This code counts top-level charges in a New York DOC daily inmates file.

Count_Daily_Inmates.R

library(tidyverse)

#you'll need this file, available in my repo, at 
#https://github.com/CharlesFainLehman/Rikers-DIC/blob/main/dat/via_github/DOC_Inmates_InCustody_Daily_20231127.csv
#You can also use any other DIC file, though, updated daily at
#https://data.cityofnewyork.us/Public-Safety/Daily-Inmates-In-Custody/7479-ugqb
#or stored in my github repo at
#https://github.com/CharlesFainLehman/Rikers-DIC/

rikers_11_26_23 <- read.csv("Daily_Inmates_In_Custody_20231127.csv")

count(rikers_11_26_23)

rikers_11_26_23 %>%
  separate(TOP_CHARGE, into = c("Title", "Section"), sep = "\\.") %>%
  mutate(Attempt = grepl("110-", Title),
         Title = gsub("110-", "", Title)) %>%
  count(Title) %>%
  arrange(-n) -> top_charges

#The top charge codes are:
#125: Homicide
#160: Robbery
#120: Assault
#140: Burglary
#265: Guns

print(top_charges)

#This is the fraction of 3,300
slice_max(top_charges, order_by = n, n = 5) %>%
  summarise(n = sum(n)) %>%
  pull(n)/3300