library(tidyverse)
#tinytex::install_tinytex()
#library(tinytex)
setwd("~/Desktop/DATA 110")
hatecrimes <- read_csv("NYPD_Hate_Crimes_19-26.csv")NY Hate Crimes 2019-2026
NY Hate Crimes 2019-2026
About this dataset
Flawed hate crime data collection - we should know how the data was collected
So now we know that there is possible bias in the dataset, what can we do with it?
Clean up the data:
Make all headers lowercase and remove spaces
names(hatecrimes) <- tolower(names(hatecrimes))
names(hatecrimes) <- gsub(" ","",names(hatecrimes))
head(hatecrimes)# A tibble: 6 × 14
fullcomplaintid complaintyearnumber monthnumber recordcreatedate
<dbl> <dbl> <dbl> <chr>
1 2.02e14 2019 1 1/23/2019
2 2.02e14 2019 2 2/25/2019
3 2.02e14 2019 2 2/27/2019
4 2.02e14 2019 4 4/16/2019
5 2.02e14 2019 6 6/20/2019
6 2.02e14 2019 7 7/31/2019
# ℹ 10 more variables: complaintprecinctcode <dbl>, patrolboroughname <chr>,
# county <chr>, lawcodecategorydescription <chr>, offensedescription <chr>,
# pdcodedescription <chr>, biasmotivedescription <chr>,
# offensecategory <chr>, arrestdate <lgl>, arrestid <chr>Explore the bias motive (biasmotivedescription)
bias_count <- hatecrimes |>
select(biasmotivedescription) |>
group_by(biasmotivedescription) |>
count() |>
arrange(desc(n))
head(bias_count)# A tibble: 6 × 2
# Groups: biasmotivedescription [6]
biasmotivedescription n
<chr> <int>
1 ANTI-JEWISH 1906
2 ANTI-MALE HOMOSEXUAL (GAY) 489
3 ANTI-ASIAN 401
4 ANTI-BLACK 315
5 ANTI-OTHER ETHNICITY 168
6 ANTI-MUSLIM 156Visualize these counts as a bar graph
ggplot(hatecrimes, aes(x = biasmotivedescription))+
geom_bar()
Use inclusion/exclusion criteria to filter
bias_count |>
head(10) |>
ggplot(aes(x=biasmotivedescription, y = n)) +
geom_col()
Arrange the bars according to height and rotate
bias_count |>
head(10) |>
ggplot(aes(x=reorder(biasmotivedescription, n), y = n)) +
geom_col() +
coord_flip()
Add title, caption for the data source, and x-axis label
bias_count |>
head(10) |>
ggplot(aes(x=reorder(biasmotivedescription, n), y = n)) +
geom_col() +
coord_flip()+
labs(x = "",
y = "Counts of hatecrime types based on motive",
title = "Bar Graph of Hate Crimes from 2019-2026",
subtitle = "Counts based on the hatecrime motive",
caption = "Source: NY State Division of Criminal Justice Services")
Finally add color and change the theme
bias_count |>
head(10) |>
ggplot(aes(x=reorder(biasmotivedescription, n), y = n)) +
geom_col(fill = "salmon") +
coord_flip()+
labs(x = "",
y = "Counts of hatecrime types based on motive",
title = "Bar Graph of Hate Crimes from 2019-2026",
subtitle = "Counts based on the hatecrime motive",
caption = "Source: NY State Division of Criminal Justice Services") +
theme_minimal()
Add annotations for counts and remove the x-axis values
bias_count |>
head(10) |>
ggplot(aes(x=reorder(biasmotivedescription, n), y = n)) +
geom_col(fill = "salmon") +
coord_flip()+
labs(x = "",
y = "Counts of hatecrime types based on motive",
title = "Bar Graph of Hate Crimes from 2019-2026",
subtitle = "Counts based on the hatecrime motive",
caption = "Source: NY State Division of Criminal Justice Services") +
theme_minimal()+
geom_text(aes(label = n), hjust = -.05, size = 3) +
theme(axis.text.x = element_blank())
Look deeper into crimes against Jewish, Asian, Black people, and gay males
First check the year totals
hate_year <- hatecrimes |>
filter(biasmotivedescription %in% c("ANTI-JEWISH", "ANTI-MALE HOMOSEXUAL (GAY)", "ANTI-ASIAN", "ANTI-BLACK"))|>
group_by(complaintyearnumber) |>
count(biasmotivedescription)|>
arrange(desc(n))
hate_year# A tibble: 28 × 3
# Groups: complaintyearnumber [7]
complaintyearnumber biasmotivedescription n
<dbl> <chr> <int>
1 2024 ANTI-JEWISH 371
2 2023 ANTI-JEWISH 343
3 2025 ANTI-JEWISH 320
4 2022 ANTI-JEWISH 279
5 2019 ANTI-JEWISH 252
6 2021 ANTI-JEWISH 215
7 2021 ANTI-ASIAN 150
8 2020 ANTI-JEWISH 126
9 2023 ANTI-MALE HOMOSEXUAL (GAY) 116
10 2022 ANTI-ASIAN 91
# ℹ 18 more rowsThen check the county totals
hate_county <- hatecrimes |>
filter(biasmotivedescription %in% c("ANTI-JEWISH", "ANTI-MALE HOMOSEXUAL (GAY)", "ANTI-ASIAN", "ANTI-BLACK"))|>
group_by(county) |>
count(biasmotivedescription)|>
arrange(desc(n))
hate_county# A tibble: 20 × 3
# Groups: county [5]
county biasmotivedescription n
<chr> <chr> <int>
1 KINGS ANTI-JEWISH 798
2 NEW YORK ANTI-JEWISH 651
3 QUEENS ANTI-JEWISH 289
4 NEW YORK ANTI-MALE HOMOSEXUAL (GAY) 237
5 NEW YORK ANTI-ASIAN 228
6 KINGS ANTI-MALE HOMOSEXUAL (GAY) 120
7 KINGS ANTI-BLACK 99
8 BRONX ANTI-JEWISH 92
9 QUEENS ANTI-MALE HOMOSEXUAL (GAY) 91
10 KINGS ANTI-ASIAN 80
11 NEW YORK ANTI-BLACK 79
12 QUEENS ANTI-ASIAN 78
13 RICHMOND ANTI-JEWISH 76
14 QUEENS ANTI-BLACK 75
15 BRONX ANTI-MALE HOMOSEXUAL (GAY) 35
16 RICHMOND ANTI-BLACK 35
17 BRONX ANTI-BLACK 27
18 BRONX ANTI-ASIAN 10
19 RICHMOND ANTI-MALE HOMOSEXUAL (GAY) 6
20 RICHMOND ANTI-ASIAN 5Check information combining totals from counties and years
hate2 <- hatecrimes |>
filter(biasmotivedescription %in% c("ANTI-JEWISH", "ANTI-MALE HOMOSEXUAL (GAY)", "ANTI-ASIAN", "ANTI-BLACK"))|>
group_by(complaintyearnumber, county) |>
count(biasmotivedescription)|>
arrange(desc(n))
hate2# A tibble: 127 × 4
# Groups: complaintyearnumber, county [35]
complaintyearnumber county biasmotivedescription n
<dbl> <chr> <chr> <int>
1 2024 KINGS ANTI-JEWISH 152
2 2024 NEW YORK ANTI-JEWISH 136
3 2025 KINGS ANTI-JEWISH 136
4 2019 KINGS ANTI-JEWISH 128
5 2023 KINGS ANTI-JEWISH 126
6 2022 KINGS ANTI-JEWISH 125
7 2023 NEW YORK ANTI-JEWISH 124
8 2025 NEW YORK ANTI-JEWISH 110
9 2022 NEW YORK ANTI-JEWISH 104
10 2021 NEW YORK ANTI-ASIAN 84
# ℹ 117 more rowsPlot these three types of hate crimes together
ggplot(data = hate2) +
geom_bar(aes(x=complaintyearnumber, y=n, fill = biasmotivedescription),
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")
What about the counties?
ggplot(data = hate2) +
geom_bar(aes(x=county, y=n, fill = biasmotivedescription),
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")
The highest counts
Put it all together with years and counties using “facet”
ggplot(data = hate2) +
geom_bar(aes(x=complaintyearnumber, y=n, fill = biasmotivedescription),
position = "dodge", stat = "identity") +
facet_wrap(~county) +
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")
How would calculations be affected by looking at hate crimes in counties per year by population densities?
setwd("~/Desktop/DATA 110")
nypop <- read_csv("nyc_census_pop_2020.csv")Rows: 62 Columns: 4
── Column specification ────────────────────────────────────────────────────────
Delimiter: ","
chr (2): Area Name, Population Percent Change
num (2): 2020 Census Population, Population Change
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 the county name to match the other dataset
nypop$`Area Name` <- gsub(" County", "", nypop$`Area Name`)
nypop2 <- nypop |>
rename(county = `Area Name`)|>
select(county, `2020 Census Population`)
head(nypop2)# A tibble: 6 × 2
county `2020 Census Population`
<chr> <dbl>
1 Albany 314848
2 Allegany 46456
3 Bronx 1472654
4 Broome 198683
5 Cattaraugus 77042
6 Cayuga 76248Join the hate2 data with nypop
datajoin <- left_join(hate2, nypop2, by=c("county"))
datajoin# A tibble: 127 × 5
# Groups: complaintyearnumber, county [35]
complaintyearnumber county biasmotivedescription n 2020 Census Populati…¹
<dbl> <chr> <chr> <int> <dbl>
1 2024 KINGS ANTI-JEWISH 152 NA
2 2024 NEW Y… ANTI-JEWISH 136 NA
3 2025 KINGS ANTI-JEWISH 136 NA
4 2019 KINGS ANTI-JEWISH 128 NA
5 2023 KINGS ANTI-JEWISH 126 NA
6 2022 KINGS ANTI-JEWISH 125 NA
7 2023 NEW Y… ANTI-JEWISH 124 NA
8 2025 NEW Y… ANTI-JEWISH 110 NA
9 2022 NEW Y… ANTI-JEWISH 104 NA
10 2021 NEW Y… ANTI-ASIAN 84 NA
# ℹ 117 more rows
# ℹ abbreviated name: ¹`2020 Census Population`It didn’t work - the new column has NA values
hate_new <- hate2 |>
mutate(county = as_factor(str_to_lower(as.character(county))))
nypop_new <- nypop2 |>
mutate(county = as_factor(str_to_lower(as.character(county))))Try joining again
datajoin <- left_join(hate_new, nypop_new, by=c("county"))
datajoin# A tibble: 127 × 5
# Groups: complaintyearnumber, county [35]
complaintyearnumber county biasmotivedescription n 2020 Census Populati…¹
<dbl> <fct> <chr> <int> <dbl>
1 2024 kings ANTI-JEWISH 152 2736074
2 2024 new y… ANTI-JEWISH 136 1694251
3 2025 kings ANTI-JEWISH 136 2736074
4 2019 kings ANTI-JEWISH 128 2736074
5 2023 kings ANTI-JEWISH 126 2736074
6 2022 kings ANTI-JEWISH 125 2736074
7 2023 new y… ANTI-JEWISH 124 1694251
8 2025 new y… ANTI-JEWISH 110 1694251
9 2022 new y… ANTI-JEWISH 104 1694251
10 2021 new y… ANTI-ASIAN 84 1694251
# ℹ 117 more rows
# ℹ abbreviated name: ¹`2020 Census Population`Calculate the rate of incidents per 100,000. Then arrange in descending order
datajoinrate <- datajoin |>
mutate(rate = n/`2020 Census Population`* 100000) |>
arrange(desc(rate))
datajoinrate# A tibble: 127 × 6
# Groups: complaintyearnumber, county [35]
complaintyearnumber county biasmotivedescription n 2020 Census Populati…¹
<dbl> <fct> <chr> <int> <dbl>
1 2024 new y… ANTI-JEWISH 136 1694251
2 2023 new y… ANTI-JEWISH 124 1694251
3 2025 new y… ANTI-JEWISH 110 1694251
4 2022 new y… ANTI-JEWISH 104 1694251
5 2024 kings ANTI-JEWISH 152 2736074
6 2025 kings ANTI-JEWISH 136 2736074
7 2021 new y… ANTI-ASIAN 84 1694251
8 2021 new y… ANTI-JEWISH 84 1694251
9 2019 kings ANTI-JEWISH 128 2736074
10 2023 kings ANTI-JEWISH 126 2736074
# ℹ 117 more rows
# ℹ abbreviated name: ¹`2020 Census Population`
# ℹ 1 more variable: rate <dbl>Positive and Negative aspects of Hate Crimes dataset.
The NY dataset of hate crimes is rich in several potential advantages that may further support a systematic analysis. Covering the years 2019-2026, it would allow the study of temporal trends and shifts in bias-motivated incidents. Other variables in the dataset include county, offense category, and bias motive. This makes it possible to conduct subgroup-level and geographic comparisons. Hence, suitable for visualization and exploratory research. However, for all its strengths, there are still a number of limitations that remain. The reliance on hate crime statistics is based on both local law enforcement and victim reports, introducing underreporting and uneven participation across jurisdictions. Moreover, differences in classification procedures and investigate capacity could change the reliability and comparability of counts. Consequently, results should be considered approximate indicators rather than exact measures. Research in the future could be channeled in two directions. One is the use of the population-adjusted rates to assess relative exposure of counties to hate crimes. Another direction would be examining the time relationships between social and political events and changes in specific biases as medium for some context factors explanation behind patterns of hate crimes.