Spotting (Holiday) Seasonality

Context

Connecticut has published a daily census of every inmate held in jail while awaiting trial.¹

Get data

I download the data on 1-8-19 and save it as CT-jail_1-8-19.csv. It has 2.88 million rows.

Call the csv and clean up.

library(data.table); library(janitor)
CT<-fread('CT-jail_1-8-19.csv')
CT<-clean_names(CT)
CT$download_date<-as.Date(CT$download_date, '%m/%d/%Y')
CT$latest_admission_date<-as.Date(CT$latest_admission_date, '%m/%d/%Y')
CT$identifier<-as.character(CT$identifier)
#fix race names
CT$race[CT$race == 'AMER IND'] <- 'Native American'
CT$race[CT$race == 'ASIAN'] <- 'Asian'
CT$race[CT$race == 'BLACK'] <- 'Black'
CT$race[CT$race == 'WHITE'] <- 'White'
CT$race[CT$race == 'HISPANIC'] <- 'Hispanic'

Make graphs

Before making graphs, I call my custom theme, as per usual.

#Load more libraries
library(ggplot2);library(ggrepel); library(extrafont); library(ggthemes);library(reshape);library(grid);
library(scales);library(RColorBrewer);library(gridExtra)
#Define theme for my visuals
my_theme <- function() {
  # Define colors for the chart
  palette <- brewer.pal("Greys", n=9)
  color.background = palette[2]
  color.grid.major = palette[4]
  color.panel = palette[3]
  color.axis.text = palette[9]
  color.axis.title = palette[9]
  color.title = palette[9]
  # Create basic construction of chart
  theme_bw(base_size=9, base_family="Palatino") + 
  # Set the entire chart region to a light gray color
  theme(panel.background=element_rect(fill=color.panel, color=color.background)) +
  theme(plot.background=element_rect(fill=color.background, color=color.background)) +
  theme(panel.border=element_rect(color=color.background)) +
  # Format grid
  theme(panel.grid.major=element_line(color=color.grid.major,size=.25)) +
  theme(panel.grid.minor=element_blank()) +
  theme(axis.ticks=element_blank()) +
  # Format legend
  theme(legend.position="right") +
  theme(legend.background = element_rect(fill=color.background)) +
  theme(legend.text = element_text(size=7,color=color.axis.title)) + 
  theme(legend.title = element_text(size=0,face="bold", color=color.axis.title)) + 
  
  #Format facet labels
  theme(strip.text.x = element_text(size = 8, face="bold"))+
  # Format title and axes labels these and tick marks
  theme(plot.title=element_text(color=color.title, size=18, face="bold", hjust=0)) +
  theme(axis.text.x=element_text(size=8,color=color.axis.text)) +
  theme(axis.text.y=element_text(size=8,color=color.axis.text)) +
  theme(axis.title.x=element_text(size=10,color=color.axis.title, vjust=-1)) +
  theme(axis.title.y=element_text(size=10,color=color.axis.title, vjust=1.8)) +
  #Format title and facet_wrap title
  theme(strip.text = element_text(size=8), plot.title = element_text(size = 14, face = "bold", colour = "black", vjust = 1, hjust=0.5))+
    
  # Plot margins
  theme(plot.margin = unit(c(.2, .2, .2, .2), "cm"))
}

Visual 1

Show line chart of inmates over time.

library(dplyr)
CTdays<- CT %>% 
  group_by(download_date) %>% 
  summarise(n = n())
ggplot(data=CTdays, aes(x=download_date, y=n)) + 
  geom_line()+
  scale_y_continuous(limits=c(0,7000))+
  my_theme()+ theme(plot.title = element_text(hjust = 0))+
  labs(x="", y="Number of Pretrial Inmates")+
  ggtitle("Gender/Race of Connecticut Pretrial Inmates (7/1/16-1/8/19)", subtitle = "Data Available via Connecticut Open Data | Visualization via Alex Albright (thelittledataset.com)")

2017-8-24 is a crazy outlier, remove it.

CTdays<- subset(CTdays, n<6000)

Visual 2

Graph by day now with 2017-8-24 removed (as I assume it must be an error).

ggplot(data=CTdays, aes(x=download_date, y=n)) + 
  geom_line()+
  my_theme()+ theme(plot.title = element_text(hjust = 0))+
  labs(x="Date", y="Number of Pretrial Inmates", caption="\nData plotted by day. Red lines mark the beginning/end of years.")+
  geom_vline(xintercept = as.numeric(as.Date(
    c("2017-01-01","2018-01-01", "2019-01-01")
    )), linetype=4, color="red")+
  scale_x_date(date_breaks = "1 month", date_labels = "%m-%y")+
  scale_y_continuous(limits=c(0,3700))+
  theme(axis.text.x = element_text(angle = 90, hjust = 1))+
  ggtitle("Connecticut Pretrial Inmate Population 7/1/16-1/8/19", subtitle = "Data Available via Connecticut Open Data | Visualization via Alex Albright (thelittledataset.com)")
  
ggsave("time-pop0.png", width=7, height=4.5, dpi=900)

Visual 3

Zoom in to see variation.

ggplot(data=CTdays, aes(x=download_date, y=n)) + 
  geom_line()+
  my_theme()+ theme(plot.title = element_text(hjust = 0))+
  labs(x="Date", y="Number of Pretrial Inmates", caption="\nData plotted by day. Red lines mark the beginning/end of years.")+
  geom_vline(xintercept = as.numeric(as.Date(
    c("2017-01-01","2018-01-01", "2019-01-01")
    )), linetype=4, color="red")+
  scale_x_date(date_breaks = "1 month", date_labels = "%m-%y")+
  theme(axis.text.x = element_text(angle = 90, hjust = 1))+
  ggtitle("Connecticut Pretrial Inmate Population 7/1/16-1/8/19", subtitle = "Data Available via Connecticut Open Data | Visualization via Alex Albright (thelittledataset.com)")
  
ggsave("time-pop.png", width=7, height=4.5, dpi=900)

Visual 4

Color december portions.

CTdays$month<-month(CTdays$download_date)
CTdays$dec<-0
CTdays$dec[CTdays$month==12]<-1
CTdays$dec<-as.numeric(CTdays$dec)
ggplot(data=CTdays, aes(x=download_date, y=n, color=dec)) + 
  geom_line()+ #scale_color_manual(values = c("black", "red"))+
  my_theme()+ theme(plot.title = element_text(hjust = 0))+
  labs(x="Date", y="Number of Pretrial Inmates", caption="\nData plotted by day. Light blue denotes days during December.")+
  scale_x_date(date_breaks = "1 month", date_labels = "%m-%y")+
  theme(axis.text.x = element_text(angle = 90, hjust = 1), legend.position="none")+
  ggtitle("Connecticut Pretrial Inmate Population 7/1/16-1/8/19", subtitle = "Data Available via Connecticut Open Data | Visualization via Alex Albright (thelittledataset.com)")
  
ggsave("time-pop-dec.png", width=7, height=4.5, dpi=900)

Visual 5

Zoom in on December for the three years… Subset down to december days and facet by year.

CTdaysdec<-subset(CTdays, CTdays$dec==1)
CTdaysdec$day<-as.numeric(format(CTdaysdec$download_date, "%d"))
CTdaysdec$year<-year(CTdaysdec$download_date)
ggplot(data=CTdaysdec, aes(x=day, y=n)) + 
  geom_line()+
  geom_point(data=subset(CTdaysdec, day==24), color="#009E73")+
  geom_point(data=subset(CTdaysdec, day==25), color="#D55E00")+
  my_theme()+ theme(plot.title = element_text(hjust = 0))+
  labs(x="Date in December", y="Number of Pretrial Inmates", caption="\nData plotted by day for December 2016, 2017, and 2018.\nGreen dots mark Xmas eve and red dots mark Xmas.")+
  scale_x_continuous(breaks=seq(1,31,3), labels=seq(1,31,3))+
  facet_wrap(~year)+
  ggtitle("Spotting Seasonality", subtitle = "Data Available via Connecticut Open Data | Visualization via Alex Albright (thelittledataset.com)")
  
ggsave("time-pop-xmas.png", width=7, height=4.5, dpi=900)

I add red/green ornaments on Christmas eve and Christmas. There are drops around holidays (xmas).

• There is a Dallas article that mentions Commissioner Mike Cantrell who says, “We go down every Christmas … People are getting their loved ones out of jail, or people are not wanting to get in jail, so they stay out.”“
• The BJS mentions this too but doesn’t attribute it to the holidays: “Comparisons of year-end data with previous midyear data need to consider seasonal variations, as jails typically hold fewer inmates at year-end than at midyear.”

---

1. H/t to Data is Plural for blasting this out way back when.↩