STATS 220

# STATS 220
## Effective data visualisation👩‍🎨

---

## Graphical perception 👀

### .blue[1.] Preattentive processing
### .blue[2.] Proximity
### .blue[3.] Position vs angle
### .blue[4.] Colour matters

???

* how human perceive a plot
* given the same amount of info from plots, which data type help us to perceive more accurate info

---

## Preattentive processing

???

* Have you noticed there are unusual data points? Can you locate them?
* how about this one?

---

## Preattentive processing .small[.green[colour > form (shape)]]

???

* Which plot helps you to distinguish the data points?
* Which plot consumes your least attention?
* viewers can sense certain features, b/f our mind starts to pay attention to any specific objs.

---

## Proximity .small[.green[Make easy comparisons by grouping elements together]]

.pull-left[
* compare time use by categories within each country
<img src="figure/fill-cat-1.png" width="480" style="display: block; margin: auto;" />
]
.pull-right[
* compare time use by countries within each category
<img src="figure/fill-country-1.png" width="480" style="display: block; margin: auto;" />
]

???

* left: it's not easy to compare how much time spent on sleep across countries

---

## Position vs angle .small[.green[position > angle]]

.pull-left[
<img src="figure/fill-country2-1.png" width="480" style="display: block; margin: auto;" />
]
.pull-right[
<img src="figure/angle-1.png" width="480" style="display: block; margin: auto;" />
.center[Pie charts are BAD‼️]
]

???

* "Other" and "Sleep", can u easily perceive these subtle differences from the pie charts?
* But
* A bar chart or dot chart is a preferable way of displaying this type of data.

---

## Absolute vs relative positions .small[.green[absolute > relative]]

.pull-left[
<img src="figure/fill-country3-1.png" width="480" style="display: block; margin: auto;" />
]
.pull-right[
<img src="figure/rel-pos-1.png" width="480" style="display: block; margin: auto;" />
]

???

* absolute -> share the same base line. we compare their heights
* right: 100% bar chart. its much harder to compare NZ to others, bc NZ is rel.
* The eye is good at judging abs and bad at judging relative.

---

## Colour matters

### .blue[1.] Colour spaces
### .blue[2.] Colour scales
### .blue[3.] Colour blindness

---

## 3 ways to represent colour spaces

1. RGB
2. HSV/HSL
3. HCL .small[.green[for humans]]

---

## RGB

* Red *(0-255)*: amount of .red[red] light
* Green *(0-255)*: amount of .green[green] light
* Blue *(0-255)*: amount of .blue[blue] light

???

* for computer & screen

---

## HSV

* Hue *(0-360)*: hue of the colour
* Saturation *(0-1)*: colourfulness relative to the brightness of the colour
* Value *(0-1)*: subjective perception of amount of light emitted

---

## HSL

* Hue *(0-360)*: hue of the colour
* Lightness *(0-1)*: brightness relative to the brightness of a illuminated white
* Saturation *(0-1)*: colourfulness relative to the brightness of the colour

---

## HCL .small[.green[aka polar LUV]]

* Hue *(0-360)*: hue of the colour
* Chroma *(0-180)*: degree of vividness of a colour
* Luminance *(0-100)*: amount of light emitted

???

HCL: perceptually-based and device-independent

---

## Encoding too much

???

* default ggplot2 colour scales -> not colour blind friendly
* more than 7 qualitative colours, matching colours to categories are cumbersome
* colour can be effective tool to enhance
* choose colour wisely

---

## Colour scales

1. use colour to distinguish groups of data from each other
2. use colour to represent data values
3. use colour to highlight

<hr>

.large[.green[**3**]] types of colour palettes .small[[ColorBrewer](https://colorbrewer2.org/#type=sequential&scheme=BuGn&n=3)]

1. Qualitative
2. Sequential
3. Diverging

---

## Qualitative palettes .small[.green[for categorical data with no intrinsic ordering]]

```r
colorspace::hcl_palettes("Qualitative", plot = TRUE, n = 7)
```

???

* use colour to distinguish discrete items/groups, but doesn't give impression of an order
* a finite set of specific colours that are chosen to look clearly distinct
* no one single colour stands out relative to the others

---

## Sequential palettes .small[.green[for ordered data from high to low]]

```r
colorspace::hcl_palettes("Sequential", plot = TRUE, n = 7)
```

???

* heatmap: used colour to represent data values, like temperature
* representing continuous/ordered values
* colours indicate which data values are larger or smaller
* the diff bt colours shows the diff b/t data values
* seq colour needs to be perceived to vary uniformly across its entire range by changing hues

---

## Diverging palettes .small[.green[for mid-range values and extremes at both ends]]

```r
colorspace::hcl_palettes("Diverging", plot = TRUE, n = 7)
```

???

* vis the deviation of data values in one of 2 directions rel to a neutral midpoint
* a straightforward eg is vis +/- values
* think of a diverging scale as joining 2 seq sales at a common midpoint

---

## Use colour palettes

```r
time_use %>% 
  ggplot(aes(country, time_minutes)) +
  geom_col(
    aes(fill = category), 
    position = "dodge") +
* scale_fill_brewer(palette = "Dark2") +
  labs(y = "") +
  theme(legend.position = "bottom")
```
]
.pull-right[
<img src="figure/gg-palette2-1.png" width="540" style="display: block; margin: auto;" />
]

---

## Set custom colours

```r
time_use %>% 
  ggplot(aes(country, time_minutes)) +
  geom_col(
    aes(fill = category),
    position = "dodge") +
* scale_fill_manual(
*   values = c("#EF476F", "#FFD166",
*              "#06D6A0", "#118AB2",
*              "#073B4C", "grey")) +
  labs(y = "") +
  theme(legend.position = "bottom")
```
]
.pull-right[
<img src="figure/gg-manual2-1.png" width="540" style="display: block; margin: auto;" />
]

---

## Colour-vision deficiency

.pull-left[
.center[<img src = "https://clauswilke.com/dataviz/pitfalls_of_color_use_files/figure-html/red-green-cvd-sim-1.png", width = 90%></img>]
* Red-green colour-vision deficiency (deuteranomaly & protanomaly) is the most common.
]
.pull-right[
.center[<img src = "https://clauswilke.com/dataviz/pitfalls_of_color_use_files/figure-html/blue-green-cvd-sim-1.png", width = 90%></img>]
* Blue-green colour-vision deficiency (tritanomaly) is rare but does occur.
]

<br>

ℹ️ *Approximately 8% of males and 0.5% of females suffer from some sort of color-vision deficiency.*

.footnote[reference: Claus O. Wilke [Fundamentals of Data Visualization](https://clauswilke.com/dataviz/)]

???

* A small prop of people with impaired colour vision have difficulty to distinguish certain types of colours

---

## Choose colours using {colorspace}

.center[<img src = "img/wizard.png", height = "320px"></img>]
]
.pull-right[
* `colorspace::hcl_color_picker()`

---

## Scales

* Control how data is mapped to perceptual properties, and produce guides (axes and legends) which allow us to read the plot.
* Important arguments: `breaks`, `labels`, and `limits`.
* Naming scheme: `scale_[aes]_[datatype]()`

---

<div id="htmlwidget-86afd2f3d6934fd9d0ed" style="width:100%;height:auto;" class="datatables html-widget"></div>
<script type="application/json" data-for="htmlwidget-86afd2f3d6934fd9d0ed">{"x":{"filter":"none","data":[["scale_alpha, scale_alpha_continuous, scale_alpha_binned, scale_alpha_discrete","scale_x_binned, scale_y_binned","scale_colour_brewer, scale_fill_brewer, scale_colour_distiller, scale_fill_distiller","scale_colour_continuous, scale_fill_continuous, scale_colour_binned, scale_fill_binned","scale_colour_discrete, scale_fill_discrete","scale_x_continuous, scale_y_continuous, scale_x_log10, scale_y_log10","scale_x_date, scale_y_date, scale_x_datetime, scale_y_datetime","scale_x_discrete, scale_y_discrete","scale_colour_gradient, scale_fill_gradient, scale_colour_gradient2, scale_fill_gradient2","scale_colour_grey, scale_fill_grey, scale_color_grey","scale_colour_hue, scale_fill_hue, scale_color_discrete, scale_color_hue","scale_colour_identity, scale_fill_identity, scale_shape_identity, scale_linetype_identity","scale_linetype, scale_linetype_binned, scale_linetype_continuous, scale_linetype_discrete","scale_colour_manual, scale_fill_manual, scale_size_manual, scale_shape_manual","scale_shape, scale_shape_binned, scale_shape_discrete, scale_shape_ordinal","scale_size, scale_size_continuous, scale_radius, scale_size_binned","scale_colour_steps, scale_colour_steps2, scale_colour_stepsn, scale_fill_steps","scale_type","scale_colour_viridis_d, scale_fill_viridis_d, scale_colour_viridis_c, scale_fill_viridis_c"],["Alpha transparency scales","Positional scales for binning continuous data (x & y)","Sequential, diverging and qualitative colour scales from colorbrewer.org","Continuous and binned colour scales","Discrete colour scales","Position scales for continuous data (x & y)","Position scales for date/time data","Position scales for discrete data","Gradient colour scales","Sequential grey colour scales","Evenly spaced colours for discrete data","Use values without scaling","Scale for line patterns","Create your own discrete scale","Scales for shapes, aka glyphs","Scales for area or radius","Binned gradient colour scales","Determine default scale type","Viridis colour scales from viridisLite"]],"container":"<table class=\"display\">\n  <thead>\n    <tr>\n      <th>scale<\/th>\n      <th>Description<\/th>\n    <\/tr>\n  <\/thead>\n<\/table>","options":{"dom":"tp","ordering":false,"pageLength":5,"width":"80%","order":[],"autoWidth":false,"orderClasses":false,"lengthMenu":[5,10,25,50,100]}},"evals":[],"jsHooks":[]}</script>

???

---

## Publication-ready visualisation 👩‍🎨

---

.left-column[
## Towards publication-ready visualisation
]
.right-column[
<blockquote class="twitter-tweet"><p lang="en" dir="ltr"><a href="https://twitter.com/hashtag/MakingOf?src=hash&amp;ref_src=twsrc%5Etfw">#MakingOf</a> of last week&#39;s <a href="https://twitter.com/hashtag/TidyTuesday?src=hash&amp;ref_src=twsrc%5Etfw">#TidyTuesday</a> plot <a href="https://t.co/Jsg41id5Nw">https://t.co/Jsg41id5Nw</a> <a href="https://t.co/dP6tSrjHy0">pic.twitter.com/dP6tSrjHy0</a></p>&mdash; Georgios Karamanis (@geokaramanis) <a href="https://twitter.com/geokaramanis/status/1374066377879908358?ref_src=twsrc%5Etfw">March 22, 2021</a></blockquote> <script async src="https://platform.twitter.com/widgets.js" charset="utf-8"></script>
]

---

* For **internal use** only. Need to be able to create rapidly because your first attempt will never be the most revealing.
* Iteration is crucial for developing multiple displays of your data.
]
.pull-right[
## .center[Communication graphics]

* When you **communicate** your findings, you need to spend much time polishing your graphics to eliminate distractions and focus on the storytelling.
* Iteration is crucial to ensure all the bits and pieces works well: labels, color choices, tick marks...
]

---

## Case study: COVID-19

```r
covid19 <- read_csv("data/covid19-daily-cases.csv")
covid19
```

```
#> # A tibble: 15,677 x 3
#>   country_region date       confirmed
#>   <chr>          <date>         <dbl>
#> 1 Afghanistan    2020-03-01         1
#> 2 Afghanistan    2020-03-02         1
#> 3 Afghanistan    2020-03-03         2
#> 4 Afghanistan    2020-03-04         4
#> 5 Afghanistan    2020-03-05         4
#> 6 Afghanistan    2020-03-06         4
#> # … with 15,671 more rows
```

---

```r
covid19 %>% 
  ggplot(aes(
    x = date, 
    y = confirmed, 
    colour = country_region)) +
  geom_line() +
* guides(colour = FALSE) # rm colour legend
```
]
]
]
]

???

full screen of legends

---

```r
covid19 %>% 
  ggplot(aes(
    x = date, 
*   y = log10(confirmed),
    colour = country_region)) +
  geom_line() +
  guides(colour = FALSE)
```
]
]
]
]

???

perceive the rate of infections, slowing down

---

```r
covid19 %>% 
  ggplot(aes(
    x = date, 
    y = confirmed, 
    colour = country_region)) +
  geom_line() +
  guides(colour = FALSE) +
* scale_y_log10()
```
]
]
]

.footnote[Rob J Hyndman's blog post on [Why log ratios are useful for tracking COVID-19](https://robjhyndman.com/hyndsight/logratios-covid19/)]
]

---

```r
covid19_rel <- covid19 %>% 
  group_by(country_region) %>% 
  mutate(days = as.numeric(date - min(date))) %>% 
  ungroup()
covid19_rel
```

```
#> # A tibble: 15,677 x 4
#>   country_region date       confirmed  days
#>   <chr>          <date>         <dbl> <dbl>
#> 1 Afghanistan    2020-03-01         1     0
#> 2 Afghanistan    2020-03-02         1     1
#> 3 Afghanistan    2020-03-03         2     2
#> 4 Afghanistan    2020-03-04         4     3
#> 5 Afghanistan    2020-03-05         4     4
#> 6 Afghanistan    2020-03-06         4     5
#> # … with 15,671 more rows
```
]

???

log(0) -> Inf

---

```r
covid19_rel %>% 
  ggplot(aes(
    x = days,
    y = confirmed, 
    colour = country_region)) +
  geom_line() +
  scale_y_log10() +
  guides(colour = FALSE)
```
]
]
]
]

---

.left-column[
## COVID-19
### - scale-y
### - scale-x
### - highlight
]
.right-column[
## Highlight New Zealand

```r
covid19_nz <- covid19_rel %>% 
  filter(country_region == "New Zealand")
p_nz <- covid19_rel %>% 
  ggplot(aes(x = days, y = confirmed, 
*   group = country_region)) +
  geom_line(colour = "grey", alpha = 0.5) +
  geom_line(colour = "#238b45", size = 1, data = covid19_nz) +
  scale_y_log10() +
  guides(colour = FALSE)
p_nz
```
]
]
]
]

---

.left-column[
## COVID-19
### - scale-y
### - scale-x
### - highlight
### - annotate
]
.right-column[
## Label New Zealand

```r
p_nz <- p_nz +
  geom_label(aes(
*   x = max(days), y = max(confirmed),
    label = country_region), data = covid19_nz,
    colour = "#238b45", nudge_x = 3, nudge_y = .5)
p_nz
```
]
]
]
]

---

.left-column[
## COVID-19
### - scale-y
### - scale-x
### - highlight
### - annotate
### - limits
]
.right-column[
## Expand limits

```r
p_nz <- p_nz +
* scale_y_log10(labels = scales::label_comma()) +
* xlim(c(0, 100))
p_nz
```
]
]
]
]

---

.left-column[
## COVID-19
### - scale-y
### - scale-x
### - highlight
### - annotate
### - limits
### - labels
]
.right-column[
## Every figure needs the title

```r
p_nz <- p_nz +
  labs(
    x = "Days since March 1",
    y = "Confirmed cases (on log10)",
    title = "Worldwide coronavirus confirmed cases",
    subtitle = "highlighting New Zealand",
    caption = "Data source: John Hopkins University, CSSE"
  )
p_nz
```
]
]
]
]

---

.left-column[
## COVID-19
### - scale-y
### - scale-x
### - highlight
### - annotate
### - limits
### - labels
### - theme
]
.right-column[
## Apply themes

```r
# remotes::install_github("Financial-Times/ftplottools")
p_nz +
  ftplottools::ft_theme() +
  theme(
    plot.title.position = "plot", 
    plot.background = element_rect(fill = "#FFF1E0"))
```
]
]
]
]

---

## Interactive graphics

---

## Easily turn ggplot2 into [plotly](https://plotly-r.com)

```r
library(plotly)
*ggplotly(p_nz)
```

.center[<iframe src="figure/plotly.html" width="800" height="500" seamless="seamless" frameBorder="0"> </iframe>]

---

## Generative art

---

## .center[A peek at [generative art works by Thomas Lin Pedersen](https://www.data-imaginist.com/art)]
<img src="https://d33wubrfki0l68.cloudfront.net/b0ca94c787e0e509fe70e7b9285fafffb47a649a/3b7de/art/005_genesis/genesis338_hu19fc60717d90451585acb0fb6a565bcb_106689_500x500_fill_box_center_2.png" width="280px">
<img src="https://d33wubrfki0l68.cloudfront.net/62f4ab9648b5f2359756c5d7e7f4019defe7faf5/e68a3/art/008_emergence/emergence6802_hu7c58ad2a8fca059ec9ebad497d24566e_22821446_500x500_fill_box_center_2.png" width="280px">
<img src="https://d33wubrfki0l68.cloudfront.net/c3f652266f3310fa6ef7bc6f8c1f3080cac74d2e/522f0/art/009_prism/prism627_hu5fd6b3df9c854c0c26e8cdeebe574e51_31622651_500x500_fill_box_center_2.png" width="280px">
<img src="https://d33wubrfki0l68.cloudfront.net/64a2403d266498344f73af33668397e34e9b2b28/857ea/art/008_emergence/emergence526_huc93094888f54e1c55d93d2c9f1d65eda_17094834_500x500_fill_box_center_2.png" width="280px">
<img src="https://d33wubrfki0l68.cloudfront.net/1d067ea931f5be062c1a93bf29fd1e292e84c72b/e1949/art/005_genesis/genesis99_hue66520854e953909155239426845f632_183306_500x500_fill_box_center_2.png" width="280px">
<img src="https://d33wubrfki0l68.cloudfront.net/ba46a11d676efa5481fb8abc447539022241d5a5/4d746/art/003_unfold/unfold06_hu9cba8b0d8a0b0efc5b2fd5f2cd3f12c5_113220_500x500_fill_box_center_2.png" width="280px">
<img src="https://d33wubrfki0l68.cloudfront.net/19592674aaa73f13cd74cee56c819f9efe6cec2c/39caf/art/007_storms/storms4500_hu299e9f5ad6cb567eb7c45aeae728a52d_2314689_500x500_fill_box_center_2.png" width="280px">
<img src="https://d33wubrfki0l68.cloudfront.net/749bf5026fe35d4c1322a8ecde2c6a43294d463d/c2664/art/005_genesis/genesis9458_hu6cbae2b11ecd76683bfe4f6d913c2b92_401118_500x500_fill_box_center_2.png" width="280px">

---

## Reading

.pull-left[
.center[[<img src="https://d33wubrfki0l68.cloudfront.net/b88ef926a004b0fce72b2526b0b5c4413666a4cb/24a30/cover.png" height="520px">](https://r4ds.had.co.nz)]
]
.pull-right[
* [Graphics for communication](https://r4ds.had.co.nz/graphics-for-communication.html)
* [BBC Visual and Data Journalism cookbook for R graphics](https://bbc.github.io/rcookbook/)
]