library(tidyverse)
library(knitr)
setwd("/Users/giovanarodrigues/Desktop/DATA 110/dataset")
hatecrimes <- read_csv("NYPD_Hate_Crimes_19-26.csv")Week 3 HW
Load The Data
Clean up the data:
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
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())
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 rowshate_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 5hate2 <- 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")
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")
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("/Users/giovanarodrigues/Desktop/DATA 110/dataset")
nypop <- read_csv("nyc_census_pop_2020.csv")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 76248datajoin <- 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`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))))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`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>At the end of your markdown/Quarto file with the hatecrimes code, include an essay of about 150-200 words which that answers the following questions:
Write about the positive and negative aspects of this hatecrimes data set.
List 2 different paths you would like to (hypothetically) study about this data set.
This data set covers several years (from 2019 to 2026) and it lets us study trends over time. The data have two features: the first is about the bias motive and second tells the county of each complaint. In which these two variables allows comparisons across groups and places. A positive aspect of this hatecrimes data set is it public datas, so the analysis can be reproduced. However, it only includes crimes that were reported and classified as hate crimes, so it probably hides real incidents. The bias motive is assigned by police, which adds subjectivity. Counties are broad areas that hide neighborhood differences, and raw counts ignore population size, so larger counties look worse by default. The latest year is also incomplete, which can make crimes seem to drop. Two paths I would study are: hate crime rates per 100,000 residents by county and year, to compare places fairly and see where risk is highest; and how specific motives, such as anti-Asian or anti-male homesexual crimes, change over time and around major events, to understand what motive leads the crimes to increase.