Fatal Encounters

Load libraries

library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.2     ✔ readr     2.1.4
## ✔ forcats   1.0.0     ✔ stringr   1.5.0
## ✔ ggplot2   3.4.2     ✔ tibble    3.2.1
## ✔ lubridate 1.9.2     ✔ tidyr     1.3.0
## ✔ purrr     1.0.1     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(sf)

## Linking to GEOS 3.10.2, GDAL 3.4.1, PROJ 8.2.1; sf_use_s2() is TRUE

library(tmap)

## The legacy packages maptools, rgdal, and rgeos, underpinning the sp package,
## which was just loaded, will retire in October 2023.
## Please refer to R-spatial evolution reports for details, especially
## https://r-spatial.org/r/2023/05/15/evolution4.html.
## It may be desirable to make the sf package available;
## package maintainers should consider adding sf to Suggests:.
## The sp package is now running under evolution status 2
##      (status 2 uses the sf package in place of rgdal)

library(leaflet)
library(here)

## here() starts at /home/rstudio/Mod 2/Major 1

library(tidycensus)
library(sf)
library(dplyr)
library(lubridate)
library(skimr)
library(maps)

## 
## Attaching package: 'maps'
## 
## The following object is masked from 'package:purrr':
## 
##     map

library(ggplot2)

read in fatal encounters file

fe <- read.csv("~/Mod 2/Major 1/FATAL ENCOUNTERS DOT ORG SPREADSHEET.csv")

skim

skim(fe)

## Warning: There was 1 warning in `dplyr::summarize()`.
## ℹ In argument: `dplyr::across(tidyselect::any_of(variable_names),
##   mangled_skimmers$funs)`.
## ℹ In group 0: .
## Caused by warning:
## ! There were 141 warnings in `dplyr::summarize()`.
## The first warning was:
## ℹ In argument: `dplyr::across(tidyselect::any_of(variable_names),
##   mangled_skimmers$funs)`.
## Caused by warning in `grepl()`:
## ! unable to translate 'Juan de Le<97>n Guti<8e>rrez' to a wide string
## ℹ Run `dplyr::last_dplyr_warnings()` to see the 140 remaining warnings.

Data summary

Name	fe
Number of rows	31498
Number of columns	36
_______________________
Column type frequency:
character	28
logical	1
numeric	7
________________________
Group variables	None

Variable type: character

skim_variable	n_missing	complete_rate	min	max	empty	n_unique	whitespace
Name	0	1.00	4	82	0	29859	0
Age	0	1.00	0	5	1221	160	0
Gender	0	1.00	0	11	144	4	0
Race	0	1.00	0	57	1	12	0
Race.with.imputations	862	0.97	0	23	6	10	0
Imputation.probability	881	0.97	0	19	3	6614	0
URL.of.image..PLS.NO.HOTLINKS.	0	1.00	0	373	16773	14668	0
Date.of.injury.resulting.in.death..month.day.year.	0	1.00	10	10	0	7736	0
Location.of.injury..address.	0	1.00	0	74	556	28893	0
Location.of.death..city.	0	1.00	0	30	36	6340	0
State	0	1.00	0	2	1	52	0
Location.of.death..county.	0	1.00	0	33	15	1536	0
Full.Address	0	1.00	0	103	1	29709	0
Latitude	0	1.00	0	17	1	29515	0
Agency.or.agencies.involved	0	1.00	0	266	78	6829	0
Highest.level.of.force	0	1.00	0	33	4	19	0
Name.Temporary	0	1.00	0	58	25969	5284	0
Armed.Unarmed	0	1.00	0	19	14419	10	0
Alleged.weapon	0	1.00	0	35	14421	269	0
Aggressive.physical.movement	0	1.00	0	42	14418	32	0
Fleeing.Not.fleeing	0	1.00	0	42	14419	26	0
Description.Temp	0	1.00	0	2239	27431	3870	0
URL.Temp	0	1.00	0	723	28281	3066	0
Brief.description	0	1.00	0	2239	2	29883	0
Dispositions.Exclusions.INTERNAL.USE..NOT.FOR.ANALYSIS	0	1.00	0	89	3	156	0
Intended.use.of.force..Developing.	0	1.00	0	22	3	9	0
Supporting.document.link	0	1.00	0	438	2	29269	0
Foreknowledge.of.mental.illness..INTERNAL.USE..NOT.FOR.ANALYSIS	0	1.00	0	19	62	5	0

Variable type: logical

skim_variable	n_missing	complete_rate	mean	count
X	31498	0	NaN	:

Variable type: numeric

skim_variable	n_missing	complete_rate	mean	sd	p0	p25	p50	p75	p100	hist
Unique.ID	1	1.00	15749.00	9092.55	1.00	7875	15749.00	23623.00	31497.00	▇▇▇▇▇
Location.of.death..zip.code.	182	0.99	58352.53	27966.03	1013.00	33147	60649.00	85033.00	99921.00	▃▇▃▆▇
Longitude	1	1.00	-95.40	16.30	-165.59	-111	-90.56	-82.57	-67.27	▁▁▅▇▇
UID.Temporary	25969	0.18	15464.08	6559.72	9759.00	11156	12549.00	19240.00	30340.00	▇▁▁▁▂
X.1	31497	0.00	10895.00	NA	10895.00	10895	10895.00	10895.00	10895.00	▁▁▇▁▁
Unique.ID.formula	31496	0.00	29497.00	2828.43	27497.00	28497	29497.00	30497.00	31497.00	▇▁▁▁▇
Unique.identifier..redundant.	1	1.00	15749.00	9092.55	1.00	7875	15749.00	23623.00	31497.00	▇▇▇▇▇

Remove na values for lat/long

fe <- fe %>%
  filter(!is.na(Latitude) & !is.na(Longitude)) 

group and count by state

fe_state <- fe %>%
  group_by(State) %>%
  summarize(
    Count = n()
  )

map by state

us_states <- st_read("tl_2012_us_state.shp")

## Reading layer `tl_2012_us_state' from data source 
##   `/home/rstudio/Mod 2/Major 1/tl_2012_us_state.shp' using driver `ESRI Shapefile'
## Simple feature collection with 56 features and 17 fields
## Geometry type: MULTIPOLYGON
## Dimension:     XY
## Bounding box:  xmin: -19951910 ymin: -1643352 xmax: 20021890 ymax: 11554790
## Projected CRS: Popular Visualisation CRS / Mercator

fe_state$STUSPS <- fe_state$State

fe_map <- us_states %>% 
  left_join(fe_state)

## Joining with `by = join_by(STUSPS)`

tmap_mode("view");

## tmap mode set to interactive viewing

tm_shape(fe_map) + 
  tm_polygons(col = "Count", style = "jenks")

Extract years and make new column

fe$Date.of.injury.resulting.in.death..month.day.year. <- tryCatch(
  mdy(fe$Date.of.injury.resulting.in.death..month.day.year.),
  error = function(e) NA
)

fe$year <- year(fe$Date.of.injury.resulting.in.death..month.day.year.)

make case count per year

fe_year <- fe %>%
  group_by(year) %>%
  summarize(
    Count = n()
  )

graph of cases over time

ggplot(data = fe_year) +
  geom_point(mapping = aes(x = year, y = Count))

Make case count by race

fe_race <- fe %>%
  group_by(Race) %>%
  summarize(
    Count = n()
  )
ggplot(data=fe_race, aes(x=Race, y=Count)) +
  geom_bar(stat="identity")