library(tidyverse)
## Warning: package 'tidyverse' was built under R version 4.0.3
## -- Attaching packages --------------------------------------- tidyverse 1.3.0 --
## v ggplot2 3.3.3 v purrr 0.3.4
## v tibble 3.0.6 v dplyr 1.0.4
## v tidyr 1.1.2 v stringr 1.4.0
## v readr 1.4.0 v forcats 0.5.0
## Warning: package 'ggplot2' was built under R version 4.0.3
## Warning: package 'tibble' was built under R version 4.0.3
## Warning: package 'tidyr' was built under R version 4.0.2
## Warning: package 'readr' was built under R version 4.0.3
## Warning: package 'dplyr' was built under R version 4.0.3
## Warning: package 'forcats' was built under R version 4.0.2
## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
library(tinytex)
## Warning: package 'tinytex' was built under R version 4.0.3
setwd("C:/Users/Joeyc/Documents/School/Fall 2021/Data 110/DataSets")
hatecrimes <- read_csv("hateCrimes2010.csv")
##
## -- Column specification --------------------------------------------------------
## cols(
## .default = col_double(),
## County = col_character(),
## `Crime Type` = col_character()
## )
## i Use `spec()` for the full column specifications.
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()
## .. )
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 Alleg~ 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>
dim(hatecrimes2)
## [1] 423 10
summary(hatecrimes2)
## county year anti-black anti-white
## Length:423 Min. :2010 Min. : 0.000 Min. : 0.0000
## Class :character 1st Qu.:2011 1st Qu.: 0.000 1st Qu.: 0.0000
## Mode :character Median :2013 Median : 1.000 Median : 0.0000
## Mean :2013 Mean : 1.761 Mean : 0.3357
## 3rd Qu.:2015 3rd Qu.: 2.000 3rd Qu.: 0.0000
## Max. :2016 Max. :18.000 Max. :11.0000
## anti-jewish anti-catholic anti-age* anti-islamic(muslim)
## Min. : 0.000 Min. : 0.0000 Min. :0.00000 Min. : 0.0000
## 1st Qu.: 0.000 1st Qu.: 0.0000 1st Qu.:0.00000 1st Qu.: 0.0000
## Median : 0.000 Median : 0.0000 Median :0.00000 Median : 0.0000
## Mean : 3.981 Mean : 0.2695 Mean :0.05201 Mean : 0.4704
## 3rd Qu.: 3.000 3rd Qu.: 0.0000 3rd Qu.:0.00000 3rd Qu.: 0.0000
## Max. :82.000 Max. :12.0000 Max. :9.00000 Max. :10.0000
## anti-gaymale anti-hispanic
## Min. : 0.000 Min. : 0.0000
## 1st Qu.: 0.000 1st Qu.: 0.0000
## Median : 0.000 Median : 0.0000
## Mean : 1.499 Mean : 0.3735
## 3rd Qu.: 1.000 3rd Qu.: 0.0000
## Max. :36.000 Max. :17.0000
hatecrimeslong <- hatecrimes2 %>%
tidyr::gather("id", "crimecount", 3:10)
hatecrimesplot <-hatecrimeslong %>%
ggplot(., aes(year, crimecount))+
geom_point()+
aes(color = id)+
facet_wrap(~id)
hatecrimesplot
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
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
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
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.
counties
## # A tibble: 277 x 3
## # Groups: county [60]
## county year sum
## <chr> <dbl> <dbl>
## 1 Kings 2012 136
## 2 Kings 2010 110
## 3 Kings 2016 101
## 4 Kings 2013 96
## 5 Kings 2014 94
## 6 Kings 2015 90
## 7 Kings 2011 86
## 8 New York 2016 86
## 9 Suffolk 2012 83
## 10 New York 2013 75
## # ... with 267 more rows
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
setwd("C:/Users/Joeyc/Documents/School/Fall 2021/Data 110/DataSets")
nypop <- read_csv("newyorkpopulation.csv")
##
## -- Column specification --------------------------------------------------------
## cols(
## Geography = col_character(),
## `2010` = col_double(),
## `2011` = col_double(),
## `2012` = col_double(),
## `2013` = col_double(),
## `2014` = col_double(),
## `2015` = col_double(),
## `2016` = col_double()
## )
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
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
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
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
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
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
Positive and Negative Aspects of this Dataset
A positive aspect is that it has a high variety of types of hate crimes in the dataset. A negative aspect is we don’t know how exactly the data was collected so we don’t know how accurate the data is. What is the critia for a hate crime.
List 2 different paths you would like to (hypothetically) study about this dataset.
Are anti-Jewish hate crimes actually happening at a higher rate than other hate crimes or is their population just higher in these areas and the hate crimes per capita the same as other hate crimes. Are the hate crimes more likely to occur against a minorities property or person.
Describe 2 things you would do to follow up after seeing these results.
Why are certain counties more likely to have hate crimes in their area. Do these hate crimes happen at higher or lower rates compared to the national average.