Here is my script:
#install.packages("tidyverse")
#install.packages("tidycensus")
library(tidyverse)
## Warning: package 'tidyverse' was built under R version 4.2.3
## Warning: package 'ggplot2' was built under R version 4.3.2
## Warning: package 'tibble' was built under R version 4.3.2
## Warning: package 'tidyr' was built under R version 4.3.2
## Warning: package 'readr' was built under R version 4.3.2
## Warning: package 'purrr' was built under R version 4.3.2
## Warning: package 'dplyr' was built under R version 4.3.2
## Warning: package 'stringr' was built under R version 4.3.2
## Warning: package 'forcats' was built under R version 4.3.2
## Warning: package 'lubridate' was built under R version 4.3.2
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.4.4 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.0
## ✔ purrr 1.0.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(tidycensus)
## Warning: package 'tidycensus' was built under R version 4.2.3
#census_api_key("0dsaf8-adf8-a0dsf-a0ds8fa-0dsf8-a0ds8f")
mydata <- get_acs(
geography = "county subdivision",
state = "TN",
variables = c(MyVar_ = "DP04_0142P"),
year = 2022,
survey = "acs5",
output = "wide")
## Getting data from the 2018-2022 5-year ACS
## Using the ACS Data Profile
mydata <-
separate_wider_delim(mydata,
NAME,
delim = ", ",
names = c("District", "County", "State"))
mydata <- filter(
mydata,
County == "Davidson County" |
County == "Cheatham County" |
County == "Robertson County" |
County == "Rutherford County" |
County == "Sumner County" |
County == "Williamson County" |
County == "Wilson County")
write.csv(mydata, "mydata.csv", row.names = FALSE)
head(mydata, 10)
## # A tibble: 10 × 6
## GEOID District County State MyVar_E MyVar_M
## <chr> <chr> <chr> <chr> <dbl> <dbl>
## 1 4702190022 District 1 Cheatham County Tennessee 31.4 12.3
## 2 4702190212 District 2 Cheatham County Tennessee 34.7 23
## 3 4702190402 District 3 Cheatham County Tennessee 27.9 18
## 4 4702190592 District 4 Cheatham County Tennessee 22.6 17.5
## 5 4702190782 District 5 Cheatham County Tennessee 36.9 17.9
## 6 4702190972 District 6 Cheatham County Tennessee 8.1 10.4
## 7 4703790038 District 1 Davidson County Tennessee 39.7 16.9
## 8 4703790228 District 2 Davidson County Tennessee 39.3 8.4
## 9 4703790418 District 3 Davidson County Tennessee 52.6 13.3
## 10 4703790608 District 4 Davidson County Tennessee 25.6 7.9
mydata <- filter(
mydata,
County == "Rutherford County")
mydata <- arrange(mydata, desc(MyVar_E))
write.csv(mydata, "mydata.csv", row.names = FALSE)