{ggplot2} and extensions geoms

{ggplot2} and extensions geomsGina Reynolds1 / 4

library(tidyverse)
library(gapminder)

2 / 4

Discrete v. Discrete3 / 4

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
3 / 4

gapminder %>%  
  filter(year == 2002)

  # A tibble: 142 x 6
     country     continent  year lifeExp       pop gdpPercap
     <fct>       <fct>     <int>   <dbl>     <int>     <dbl>
   1 Afghanistan Asia       2002    42.1  25268405      727.
   2 Albania     Europe     2002    75.7   3508512     4604.
   3 Algeria     Africa     2002    71.0  31287142     5288.
   4 Angola      Africa     2002    41.0  10866106     2773.
   5 Argentina   Americas   2002    74.3  38331121     8798.
   6 Australia   Oceania    2002    80.4  19546792    30688.
   7 Austria     Europe     2002    79.0   8148312    32418.
   8 Bahrain     Asia       2002    74.8    656397    23404.
   9 Bangladesh  Asia       2002    62.0 135656790     1136.
  10 Belgium     Europe     2002    78.3  10311970    30486.
  # … with 132 more rows
3 / 4

gapminder %>%  
  filter(year == 2002) %>%  
  mutate(seventy_plus = lifeExp >= 75)

  # A tibble: 142 x 7
     country     continent  year lifeExp       pop gdpPercap seventy_plus
     <fct>       <fct>     <int>   <dbl>     <int>     <dbl> <lgl>       
   1 Afghanistan Asia       2002    42.1  25268405      727. FALSE       
   2 Albania     Europe     2002    75.7   3508512     4604. TRUE        
   3 Algeria     Africa     2002    71.0  31287142     5288. FALSE       
   4 Angola      Africa     2002    41.0  10866106     2773. FALSE       
   5 Argentina   Americas   2002    74.3  38331121     8798. FALSE       
   6 Australia   Oceania    2002    80.4  19546792    30688. TRUE        
   7 Austria     Europe     2002    79.0   8148312    32418. TRUE        
   8 Bahrain     Asia       2002    74.8    656397    23404. FALSE       
   9 Bangladesh  Asia       2002    62.0 135656790     1136. FALSE       
  10 Belgium     Europe     2002    78.3  10311970    30486. TRUE        
  # … with 132 more rows
3 / 4

gapminder %>%  
  filter(year == 2002) %>%  
  mutate(seventy_plus = lifeExp >= 75) %>%  
  mutate(age_category =
           case_when(seventy_plus == T ~
                       "Seventy +",
                     seventy_plus == F ~
                       "< Seventy"))

  # A tibble: 142 x 8
     country   continent  year lifeExp     pop gdpPercap seventy_plus age_category
     <fct>     <fct>     <int>   <dbl>   <int>     <dbl> <lgl>        <chr>       
   1 Afghanis… Asia       2002    42.1  2.53e7      727. FALSE        < Seventy   
   2 Albania   Europe     2002    75.7  3.51e6     4604. TRUE         Seventy +   
   3 Algeria   Africa     2002    71.0  3.13e7     5288. FALSE        < Seventy   
   4 Angola    Africa     2002    41.0  1.09e7     2773. FALSE        < Seventy   
   5 Argentina Americas   2002    74.3  3.83e7     8798. FALSE        < Seventy   
   6 Australia Oceania    2002    80.4  1.95e7    30688. TRUE         Seventy +   
   7 Austria   Europe     2002    79.0  8.15e6    32418. TRUE         Seventy +   
   8 Bahrain   Asia       2002    74.8  6.56e5    23404. FALSE        < Seventy   
   9 Banglade… Asia       2002    62.0  1.36e8     1136. FALSE        < Seventy   
  10 Belgium   Europe     2002    78.3  1.03e7    30486. TRUE         Seventy +   
  # … with 132 more rows
3 / 4

gapminder %>%  
  filter(year == 2002) %>%  
  mutate(seventy_plus = lifeExp >= 75) %>%  
  mutate(age_category =  
           case_when(seventy_plus == T ~  
                       "Seventy +",  
                     seventy_plus == F ~  
                       "< Seventy")) %>%  
  ggplot()

3 / 4

gapminder %>%  
  filter(year == 2002) %>%  
  mutate(seventy_plus = lifeExp >= 75) %>%  
  mutate(age_category =  
           case_when(seventy_plus == T ~  
                       "Seventy +",  
                     seventy_plus == F ~  
                       "< Seventy")) %>%  
  ggplot() +  
  aes(x = continent)

3 / 4

gapminder %>%  
  filter(year == 2002) %>%  
  mutate(seventy_plus = lifeExp >= 75) %>%  
  mutate(age_category =  
           case_when(seventy_plus == T ~  
                       "Seventy +",  
                     seventy_plus == F ~  
                       "< Seventy")) %>%  
  ggplot() +  
  aes(x = continent) +  
  aes(y = age_category)

3 / 4

gapminder %>%  
  filter(year == 2002) %>%  
  mutate(seventy_plus = lifeExp >= 75) %>%  
  mutate(age_category =  
           case_when(seventy_plus == T ~  
                       "Seventy +",  
                     seventy_plus == F ~  
                       "< Seventy")) %>%  
  ggplot() +  
  aes(x = continent) +  
  aes(y = age_category) +  
  geom_jitter(col = "blue", alpha = .3, width = .35, height = .35)

3 / 4

gapminder %>%  
  filter(year == 2002) %>%  
  mutate(seventy_plus = lifeExp >= 75) %>%  
  mutate(age_category =  
           case_when(seventy_plus == T ~  
                       "Seventy +",  
                     seventy_plus == F ~  
                       "< Seventy")) %>%  
  ggplot() +  
  aes(x = continent) +  
  aes(y = age_category) +  
  geom_jitter(col = "blue", alpha = .3, width = .35, height = .35) +  
  geom_count(col = "magenta", alpha = .6) +  
  theme_minimal()

3 / 4

gapminder %>%  
  filter(year == 2002) %>%  
  mutate(seventy_plus = lifeExp >= 75) %>%  
  mutate(age_category =  
           case_when(seventy_plus == T ~  
                       "Seventy +",  
                     seventy_plus == F ~  
                       "< Seventy")) %>%  
  ggplot() +  
  aes(x = continent) +  
  aes(y = age_category) +  
  geom_jitter(col = "blue", alpha = .3, width = .35, height = .35) +  
  geom_text(data = . %>% group_by(age_category, continent) %>% count(), aes(label = n)) +
  theme_minimal()

3 / 4

gapminder %>%  
  filter(year == 2002) %>%  
  mutate(seventy_plus = lifeExp >= 75) %>%  
  mutate(age_category =  
           case_when(seventy_plus == T ~  
                       "Seventy +",  
                     seventy_plus == F ~  
                       "< Seventy")) %>%  
  ggplot() +  
  aes(x = continent) +  
  aes(y = age_category) +  
  geom_jitter(col = "blue", alpha = .3, width = .35, height = .35) +  
  geom_label(data = . %>% group_by(age_category, continent) %>% count(), aes(label = n)) +
  theme_minimal()

3 / 4

gapminder %>%  
  filter(year == 2002) %>%  
  mutate(seventy_plus = lifeExp >= 75) %>%  
  mutate(age_category =  
           case_when(seventy_plus == T ~  
                       "Seventy +",  
                     seventy_plus == F ~  
                       "< Seventy")) %>%  
  ggplot() +  
  aes(x = continent) +  
  aes(y = age_category) +  
  geom_jitter(col = "blue", alpha = .3, width = .35, height = .35) +  
  geom_point(position = ggforce::position_jitternormal()) +
  theme_minimal()

3 / 4

gapminder %>%  
  filter(year == 2002) %>%  
  mutate(seventy_plus = lifeExp >= 75) %>%  
  mutate(age_category =  
           case_when(seventy_plus == T ~  
                       "Seventy +",  
                     seventy_plus == F ~  
                       "< Seventy")) %>%  
  ggplot() +  
  aes(x = continent) +  
  aes(y = age_category) +  
  geom_jitter(col = "blue", alpha = .3, width = .35, height = .35) +  
  geom_point(position = ggforce::position_jitternormal(sd_x = 0.15, sd_y = 0.01)) +
  theme_minimal()

3 / 4

gapminder %>%  
  filter(year == 2002) %>%  
  mutate(seventyfive_plus = lifeExp >= 75) %>%  
  mutate(age_category =  
           case_when(seventyfive_plus == T ~  
                       "75+",  
                     seventyfive_plus == F ~  
                       "<75")) %>%  
  ggplot() +  
  aes(x = age_category) +  
  aes(fill = continent) +  
  geom_point(stat = "count") +  
  geom_bar(position = "dodge", alpha = .6) +  
  theme_minimal()

3 / 4

gapminder %>%  
  filter(year == 2002) %>%  
  mutate(seventyfive_plus = lifeExp >= 75) %>%  
  mutate(age_category =  
           case_when(seventyfive_plus == T ~  
                       "75+",  
                     seventyfive_plus == F ~  
                       "<75")) %>%  
  ggplot() +  
  aes(x = age_category) +  
  aes(fill = continent) +  
  geom_point(stat = "count") +  
  geom_bar(alpha = .6) +
  theme_minimal()

3 / 4

Mosaic4 / 4

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
4 / 4

gapminder %>%  
  filter(year == 2002)

  # A tibble: 142 x 6
     country     continent  year lifeExp       pop gdpPercap
     <fct>       <fct>     <int>   <dbl>     <int>     <dbl>
   1 Afghanistan Asia       2002    42.1  25268405      727.
   2 Albania     Europe     2002    75.7   3508512     4604.
   3 Algeria     Africa     2002    71.0  31287142     5288.
   4 Angola      Africa     2002    41.0  10866106     2773.
   5 Argentina   Americas   2002    74.3  38331121     8798.
   6 Australia   Oceania    2002    80.4  19546792    30688.
   7 Austria     Europe     2002    79.0   8148312    32418.
   8 Bahrain     Asia       2002    74.8    656397    23404.
   9 Bangladesh  Asia       2002    62.0 135656790     1136.
  10 Belgium     Europe     2002    78.3  10311970    30486.
  # … with 132 more rows
4 / 4

gapminder %>%  
  filter(year == 2002) %>%  
  mutate(higher_income = gdpPercap > 20000)

  # A tibble: 142 x 7
     country     continent  year lifeExp       pop gdpPercap higher_income
     <fct>       <fct>     <int>   <dbl>     <int>     <dbl> <lgl>        
   1 Afghanistan Asia       2002    42.1  25268405      727. FALSE        
   2 Albania     Europe     2002    75.7   3508512     4604. FALSE        
   3 Algeria     Africa     2002    71.0  31287142     5288. FALSE        
   4 Angola      Africa     2002    41.0  10866106     2773. FALSE        
   5 Argentina   Americas   2002    74.3  38331121     8798. FALSE        
   6 Australia   Oceania    2002    80.4  19546792    30688. TRUE         
   7 Austria     Europe     2002    79.0   8148312    32418. TRUE         
   8 Bahrain     Asia       2002    74.8    656397    23404. TRUE         
   9 Bangladesh  Asia       2002    62.0 135656790     1136. FALSE        
  10 Belgium     Europe     2002    78.3  10311970    30486. TRUE         
  # … with 132 more rows
4 / 4

gapminder %>%  
  filter(year == 2002) %>%  
  mutate(higher_income = gdpPercap > 20000) %>%  
  group_by(continent, higher_income)

  # A tibble: 142 x 7
  # Groups:   continent, higher_income [8]
     country     continent  year lifeExp       pop gdpPercap higher_income
     <fct>       <fct>     <int>   <dbl>     <int>     <dbl> <lgl>        
   1 Afghanistan Asia       2002    42.1  25268405      727. FALSE        
   2 Albania     Europe     2002    75.7   3508512     4604. FALSE        
   3 Algeria     Africa     2002    71.0  31287142     5288. FALSE        
   4 Angola      Africa     2002    41.0  10866106     2773. FALSE        
   5 Argentina   Americas   2002    74.3  38331121     8798. FALSE        
   6 Australia   Oceania    2002    80.4  19546792    30688. TRUE         
   7 Austria     Europe     2002    79.0   8148312    32418. TRUE         
   8 Bahrain     Asia       2002    74.8    656397    23404. TRUE         
   9 Bangladesh  Asia       2002    62.0 135656790     1136. FALSE        
  10 Belgium     Europe     2002    78.3  10311970    30486. TRUE         
  # … with 132 more rows
4 / 4

gapminder %>%  
  filter(year == 2002) %>%  
  mutate(higher_income = gdpPercap > 20000) %>%  
  group_by(continent, higher_income) %>%  
  summarise(count = n())

  # A tibble: 8 x 3
  # Groups:   continent [5]
    continent higher_income count
    <fct>     <lgl>         <int>
  1 Africa    FALSE            52
  2 Americas  FALSE            23
  3 Americas  TRUE              2
  4 Asia      FALSE            26
  5 Asia      TRUE              7
  6 Europe    FALSE            13
  7 Europe    TRUE             17
  8 Oceania   TRUE              2
4 / 4

gapminder %>%  
  filter(year == 2002) %>%  
  mutate(higher_income = gdpPercap > 20000) %>%  
  group_by(continent, higher_income) %>%  
  summarise(count = n()) %>%  
  mutate(num_in_continents = sum(count),
         prop = count/sum(count))

  # A tibble: 8 x 5
  # Groups:   continent [5]
    continent higher_income count num_in_continents  prop
    <fct>     <lgl>         <int>             <int> <dbl>
  1 Africa    FALSE            52                52 1    
  2 Americas  FALSE            23                25 0.92 
  3 Americas  TRUE              2                25 0.08 
  4 Asia      FALSE            26                33 0.788
  5 Asia      TRUE              7                33 0.212
  6 Europe    FALSE            13                30 0.433
  7 Europe    TRUE             17                30 0.567
  8 Oceania   TRUE              2                 2 1
4 / 4

gapminder %>%  
  filter(year == 2002) %>%  
  mutate(higher_income = gdpPercap > 20000) %>%  
  group_by(continent, higher_income) %>%  
  summarise(count = n()) %>%  
  mutate(num_in_continents = sum(count),  
         prop = count/sum(count)) %>%  
  ungroup()

  # A tibble: 8 x 5
    continent higher_income count num_in_continents  prop
    <fct>     <lgl>         <int>             <int> <dbl>
  1 Africa    FALSE            52                52 1    
  2 Americas  FALSE            23                25 0.92 
  3 Americas  TRUE              2                25 0.08 
  4 Asia      FALSE            26                33 0.788
  5 Asia      TRUE              7                33 0.212
  6 Europe    FALSE            13                30 0.433
  7 Europe    TRUE             17                30 0.567
  8 Oceania   TRUE              2                 2 1
4 / 4

gapminder %>%  
  filter(year == 2002) %>%  
  mutate(higher_income = gdpPercap > 20000) %>%  
  group_by(continent, higher_income) %>%  
  summarise(count = n()) %>%  
  mutate(num_in_continents = sum(count),  
         prop = count/sum(count)) %>%  
  ungroup() %>%  
  ggplot()

4 / 4

gapminder %>%  
  filter(year == 2002) %>%  
  mutate(higher_income = gdpPercap > 20000) %>%  
  group_by(continent, higher_income) %>%  
  summarise(count = n()) %>%  
  mutate(num_in_continents = sum(count),  
         prop = count/sum(count)) %>%  
  ungroup() %>%  
  ggplot() +  
  aes(x = continent, y = prop)

4 / 4

gapminder %>%  
  filter(year == 2002) %>%  
  mutate(higher_income = gdpPercap > 20000) %>%  
  group_by(continent, higher_income) %>%  
  summarise(count = n()) %>%  
  mutate(num_in_continents = sum(count),  
         prop = count/sum(count)) %>%  
  ungroup() %>%  
  ggplot() +  
  aes(x = continent, y = prop) +  
  geom_bar(stat = "identity",
           position = "fill",
           color = "lightgrey")

4 / 4

gapminder %>%  
  filter(year == 2002) %>%  
  mutate(higher_income = gdpPercap > 20000) %>%  
  group_by(continent, higher_income) %>%  
  summarise(count = n()) %>%  
  mutate(num_in_continents = sum(count),  
         prop = count/sum(count)) %>%  
  ungroup() %>%  
  ggplot() +  
  aes(x = continent, y = prop) +  
  geom_bar(stat = "identity",  
           position = "fill",  
           color = "lightgrey") +  
  facet_grid(~continent, scales = "free_x", space = "free_x")

4 / 4

gapminder %>%  
  filter(year == 2002) %>%  
  mutate(higher_income = gdpPercap > 20000) %>%  
  group_by(continent, higher_income) %>%  
  summarise(count = n()) %>%  
  mutate(num_in_continents = sum(count),  
         prop = count/sum(count)) %>%  
  ungroup() %>%  
  ggplot() +  
  aes(x = continent, y = prop) +  
  geom_bar(stat = "identity",  
           position = "fill",  
           color = "lightgrey") +  
  facet_grid(~continent, scales = "free_x", space = "free_x") +  
  aes(width = num_in_continents)

4 / 4

gapminder %>%  
  filter(year == 2002) %>%  
  mutate(higher_income = gdpPercap > 20000) %>%  
  group_by(continent, higher_income) %>%  
  summarise(count = n()) %>%  
  mutate(num_in_continents = sum(count),  
         prop = count/sum(count)) %>%  
  ungroup() %>%  
  ggplot() +  
  aes(x = continent, y = prop) +  
  geom_bar(stat = "identity",  
           position = "fill",  
           color = "lightgrey") +  
  facet_grid(~continent, scales = "free_x", space = "free_x") +  
  aes(width = num_in_continents) +  
  aes(fill = higher_income)

4 / 4

gapminder %>%  
  filter(year == 2002) %>%  
  mutate(higher_income = gdpPercap > 20000) %>%  
  group_by(continent, higher_income) %>%  
  summarise(count = n()) %>%  
  mutate(num_in_continents = sum(count),  
         prop = count/sum(count)) %>%  
  ungroup() %>%  
  ggplot() +  
  aes(x = continent, y = prop) +  
  geom_bar(stat = "identity",  
           position = "fill",  
           color = "lightgrey") +  
  facet_grid(~continent, scales = "free_x", space = "free_x") +  
  aes(width = num_in_continents) +  
  aes(fill = higher_income) +  
  theme(panel.spacing.x = unit(0, "npc"))

4 / 4

gapminder %>%  
  filter(year == 2002) %>%  
  mutate(higher_income = gdpPercap > 20000) %>%  
  group_by(continent, higher_income) %>%  
  summarise(count = n()) %>%  
  mutate(num_in_continents = sum(count),  
         prop = count/sum(count)) %>%  
  ungroup() %>%  
  ggplot() +  
  aes(x = continent, y = prop) +  
  geom_bar(stat = "identity",  
           position = "fill",  
           color = "lightgrey") +  
  facet_grid(~continent, scales = "free_x", space = "free_x") +  
  aes(width = num_in_continents) +  
  aes(fill = higher_income) +  
  theme(panel.spacing.x = unit(0, "npc")) +  
  theme(strip.text = element_blank())

↑, ←, 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

{ggplot2} and extensions geoms

Gina Reynolds

Discrete v. Discrete

Mosaic

Help