library(tidyverse)
## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --
## v ggplot2 3.3.5 v purrr 0.3.4
## v tibble 3.1.4 v dplyr 1.0.7
## v tidyr 1.1.3 v stringr 1.4.0
## v readr 2.0.1 v forcats 0.5.1
## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
library(tinytex)
setwd("~/Data110")
hatecrimes <- read_csv("hateCrimes2010.csv")
## Rows: 423 Columns: 44
## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (2): County, Crime Type
## dbl (42): Year, Anti-Male, Anti-Female, Anti-Transgender, Anti-Gender Identi...
##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.
Clean up the data:
Make all headers lowercase and remove spaces
names(hatecrimes) <- tolower(names(hatecrimes))
names(hatecrimes) <- gsub(" ","",names(hatecrimes))
str(hatecrimes)
## spec_tbl_df [423 x 44] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
## $ county : chr [1:423] "Albany" "Albany" "Allegany" "Bronx" ...
## $ year : num [1:423] 2016 2016 2016 2016 2016 ...
## $ crimetype : chr [1:423] "Crimes Against Persons" "Property Crimes" "Property Crimes" "Crimes Against Persons" ...
## $ anti-male : num [1:423] 0 0 0 0 0 0 0 0 0 0 ...
## $ anti-female : num [1:423] 0 0 0 0 0 0 0 0 0 0 ...
## $ anti-transgender : num [1:423] 0 0 0 4 0 0 0 0 0 0 ...
## $ anti-genderidentityexpression : num [1:423] 0 0 0 0 0 0 0 0 0 0 ...
## $ anti-age* : num [1:423] 0 0 0 0 0 0 0 0 0 0 ...
## $ anti-white : num [1:423] 0 0 0 1 1 0 0 0 0 0 ...
## $ anti-black : num [1:423] 1 2 1 0 0 1 0 1 0 2 ...
## $ anti-americanindian/alaskannative : num [1:423] 0 0 0 0 0 0 0 0 0 0 ...
## $ anti-asian : num [1:423] 0 0 0 0 0 1 0 0 0 0 ...
## $ anti-nativehawaiian/pacificislander : num [1:423] 0 0 0 0 0 0 0 0 0 0 ...
## $ anti-multi-racialgroups : num [1:423] 0 0 0 0 0 0 0 0 0 0 ...
## $ anti-otherrace : num [1:423] 0 0 0 0 0 0 0 0 0 0 ...
## $ anti-jewish : num [1:423] 0 0 0 0 1 0 1 0 0 0 ...
## $ anti-catholic : num [1:423] 0 0 0 0 0 0 0 0 0 0 ...
## $ anti-protestant : num [1:423] 0 0 0 0 0 0 0 0 0 0 ...
## $ anti-islamic(muslim) : num [1:423] 1 0 0 6 0 0 0 0 1 0 ...
## $ anti-multi-religiousgroups : num [1:423] 0 1 0 0 0 0 0 0 0 0 ...
## $ anti-atheism/agnosticism : num [1:423] 0 0 0 0 0 0 0 0 0 0 ...
## $ anti-religiouspracticegenerally : num [1:423] 0 0 0 0 0 0 0 0 0 0 ...
## $ anti-otherreligion : num [1:423] 0 0 0 0 0 0 0 0 0 0 ...
## $ anti-buddhist : num [1:423] 0 0 0 0 0 0 0 0 0 0 ...
## $ anti-easternorthodox(greek,russian,etc.): num [1:423] 0 0 0 0 0 0 0 0 0 0 ...
## $ anti-hindu : num [1:423] 0 0 0 0 0 0 0 0 0 0 ...
## $ anti-jehovahswitness : num [1:423] 0 0 0 0 0 0 0 0 0 0 ...
## $ anti-mormon : num [1:423] 0 0 0 0 0 0 0 0 0 0 ...
## $ anti-otherchristian : num [1:423] 0 0 0 0 0 0 0 0 0 0 ...
## $ anti-sikh : num [1:423] 0 0 0 0 0 0 0 0 0 0 ...
## $ anti-hispanic : num [1:423] 0 0 0 0 0 0 0 0 0 0 ...
## $ anti-arab : num [1:423] 0 0 0 0 0 0 0 0 0 0 ...
## $ anti-otherethnicity/nationalorigin : num [1:423] 0 0 0 0 0 0 0 0 0 0 ...
## $ anti-non-hispanic* : num [1:423] 0 0 0 0 0 0 0 0 0 0 ...
## $ anti-gaymale : num [1:423] 1 0 0 8 0 1 0 0 0 0 ...
## $ anti-gayfemale : num [1:423] 0 0 0 1 0 0 0 0 0 0 ...
## $ anti-gay(maleandfemale) : num [1:423] 0 0 0 0 0 0 0 0 0 0 ...
## $ anti-heterosexual : num [1:423] 0 0 0 0 0 0 0 0 0 0 ...
## $ anti-bisexual : num [1:423] 0 0 0 0 0 0 0 0 0 0 ...
## $ anti-physicaldisability : num [1:423] 0 0 0 0 0 0 0 0 0 0 ...
## $ anti-mentaldisability : num [1:423] 0 0 0 0 0 0 0 0 0 0 ...
## $ totalincidents : num [1:423] 3 3 1 20 2 3 1 1 1 2 ...
## $ totalvictims : num [1:423] 4 3 1 20 2 3 1 1 1 2 ...
## $ totaloffenders : num [1:423] 3 3 1 25 2 3 1 1 1 2 ...
## - attr(*, "spec")=
## .. cols(
## .. County = col_character(),
## .. Year = col_double(),
## .. `Crime Type` = col_character(),
## .. `Anti-Male` = col_double(),
## .. `Anti-Female` = col_double(),
## .. `Anti-Transgender` = col_double(),
## .. `Anti-Gender Identity Expression` = col_double(),
## .. `Anti-Age*` = col_double(),
## .. `Anti-White` = col_double(),
## .. `Anti-Black` = col_double(),
## .. `Anti-American Indian/Alaskan Native` = col_double(),
## .. `Anti-Asian` = col_double(),
## .. `Anti-Native Hawaiian/Pacific Islander` = col_double(),
## .. `Anti-Multi-Racial Groups` = col_double(),
## .. `Anti-Other Race` = col_double(),
## .. `Anti-Jewish` = col_double(),
## .. `Anti-Catholic` = col_double(),
## .. `Anti-Protestant` = col_double(),
## .. `Anti-Islamic (Muslim)` = col_double(),
## .. `Anti-Multi-Religious Groups` = col_double(),
## .. `Anti-Atheism/Agnosticism` = col_double(),
## .. `Anti-Religious Practice Generally` = col_double(),
## .. `Anti-Other Religion` = col_double(),
## .. `Anti-Buddhist` = col_double(),
## .. `Anti-Eastern Orthodox (Greek, Russian, etc.)` = col_double(),
## .. `Anti-Hindu` = col_double(),
## .. `Anti-Jehovahs Witness` = col_double(),
## .. `Anti-Mormon` = col_double(),
## .. `Anti-Other Christian` = col_double(),
## .. `Anti-Sikh` = col_double(),
## .. `Anti-Hispanic` = col_double(),
## .. `Anti-Arab` = col_double(),
## .. `Anti-Other Ethnicity/National Origin` = col_double(),
## .. `Anti-Non-Hispanic*` = col_double(),
## .. `Anti-Gay Male` = col_double(),
## .. `Anti-Gay Female` = col_double(),
## .. `Anti-Gay (Male and Female)` = col_double(),
## .. `Anti-Heterosexual` = col_double(),
## .. `Anti-Bisexual` = col_double(),
## .. `Anti-Physical Disability` = col_double(),
## .. `Anti-Mental Disability` = col_double(),
## .. `Total Incidents` = col_double(),
## .. `Total Victims` = col_double(),
## .. `Total Offenders` = col_double()
## .. )
## - attr(*, "problems")=<externalptr>
Select only certain hate-crimes
hatecrimes2 <- hatecrimes %>%
select(county, year, `anti-black`, 'anti-white', `anti-jewish`, 'anti-catholic','anti-age*','anti-islamic(muslim)', 'anti-gaymale', 'anti-hispanic') %>%
group_by(county, year)
head(hatecrimes2)
## # A tibble: 6 x 10
## # Groups: county, year [4]
## county year `anti-black` `anti-white` `anti-jewish` `anti-catholic`
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Albany 2016 1 0 0 0
## 2 Albany 2016 2 0 0 0
## 3 Allegany 2016 1 0 0 0
## 4 Bronx 2016 0 1 0 0
## 5 Bronx 2016 0 1 1 0
## 6 Broome 2016 1 0 0 0
## # ... with 4 more variables: anti-age* <dbl>, anti-islamic(muslim) <dbl>,
## # anti-gaymale <dbl>, anti-hispanic <dbl>
Check the Dimensions and the summary to make sure no missing values
dim(hatecrimes2)
## [1] 423 10
Use Facet_Wap
hatecrimeslong <- hatecrimes2 %>%
tidyr::gather("id", "crimecount", 3:10)
hatecrimesplot <-hatecrimeslong %>%
ggplot(., aes(year, crimecount))+
geom_point()+
aes(color = id)+
facet_wrap(~id)
hatecrimesplot
Look deeper into crimes against blacks, gay males, and jews
hatenew <- hatecrimeslong %>%
filter( id== "anti-black" | id == "anti-jewish" | id == "anti-gaymale")%>%
group_by(year, county) %>%
arrange(desc(crimecount))
hatenew
## # A tibble: 1,269 x 4
## # Groups: year, county [277]
## county year id crimecount
## <chr> <dbl> <chr> <dbl>
## 1 Kings 2012 anti-jewish 82
## 2 Kings 2016 anti-jewish 51
## 3 Suffolk 2014 anti-jewish 48
## 4 Suffolk 2012 anti-jewish 48
## 5 Kings 2011 anti-jewish 44
## 6 Kings 2013 anti-jewish 41
## 7 Kings 2010 anti-jewish 39
## 8 Nassau 2011 anti-jewish 38
## 9 Suffolk 2013 anti-jewish 37
## 10 Nassau 2016 anti-jewish 36
## # ... with 1,259 more rows
Plot these three types of hate crimes together
plot2 <- hatenew %>%
ggplot() +
geom_bar(aes(x=year, y=crimecount, fill = id),
position = "dodge", stat = "identity") +
ggtitle("Hate Crime Type in NY Counties Between 2010-2016") +
ylab("Number of Hate Crime Incidents") +
labs(fill = "Hate Crime Type")
plot2
What about the counties?
plot3 <- hatenew %>%
ggplot() +
geom_bar(aes(x=county, y=crimecount, fill = id),
position = "dodge", stat = "identity") +
ggtitle("Hate Crime Type in NY Counties Between 2010-2016") +
ylab("Number of Hate Crime Incidents") +
labs(fill = "Hate Crime Type")
plot3
So many counties
counties <- hatenew %>%
group_by(county, year)%>%
summarize(sum = sum(crimecount)) %>%
arrange(desc(sum))
## `summarise()` has grouped output by 'county'. You can override using the `.groups` argument.
Barplot 5 counties in 2012 with the highest incidents of hate-crimes
plot4 <- hatenew %>%
filter(county =="Kings" | county =="New York" | county == "Suffolk" | county == "Nassau" | county == "Queens") %>%
ggplot() +
geom_bar(aes(x=county, y=crimecount, fill = id),
position = "dodge", stat = "identity") +
labs(ylab = "Number of Hate Crime Incidents",
title = "5 Counties in NY with Highest Incidents of Hate Crimes",
subtitle = "Between 2010-2016",
fill = "Hate Crime Type")
plot4
How would calculations be affected by looking at hate crimes in counties per year by population densities?
setwd("~/Data110")
nypop <- read_csv("newyorkpopulation.csv")
## Rows: 62 Columns: 8
## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (1): Geography
## dbl (7): 2010, 2011, 2012, 2013, 2014, 2015, 2016
##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.
#Rename the variable “Geography” as “county” so that it matches in the other dataset.
nypop$Geography <- gsub(" , New York", "", nypop$Geography)
nypop$Geography <- gsub("County", "", nypop$Geography)
nypoplong <- nypop %>%
rename(county = Geography) %>%
gather("year", "population", 2:8)
nypoplong$year <- as.double(nypoplong$year)
head(nypoplong)
## # A tibble: 6 x 3
## county year population
## <chr> <dbl> <dbl>
## 1 Albany , New York 2010 304078
## 2 Allegany , New York 2010 48949
## 3 Bronx , New York 2010 1388240
## 4 Broome , New York 2010 200469
## 5 Cattaraugus , New York 2010 80249
## 6 Cayuga , New York 2010 79844
Focus on 2012
nypoplong12 <- nypoplong %>%
filter(year == 2012) %>%
arrange(desc(population)) %>%
head(10)
nypoplong12$county<-gsub(" , New York","",nypoplong12$county)
nypoplong12
## # A tibble: 10 x 3
## county year population
## <chr> <dbl> <dbl>
## 1 Kings 2012 2572282
## 2 Queens 2012 2278024
## 3 New York 2012 1625121
## 4 Suffolk 2012 1499382
## 5 Bronx 2012 1414774
## 6 Nassau 2012 1350748
## 7 Westchester 2012 961073
## 8 Erie 2012 920792
## 9 Monroe 2012 748947
## 10 Richmond 2012 470978
Filter hate crimes just for 2012 as well
counties12 <- counties %>%
filter(year == 2012) %>%
arrange(desc(sum))
counties12
## # A tibble: 41 x 3
## # Groups: county [41]
## county year sum
## <chr> <dbl> <dbl>
## 1 Kings 2012 136
## 2 Suffolk 2012 83
## 3 New York 2012 71
## 4 Nassau 2012 48
## 5 Queens 2012 48
## 6 Erie 2012 28
## 7 Bronx 2012 23
## 8 Richmond 2012 18
## 9 Multiple 2012 14
## 10 Westchester 2012 13
## # ... with 31 more rows
Join the Hate Crimes data with NY population data for 2012
datajoin <- counties12 %>%
full_join(nypoplong12, by=c("county", "year"))
datajoin
## # A tibble: 41 x 4
## # Groups: county [41]
## county year sum population
## <chr> <dbl> <dbl> <dbl>
## 1 Kings 2012 136 2572282
## 2 Suffolk 2012 83 1499382
## 3 New York 2012 71 1625121
## 4 Nassau 2012 48 1350748
## 5 Queens 2012 48 2278024
## 6 Erie 2012 28 920792
## 7 Bronx 2012 23 1414774
## 8 Richmond 2012 18 470978
## 9 Multiple 2012 14 NA
## 10 Westchester 2012 13 961073
## # ... with 31 more rows
Calculate the rate of incidents per 100,000. Then arrange in descending order
datajoinrate <- datajoin %>%
mutate(rate = sum/population*100000) %>%
arrange(desc(rate))
datajoinrate
## # A tibble: 41 x 5
## # Groups: county [41]
## county year sum population rate
## <chr> <dbl> <dbl> <dbl> <dbl>
## 1 Suffolk 2012 83 1499382 5.54
## 2 Kings 2012 136 2572282 5.29
## 3 New York 2012 71 1625121 4.37
## 4 Richmond 2012 18 470978 3.82
## 5 Nassau 2012 48 1350748 3.55
## 6 Erie 2012 28 920792 3.04
## 7 Queens 2012 48 2278024 2.11
## 8 Bronx 2012 23 1414774 1.63
## 9 Westchester 2012 13 961073 1.35
## 10 Monroe 2012 5 748947 0.668
## # ... with 31 more rows
Notice that the highest rates of hate crimes in 2012 happened in:
dt <- datajoinrate[,c("county","rate")]
dt
## # A tibble: 41 x 2
## # Groups: county [41]
## county rate
## <chr> <dbl>
## 1 Suffolk 5.54
## 2 Kings 5.29
## 3 New York 4.37
## 4 Richmond 3.82
## 5 Nassau 3.55
## 6 Erie 3.04
## 7 Queens 2.11
## 8 Bronx 1.63
## 9 Westchester 1.35
## 10 Monroe 0.668
## # ... with 31 more rows
The dataset is consistently structured and effortlessly standardized. There’s a quantitative variable for each type of “hate-crime” which can be analyzed using statistical analysis. Nonetheless, the fact that the data collection is voluntary for states or even counties, introduces bias. It might appear that in a neighboring county/state hate crimes are more likely to happen when in fact it’s a lack of reporting. Also, without the census bureau population data, the numbers could have been very misleading as in the case of the following NY counties: Kings, New York, Queens etc.…
Perhaps, in addition to mandatory reporting for all states/counties, a few more variables could be added to improve this dataset. For example, in order to understand the psychology of hate crimes, characteristics about the offenders’ race, gender, religion or even level of education could have been added, of course when available. We could also tell that law enforcement agencies, when building this data set, had no intention of using it as a prevention tool.