Transform data with dplyr

# Visualize data<br>with ggplot2

.class-info[
<figure>
  <img src="img/01-class/03/ggplot-logo.png" alt="ggplot" title="ggplot" width="15%">
</figure>
]

---

# Cars and displacement

.box-inv-1.medium[What is the relationship between a car's<br>engine weight (displacement) and its mileage (miles per gallon)?]

---

# Your turn #1

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

---

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

---

class: bg-full bg-y-75
background-image: url("img/01-class/03/napoleon-retreat.jpg")

???

Source: [Wikipedia](https://en.wikipedia.org/wiki/File:National_Museum_in_Poznan_-_Przej%C5%9Bcie_przez_Berezyn%C4%99.JPG)

---

---

# Long distance!

.center[
<figure>
  <img src="img/01-class/03/napoleon-google-maps.png" alt="Moscow to Vilnius" title="Moscow to Vilnius" width="80%">
  <figcaption>Moscow to Vilnius</figcaption>
</figure>
]

---

# Very cold!

---

# Lots of people died!

---

???

Source: [Wikimedia Commons](https://upload.wikimedia.org/wikipedia/commons/2/29/Minard.png)

---

---

# Mapping data to aesthetics

.pull-left.center[

]

.box-inv-1.medium[Aesthetic]

.box-1.sp-after[Position, shape, color, etc.]

.box-inv-1.medium[Data]

]

---

# Mapping data to aesthetics

<table>
  <tr>
    <th class="cell-left">Data</th>
    <th class="cell-left">Aesthetic</th>
    <th class="cell-left">Graphic/Geometry</th>
  </tr>
  <tr>
    <td class="cell-left">Longitude</td>
    <td class="cell-left">Position (x-axis)&emsp;</td>
    <td class="cell-left">Point</td>
  </tr>
  <tr>
    <td class="cell-left">Latitude</td>
    <td class="cell-left">Position (y-axis)</td>
    <td class="cell-left">Point</td>
  </tr>
  <tr>
    <td class="cell-left">Army size</td>
    <td class="cell-left">Size</td>
    <td class="cell-left">Path</td>
  </tr>
  <tr>
    <td class="cell-left">Army direction&emsp;</td>
    <td class="cell-left">Color</td>
    <td class="cell-left">Path</td>
  </tr>
  <tr>
    <td class="cell-left">Date</td>
    <td class="cell-left">Position (x-axis)</td>
    <td class="cell-left">Line + text</td>
  </tr>
  <tr>
    <td class="cell-left">Temperature</td>
    <td class="cell-left">Position (y-axis)</td>
    <td class="cell-left">Line + text</td>
  </tr>
</table>

---

# Mapping data to aesthetics

<table>
  <tr>
    <th class="cell-left">Data</th>
    <th class="cell-left"><code class="remark-inline-code">aes()</code></th>
    <th class="cell-left"><code class="remark-inline-code">geom</code></th>
  </tr>
  <tr>
    <td class="cell-left">Longitude</td>
    <td class="cell-left"><code class="remark-inline-code">x</code></td>
    <td class="cell-left"><code class="remark-inline-code">geom_point()</code></td>
  </tr>
  <tr>
    <td class="cell-left">Latitude</td>
    <td class="cell-left"><code class="remark-inline-code">y</code></td>
    <td class="cell-left"><code class="remark-inline-code">geom_point()</code></td>
  </tr>
  <tr>
    <td class="cell-left">Army size</td>
    <td class="cell-left"><code class="remark-inline-code">size</code></td>
    <td class="cell-left"><code class="remark-inline-code">geom_path()</code></td>
  </tr>
  <tr>
    <td class="cell-left">Army direction&emsp;</td>
    <td class="cell-left"><code class="remark-inline-code">color</code>&emsp;</td>
    <td class="cell-left"><code class="remark-inline-code">geom_path()</code></td>
  </tr>
  <tr>
    <td class="cell-left">Date</td>
    <td class="cell-left"><code class="remark-inline-code">x</code></td>
    <td class="cell-left"><code class="remark-inline-code">geom_line() + geom_text()</code></td>
  </tr>
  <tr>
    <td class="cell-left">Temperature</td>
    <td class="cell-left"><code class="remark-inline-code">y</code></td>
    <td class="cell-left"><code class="remark-inline-code">geom_line() + geom_text()</code></td>
  </tr>
</table>

---

# `ggplot()` template

<code class ='r hljs remark-code'>ggplot(data = <b><span style="background-color:#CBB5FF">DATA</span></b>) +<br>&nbsp;&nbsp;<b><span style="background-color:#FFDFD1">GEOM_FUNCTION</span></b>(mapping = aes(<b><span style="background-color:#FFD0CF">AESTHETIC MAPPINGS</span></b>))</code>

<code class ='r hljs remark-code'>ggplot(data = <b><span style="background-color:#CBB5FF">troops</span></b>) +<br>&nbsp;&nbsp;<b><span style="background-color:#FFDFD1">geom_path</span></b>(mapping = aes(<b><span style="background-color:#FFD0CF">x = longitude</span></b>,<br>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;<b><span style="background-color:#FFD0CF">y = latitude</span></b>,<br>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;<b><span style="background-color:#FFD0CF">color = direction</span></b>,<br>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;<b><span style="background-color:#FFD0CF">size = survivors</span></b>))</code>

---

<table>
 <thead>
  <tr>
   <th style="text-align:left;"> longitude </th>
   <th style="text-align:left;"> latitude </th>
   <th style="text-align:left;"> direction </th>
   <th style="text-align:left;"> survivors </th>
  </tr>
 </thead>
<tbody>
  <tr>
   <td style="text-align:left;"> 24 </td>
   <td style="text-align:left;"> 54.9 </td>
   <td style="text-align:left;"> A </td>
   <td style="text-align:left;"> 340000 </td>
  </tr>
  <tr>
   <td style="text-align:left;"> 24.5 </td>
   <td style="text-align:left;"> 55 </td>
   <td style="text-align:left;"> A </td>
   <td style="text-align:left;"> 340000 </td>
  </tr>
  <tr>
   <td style="text-align:left;"> … </td>
   <td style="text-align:left;"> … </td>
   <td style="text-align:left;"> … </td>
   <td style="text-align:left;"> … </td>
  </tr>
</tbody>
</table>

]

---

---

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

---

---

# Heavy cars with better mileage?

---

# Aesthetics

.box-inv-1.small[`color` (discrete)]

.box-inv-1.small[`color` (continuous)]

<img src="01-class_04_visualize-data_files/figure-html/aes-color-continuous-1.png" width="100%" style="display: block; margin: auto;" />
]

.box-inv-1.small[`size`]

.box-inv-1.small[`fill`]

<img src="01-class_04_visualize-data_files/figure-html/aes-fill-1.png" width="100%" style="display: block; margin: auto;" />
]

.box-inv-1.small[`shape`]

.box-inv-1.small[`alpha`]

<img src="01-class_04_visualize-data_files/figure-html/aes-alpha-1.png" width="100%" style="display: block; margin: auto;" />
]

---

# Mapping columns to aesthetics

```r
ggplot(mpg) + geom_point(aes(x = displ, y = hwy, color = class))
ggplot(mpg) + geom_point(aes(x = displ, y = hwy, size = class))
ggplot(mpg) + geom_point(aes(x = displ, y = hwy, shape = class))
ggplot(mpg) + geom_point(aes(x = displ, y = hwy, alpha = class))
```
]

---

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

---

# Your turn #2

---

# How would you make this plot?

---

```r
ggplot(mpg) +
  geom_point(aes(x = displ, y = hwy, 
                 color = class))
```
]

---

```r
ggplot(mpg) +
  geom_point(aes(x = displ, y = hwy), 
             color = "blue")
```
]

---

```r
ggplot(mpg) +
  geom_point(aes(x = displ, y = hwy, 
                 color = "blue"))
```

<img src="01-class_04_visualize-data_files/figure-html/unnamed-chunk-9-1.png" width="100%" style="display: block; margin: auto;" />
]
]

```r
ggplot(mpg) +
  geom_point(aes(x = displ, y = hwy), 
             color = "blue")
```

<img src="01-class_04_visualize-data_files/figure-html/unnamed-chunk-10-1.png" width="100%" style="display: block; margin: auto;" />
]
]

---

---

# What's the same? What's different?

.pull-left[
<img src="01-class_04_visualize-data_files/figure-html/unnamed-chunk-11-1.png" width="100%" style="display: block; margin: auto;" />
]

.pull-right[
<img src="01-class_04_visualize-data_files/figure-html/unnamed-chunk-12-1.png" width="100%" style="display: block; margin: auto;" />
]

---

# Geoms

---

# Possible geoms

<table>
  <tr>
    <th class="cell-left"></th>
    <th class="cell-left">Example geom</th>
    <th class="cell-left">What it makes</th>
  </tr>
  <tr>
    <td class="cell-left"><img src="img/01-class/03/geom_bar.png"></td>
    <td class="cell-left"><code class="remark-inline-code">geom_col()</code></td>
    <td class="cell-left">Bar charts</td>
  </tr>
  <tr>
    <td class="cell-left"><img src="img/01-class/03/geom_text.png"></td>
    <td class="cell-left"><code class="remark-inline-code">geom_text()</code></td>
    <td class="cell-left">Text</td>
  </tr>
  <tr>
    <td class="cell-left"><img src="img/01-class/03/geom_point.png"></td>
    <td class="cell-left"><code class="remark-inline-code">geom_point()</code></td>
    <td class="cell-left">Points</td>
  </tr>
  <tr>
    <td class="cell-left"><img src="img/01-class/03/geom_boxplot.png"></td>
    <td class="cell-left"><code class="remark-inline-code">geom_boxplot()</code>&emsp;</td>
    <td class="cell-left">Boxplots</td>
  </tr>
  <tr>
    <td class="cell-left"><img src="img/01-class/03/geom_sf.png"></td>
    <td class="cell-left"><code class="remark-inline-code">geom_sf()</code></td>
    <td class="cell-left">Maps</td>
  </tr>
</table>

---

# Possible geoms

.box-1[See [the **ggplot2** documentation](https://ggplot2.tidyverse.org/reference/index.html#section-layer-geoms) for<br>complete examples of all the different geom layers]

---

# Your turn #3

.pull-left[
<img src="01-class_04_visualize-data_files/figure-html/unnamed-chunk-13-1.png" width="100%" style="display: block; margin: auto;" />
]

.pull-right[
<img src="01-class_04_visualize-data_files/figure-html/unnamed-chunk-14-1.png" width="100%" style="display: block; margin: auto;" />
]

---

# Your turn #4

---

# Your turn #5

.box-1[Make this density plot of `hwy` colored by `class`.<br>Use the cheatsheet. Hint: don't supply a `y` variable.]

---

# Complex graphs!

---

# Your turn #6

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

---

# Global vs. local

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

<img src="01-class_04_visualize-data_files/figure-html/unnamed-chunk-21-1.png" width="60%" style="display: block; margin: auto;" />
]

---

# Global vs. local

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

<img src="01-class_04_visualize-data_files/figure-html/unnamed-chunk-22-1.png" width="60%" style="display: block; margin: auto;" />
]

---

---

# So much more!

.box-inv-1[We sequentially add layers onto the foundational `ggplot()` plot to create complex figures]
]

---

# Putting it all together

.box-inv-1.medium[We can build a plot sequentially<br>to see how each grammatical layer<br>changes the appearance]

---

```r
*ggplot(data = mpg,
*      mapping = aes(x = displ,
*                    y = hwy,
*                    color = drv))
```
]

---

```r
ggplot(data = mpg,
       mapping = aes(x = displ,
                     y = hwy,
                     color = drv)) +
* geom_point()
```
]

---

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

---

```r
ggplot(data = mpg,
       mapping = aes(x = displ,
                     y = hwy,
                     color = drv)) +
  geom_point() +
* geom_smooth(method = "lm")
```
]

---

```r
ggplot(data = mpg,
       mapping = aes(x = displ,
                     y = hwy,
                     color = drv)) +
  geom_point() +
  geom_smooth(method = "lm") +
* scale_color_viridis_d()
```
]

---

```r
ggplot(data = mpg,
       mapping = aes(x = displ,
                     y = hwy,
                     color = drv)) +
  geom_point() +
  geom_smooth(method = "lm") +
  scale_color_viridis_d() +
* facet_wrap(vars(drv), ncol = 1)
```
]

---

```r
ggplot(data = mpg,
       mapping = aes(x = displ,
                     y = hwy,
                     color = drv)) +
  geom_point() +
  geom_smooth(method = "lm") +
  scale_color_viridis_d() +
  facet_wrap(vars(drv), ncol = 1) +
* labs(x = "Displacement", y = "Highway MPG",
*      color = "Drive",
*      title = "Heavier cars get lower mileage",
*      subtitle = "Displacement indicates weight(?)",
*      caption = "I know nothing about cars")
```
]

---

```r
ggplot(data = mpg,
       mapping = aes(x = displ,
                     y = hwy,
                     color = drv)) +
  geom_point() +
  geom_smooth(method = "lm") +
  scale_color_viridis_d() +
  facet_wrap(vars(drv), ncol = 1) +
  labs(x = "Displacement", y = "Highway MPG",
       color = "Drive", 
       title = "Heavier cars get lower mileage",
       subtitle = "Displacement indicates weight(?)",
       caption = "I know nothing about cars") +
* theme_bw()
```
]

---

```r
ggplot(data = mpg, 
       mapping = aes(x = displ,
                     y = hwy,
                     color = drv)) +
  geom_point() +
  geom_smooth(method = "lm") +
  scale_color_viridis_d() +
  facet_wrap(vars(drv), ncol = 1) +
  labs(x = "Displacement", y = "Highway MPG",
       color = "Drive", 
       title = "Heavier cars get lower mileage",
       subtitle = "Displacement indicates weight(?)",
       caption = "I know nothing about cars") +
  theme_bw() +
* theme(legend.position = "bottom",
*       plot.title = element_text(face = "bold"))
```
]

---

```r
ggplot(data = mpg, 
       mapping = aes(x = displ,
                     y = hwy,
                     color = drv)) +
  geom_point() +
  geom_smooth(method = "lm") + 
  scale_color_viridis_d() +
  facet_wrap(vars(drv), ncol = 1) +
  labs(x = "Displacement", y = "Highway MPG",
       color = "Drive", 
       title = "Heavier cars get lower mileage",
       subtitle = "Displacement indicates weight(?)",
       caption = "I know nothing about cars") +
  theme_bw() +
  theme(legend.position = "bottom",
        plot.title = element_text(face = "bold"))
```
]

---

# Next up

.box-inv-1.medium[Transforming and<br>manipulating data with dplyr]