Guerry’s data on crime and literacy

This example shows the development of plots of Andre-Michel Guerry’s (1833) data on crime and literacy in France ## Load packages

library(ggplot2)
library(ggrepel)

Load the data

data(Guerry, package="Guerry")
head(Guerry[, 1:9])

##   dept Region   Department Crime_pers Crime_prop Literacy Donations Infants
## 1    1      E          Ain      28870      15890       37      5098   33120
## 2    2      N        Aisne      26226       5521       51      8901   14572
## 3    3      C       Allier      26747       7925       13     10973   17044
## 4    4      E Basses-Alpes      12935       7289       46      2733   23018
## 5    5      E Hautes-Alpes      17488       8174       69      6962   23076
## 6    7      S      Ardeche       9474      10263       27      3188   42117
##   Suicides
## 1    35039
## 2    12831
## 3   114121
## 4    14238
## 5    16171
## 6    52547

Start with basic scatterplot

ggplot(aes(x=Literacy, y=Crime_pers/1000), data=Guerry) +
  geom_point(size=2) 

# ggsave("guerry-crime1.png", width=5, height=5)

Add data ellipses

Data ellipses give a visual assessment of the correlation between variables

ggplot(aes(x=Literacy, y=Crime_pers/1000), data=Guerry) +
  geom_point(size=2) +
  stat_ellipse(level=0.68, color="blue", size=1.2) +  
  stat_ellipse(level=0.95, color="gray", size=1, linetype=2) 

# ggsave("guerry-crime2.png", width=5, height=5)

Add smooths

ggplot(aes(x=Literacy, y=Crime_pers/1000), data=Guerry) +
  geom_point(size=2) +
  stat_ellipse(level=0.68, color="blue", size=1.2) +  
  stat_ellipse(level=0.95, color="gray", size=1, linetype=2) + 
  geom_smooth(method="lm", formula=y~x, fill="lightblue") +
  geom_smooth(method="loess", formula=y~x, color="red", se=FALSE) 

# ggsave("guerry-crime3.png", width=5, height=5)

Do some styling

gplot <- last_plot()
gplot + theme_bw(base_size = 18) 

Put the steps together

ggplot(aes(x=Literacy, y=Crime_pers/1000), data=Guerry) +
  geom_point(size=2) +
  stat_ellipse(level=0.68, color="blue", size=1.2) +  
  stat_ellipse(level=0.95, color="gray", size=1, linetype=2) + 
  geom_smooth(method="lm", formula=y~x, fill="lightblue") +
  geom_smooth(method="loess", formula=y~x, color="red", se=FALSE) +
  theme_bw() + theme(text = element_text(size=18))

# ggsave("guerry-crime4.png", width=5, height=5)

Use Mahalanobis Dsq to label unusual points

gdf <- Guerry[, c("Literacy", "Crime_pers", "Department")]
gdf$dsq <- heplots::Mahalanobis(gdf[, 1:2])

ggplot(aes(x=Literacy, y=Crime_pers/1000), data=Guerry) +
  geom_point(size=2) +
  stat_ellipse(level=0.68, color="blue", size=1.2) +  
  stat_ellipse(level=0.95, color="gray", size=1, linetype=2) + 
  geom_smooth(method="lm", formula=y~x, fill="lightblue") +
  geom_smooth(method="loess", formula=y~x, color="red", se=FALSE) +
    geom_label_repel(aes(label=Department), data = gdf[gdf$dsq > 4.6,]) +
  theme_bw() + theme(text = element_text(size=18))

# ggsave("guerry-crime5.png", width=5, height=5)

gplot + 
     theme_bw() + 
     theme(text = element_text(size=18)) +        
       geom_label_repel(aes(label=Department), data = gdf[gdf$dsq > 4.6,])

Do the same for property crime

gdf <- Guerry[, c("Literacy", "Crime_prop", "Department")]
gdf$dsq <- heplots::Mahalanobis(gdf[, 1:2])

ggplot(aes(x=Literacy, y=Crime_prop/1000), data=Guerry) +
  geom_point(size=2) +
  stat_ellipse(level=0.68, color="blue", size=1.2) +  
  stat_ellipse(level=0.95, color="gray", size=1, linetype=2) + 
  geom_smooth(method="lm", formula=y~x, fill="lightblue") +
  geom_smooth(method="loess", formula=y~x, color="red", se=FALSE) +
    geom_label_repel(aes(label=Department), data = gdf[gdf$dsq > 4.6,]) +
  theme_bw() + theme(text = element_text(size=18))

# ggsave("guerry-crime-prop.png", width=5, height=5)