Intro Stuff
##install.packages("tidyverse")
library(tidyverse)
## -- Attaching packages -------------------------------------------------------------------------------- tidyverse 1.3.0 --
## v ggplot2 3.3.2 v purrr 0.3.4
## v tibble 3.0.1 v dplyr 1.0.0
## v tidyr 1.1.0 v stringr 1.4.0
## v readr 1.3.1 v forcats 0.5.0
## -- Conflicts ----------------------------------------------------------------------------------- tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
##setwd("C:Users/Jerome/Documents/From_Toshiba_HD_Work_Files/0000_Montgomery_College/Data_Science_110/Datasets")
getwd()
## [1] "C:/Users/Jerome/Documents/Data_Science_110/Datasets"
setwd("C:/Users/Jerome/Documents/Data_Science_110/Datasets")
getwd()
## [1] "C:/Users/Jerome/Documents/Data_Science_110/Datasets"
hatecrimes <-read_csv("hateCrimes.csv")
## Parsed with column specification:
## cols(
## .default = col_double(),
## county = col_character(),
## crimetype = col_character()
## )
## See spec(...) for full column specifications.
Clean the Data
names(hatecrimes) <-tolower(names(hatecrimes))
names(hatecrimes)<-gsub(" ", "",names(hatecrimes))
str(hatecrimes)
## tibble [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(),
## .. crimetype = col_character(),
## .. `anti-male` = col_double(),
## .. `anti-female` = col_double(),
## .. `anti-transgender` = col_double(),
## .. `anti-genderidentityexpression` = col_double(),
## .. `anti-age*` = col_double(),
## .. `anti-white` = col_double(),
## .. `anti-black` = col_double(),
## .. `anti-americanindian/alaskannative` = col_double(),
## .. `anti-asian` = col_double(),
## .. `anti-nativehawaiian/pacificislander` = col_double(),
## .. `anti-multi-racialgroups` = col_double(),
## .. `anti-otherrace` = col_double(),
## .. `anti-jewish` = col_double(),
## .. `anti-catholic` = col_double(),
## .. `anti-protestant` = col_double(),
## .. `anti-islamic(muslim)` = col_double(),
## .. `anti-multi-religiousgroups` = col_double(),
## .. `anti-atheism/agnosticism` = col_double(),
## .. `anti-religiouspracticegenerally` = col_double(),
## .. `anti-otherreligion` = col_double(),
## .. `anti-buddhist` = col_double(),
## .. `anti-easternorthodox(greek,russian,etc.)` = col_double(),
## .. `anti-hindu` = col_double(),
## .. `anti-jehovahswitness` = col_double(),
## .. `anti-mormon` = col_double(),
## .. `anti-otherchristian` = col_double(),
## .. `anti-sikh` = col_double(),
## .. `anti-hispanic` = col_double(),
## .. `anti-arab` = col_double(),
## .. `anti-otherethnicity/nationalorigin` = col_double(),
## .. `anti-non-hispanic*` = col_double(),
## .. `anti-gaymale` = col_double(),
## .. `anti-gayfemale` = col_double(),
## .. `anti-gay(maleandfemale)` = col_double(),
## .. `anti-heterosexual` = col_double(),
## .. `anti-bisexual` = col_double(),
## .. `anti-physicaldisability` = col_double(),
## .. `anti-mentaldisability` = col_double(),
## .. totalincidents = col_double(),
## .. totalvictims = col_double(),
## .. totaloffenders = col_double()
## .. )
write_csv(hatecrimes,"hatecrimes.csv")
str(hatecrimes)
## tibble [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(),
## .. crimetype = col_character(),
## .. `anti-male` = col_double(),
## .. `anti-female` = col_double(),
## .. `anti-transgender` = col_double(),
## .. `anti-genderidentityexpression` = col_double(),
## .. `anti-age*` = col_double(),
## .. `anti-white` = col_double(),
## .. `anti-black` = col_double(),
## .. `anti-americanindian/alaskannative` = col_double(),
## .. `anti-asian` = col_double(),
## .. `anti-nativehawaiian/pacificislander` = col_double(),
## .. `anti-multi-racialgroups` = col_double(),
## .. `anti-otherrace` = col_double(),
## .. `anti-jewish` = col_double(),
## .. `anti-catholic` = col_double(),
## .. `anti-protestant` = col_double(),
## .. `anti-islamic(muslim)` = col_double(),
## .. `anti-multi-religiousgroups` = col_double(),
## .. `anti-atheism/agnosticism` = col_double(),
## .. `anti-religiouspracticegenerally` = col_double(),
## .. `anti-otherreligion` = col_double(),
## .. `anti-buddhist` = col_double(),
## .. `anti-easternorthodox(greek,russian,etc.)` = col_double(),
## .. `anti-hindu` = col_double(),
## .. `anti-jehovahswitness` = col_double(),
## .. `anti-mormon` = col_double(),
## .. `anti-otherchristian` = col_double(),
## .. `anti-sikh` = col_double(),
## .. `anti-hispanic` = col_double(),
## .. `anti-arab` = col_double(),
## .. `anti-otherethnicity/nationalorigin` = col_double(),
## .. `anti-non-hispanic*` = col_double(),
## .. `anti-gaymale` = col_double(),
## .. `anti-gayfemale` = col_double(),
## .. `anti-gay(maleandfemale)` = col_double(),
## .. `anti-heterosexual` = col_double(),
## .. `anti-bisexual` = col_double(),
## .. `anti-physicaldisability` = col_double(),
## .. `anti-mentaldisability` = col_double(),
## .. totalincidents = col_double(),
## .. totalvictims = col_double(),
## .. totaloffenders = col_double()
## .. )
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 Alleg~ 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>
dim(hatecrimes2)
## [1] 423 10
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
write_csv (hatecrimes2, "hatecrimes2.csv")
##install.packages("reshape2")
library(reshape2)
##
## Attaching package: 'reshape2'
## The following object is masked from 'package:tidyr':
##
## smiths
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
write_csv(hatenew, "hatenew_csv")
Plot 3 types of hate crimes together
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
Bar Plot by County
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
Five Counties w/ HIghest # of Incidents
counties <- hatenew %>%
group_by(county, year)%>%
summarize(sum = sum(crimecount)) %>%
arrange(desc(sum))
## `summarise()` regrouping output by 'county' (override with `.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
write_csv(counties, "counties_csv")
Five Counties, Highest # of Incidents in 2012
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
nypop <- read_csv("newyorkpopulation.csv")
## Parsed with 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()
## )
library(tidyverse)
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
Work with only 2012
nypoplong12 <- nypoplong %>%
filter(year == 2012) %>%
arrange(desc(population)) %>%
head(10)
nypoplong12
## # A tibble: 10 x 3
## county year population
## <chr> <dbl> <dbl>
## 1 Kings , New York 2012 2572282
## 2 Queens , New York 2012 2278024
## 3 New York , New York 2012 1625121
## 4 Suffolk , New York 2012 1499382
## 5 Bronx , New York 2012 1414774
## 6 Nassau , New York 2012 1350748
## 7 Westchester , New York 2012 961073
## 8 Erie , New York 2012 920792
## 9 Monroe , New York 2012 748947
## 10 Richmond , New York 2012 470978
Filter hate crimes for just 2012
read_csv("counties.csv")
## Parsed with column specification:
## cols(
## `county,year,sum` = col_character()
## )
## # A tibble: 277 x 1
## `county,year,sum`
## <chr>
## 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
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 Hate Crimes w/ NY Pop Data
datajoin <- counties12 %>%
full_join(nypoplong12, by=c("county","year"))
datajoin
## # A tibble: 51 x 4
## # Groups: county [51]
## county year sum population
## <chr> <dbl> <dbl> <dbl>
## 1 Kings 2012 136 NA
## 2 Suffolk 2012 83 NA
## 3 New York 2012 71 NA
## 4 Nassau 2012 48 NA
## 5 Queens 2012 48 NA
## 6 Erie 2012 28 NA
## 7 Bronx 2012 23 NA
## 8 Richmond 2012 18 NA
## 9 Multiple 2012 14 NA
## 10 Westchester 2012 13 NA
## # ... with 41 more rows
Calc rate of incidents/100,000. Arrange descending.
datajoinrate <- datajoin %>%
mutate(rate = sum/population*100000) %>%
arrange(desc(rate))
datajoinrate
## # A tibble: 51 x 5
## # Groups: county [51]
## county year sum population rate
## <chr> <dbl> <dbl> <dbl> <dbl>
## 1 Kings 2012 136 NA NA
## 2 Suffolk 2012 83 NA NA
## 3 New York 2012 71 NA NA
## 4 Nassau 2012 48 NA NA
## 5 Queens 2012 48 NA NA
## 6 Erie 2012 28 NA NA
## 7 Bronx 2012 23 NA NA
## 8 Richmond 2012 18 NA NA
## 9 Multiple 2012 14 NA NA
## 10 Westchester 2012 13 NA NA
## # ... with 41 more rows
dt <- datajoinrate[,c("county","rate")]
dt
## # A tibble: 51 x 2
## # Groups: county [51]
## county rate
## <chr> <dbl>
## 1 Kings NA
## 2 Suffolk NA
## 3 New York NA
## 4 Nassau NA
## 5 Queens NA
## 6 Erie NA
## 7 Bronx NA
## 8 Richmond NA
## 9 Multiple NA
## 10 Westchester NA
## # ... with 41 more rows