION>`(mapping = aes(`<MAPPINGS>`))

`+`

`<THEME_FUNCTION>`(mapping = aes(`<MAPPINGS>`))

`+`

`<FACET_FUNCTION>`(mapping = aes(`<MAPPINGS>`))

`$$\vdots$$`

]

---

### One variable?

.center[
| Expression | Function | |
|----|----|-----|
| Area | `geom_area()` | <img src = "Figures/geom_area.png"> | 
| Density | `geom_density()` | <img src = "Figures/geom_density.png"> | 
| Dots | `geom_dotplot()` | <img src = "Figures/geom_dotplot.png"> | 
| Frequencies | `geom_freqpoly()` | <img src = "Figures/geom_freqplot.png"> | 
| Histogram | `geom_histogram()` | <img src = "Figures/geom_histogram.png"> | 
]

---

### Two variables?

.center[
| Expression | Function | |
|----|----|-----|
| Continuous Points | `geom_point()` | <img src = "Figures/geom_point.png"> | 
| Continous Lines | `geom_line()` | <img src = "Figures/geom_line.png"> | 
| Discrete Counts | `geom_count()` | <img src = "Figures/geom_count.png"> | 
| Continuous and Discrete Distributions | `geom_boxplot()` | <img src = "Figures/geom_boxplot.png"> | 
| Densities | `geom_hex()` | <img src = "Figures/geom_hex.png"> | 
]

---

### Three variables?

.center[
| Expression | Function | |
|----|----|-----|
| Densities | `geom_contour()` | <img src = "Figures/geom_contour.png"> | 
| Intensities | `geom_tile()` | <img src = "Figures/geom_tile.png"> | 
| Intensities | `geom_raster()` | <img src = "Figures/geom_raster.png"> | 
| Spatial | `geom_map()` | <img src = "Figures/geom_map.png"> | 
]

Just a taste. Wide array of ways to express data in a geometric space. See reading and [data visualization cheatsheet](https://github.com/tidyverse/ggplot2) for guidance.

---

### Function Types in `ggplot2`

| Type | Function Header | Description |
|------|-----------------|-------------|
|  Generate layers from data   |  `geom_` | Use a geom function to represent data points, use the geom’s aesthetic properties to represent variables. Each function returns a layer. |
|   Construct statistics layers   |  `stat_` | A stat builds new variables to plot (e.g., count, prop) |
|   Change mapping characteristics   |  `scale_` | Scales map data values to the visual values of an aesthetic. To change a mapping, add a new scale. |
|   Generate subplots   |  `facet_` | Facets divide a plot into subplots based on the values of one or more discrete variables.  |
|   Alter the plots theme   |  `theme_` | Change the aesthetics of the plot background and feature (e.g. axes, text, grid lines, etc.)  |

---

### Exporting Plots

Note that `ggplot` objects can assigned to an object.

```r
my_plot <- ggplot(cars,aes(speed,dist)) + geom_point()
my_plot
```

We can export (or build off of) these plot objects using `ggsave()`

```r
ggsave(plot = my_plot,filename = "my_plot.pdf",device = "pdf",width=5,height = 5)
ggsave(plot = my_plot,filename = "my_plot.png",device = "png",dpi = 300)
```

> Supports "eps", "ps", "tex" (pictex), "pdf", "jpeg", "tiff", "png", "bmp", "svg" or "wmf" (windows only).