library(tidyverse)
## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.1 ──
## ✓ ggplot2 3.3.3 ✓ purrr 0.3.4
## ✓ tibble 3.1.2 ✓ dplyr 1.0.6
## ✓ tidyr 1.1.3 ✓ stringr 1.4.0
## ✓ readr 1.4.0 ✓ forcats 0.5.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
## install tinytex
library(tinytex)
setwd("~/Desktop/rsconnect/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.
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 headers
names(hatecrimes) <- tolower(names(hatecrimes))
names(hatecrimes) <- gsub(" ", "",names(hatecrimes))
str(hatecrimes)
## spec_tbl_df [423 × 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()
## .. )
#summary(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>
## checking dimensions
dim(hatecrimes2)
## [1] 423 10
## summary(hatecrimes2h)
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
## `summarise()` regrouping output by 'county' (override with `.groups` argument)
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("~/Desktop/rsconnect/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()
## )
## newyorkpopulation
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