R Notebook

library(tidyverse)
library(tidycensus)
library(sf)
library(scales)
library(viridisLite)
library(RColorBrewer)
library(readxl)
library(readr)

crash <- raw_crash|>
  select("CRASH DATE","BOROUGH", "ZIP CODE", "LOCATION", "NUMBER OF PERSONS INJURED", 
         "NUMBER OF PERSONS KILLED","NUMBER OF PEDESTRIANS INJURED", 
         "NUMBER OF PEDESTRIANS KILLED","NUMBER OF CYCLIST INJURED", 
         "NUMBER OF CYCLIST KILLED", "NUMBER OF MOTORIST INJURED", 
         "NUMBER OF MOTORIST KILLED")|>
  group_by(BOROUGH)|>
  filter(BOROUGH != "NA")|>
  summarise(collisions = n(),
            deaths = sum(`NUMBER OF PERSONS KILLED`, na.rm=T))|>
  mutate(fatality_rate = (deaths/collisions))

## import borough shapefiles from NYC Open Data
boros <- st_read("~/Desktop/Stuff & Things/School/Grad School/DUE Methods 1/part2/data/raw/geo/Borough Boundaries.geojson")
## import Neighborhood Tabulation Areas for NYC
nabes <- st_read("~/Desktop/Stuff & Things/School/Grad School/DUE Methods 1/part2/data/raw/geo/nynta2020.shp")

#playing with the data
ggplot(data=crash, aes(x=BOROUGH, y=collisions, fill=-fatality_rate)) +
  geom_col() +
  theme(axis.text.x=element_text(angle=90,hjust=1,vjust=0.5)) + 
  labs(x = "Borough", y = "Collisions", fill ="Fatality Rate (Deaths per Collision)", caption = "Source: NYC OpenData") 

This graph shows that the highest rate of collisions are in Brooklyn. Manhattan has a large number of collisions, but the lowest fatality rate, which may be due to the high density of cars but low speed limit. The lowest number of collisions is in Staten Island, but it has the highest faltality rate.