library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.4.4 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.1
## ✔ purrr 1.0.2
## ── 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
#tinytex::install_tinytex()
#library(tinytex)
setwd("C:/Users/Neked Shep/Desktop/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.
summary("hateCrimes2010.csv")
## Length Class Mode
## 1 character character
names(hatecrimes) <- tolower(names(hatecrimes))
names(hatecrimes) <- gsub(" ","",names(hatecrimes))
head(hatecrimes)
## # A tibble: 6 × 44
## county year crimetype `anti-male` `anti-female` `anti-transgender`
## <chr> <dbl> <chr> <dbl> <dbl> <dbl>
## 1 Albany 2016 Crimes Against Pe… 0 0 0
## 2 Albany 2016 Property Crimes 0 0 0
## 3 Allegany 2016 Property Crimes 0 0 0
## 4 Bronx 2016 Crimes Against Pe… 0 0 4
## 5 Bronx 2016 Property Crimes 0 0 0
## 6 Broome 2016 Crimes Against Pe… 0 0 0
## # ℹ 38 more variables: `anti-genderidentityexpression` <dbl>,
## # `anti-age*` <dbl>, `anti-white` <dbl>, `anti-black` <dbl>,
## # `anti-americanindian/alaskannative` <dbl>, `anti-asian` <dbl>,
## # `anti-nativehawaiian/pacificislander` <dbl>,
## # `anti-multi-racialgroups` <dbl>, `anti-otherrace` <dbl>,
## # `anti-jewish` <dbl>, `anti-catholic` <dbl>, `anti-protestant` <dbl>,
## # `anti-islamic(muslim)` <dbl>, `anti-multi-religiousgroups` <dbl>, …
hatecrimes2 <- hatecrimes |>
select(county, year, 'anti-transgender', 'anti-age*', 'anti-white', 'anti-black', 'anti-asian', 'anti-jewish', 'anti-catholic', 'anti-islamic(muslim)', 'anti-multi-religiousgroups', 'anti-hispanic', 'anti-otherethnicity/nationalorigin', 'anti-gaymale', 'anti-gayfemale', `anti-otherethnicity/nationalorigin`) |>
group_by(county, year)
head(hatecrimes2)
## # A tibble: 6 × 15
## # Groups: county, year [4]
## county year `anti-transgender` `anti-age*` `anti-white` `anti-black`
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Albany 2016 0 0 0 1
## 2 Albany 2016 0 0 0 2
## 3 Allegany 2016 0 0 0 1
## 4 Bronx 2016 4 0 1 0
## 5 Bronx 2016 0 0 1 0
## 6 Broome 2016 0 0 0 1
## # ℹ 9 more variables: `anti-asian` <dbl>, `anti-jewish` <dbl>,
## # `anti-catholic` <dbl>, `anti-islamic(muslim)` <dbl>,
## # `anti-multi-religiousgroups` <dbl>, `anti-hispanic` <dbl>,
## # `anti-otherethnicity/nationalorigin` <dbl>, `anti-gaymale` <dbl>,
## # `anti-gayfemale` <dbl>
dim(hatecrimes2)
## [1] 423 15
# There are currently 12 variables with 423 rows.
summary(hatecrimes2)
## county year anti-transgender anti-age*
## Length:423 Min. :2010 Min. :0.00000 Min. :0.00000
## Class :character 1st Qu.:2011 1st Qu.:0.00000 1st Qu.:0.00000
## Mode :character Median :2013 Median :0.00000 Median :0.00000
## Mean :2013 Mean :0.04728 Mean :0.05201
## 3rd Qu.:2015 3rd Qu.:0.00000 3rd Qu.:0.00000
## Max. :2016 Max. :5.00000 Max. :9.00000
## anti-white anti-black anti-asian anti-jewish
## Min. : 0.0000 Min. : 0.000 Min. :0.0000 Min. : 0.000
## 1st Qu.: 0.0000 1st Qu.: 0.000 1st Qu.:0.0000 1st Qu.: 0.000
## Median : 0.0000 Median : 1.000 Median :0.0000 Median : 0.000
## Mean : 0.3357 Mean : 1.761 Mean :0.1773 Mean : 3.981
## 3rd Qu.: 0.0000 3rd Qu.: 2.000 3rd Qu.:0.0000 3rd Qu.: 3.000
## Max. :11.0000 Max. :18.000 Max. :8.0000 Max. :82.000
## anti-catholic anti-islamic(muslim) anti-multi-religiousgroups
## Min. : 0.0000 Min. : 0.0000 Min. : 0.00000
## 1st Qu.: 0.0000 1st Qu.: 0.0000 1st Qu.: 0.00000
## Median : 0.0000 Median : 0.0000 Median : 0.00000
## Mean : 0.2695 Mean : 0.4704 Mean : 0.07565
## 3rd Qu.: 0.0000 3rd Qu.: 0.0000 3rd Qu.: 0.00000
## Max. :12.0000 Max. :10.0000 Max. :10.00000
## anti-hispanic anti-otherethnicity/nationalorigin anti-gaymale
## Min. : 0.0000 Min. : 0.0000 Min. : 0.000
## 1st Qu.: 0.0000 1st Qu.: 0.0000 1st Qu.: 0.000
## Median : 0.0000 Median : 0.0000 Median : 0.000
## Mean : 0.3735 Mean : 0.2837 Mean : 1.499
## 3rd Qu.: 0.0000 3rd Qu.: 0.0000 3rd Qu.: 1.000
## Max. :17.0000 Max. :19.0000 Max. :36.000
## anti-gayfemale
## Min. :0.0000
## 1st Qu.:0.0000
## Median :0.0000
## Mean :0.2411
## 3rd Qu.:0.0000
## Max. :8.0000
hatelong <- hatecrimes2 |>
pivot_longer(
cols = 3:12,
names_to = "victim_cat",
values_to = "crimecount")
hatecrimplot <-hatelong |>
ggplot(aes(year, crimecount))+
geom_point()+
aes(color = victim_cat)+
facet_wrap(~victim_cat)
hatecrimplot
hatenew <- hatelong |>
filter( victim_cat %in% c("anti-black", "anti-jewish", "anti-gaymale"))|>
group_by(year, county) |>
arrange(desc(crimecount))
hatenew
## # A tibble: 846 × 7
## # Groups: year, county [277]
## county year anti-otherethnicity/nationalo…¹ `anti-gaymale` `anti-gayfemale`
## <chr> <dbl> <dbl> <dbl> <dbl>
## 1 Kings 2012 0 0 0
## 2 Kings 2016 1 2 0
## 3 Suffolk 2014 0 2 0
## 4 Suffolk 2012 2 2 0
## 5 Kings 2011 0 2 0
## 6 Kings 2013 1 1 0
## 7 Kings 2010 0 1 0
## 8 Nassau 2011 0 0 0
## 9 Suffolk 2013 0 1 0
## 10 Nassau 2016 0 0 0
## # ℹ 836 more rows
## # ℹ abbreviated name: ¹`anti-otherethnicity/nationalorigin`
## # ℹ 2 more variables: victim_cat <chr>, crimecount <dbl>
plot2 <- hatenew |>
ggplot() +
geom_bar(aes(x=year, y=crimecount, fill = victim_cat),
position = "dodge", stat = "identity") +
labs(fill = "Hate Crime Type",
y = "Number of Hate Crime Incidents",
title = "Hate Crime Type in NY Counties Between 2010-2016",
caption = "Source: NY State Division of Criminal Justice Services")
plot2
plot3 <- hatenew |>
ggplot() +
geom_bar(aes(x=county, y=crimecount, fill = victim_cat),
position = "dodge", stat = "identity") +
labs(fill = "Hate Crime Type",
y = "Number of Hate Crime Incidents",
title = "Hate Crime Type in NY Counties Between 2010-2016",
caption = "Source: NY State Division of Criminal Justice Services")
plot3
counties <- hatenew |>
group_by(year, county)|>
summarize(sum = sum(crimecount)) |>
arrange(desc(sum))
## `summarise()` has grouped output by 'year'. You can override using the
## `.groups` argument.
counties
## # A tibble: 277 × 3
## # Groups: year [7]
## year county sum
## <dbl> <chr> <dbl>
## 1 2012 Kings 124
## 2 2010 Kings 89
## 3 2016 Kings 83
## 4 2012 Suffolk 80
## 5 2014 Kings 69
## 6 2015 Kings 69
## 7 2011 Kings 68
## 8 2013 Kings 68
## 9 2014 Suffolk 65
## 10 2013 Suffolk 64
## # ℹ 267 more rows
counties2 <- hatenew |>
group_by(county)|>
summarize(sum = sum(crimecount)) |>
slice_max(order_by = sum, n=5)
counties2
## # A tibble: 5 × 2
## county sum
## <chr> <dbl>
## 1 Kings 570
## 2 Suffolk 317
## 3 Nassau 283
## 4 New York 266
## 5 Queens 175
plot4 <- hatenew |>
filter(county %in% c("Kings", "New York", "Suffolk", "Nassau", "Queens")) |>
ggplot() +
geom_bar(aes(x=county, y=crimecount, fill = victim_cat),
position = "dodge", stat = "identity") +
labs(y = "Number of Hate Crime Incidents",
title = "5 Counties in NY with Highest Incidents of Hate Crimes",
subtitle = "Between 2010-2016",
fill = "Hate Crime Type",
caption = "Source: NY State Division of Criminal Justice Services")
plot4
setwd("C:/Users/Neked Shep/Desktop/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.
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 × 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 × 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 × 3
## # Groups: year [1]
## year county sum
## <dbl> <chr> <dbl>
## 1 2012 Kings 124
## 2 2012 Suffolk 80
## 3 2012 New York 54
## 4 2012 Nassau 48
## 5 2012 Queens 38
## 6 2012 Erie 20
## 7 2012 Bronx 19
## 8 2012 Richmond 16
## 9 2012 Multiple 14
## 10 2012 Dutchess 9
## # ℹ 31 more rows
datajoin <- counties12 |>
full_join(nypoplong12, by=c("county", "year"))
datajoin
## # A tibble: 41 × 4
## # Groups: year [1]
## year county sum population
## <dbl> <chr> <dbl> <dbl>
## 1 2012 Kings 124 2572282
## 2 2012 Suffolk 80 1499382
## 3 2012 New York 54 1625121
## 4 2012 Nassau 48 1350748
## 5 2012 Queens 38 2278024
## 6 2012 Erie 20 920792
## 7 2012 Bronx 19 1414774
## 8 2012 Richmond 16 470978
## 9 2012 Multiple 14 NA
## 10 2012 Dutchess 9 NA
## # ℹ 31 more rows
datajoinrate <- datajoin |>
mutate(rate = sum/population*100000) |>
arrange(desc(rate))
datajoinrate
## # A tibble: 41 × 5
## # Groups: year [1]
## year county sum population rate
## <dbl> <chr> <dbl> <dbl> <dbl>
## 1 2012 Suffolk 80 1499382 5.34
## 2 2012 Kings 124 2572282 4.82
## 3 2012 Nassau 48 1350748 3.55
## 4 2012 Richmond 16 470978 3.40
## 5 2012 New York 54 1625121 3.32
## 6 2012 Erie 20 920792 2.17
## 7 2012 Queens 38 2278024 1.67
## 8 2012 Bronx 19 1414774 1.34
## 9 2012 Monroe 5 748947 0.668
## 10 2012 Westchester 6 961073 0.624
## # ℹ 31 more rows
dt <- datajoinrate[,c("county","rate")]
dt
## # A tibble: 41 × 2
## county rate
## <chr> <dbl>
## 1 Suffolk 5.34
## 2 Kings 4.82
## 3 Nassau 3.55
## 4 Richmond 3.40
## 5 New York 3.32
## 6 Erie 2.17
## 7 Queens 1.67
## 8 Bronx 1.34
## 9 Monroe 0.668
## 10 Westchester 0.624
## # ℹ 31 more rows
aggregategroups <- hatecrimes |>
pivot_longer(
cols = 4:44,
names_to = "victim_cat",
values_to = "crimecount"
)
unique(aggregategroups$victim_cat)
## [1] "anti-male"
## [2] "anti-female"
## [3] "anti-transgender"
## [4] "anti-genderidentityexpression"
## [5] "anti-age*"
## [6] "anti-white"
## [7] "anti-black"
## [8] "anti-americanindian/alaskannative"
## [9] "anti-asian"
## [10] "anti-nativehawaiian/pacificislander"
## [11] "anti-multi-racialgroups"
## [12] "anti-otherrace"
## [13] "anti-jewish"
## [14] "anti-catholic"
## [15] "anti-protestant"
## [16] "anti-islamic(muslim)"
## [17] "anti-multi-religiousgroups"
## [18] "anti-atheism/agnosticism"
## [19] "anti-religiouspracticegenerally"
## [20] "anti-otherreligion"
## [21] "anti-buddhist"
## [22] "anti-easternorthodox(greek,russian,etc.)"
## [23] "anti-hindu"
## [24] "anti-jehovahswitness"
## [25] "anti-mormon"
## [26] "anti-otherchristian"
## [27] "anti-sikh"
## [28] "anti-hispanic"
## [29] "anti-arab"
## [30] "anti-otherethnicity/nationalorigin"
## [31] "anti-non-hispanic*"
## [32] "anti-gaymale"
## [33] "anti-gayfemale"
## [34] "anti-gay(maleandfemale)"
## [35] "anti-heterosexual"
## [36] "anti-bisexual"
## [37] "anti-physicaldisability"
## [38] "anti-mentaldisability"
## [39] "totalincidents"
## [40] "totalvictims"
## [41] "totaloffenders"
aggregategroups <- aggregategroups |>
mutate(group = case_when(
victim_cat %in% c("anti-transgender", "anti-gayfemale", "anti-gendervictim_catendityexpression", "anti-gaymale", "anti-gay(maleandfemale", "anti-bisexual") ~ "anti-lgbtq",
victim_cat %in% c("anti-multi-racialgroups", "anti-jewish", "anti-protestant", "anti-multi-religousgroups", "anti-religiouspracticegenerally", "anti-buddhist", "anti-hindu", "anti-mormon", "anti-sikh", "anti-catholic", "anti-islamic(muslim)", "anti-atheism/agnosticism", "anti-otherreligion", "anti-easternorthodox(greek,russian,etc.)", "anti-jehovahswitness", "anti-otherchristian") ~ "anti-religion",
victim_cat %in% c("anti-asian", "anti-arab", "anti-non-hispanic", "anti-white", "anti-americanindian/alaskannative", "anti-nativehawaiian/pacificislander", "anti-otherrace", "anti-hispanic", "anti-otherethnicity/nationalorigin") ~ "anti-ethnicity",
victim_cat %in% c("anti-physicaldisability", "anti-mentaldisability") ~ "anti-disability",
victim_cat %in% c("anti-female", "anti-male") ~ "anti-gender",
TRUE ~ "others"))
aggregategroups
## # A tibble: 17,343 × 6
## county year crimetype victim_cat crimecount group
## <chr> <dbl> <chr> <chr> <dbl> <chr>
## 1 Albany 2016 Crimes Against Persons anti-male 0 anti…
## 2 Albany 2016 Crimes Against Persons anti-female 0 anti…
## 3 Albany 2016 Crimes Against Persons anti-transgender 0 anti…
## 4 Albany 2016 Crimes Against Persons anti-genderidentityexpr… 0 othe…
## 5 Albany 2016 Crimes Against Persons anti-age* 0 othe…
## 6 Albany 2016 Crimes Against Persons anti-white 0 anti…
## 7 Albany 2016 Crimes Against Persons anti-black 1 othe…
## 8 Albany 2016 Crimes Against Persons anti-americanindian/ala… 0 anti…
## 9 Albany 2016 Crimes Against Persons anti-asian 0 anti…
## 10 Albany 2016 Crimes Against Persons anti-nativehawaiian/pac… 0 anti…
## # ℹ 17,333 more rows
lgbtq <- hatecrimes |>
pivot_longer(
cols = 4:44,
names_to = "victim_cat",
values_to = "crimecount") |>
filter(victim_cat %in% c("anti-transgender", "anti-gayfemale", "anti-gendervictim_catendityexpression", "anti-gaymale", "anti-gay(maleandfemale", "anti-bisexual"))
lgbtq
## # A tibble: 1,692 × 5
## county year crimetype victim_cat crimecount
## <chr> <dbl> <chr> <chr> <dbl>
## 1 Albany 2016 Crimes Against Persons anti-transgender 0
## 2 Albany 2016 Crimes Against Persons anti-gaymale 1
## 3 Albany 2016 Crimes Against Persons anti-gayfemale 0
## 4 Albany 2016 Crimes Against Persons anti-bisexual 0
## 5 Albany 2016 Property Crimes anti-transgender 0
## 6 Albany 2016 Property Crimes anti-gaymale 0
## 7 Albany 2016 Property Crimes anti-gayfemale 0
## 8 Albany 2016 Property Crimes anti-bisexual 0
## 9 Allegany 2016 Property Crimes anti-transgender 0
## 10 Allegany 2016 Property Crimes anti-gaymale 0
## # ℹ 1,682 more rows
- The positive aspects of this dataset are that the data is very
specific. There is lots of data going back as far as 5 years. The data
is also very specific in the sense of documenting who is experiencing
the hate crimes.
- One thing I would like to study more about this data set is why are
there counties reporting zero hate crimes? Its a good thing that there
aren’t any hate crimes, but how accurate is the information? Another
thing I would like to study is what the exact hate crime was. Was it
violent, was it verbal, etc.
- To follow up after seeing the output, I would like to show the
graphs with in different formats, so that there are different ways to
present the dataset. Another thing I would do is provide text for the
reader to gain more detailed information about the data set.