Recreating FiveThirtyEight Voter Registrations Graph

Let’s practice our visualization skills with ggplot2 and recreate the graph from the “Voter Registrations Are Way, Way Down During The Pandemic” article.

First, Let’s get and prepare the data

# Import data 
vreg<-read.csv("https://raw.githubusercontent.com/fivethirtyeight/data/master/voter-registration/new-voter-registrations.csv",
header=TRUE)

# Level the Month variable so that its in the right order (ie not alphabetical)
vreg$Month<-factor(vreg$Month,
levels=c("Jan", "Feb", "Mar", "Apr", "May"))

### USE spread() FROM tidyr
vreg<-vreg%>%
spread(Year, New.registered.voters)

### RENAME THE COLUMNS
colnames(vreg)<-c("Jurisdiction", "Month", "Y2016", "Y2020")

### mutate() FROM dplyr()
vreg<-vreg%>%
mutate(change= Y2020-Y2016)%>%
  mutate(Color = ifelse(change > 0,"#48E5E8", "#F56C6A"))

a<- function(change){number_format(accuracy = 1,
                                  scale = 1/1000,
                                  suffix = "K")(change)}

## 'data.frame':    53 obs. of  6 variables:
##  $ Jurisdiction: chr  "Arizona" "Arizona" "Arizona" "Arizona" ...
##  $ Month       : Factor w/ 5 levels "Jan","Feb","Mar",..: 1 2 3 4 1 2 3 4 1 2 ...
##  $ Y2016       : int  25852 51155 48614 30668 87574 103377 174278 185478 17024 20707 ...
##  $ Y2020       : int  33229 50853 31872 10249 151595 238281 176810 38970 20260 33374 ...
##  $ change      : int  7377 -302 -16742 -20419 64021 134904 2532 -146508 3236 12667 ...
##  $ Color       : chr  "#48E5E8" "#F56C6A" "#F56C6A" "#F56C6A" ...

Now the graph

ggplot(vreg, aes(x= Month, y= change, fill = Color))+
geom_col()+ 
geom_hline( yintercept = 0, color= "black")+

geom_rect(data = data.frame(Jurisdiction = "Arizona"), 
              aes(xmin = 4.5, xmax= 5.5, ymin= -Inf, ymax = Inf), 
              color = "lightgrey", 
              fill = "white", 
              alpha = 0, 
              linetype = "dotted", 
              inherit.aes = FALSE)+
  geom_rect(data = data.frame(Jurisdiction = "California"), 
            aes(xmin = 4.5, xmax= 5.5, ymin= -Inf, ymax = Inf), 
            color = "lightgrey", 
            fill = "white", 
            alpha = 0, 
            linetype = "dotted", 
            inherit.aes = FALSE)+
   geom_rect(data = data.frame(Jurisdiction = "Colorado"), 
             aes(xmin = 4.5, xmax= 5.5, ymin= -Inf, ymax = Inf), 
             color = "lightgrey", 
             fill = "white", 
             alpha = 0, 
             linetype = "dotted", 
             inherit.aes = FALSE)+
  geom_rect(data = data.frame(Jurisdiction = "Delaware"), 
            aes(xmin = 4.5, xmax= 5.5, ymin= -Inf, ymax = Inf), 
            color = "lightgrey", fill = "white", 
            alpha = 0, 
            linetype = "dotted", 
            inherit.aes = FALSE)+
  geom_rect(data = data.frame(Jurisdiction = "Florida"), 
            aes(xmin = 4.5, xmax= 5.5, ymin= -Inf, ymax = Inf), 
            color = "lightgrey", 
            fill = "white", 
            alpha = 0, 
            linetype = "dotted", inherit.aes = FALSE)+
  geom_rect(data = data.frame(Jurisdiction = "Georgia"), 
            aes(xmin = 4.5, xmax= 5.5, ymin= -Inf, ymax = Inf), 
            color = "lightgrey", 
            fill = "white", 
            alpha = 0, 
            linetype = "dotted", 
            inherit.aes = FALSE)+
  geom_rect(data = data.frame(Jurisdiction = "Illinois"), 
            aes(xmin = 4.5, xmax= 5.5, ymin= -Inf, ymax = Inf), 
            color = "lightgrey", 
            fill = "white", 
            alpha = 0, 
            linetype = "dotted", 
            inherit.aes = FALSE)+
  
  facet_wrap(~Jurisdiction, scales = "free_y")+

  scale_fill_identity(guide= FALSE)+
  scale_x_discrete(limits=c("Jan", "Feb", "Mar", "Apr", "May"), 
                   breaks=c("Jan","May"))+
  scale_y_continuous(labels = label_number_si(a =! 0), n.breaks = 4)+

  labs(
        x="",
        y="",
      title = "Voter registration dropped dramatically during the pandemic",
      subtitle = "Difference in the number of newly registered voters for each month in 2020 compared to the same month in 2016",
      caption = "Some states treat voters who move between counties within a state as new registrants because they're unregistered from their old county and nearly registered in the new ones.          ",
      
      tag= "FiveThirtyEight") +

    theme_classic()+
    theme(
          axis.line.y=element_blank(),
          axis.line.x = element_blank(),
          axis.ticks = element_blank(),
          axis.text.y = element_text(size = 6.5, color = "gray"), 
          axis.text.x = element_text(size= 6.5, color = "gray"),
          
          
          plot.title = element_text(size =9, face = "bold", hjust = 0.55),
          plot.title.position = "plot",
          plot.subtitle= element_text(size = 8, hjust = 0.55),
          
          plot.caption = element_text(hjust = 0, size = 6, color = "grey50",
                                      margin = margin(r=5)),
          plot.background = element_rect(fill= "white"),
          plot.tag.position = "bottom",
          plot.tag = element_text(size= 5, color = "gray", hjust =0.1, 
                                  margin=margin(t=1, 
                                                r=5, 
                                                b=1, 
                                                l=20, 
                                                unit="pt")),
          panel.grid.minor.y = element_blank(),
          panel.grid.major.y = element_line(size= 0.1, color= "lightgrey",
                                            linetype= "solid"),
          panel.background = element_rect(fill = "white"),
          panel.border = element_blank(),
          panel.spacing = unit(1, "lines"),
          
          strip.background= element_rect(fill= "white", linetype = "blank"),
          strip.text = element_text(color= "black", face= "bold"),
          strip.text.x = element_text(face = "bold", size= 7),

          
          legend.title = element_blank(),
          legend.position = "none"
    
)

Here is the result