Data Visualization

class: center, middle, inverse, title-slide

# Data Visualization
## Using the grammar of graphics (ggplot2)
### Andrew Irwin, <a href="mailto:a.irwin@dal.ca" class="email">a.irwin@dal.ca</a>
### Math & Stats, Dalhousie University
### 2021-01-20 (updated: 2021-01-06)

---

class: middle

# ggplot2 examples

A series of examples to demonstrate how to use the grammar of graphics to plan and create visualizations.

Using `gss_sm` and `gss_cat` in the `socviz` package which contains a general social survey with 2867 observations (rows) and 32 variables (columns).

Basic examples using selected geometries, plus some elaborations.

---
class: middle, inverse
# What data do you have?

* One (or two) categorical: `geom_bar`

* One quantitative: `geom_histogram`

* One categorical and one quantitative: `geom_boxplot`

* Two quantitative: `geom_point`

---
class: middle
### One categorical variable

```r
gss_sm %>% ggplot(aes(y = region)) + geom_bar()
```

---
class: middle
### Two categorical variables

```r
gss_sm %>% ggplot(aes(y = region, fill = degree)) + geom_bar() 
```

---
class: middle
#### Two categorical variables, using area for counts

```r
gss_sm %>% ggplot(aes(y=income16, x = happy)) + geom_count()
```

---
class: middle
### Same data using bars

```r
gss_sm %>% ggplot(aes(y=income16, fill = happy)) + geom_bar() 
```

---
class: middle
#### Same data, too many colors

```r
gss_sm %>% ggplot(aes(fill=income16, x = happy)) + geom_bar() 
```

---
class: middle
### One quantitative variable

```r
gss_sm %>% ggplot(aes(x = age)) + geom_histogram()
```

---
class: middle
#### One categorical, one quantitative variable

```r
gss_sm %>% ggplot(aes(x = age, y=factor(childs))) + 
* geom_boxplot() +
* labs(y="Number of children")
```

---
class: middle
#### Two quantitative variables

```r
gss_cat %>% slice_sample(n=2000) %>% 
  ggplot(aes(x = age, y= tvhours)) + 
* geom_point(size=0.2)
```

---
class: middle
#### Two quantitative variables

```r
gss_cat %>% slice_sample(n=2000) %>% 
  ggplot(aes(x = age, y= tvhours)) + 
* geom_jitter(size=0.2) +
* geom_smooth()
```

---
class: middle
#### Two quantitative variables, show variability in one

```r
gss_cat %>% ggplot(aes(x = age, y = tvhours )) + 
* stat_summary(fun.data = "mean_se")
```

---
class: middle

# Summary

* Showed variations on introductory example with 1 or 2 categorical and quantitative variables

* Demonstrated a few embelishments (colours, standard deviations, symbol area, smooths, jitter points)

* Showed some visualizations that "don't work" -- too many categories

---
class: middle

# Further reading

* Lots more examples with different data in the course notes

* "Extras" including axis labels, text on figures, other annotations

---
class: middle, inverse

## Task

Practice these graphs by

* reproducing them, and

* modifying them by changing variables used in aesthetic mappings.

If you would like, use other data sources described in "Data Sources" chapter in course notes.