“Black Lives Matter” was evoked by “incidents of police brutality and racially motivated violence against black people” (source: Wikipedia). The information I want to extract from the fatal encounters dataset is 1) how disproportionate police killings of black people are to the population share of them and 2) whether there exists any difference in the disproportionateness across states.
## Load pacakges
library(tidyverse)## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
## ✔ ggplot2 3.3.6 ✔ purrr 0.3.4
## ✔ tibble 3.1.8 ✔ dplyr 1.0.10
## ✔ tidyr 1.2.1 ✔ stringr 1.4.1
## ✔ readr 2.1.2 ✔ forcats 0.5.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()library(sf)## Linking to GEOS 3.9.1, GDAL 3.4.3, PROJ 7.2.1; sf_use_s2() is TRUElibrary(here)## here() starts at C:/Users/iskim/Dropbox (GaTech)/2022-2023/2022 Fall/CP 8883 Intro to Urban Analytics/UA_module5library(tmap)
library(tidycensus)
## print the session info
sessionInfo()## R version 4.2.1 (2022-06-23 ucrt)
## Platform: x86_64-w64-mingw32/x64 (64-bit)
## Running under: Windows 10 x64 (build 22621)
##
## Matrix products: default
##
## locale:
## [1] LC_COLLATE=English_United States.utf8
## [2] LC_CTYPE=English_United States.utf8
## [3] LC_MONETARY=English_United States.utf8
## [4] LC_NUMERIC=C
## [5] LC_TIME=English_United States.utf8
##
## attached base packages:
## [1] stats graphics grDevices utils datasets methods base
##
## other attached packages:
## [1] tidycensus_1.2.3 tmap_3.3-3 here_1.0.1 sf_1.0-8
## [5] forcats_0.5.2 stringr_1.4.1 dplyr_1.0.10 purrr_0.3.4
## [9] readr_2.1.2 tidyr_1.2.1 tibble_3.1.8 ggplot2_3.3.6
## [13] tidyverse_1.3.2
##
## loaded via a namespace (and not attached):
## [1] fs_1.5.2 lubridate_1.8.0 RColorBrewer_1.1-3
## [4] httr_1.4.4 rprojroot_2.0.3 tools_4.2.1
## [7] backports_1.4.1 bslib_0.4.0 rgdal_1.5-32
## [10] utf8_1.2.2 R6_2.5.1 KernSmooth_2.23-20
## [13] DBI_1.1.3 colorspace_2.0-3 raster_3.5-29
## [16] sp_1.5-0 withr_2.5.0 tidyselect_1.1.2
## [19] leaflet_2.1.1 compiler_4.2.1 leafem_0.2.0
## [22] cli_3.4.0 rvest_1.0.3 xml2_1.3.3
## [25] sass_0.4.2 scales_1.2.1 classInt_0.4-7
## [28] proxy_0.4-27 rappdirs_0.3.3 digest_0.6.29
## [31] foreign_0.8-82 rmarkdown_2.16 base64enc_0.1-3
## [34] dichromat_2.0-0.1 pkgconfig_2.0.3 htmltools_0.5.3
## [37] dbplyr_2.2.1 fastmap_1.1.0 htmlwidgets_1.5.4
## [40] rlang_1.0.5 readxl_1.4.1 rstudioapi_0.14
## [43] jquerylib_0.1.4 generics_0.1.3 jsonlite_1.8.0
## [46] crosstalk_1.2.0 googlesheets4_1.0.1 magrittr_2.0.3
## [49] Rcpp_1.0.9 munsell_0.5.0 fansi_1.0.3
## [52] abind_1.4-5 terra_1.6-17 lifecycle_1.0.2
## [55] stringi_1.7.8 leafsync_0.1.0 yaml_2.3.5
## [58] tmaptools_3.1-1 maptools_1.1-4 grid_4.2.1
## [61] parallel_4.2.1 crayon_1.5.1 lattice_0.20-45
## [64] haven_2.5.1 stars_0.5-6 hms_1.1.2
## [67] knitr_1.40 pillar_1.8.1 uuid_1.1-0
## [70] codetools_0.2-18 reprex_2.0.2 XML_3.99-0.10
## [73] glue_1.6.2 evaluate_0.16 modelr_0.1.9
## [76] png_0.1-7 vctrs_0.4.1 tzdb_0.3.0
## [79] cellranger_1.1.0 gtable_0.3.1 assertthat_0.2.1
## [82] cachem_1.0.6 xfun_0.32 lwgeom_0.2-8
## [85] broom_1.0.1 e1071_1.7-11 class_7.3-20
## [88] googledrive_2.0.0 viridisLite_0.4.1 gargle_1.2.1
## [91] tigris_1.6.1 units_0.8-0 ellipsis_0.3.2“Race” column contains the race of murdered indiviuals by police. Because the column has 11 categories including “Race unspecified”, I reduced the number of categories to four: Black, White, Other, and Unspecified. The table below shows the distribution of race (both count and percentage values) after the reclassification process; 22.26% are black and 33.81% are white. Since more than a quarter of individuals in the dataset (27.88%) do not have race information attached to them, it would be better to compare the ratio of black and white in the dataset and the ratio in population rather than to compare the share of black people in the dataset and the share in population. The map following the table shows the sptial distribution of police killings of civilians with dots colored with race.
## Load data
df <- read_rds(here("data", "fe_data_sf_XYswap.rds"))
## Recode "Race" variable
df <- df %>%
mutate(Race_reclassified = case_when(
str_detect(Race, "African|Black") ~ "Black",
str_detect(Race, "White") ~ "White",
str_detect(Race, "Race unspecified") ~ "Unspecified",
TRUE ~ "Other"
)
)
## Check the distribution of the recoded variable (Race_reclassified)
df %>%
st_drop_geometry() %>%
count(Race_reclassified) %>%
mutate(percentage = round(n/nrow(df)*100, 2)) %>%
rename(count = n)## Race_reclassified count percentage
## 1 Black 7012 22.26
## 2 Other 5054 16.05
## 3 Unspecified 8780 27.88
## 4 White 10650 33.81## Create dummy variables indicating the race
df <- df %>%
mutate(black = case_when(Race_reclassified == "Black" ~ 1, TRUE ~ 0),
white = case_when(Race_reclassified == "White" ~ 1, TRUE ~ 0))## Map the recoded variable (Race_reclassified)
tmap_mode('view') %>% suppressMessages()
tm_shape(df) + tm_dots(col = "Race_reclassified")