HateCrimesData Homework
Samuel Kalibala
6/13/2021
library(tidyverse)## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --## v ggplot2 3.3.3 v purrr 0.3.4
## v tibble 3.1.2 v dplyr 1.0.6
## v tidyr 1.1.3 v stringr 1.4.0
## v readr 1.4.0 v forcats 0.5.1## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()library(fansi)
library(ggplot2)library(tinytex)getwd()## [1] "C:/Documents - Copy/PERSONAL/Data 110_MC_Class"setwd("C:/Documents - Copy/PERSONAL/Data 110_MC_Class")
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.print(hatecrimes)## # A tibble: 423 x 44
## County Year `Crime Type` `Anti-Male` `Anti-Female` `Anti-Transgende~
## <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
## 7 Cayuga 2016 Property Crimes 0 0 0
## 8 Chemung 2016 Crimes Against Pe~ 0 0 0
## 9 Chemung 2016 Property Crimes 0 0 0
## 10 Chenango 2016 Crimes Against Pe~ 0 0 0
## # ... with 413 more rows, and 38 more variables:
## # Anti-Gender Identity Expression <dbl>, Anti-Age* <dbl>, Anti-White <dbl>,
## # Anti-Black <dbl>, Anti-American Indian/Alaskan Native <dbl>,
## # Anti-Asian <dbl>, Anti-Native Hawaiian/Pacific Islander <dbl>,
## # Anti-Multi-Racial Groups <dbl>, Anti-Other Race <dbl>, Anti-Jewish <dbl>,
## # Anti-Catholic <dbl>, Anti-Protestant <dbl>, Anti-Islamic (Muslim) <dbl>,
## # Anti-Multi-Religious Groups <dbl>, Anti-Atheism/Agnosticism <dbl>,
## # Anti-Religious Practice Generally <dbl>, Anti-Other Religion <dbl>,
## # Anti-Buddhist <dbl>, Anti-Eastern Orthodox (Greek, Russian, etc.) <dbl>,
## # Anti-Hindu <dbl>, Anti-Jehovahs Witness <dbl>, Anti-Mormon <dbl>,
## # Anti-Other Christian <dbl>, Anti-Sikh <dbl>, Anti-Hispanic <dbl>,
## # Anti-Arab <dbl>, Anti-Other Ethnicity/National Origin <dbl>,
## # Anti-Non-Hispanic* <dbl>, Anti-Gay Male <dbl>, Anti-Gay Female <dbl>,
## # Anti-Gay (Male and Female) <dbl>, Anti-Heterosexual <dbl>,
## # Anti-Bisexual <dbl>, Anti-Physical Disability <dbl>,
## # Anti-Mental Disability <dbl>, Total Incidents <dbl>, Total Victims <dbl>,
## # Total Offenders <dbl>#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()
## .. )Use “summary” to look at the crime typed and select crime types to focus on
summary(hatecrimes)## county year crimetype anti-male
## Length:423 Min. :2010 Length:423 Min. :0.000000
## Class :character 1st Qu.:2011 Class :character 1st Qu.:0.000000
## Mode :character Median :2013 Mode :character Median :0.000000
## Mean :2013 Mean :0.007092
## 3rd Qu.:2015 3rd Qu.:0.000000
## Max. :2016 Max. :1.000000
## anti-female anti-transgender anti-genderidentityexpression
## Min. :0.00000 Min. :0.00000 Min. :0.00000
## 1st Qu.:0.00000 1st Qu.:0.00000 1st Qu.:0.00000
## Median :0.00000 Median :0.00000 Median :0.00000
## Mean :0.01655 Mean :0.04728 Mean :0.05674
## 3rd Qu.:0.00000 3rd Qu.:0.00000 3rd Qu.:0.00000
## Max. :1.00000 Max. :5.00000 Max. :3.00000
## anti-age* anti-white anti-black
## Min. :0.00000 Min. : 0.0000 Min. : 0.000
## 1st Qu.:0.00000 1st Qu.: 0.0000 1st Qu.: 0.000
## Median :0.00000 Median : 0.0000 Median : 1.000
## Mean :0.05201 Mean : 0.3357 Mean : 1.761
## 3rd Qu.:0.00000 3rd Qu.: 0.0000 3rd Qu.: 2.000
## Max. :9.00000 Max. :11.0000 Max. :18.000
## anti-americanindian/alaskannative anti-asian
## Min. :0.000000 Min. :0.0000
## 1st Qu.:0.000000 1st Qu.:0.0000
## Median :0.000000 Median :0.0000
## Mean :0.007092 Mean :0.1773
## 3rd Qu.:0.000000 3rd Qu.:0.0000
## Max. :1.000000 Max. :8.0000
## anti-nativehawaiian/pacificislander anti-multi-racialgroups anti-otherrace
## Min. :0 Min. :0.00000 Min. :0
## 1st Qu.:0 1st Qu.:0.00000 1st Qu.:0
## Median :0 Median :0.00000 Median :0
## Mean :0 Mean :0.08511 Mean :0
## 3rd Qu.:0 3rd Qu.:0.00000 3rd Qu.:0
## Max. :0 Max. :3.00000 Max. :0
## anti-jewish anti-catholic anti-protestant 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 :0.02364 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. :1.00000 Max. :10.0000
## anti-multi-religiousgroups anti-atheism/agnosticism
## Min. : 0.00000 Min. :0
## 1st Qu.: 0.00000 1st Qu.:0
## Median : 0.00000 Median :0
## Mean : 0.07565 Mean :0
## 3rd Qu.: 0.00000 3rd Qu.:0
## Max. :10.00000 Max. :0
## anti-religiouspracticegenerally anti-otherreligion anti-buddhist
## Min. :0.000000 Min. :0.000 Min. :0
## 1st Qu.:0.000000 1st Qu.:0.000 1st Qu.:0
## Median :0.000000 Median :0.000 Median :0
## Mean :0.007092 Mean :0.104 Mean :0
## 3rd Qu.:0.000000 3rd Qu.:0.000 3rd Qu.:0
## Max. :2.000000 Max. :4.000 Max. :0
## anti-easternorthodox(greek,russian,etc.) anti-hindu
## Min. :0.000000 Min. :0.000000
## 1st Qu.:0.000000 1st Qu.:0.000000
## Median :0.000000 Median :0.000000
## Mean :0.002364 Mean :0.002364
## 3rd Qu.:0.000000 3rd Qu.:0.000000
## Max. :1.000000 Max. :1.000000
## anti-jehovahswitness anti-mormon anti-otherchristian anti-sikh
## Min. :0 Min. :0 Min. :0.00000 Min. :0
## 1st Qu.:0 1st Qu.:0 1st Qu.:0.00000 1st Qu.:0
## Median :0 Median :0 Median :0.00000 Median :0
## Mean :0 Mean :0 Mean :0.01655 Mean :0
## 3rd Qu.:0 3rd Qu.:0 3rd Qu.:0.00000 3rd Qu.:0
## Max. :0 Max. :0 Max. :3.00000 Max. :0
## anti-hispanic anti-arab anti-otherethnicity/nationalorigin
## Min. : 0.0000 Min. :0.00000 Min. : 0.0000
## 1st Qu.: 0.0000 1st Qu.:0.00000 1st Qu.: 0.0000
## Median : 0.0000 Median :0.00000 Median : 0.0000
## Mean : 0.3735 Mean :0.06619 Mean : 0.2837
## 3rd Qu.: 0.0000 3rd Qu.:0.00000 3rd Qu.: 0.0000
## Max. :17.0000 Max. :2.00000 Max. :19.0000
## anti-non-hispanic* anti-gaymale anti-gayfemale anti-gay(maleandfemale)
## Min. :0 Min. : 0.000 Min. :0.0000 Min. :0.0000
## 1st Qu.:0 1st Qu.: 0.000 1st Qu.:0.0000 1st Qu.:0.0000
## Median :0 Median : 0.000 Median :0.0000 Median :0.0000
## Mean :0 Mean : 1.499 Mean :0.2411 Mean :0.1017
## 3rd Qu.:0 3rd Qu.: 1.000 3rd Qu.:0.0000 3rd Qu.:0.0000
## Max. :0 Max. :36.000 Max. :8.0000 Max. :4.0000
## anti-heterosexual anti-bisexual anti-physicaldisability
## Min. :0.000000 Min. :0.000000 Min. :0.00000
## 1st Qu.:0.000000 1st Qu.:0.000000 1st Qu.:0.00000
## Median :0.000000 Median :0.000000 Median :0.00000
## Mean :0.002364 Mean :0.004728 Mean :0.01182
## 3rd Qu.:0.000000 3rd Qu.:0.000000 3rd Qu.:0.00000
## Max. :1.000000 Max. :1.000000 Max. :1.00000
## anti-mentaldisability totalincidents totalvictims totaloffenders
## Min. :0.000000 Min. : 1.00 Min. : 1.00 Min. : 1.00
## 1st Qu.:0.000000 1st Qu.: 1.00 1st Qu.: 1.00 1st Qu.: 1.00
## Median :0.000000 Median : 3.00 Median : 3.00 Median : 3.00
## Mean :0.009456 Mean : 10.09 Mean : 10.48 Mean : 11.77
## 3rd Qu.:0.000000 3rd Qu.: 10.00 3rd Qu.: 10.00 3rd Qu.: 11.00
## Max. :1.000000 Max. :101.00 Max. :106.00 Max. :113.00Select and focus on these with a max incidence of 9 or more and put these in a new dataset, “hatecrimes”.
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 ##Also check the dimensions to count how many variables remain
dim(hatecrimes2)## [1] 423 10# There are currently 13 variables with 423 rows.
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##Use “head” to look at the top six rows.
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>##use "tail) to look at the bottom six rows
tail(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 Ulster 2010 1 0 0 0
## 2 Ulster 2010 0 0 0 1
## 3 Washington 2010 0 0 0 0
## 4 Wayne 2010 2 0 0 0
## 5 Westchester 2010 3 1 6 0
## 6 Westchester 2010 1 1 5 0
## # ... with 4 more variables: anti-age* <dbl>, anti-islamic(muslim) <dbl>,
## # anti-gaymale <dbl>, anti-hispanic <dbl>#Use Facet_Wrap ##Look at each set of hate-crimes for each type for each year. Use the package “tidyr” to convert the dataset from wide to long with the command “gather”. It will take each column’s hate-crime type combine them all into one column called “id”. Then each cell count will go into the new column, “crimecount”. Finally, we are only doing this for the quantitiative variables, which are in columns 3 - 10. Note the command facet_wrap requires (~) before “id”.
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. Create a new dataset “hatenew” for them.Grouped by year and county and lisetd in descending order.
##From the facet_wrap plot above, anti-black, anti-gay males, and anti-jewish categories seem to have highest rates of offenses reported. Filter out just for those 3 crimes.
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 ##Use the following commands to finalize your barplot: - position = “dodge” makes side-by-side bars, rather than stacked bars - stat = “identity” allows you to plot each set of bars for each year between 2010 and 2016 - ggtitle gives the plot a title - labs gives a title to the legend
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? ##I have not dealt with the counties, but I think that is the next place to explore. I can make bar graphs by county instead of by year.
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 ##There are too many counties for this plot to make sense, but maybe we can just look at the 5 counties with the highest number of incidents. - use “group_by” to group each row by counties - use summarize to get the total sum of incidents by county - use arrange(desc) to arrange those sums of total incidents by counties in descending order - use top_n to list the 5 counties with highest total incidents
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.summary(counties)## county year sum
## Length:277 Min. :2010 Min. : 0.00
## Class :character 1st Qu.:2011 1st Qu.: 1.00
## Mode :character Median :2013 Median : 2.00
## Mean :2013 Mean : 11.06
## 3rd Qu.:2015 3rd Qu.: 10.00
## Max. :2016 Max. :136.00print(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##Finally, create the barplot above, but only for the 5 counties in 2012 with the highest incidents of hate-crimes. The command “labs” is nice, because you can get a title, subtitle, y-axis label, and legend title, all in one command.
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? ##Bring in census data for populations of New York counties. These are estimates from the 2010 census.
setwd("C:/Documents - Copy/PERSONAL/Data 110_MC_Class")
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()
## )print(nypop)## # A tibble: 62 x 8
## Geography `2010` `2011` `2012` `2013` `2014` `2015` `2016`
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Albany County, New York 304078 305019 306384 307496 308295 3.08e5 3.09e5
## 2 Allegany County, New Y~ 48949 48818 48247 48005 47765 4.74e4 4.71e4
## 3 Bronx County, New York 1388240 1399990 1414774 1426550 1437687 1.45e6 1.46e6
## 4 Broome County, New York 200469 199459 198916 198370 197669 1.97e5 1.95e5
## 5 Cattaraugus County, Ne~ 80249 79839 79365 78958 78621 7.79e4 7.77e4
## 6 Cayuga County, New York 79844 79811 79637 79242 78857 7.83e4 7.79e4
## 7 Chautauqua County, New~ 134760 134266 133438 133005 131980 1.31e5 1.30e5
## 8 Chemung County, New Yo~ 88972 88988 89264 88498 87506 8.71e4 8.63e4
## 9 Chenango County, New Y~ 50371 50254 49919 49522 49432 4.90e4 4.86e4
## 10 Clinton County, New Yo~ 82068 81852 81869 81749 81682 8.12e4 8.11e4
## # ... with 52 more rows#Clean the county name to match the other dataset ##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 ##Since 2012 had the highest counts of hate crimes, let’s look at the populations of the counties in 2012.
##Clean the nypoplong12 variable, county, so that matches the counties12 variable by Cutting off the “, New York” portion of the county listing
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##Not surprisingly, 4/5 of the counties with the highest populations also were listed in the counties with the highest number of hate crimes. Only the Bronx, which has the fifth highest population is not in the list with the highest number of total hate crimes over the period from 2010 to 2016.
#Recall the total hate crime counts: #Kings 713 #New York 459 #Suffolk 360 #Nassau 298 #Queens 235
#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#But the highest populated counties were: Kings (Brooklyn), Queens, New York, Suffolk (Long Island), Bronx, and Nassau. They do not correspond directly, though they are similar, to the counties with highest rates of hate crimes.
#So what does all of this mean? #Important Findings: ##I wonder what the data would look like if there was a universally accepted requirement for this type of data collection.
##The Bronx appears to have much lower than expected incidents of hate crimes relative to its population density in comparison to other NY counties.
##In Kings County, NY (which is home to Brooklyn; according to Wikipedia, it is New York’s most populous borough and the second most densly populated county in the US) in 2012, there was a spike in hate crimes against jews.
##All of these findings are corroborated in Hate Crime in New York State 2012 Annual Report: https://www.criminaljustice.ny.gov/crimnet/ojsa/hate-crime-in-nys-2012-annual-report.pdf