+ - 0:00:00
Notes for current slide

Welcome to the workshop on ggplot.

Where we'll show you how to create impressive data visualisations.

Notes for next slide

NHS Workshop
Introduction to ggplot

ggplot - Distributions/Relationships

Eugene Hickey
January 21st 2021

Graphic by Elaine Hickey

Welcome to the workshop on ggplot.

Where we'll show you how to create impressive data visualisations.

Picturing Data Different Ways with ggplot

We're going to set out some of the options for looking at data

these depend on what kind of data you have

and what you want to investigate

Lots of these come from Top 50 Visualizations in R

  1. Visualising Amounts
  2. Visualising Proportions
  3. Visualising Distributions
  4. Visualising Relationships
  5. Visualising Time Series
  6. Visualising Groups
  7. Visualising Networks
  8. Visualising Spatial Data

    Items in red we'll cover this afternoon. In blue will have to wait for a future workshop.

Visualising Distributions

  • histograms
  • density plots
  • boxplot
  • violin plot
  • ridge plots
basketball
## # A tibble: 3,366 x 8
##    name     year_start year_end position height weight birth_date   college     
##    <chr>         <dbl>    <dbl> <chr>     <dbl>  <dbl> <chr>        <chr>       
##  1 Kareem ~       1970     1989 C          218.  102.  April 16, 1~ University ~
##  2 Mahmoud~       1991     2001 G          185.   73.5 March 9, 19~ Louisiana S~
##  3 Tariq A~       1998     2003 F          198.  101.  November 3,~ San Jose St~
##  4 Shareef~       1997     2008 F          206.  102.  December 11~ University ~
##  5 Tom Abe~       1977     1981 F          201.   99.8 May 6, 1954  Indiana Uni~
##  6 Forest ~       1957     1957 G          190.   81.6 July 27, 19~ Western Ken~
##  7 John Ab~       1947     1948 F          190.   88.5 February 9,~ Salem Inter~
##  8 Alex Ac~       2006     2009 G          196.   83.9 January 21,~ Pepperdine ~
##  9 Don Ack~       1954     1954 G          183.   83.0 September 4~ Long Island~
## 10 Bud Act~       1968     1968 F          198.   95.3 January 11,~ Hillsdale C~
## # ... with 3,356 more rows
basketball %>%
  ggplot(aes(weight))

basketball %>%
  ggplot(aes(weight)) +
  geom_histogram(fill = "firebrick4",
                 bins = 50)

basketball %>%
  ggplot(aes(weight)) +
  geom_histogram(fill = "firebrick4",
                 bins = 50) +
  labs(x = "weight (kg)",
       y = "",
       caption = "@Data from Kaggle",
       title = "Weight of NBA Players")

basketball
## # A tibble: 3,366 x 8
##    name     year_start year_end position height weight birth_date   college     
##    <chr>         <dbl>    <dbl> <chr>     <dbl>  <dbl> <chr>        <chr>       
##  1 Kareem ~       1970     1989 C          218.  102.  April 16, 1~ University ~
##  2 Mahmoud~       1991     2001 G          185.   73.5 March 9, 19~ Louisiana S~
##  3 Tariq A~       1998     2003 F          198.  101.  November 3,~ San Jose St~
##  4 Shareef~       1997     2008 F          206.  102.  December 11~ University ~
##  5 Tom Abe~       1977     1981 F          201.   99.8 May 6, 1954  Indiana Uni~
##  6 Forest ~       1957     1957 G          190.   81.6 July 27, 19~ Western Ken~
##  7 John Ab~       1947     1948 F          190.   88.5 February 9,~ Salem Inter~
##  8 Alex Ac~       2006     2009 G          196.   83.9 January 21,~ Pepperdine ~
##  9 Don Ack~       1954     1954 G          183.   83.0 September 4~ Long Island~
## 10 Bud Act~       1968     1968 F          198.   95.3 January 11,~ Hillsdale C~
## # ... with 3,356 more rows
basketball %>%
  ggplot(aes(weight,
             fill = position))

basketball %>%
  ggplot(aes(weight,
             fill = position)) +
  geom_histogram(bins = 20,
                 position = "dodge")

basketball %>%
  ggplot(aes(weight,
             fill = position)) +
  geom_histogram(bins = 20,
                 position = "dodge") +
  labs(x = "weight (kg)",
       y = "",
       caption = "@Data from Kaggle",
       title = "Weight of NBA Players by Position")

basketball
## # A tibble: 3,366 x 8
##    name     year_start year_end position height weight birth_date   college     
##    <chr>         <dbl>    <dbl> <chr>     <dbl>  <dbl> <chr>        <chr>       
##  1 Kareem ~       1970     1989 C          218.  102.  April 16, 1~ University ~
##  2 Mahmoud~       1991     2001 G          185.   73.5 March 9, 19~ Louisiana S~
##  3 Tariq A~       1998     2003 F          198.  101.  November 3,~ San Jose St~
##  4 Shareef~       1997     2008 F          206.  102.  December 11~ University ~
##  5 Tom Abe~       1977     1981 F          201.   99.8 May 6, 1954  Indiana Uni~
##  6 Forest ~       1957     1957 G          190.   81.6 July 27, 19~ Western Ken~
##  7 John Ab~       1947     1948 F          190.   88.5 February 9,~ Salem Inter~
##  8 Alex Ac~       2006     2009 G          196.   83.9 January 21,~ Pepperdine ~
##  9 Don Ack~       1954     1954 G          183.   83.0 September 4~ Long Island~
## 10 Bud Act~       1968     1968 F          198.   95.3 January 11,~ Hillsdale C~
## # ... with 3,356 more rows
basketball %>%
  ggplot(aes(weight,
             col = position))

basketball %>%
  ggplot(aes(weight,
             col = position)) +
  stat_density(geom = "line",
               position = "identity")

basketball %>%
  ggplot(aes(weight,
             col = position)) +
  stat_density(geom = "line",
               position = "identity") +
  labs(x = "weight (kg)",
       y = "",
       caption = "@Data from Kaggle",
       title = "Weight of NBA Players by Position")

basketball %>%
  ggplot(aes(weight,
             col = position)) +
  stat_density(geom = "line",
               position = "identity") +
  labs(x = "weight (kg)",
       y = "",
       caption = "@Data from Kaggle",
       title = "Weight of NBA Players by Position") +
  geom_rug()

basketball
## # A tibble: 3,366 x 8
##    name     year_start year_end position height weight birth_date   college     
##    <chr>         <dbl>    <dbl> <chr>     <dbl>  <dbl> <chr>        <chr>       
##  1 Kareem ~       1970     1989 C          218.  102.  April 16, 1~ University ~
##  2 Mahmoud~       1991     2001 G          185.   73.5 March 9, 19~ Louisiana S~
##  3 Tariq A~       1998     2003 F          198.  101.  November 3,~ San Jose St~
##  4 Shareef~       1997     2008 F          206.  102.  December 11~ University ~
##  5 Tom Abe~       1977     1981 F          201.   99.8 May 6, 1954  Indiana Uni~
##  6 Forest ~       1957     1957 G          190.   81.6 July 27, 19~ Western Ken~
##  7 John Ab~       1947     1948 F          190.   88.5 February 9,~ Salem Inter~
##  8 Alex Ac~       2006     2009 G          196.   83.9 January 21,~ Pepperdine ~
##  9 Don Ack~       1954     1954 G          183.   83.0 September 4~ Long Island~
## 10 Bud Act~       1968     1968 F          198.   95.3 January 11,~ Hillsdale C~
## # ... with 3,356 more rows
basketball %>%
   ggplot(aes(x = position,
              y = weight,
              colour = position))

basketball %>%
   ggplot(aes(x = position,
              y = weight,
              colour = position)) +
   geom_boxplot(show.legend = F)

basketball %>%
   ggplot(aes(x = position,
              y = weight,
              colour = position)) +
   geom_boxplot(show.legend = F) +
   labs(y = "weight (kg)",
        x = "position",
        caption = "@Data from Kaggle",
        title = "Weight of NBA Players by Position")

basketball %>%
   ggplot(aes(x = position,
              y = weight,
              colour = position)) +
   geom_boxplot(show.legend = F) +
   labs(y = "weight (kg)",
        x = "position",
        caption = "@Data from Kaggle",
        title = "Weight of NBA Players by Position") +
  geom_jitter(size = 0.4,
              alpha = 0.2,
              show.legend = F)

count: false

basketball
## # A tibble: 3,366 x 8
##    name     year_start year_end position height weight birth_date   college     
##    <chr>         <dbl>    <dbl> <chr>     <dbl>  <dbl> <chr>        <chr>       
##  1 Kareem ~       1970     1989 C          218.  102.  April 16, 1~ University ~
##  2 Mahmoud~       1991     2001 G          185.   73.5 March 9, 19~ Louisiana S~
##  3 Tariq A~       1998     2003 F          198.  101.  November 3,~ San Jose St~
##  4 Shareef~       1997     2008 F          206.  102.  December 11~ University ~
##  5 Tom Abe~       1977     1981 F          201.   99.8 May 6, 1954  Indiana Uni~
##  6 Forest ~       1957     1957 G          190.   81.6 July 27, 19~ Western Ken~
##  7 John Ab~       1947     1948 F          190.   88.5 February 9,~ Salem Inter~
##  8 Alex Ac~       2006     2009 G          196.   83.9 January 21,~ Pepperdine ~
##  9 Don Ack~       1954     1954 G          183.   83.0 September 4~ Long Island~
## 10 Bud Act~       1968     1968 F          198.   95.3 January 11,~ Hillsdale C~
## # ... with 3,356 more rows
basketball %>%
   ggplot(aes(x = position,
              y = weight,
              colour = position))

basketball %>%
   ggplot(aes(x = position,
              y = weight,
              colour = position)) +
   geom_violin(show.legend = F)

basketball %>%
   ggplot(aes(x = position,
              y = weight,
              colour = position)) +
   geom_violin(show.legend = F) +
   labs(x = "position",
        y = "weight (kg)",
        caption = "@Data from Kaggle",
        title = "Weight of NBA Players by Position")

basketball %>%
   ggplot(aes(x = position,
              y = weight,
              colour = position)) +
   geom_violin(show.legend = F) +
   labs(x = "position",
        y = "weight (kg)",
        caption = "@Data from Kaggle",
        title = "Weight of NBA Players by Position") +
   geom_jitter(size = 0.4,
               alpha = 0.2,
               show.legend = F)

gapminder::gapminder
## # A tibble: 1,704 x 6
##    country     continent  year lifeExp      pop gdpPercap
##    <fct>       <fct>     <int>   <dbl>    <int>     <dbl>
##  1 Afghanistan Asia       1952    28.8  8425333      779.
##  2 Afghanistan Asia       1957    30.3  9240934      821.
##  3 Afghanistan Asia       1962    32.0 10267083      853.
##  4 Afghanistan Asia       1967    34.0 11537966      836.
##  5 Afghanistan Asia       1972    36.1 13079460      740.
##  6 Afghanistan Asia       1977    38.4 14880372      786.
##  7 Afghanistan Asia       1982    39.9 12881816      978.
##  8 Afghanistan Asia       1987    40.8 13867957      852.
##  9 Afghanistan Asia       1992    41.7 16317921      649.
## 10 Afghanistan Asia       1997    41.8 22227415      635.
## # ... with 1,694 more rows
gapminder::gapminder %>%
  ggplot(aes(x = lifeExp,
             y = factor(year)))

gapminder::gapminder %>%
  ggplot(aes(x = lifeExp,
             y = factor(year))) +
  geom_density_ridges(fill = "firebrick4",
                      colour = "firebrick4",
                      alpha = 0.4)

gapminder::gapminder %>%
  ggplot(aes(x = lifeExp,
             y = factor(year))) +
  geom_density_ridges(fill = "firebrick4",
                      colour = "firebrick4",
                      alpha = 0.4) +
  theme_ridges()

gapminder::gapminder %>%
  ggplot(aes(x = lifeExp,
             y = factor(year))) +
  geom_density_ridges(fill = "firebrick4",
                      colour = "firebrick4",
                      alpha = 0.4) +
  theme_ridges() +
  labs(x = "Life Expectancy (years)",
       y = "",
       caption = "@Data Gapminder (WHO)")

Summary of Distributions

  • hugely important
  • great way to explore your data / introduce it to others
  • make sure you show you data when possible
    • use geom_rug()
    • use geom_jitter()
    • if lots of points, then use alpha to mute them

Visualising Relationships

  • scatter plots
    • encircling
    • jittering
    • using colour / size / shape
    • fitting lines
    • histograms and boxplots on the axes (and geom_rug())
  • line plots
  • correlation
stars
##                 star magnitude  temp type
## 1                Sun       4.8  5840    G
## 2            SiriusA       1.4  9620    A
## 3            Canopus      -3.1  7400    F
## 4           Arcturus      -0.4  4590    K
## 5     AlphaCentauriA       4.3  5840    G
## 6               Vega       0.5  9900    A
## 7            Capella      -0.6  5150    G
## 8              Rigel      -7.2 12140    B
## 9           ProcyonA       2.6  6580    F
## 10        Betelgeuse      -5.7  3200    M
## 11           Achemar      -2.4 20500    B
## 12             Hadar      -5.3 25500    B
## 13            Altair       2.2  8060    A
## 14         Aldebaran      -0.8  4130    K
## 15             Spica      -3.4 25500    B
## 16           Antares      -5.2  3340    M
## 17         Fomalhaut       2.0  9060    A
## 18            Pollux       1.0  4900    K
## 19             Deneb      -7.2  9340    A
## 20        BetaCrucis      -4.7 28000    B
## 21           Regulus      -0.8 13260    B
## 22             Acrux      -4.0 28000    B
## 23            Adhara      -5.2 23000    B
## 24            Shaula      -3.4 25500    B
## 25         Bellatrix      -4.3 23000    B
## 26            Castor       1.2  9620    A
## 27            Gacrux      -0.5  3750    M
## 28      BetaCentauri      -5.1 25500    B
## 29    AlphaCentauriB       5.8  4730    K
## 30           AlNa'ir      -1.1 15550    B
## 31       Miaplacidus      -0.6  9300    A
## 32            Elnath      -1.6 12400    B
## 33           Alnilam      -6.2 26950    B
## 34            Mirfak      -4.6  7700    F
## 35           Alnitak      -5.9 33600    O
## 36             Dubhe       0.2  4900    K
## 37            Alioth       0.4  9900    A
## 38           Peacock      -2.3 20500    B
## 39     KausAustralis      -0.3 11000    B
## 40      ThetaScorpii      -5.6  7400    F
## 41             Atria      -0.1  4590    K
## 42            Alkaid      -1.7 20500    B
## 43      AlphaCrucisB      -3.3 20500    B
## 44             Avior      -2.1  4900    K
## 45 DeltaCanisMajoris      -8.0  6100    F
## 46            Alhena       0.0  9900    A
## 47        Menkalinan       0.6  9340    A
## 48           Polaris      -4.6  6100    F
## 49            Mirzam      -4.8 25500    B
## 50   DeltaVulpeculae       0.6  9900    A
## 51  *ProximaCentauri      15.5  2670    M
## 52   *AlphaCentauriB       5.8  4900    K
## 53     Barnard'sStar      13.2  2800    M
## 54           Wolf359      16.7  2670    M
## 55           HD93735      10.5  3200    M
## 56           *L726-8      15.5  2670    M
## 57           *UVCeti      16.0  2670    M
## 58          *SiriusA       1.4  9620    A
## 59          *SiriusB      11.2 14800   DA
## 60           Ross154      13.1  2800    M
## 61           Ross248      14.8  2670    M
## 62    EpsilonEridani       6.1  4590    K
## 63           Ross128      13.5  2800    M
## 64            L789-6      14.5  2670    M
## 65     *GXAndromedae      10.4  3340    M
## 66     *GQAndromedae      13.4  2670    M
## 67       EpsilonIndi       7.0  4130    K
## 68         *61CygniA       7.6  4130    K
## 69         *61CygniB       8.4  3870    K
## 70      *Struve2398A      11.2  3070    M
## 71      *Struve2398B      11.9  2940    M
## 72           TauCeti       5.7  5150    G
## 73         *ProcyonA       2.6  6600    F
## 74         *ProcyonB      13.0  9700   DF
## 75      Lacaille9352       9.6  3340    M
## 76            G51-I5      17.0  2500    M
## 77            YZCeti      14.1  2670    M
## 78         BD+051668      11.9  2800    M
## 79      Lacaille8760       8.7  3340    K
## 80      KapteynsStar      10.9  3480    M
## 81        *Kruger60A      11.9  2940    M
## 82        *Kruger60B      13.3  2670    M
## 83         BD-124523      12.1  2940    M
## 84          Ross614A      13.1  2800    M
## 85          Wolf424A      15.0  2670    M
## 86   vanMaanen'sStar      14.2 13000   DB
## 87         TZArietis      14.0  2800    M
## 88          HD225213      10.3  3200    M
## 89            Altair       2.2  8060    A
## 90          ADLeonis      11.0  2940    M
## 91       *40EridaniA       6.0  4900    K
## 92       *40EridaniB      11.1 10000   DA
## 93       *40EridaniC      12.8  2940    M
## 94      *70OphiuchiA       5.8  4950    K
## 95      *70OphiuchiB       7.5  3870    K
## 96        EVLacertae      11.7  2800    M
stars %>%
  ggplot(aes(temp,
             magnitude,
             col = type))

stars %>%
  ggplot(aes(temp,
             magnitude,
             col = type)) +
  geom_point(show.legend = F)

stars %>%
  ggplot(aes(temp,
             magnitude,
             col = type)) +
  geom_point(show.legend = F) +
  geom_encircle(data = stars %>%
                  dplyr::filter(type == "B" | (type == "M" & magnitude > 9)),
                show.legend = F)

stars %>%
  ggplot(aes(temp,
             magnitude,
             col = type)) +
  geom_point(show.legend = F) +
  geom_encircle(data = stars %>%
                  dplyr::filter(type == "B" | (type == "M" & magnitude > 9)),
                show.legend = F) +
  scale_x_log10()

stars %>%
  ggplot(aes(temp,
             magnitude,
             col = type)) +
  geom_point(show.legend = F) +
  geom_encircle(data = stars %>%
                  dplyr::filter(type == "B" | (type == "M" & magnitude > 9)),
                show.legend = F) +
  scale_x_log10() +
  annotate("text",
           x = c(15000, 5000),
           y = c(-4, 14),
           label = c("Type B Stars", "Faint Type M Stars"),
           col = c("blue", "olivedrab3"),
           family = "Ink Free",
           size = 4,
           fontface = 2)

stars %>%
  ggplot(aes(temp,
             magnitude,
             col = type)) +
  geom_point(show.legend = F) +
  geom_encircle(data = stars %>%
                  dplyr::filter(type == "B" | (type == "M" & magnitude > 9)),
                show.legend = F) +
  scale_x_log10() +
  annotate("text",
           x = c(15000, 5000),
           y = c(-4, 14),
           label = c("Type B Stars", "Faint Type M Stars"),
           col = c("blue", "olivedrab3"),
           family = "Ink Free",
           size = 4,
           fontface = 2) +
  scale_color_viridis_d()

scatter <- Galton %>% 
  ggplot(aes(parent, child)) +
  geom_point()
jittered <- Galton %>% ggplot(aes(parent, child)) + geom_jitter(width = 0.4, height = 0.4)
scatter + plot_spacer() + jittered

Picturing Data Different Ways with ggplot

We're going to set out some of the options for looking at data

these depend on what kind of data you have

and what you want to investigate

Lots of these come from Top 50 Visualizations in R

Paused

Help

Keyboard shortcuts

↑, ←, Pg Up, k Go to previous slide
↓, →, Pg Dn, Space, j Go to next slide
Home Go to first slide
End Go to last slide
Number + Return Go to specific slide
b / m / f Toggle blackout / mirrored / fullscreen mode
c Clone slideshow
p Toggle presenter mode
t Restart the presentation timer
?, h Toggle this help
oTile View: Overview of Slides
Esc Back to slideshow