Colors

Lecture 18

Dr. Mine Çetinkaya-Rundel

Duke University
STA 113 - Fall 2023

Warm-up

Announcements

Any project questions?
Any specific requests for tips to cover on Tuesday?

Setup

library(countdown)
library(tidyverse)
library(scales)
library(ggthemes)
library(cowplot)
library(colorspace)
library(ggrepel)

theme_set(theme_gray(14)) # 16 for full width, 18 for half width

Color scales

Uses of color in data visualization

Distinguish categories (qualitative)

Qualitative scale example

Palette name: Okabe-Ito

Qualitative scale example

Palette name: ColorBrewer Set1

Qualitative scale example

Palette name: ColorBrewer Set3

Uses of color in data visualization

Distinguish categories (qualitative)
Represent numeric values (sequential)

Sequential scale example

Palette name: Viridis

Sequential scale example

Palette name: Inferno

Sequential scale example

Palette name: Cividis

Uses of color in data visualization

Distinguish categories (qualitative)
Represent numeric values (sequential)
Represent numeric values (diverging)

Diverging scale example

Palette name: ColorBrewer PiYG

Diverging scale example

Palette name: Carto Earth

Diverging scale example

Palette name: Blue-Red

Uses of color in data visualization

Distinguish categories (qualitative)
Represent numeric values (sequential)
Represent numeric values (diverging)
Highlight

Highlight example

Palette name: Grays with accents

Highlight example

Palette name: Okabe-Ito accent

Highlight example

Palette name: ColorBrewer accent

Uses of color in data visualization

Distinguish categories (qualitative)
Represent numeric values (sequential)
Represent numeric values (diverging)
Highlight

Color scales in ggplot2

`temps_months` data

Getting the temps_months data:

temps_months <- read_csv("data/tempnormals.csv") |>
  group_by(location, month_name) |>
  summarize(mean = mean(temperature)) |>
  mutate(
    month = factor(
      month_name,
      levels = c("Jan", "Feb", "Mar", "Apr", "May", "Jun",
                 "Jul", "Aug", "Sep", "Oct", "Nov", "Dec")
    ),
    location = factor(
      location, levels = c("Death Valley", "Houston", "San Diego", "Chicago")
    )
  ) |>
  select(-month_name)

`temps_months` data

The temps_months data:

temps_months

# A tibble: 48 × 3
# Groups:   location [4]
   location  mean month
   <fct>    <dbl> <fct>
 1 Chicago   50.4 Apr  
 2 Chicago   74.1 Aug  
 3 Chicago   29   Dec  
 4 Chicago   28.9 Feb  
 5 Chicago   24.8 Jan  
 6 Chicago   75.8 Jul  
 7 Chicago   71.0 Jun  
 8 Chicago   38.8 Mar  
 9 Chicago   60.9 May  
10 Chicago   41.6 Nov  
# ℹ 38 more rows

`popgrowth` data

Getting the popgrowth data:

US_census <- read_csv("data/US_census.csv")
US_regions <- read_csv("data/US_regions.csv")
popgrowth <- left_join(US_census, US_regions) |>
    group_by(region, division, state) |>
    summarize(
      pop2000 = sum(pop2000, na.rm = TRUE),
      pop2010 = sum(pop2010, na.rm = TRUE),
      popgrowth = (pop2010-pop2000)/pop2000,
      .groups = "drop"
    ) |>
    mutate(region = factor(region, levels = c("West", "South", "Midwest", "Northeast")))

`popgrowth` data

The popgrowth data:

popgrowth

# A tibble: 51 × 6
   region  division           state      pop2000  pop2010 popgrowth
   <fct>   <chr>              <chr>        <dbl>    <dbl>     <dbl>
 1 Midwest East North Central Illinois  12419293 12830632   0.0331 
 2 Midwest East North Central Indiana    6080485  6483802   0.0663 
 3 Midwest East North Central Michigan   9938444  9883640  -0.00551
 4 Midwest East North Central Ohio      11353140 11536504   0.0162 
 5 Midwest East North Central Wisconsin  5363675  5686986   0.0603 
 6 Midwest West North Central Iowa       2926324  3046355   0.0410 
 7 Midwest West North Central Kansas     2688418  2853118   0.0613 
 8 Midwest West North Central Minnesota  4919479  5303925   0.0781 
 9 Midwest West North Central Missouri   5595211  5988927   0.0704 
10 Midwest West North Central Nebraska   1711263  1826341   0.0672 
# ℹ 41 more rows

ggplot2 color scale functions

Scale function	Aesthetic	Data type	Palette type
`scale_color_hue()`	`color`	discrete	qualitative

ggplot2 color scale functions

Scale function	Aesthetic	Data type	Palette type
`scale_color_hue()`	`color`	discrete	qualitative
`scale_fill_hue()`	`fill`	discrete	qualitative

ggplot2 color scale functions

Scale function	Aesthetic	Data type	Palette type
`scale_color_hue()`	`color`	discrete	qualitative
`scale_fill_hue()`	`fill`	discrete	qualitative
`scale_color_gradient()`	`color`	continuous	sequential

ggplot2 color scale functions

Scale function	Aesthetic	Data type	Palette type
`scale_color_hue()`	`color`	discrete	qualitative
`scale_fill_hue()`	`fill`	discrete	qualitative
`scale_color_gradient()`	`color`	continuous	sequential
`scale_color_gradient2()`	`color`	continuous	diverging

ggplot2 color scale functions

Scale function	Aesthetic	Data type	Palette type
`scale_color_hue()`	`color`	discrete	qualitative
`scale_fill_hue()`	`fill`	discrete	qualitative
`scale_color_gradient()`	`color`	continuous	sequential
`scale_color_gradient2()`	`color`	continuous	diverging
`scale_fill_viridis_c()`	`color`	continuous	sequential
`scale_fill_viridis_d()`	`fill`	discrete	sequential
`scale_color_brewer()`	`color`	discrete	qualitative, diverging, sequential
`scale_fill_brewer()`	`fill`	discrete	qualitative, diverging, sequential
`scale_color_distiller()`	`color`	continuous	qualitative, diverging, sequential

… and there are many many more

Examples

ggplot(temps_months, aes(x = month, y = location, fill = mean)) + 
  geom_tile(width = 0.95, height = 0.95) + 
  coord_fixed(expand = FALSE) +
  theme_classic()
  # no fill scale defined, default is scale_fill_gradient()

Examples

ggplot(temps_months, aes(x = month, y = location, fill = mean)) + 
  geom_tile(width = 0.95, height = 0.95) + 
  coord_fixed(expand = FALSE) +
  theme_classic() +
  scale_fill_gradient()

Examples

ggplot(temps_months, aes(x = month, y = location, fill = mean)) + 
  geom_tile(width = 0.95, height = 0.95) + 
  coord_fixed(expand = FALSE) +
  theme_classic() +
  scale_fill_viridis_c()

Examples

ggplot(temps_months, aes(x = month, y = location, fill = mean)) + 
  geom_tile(width = 0.95, height = 0.95) + 
  coord_fixed(expand = FALSE) +
  theme_classic() +
  scale_fill_viridis_c(option = "B", begin = 0.15)

Examples

ggplot(temps_months, aes(x = month, y = location, fill = mean)) + 
  geom_tile(width = 0.95, height = 0.95) + 
  coord_fixed(expand = FALSE) +
  theme_classic() +
  scale_fill_distiller(palette = "YlGnBu")

Color scales in the colorspace package

The colorspace package creates some order

Scale name: scale_<aesthetic>_<datatype>_<colorscale>()

<aesthetic>: name of the aesthetic (fill, color, colour)
<datatype>: type of variable plotted (discrete, continuous, binned)
<colorscale>: type of the color scale (qualitative, sequential, diverging, divergingx)

Scale function	Aesthetic	Data type	Palette type
`scale_color_discrete_qualitative()`	`color`	discrete	qualitative
`scale_fill_continuous_sequential()`	`fill`	continuous	sequential
`scale_colour_continous_divergingx()`	`colour`	continuous	diverging

Examples

ggplot(temps_months, aes(x = month, y = location, fill = mean)) + 
  geom_tile(width = 0.95, height = 0.95) + 
  coord_fixed(expand = FALSE) +
  theme_classic() +
  scale_fill_continuous_sequential(palette = "YlGnBu", rev = FALSE)

Examples

ggplot(temps_months, aes(x = month, y = location, fill = mean)) + 
  geom_tile(width = 0.95, height = 0.95) + 
  coord_fixed(expand = FALSE) +
  theme_classic() +
  scale_fill_continuous_sequential(palette = "Viridis", rev = FALSE)

Examples

ggplot(temps_months, aes(x = month, y = location, fill = mean)) + 
  geom_tile(width = 0.95, height = 0.95) + 
  coord_fixed(expand = FALSE) +
  theme_classic() +
  scale_fill_continuous_sequential(palette = "Inferno", begin = 0.15, rev = FALSE)

HCL (Hue-Chroma-Luminance) palettes: Sequential

colorspace::hcl_palettes(type = "sequential", plot = TRUE)

HCL palettes: Diverging

colorspace::hcl_palettes(type = "diverging", plot = TRUE, n = 9)

HCL palettes: Divergingx

colorspace::divergingx_palettes(plot = TRUE, n = 9)

Setting colors manually

Discrete, qualitative scales are best set manually

ggplot(popgrowth, aes(x = pop2000, y = popgrowth, color = region)) +
  geom_point() +
  scale_x_log10()
  # no color scale defined, default is scale_color_hue()

Discrete, qualitative scales are best set manually

ggplot(popgrowth, aes(x = pop2000, y = popgrowth, color = region)) +
  geom_point() +
  scale_x_log10() +
  scale_color_hue()

Discrete, qualitative scales are best set manually

library(ggthemes)  # for scale_color_colorblind()

ggplot(popgrowth, aes(x = pop2000, y = popgrowth, color = region)) +
  geom_point() +
  scale_x_log10() +
  scale_color_colorblind()  # uses Okabe-Ito colors

Discrete, qualitative scales are best set manually

ggplot(popgrowth, aes(x = pop2000, y = popgrowth, color = region)) +
  geom_point() +
  scale_x_log10() +
  scale_color_manual(
    values = c(West = "#E69F00", South = "#56B4E9", Midwest = "#009E73", Northeast = "#F0E442")
  )

Okabe-Ito RGB codes

Name	Hex code	R, G, B (0-255)
orange	#E69F00	230, 159, 0
sky blue	#56B4E9	86, 180, 233
bluish green	#009E73	0, 158, 115
yellow	#F0E442	240, 228, 66
blue	#0072B2	0, 114, 178
vermilion	#D55E00	213, 94, 0
reddish purple	#CC79A7	204, 121, 167
black	#000000	0, 0, 0

A few considerations when choosing colors

1. Avoid high chroma

High chroma: Toys

Low chroma: “Elegance”

2. Be aware of color-vision deficiency

5%–8% of men are color blind!

Red-green color-vision deficiency is the most common

2. Be aware of color-vision deficiency

5%–8% of men are color blind!

Blue-green color-vision deficiency is rare but does occur

2. Be aware of color-vision deficiency

Choose colors that can be distinguished with CVD

Consider using the Okabe-Ito scale

Name	Hex code	R, G, B (0-255)
orange	#E69F00	230, 159, 0
sky blue	#56B4E9	86, 180, 233
bluish green	#009E73	0, 158, 115
yellow	#F0E442	240, 228, 66
blue	#0072B2	0, 114, 178
vermilion	#D55E00	213, 94, 0
reddish purple	#CC79A7	204, 121, 167
black	#000000	0, 0, 0

CVD is worse for thin lines and tiny dots

When in doubt, run CVD simulations

Colors

Warm-up

Announcements

Setup

Color scales

Uses of color in data visualization

Qualitative scale example

Qualitative scale example

Qualitative scale example

Uses of color in data visualization

Sequential scale example

Sequential scale example

Sequential scale example

Uses of color in data visualization

Diverging scale example

Diverging scale example

Diverging scale example

Uses of color in data visualization

Highlight example

Highlight example

Highlight example

Uses of color in data visualization

Color scales in ggplot2

temps_months data

temps_months data

popgrowth data

popgrowth data

ggplot2 color scale functions

ggplot2 color scale functions

ggplot2 color scale functions

ggplot2 color scale functions

ggplot2 color scale functions

Examples

Examples

Examples

Examples

Examples

Color scales in the colorspace package

The colorspace package creates some order

Examples

Examples

Examples

HCL (Hue-Chroma-Luminance) palettes: Sequential

HCL palettes: Diverging

HCL palettes: Divergingx

Setting colors manually

Discrete, qualitative scales are best set manually

Discrete, qualitative scales are best set manually

Discrete, qualitative scales are best set manually

Discrete, qualitative scales are best set manually

Okabe-Ito RGB codes

Further reading

A few considerations when choosing colors

1. Avoid high chroma

2. Be aware of color-vision deficiency

2. Be aware of color-vision deficiency

2. Be aware of color-vision deficiency

Consider using the Okabe-Ito scale

CVD is worse for thin lines and tiny dots

Further reading

`temps_months` data

`temps_months` data

`popgrowth` data

`popgrowth` data