Week 10 Lab
Dylan Simmons
2024-03-22
# Installing and loading required packages
if (!require("tidyverse")) install.packages("tidyverse")## Loading required package: tidyverse## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.4.4 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.1
## ✔ 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 errorsif (!require("tidycensus")) install.packages("tidycensus")## Loading required package: tidycensusif (!require("sf")) install.packages("sf")## Loading required package: sf
## Linking to GEOS 3.11.0, GDAL 3.5.3, PROJ 9.1.0; sf_use_s2() is TRUEif (!require("mapview")) install.packages("mapview")## Loading required package: mapviewlibrary(tidyverse)
library(tidycensus)
library(sf)
library(mapview)
# Transmitting API key
census_api_key("33060ddff9e66f647b10ef7b540ab19f3dd5e9c4")## To install your API key for use in future sessions, run this function with `install = TRUE`.# Fetching ACS codebooks
DetailedTables <- load_variables(2022, "acs5", cache = TRUE)
SubjectTables <- load_variables(2022, "acs5/subject", cache = TRUE)
ProfileTables <- load_variables(2022, "acs5/profile", cache = TRUE)
# Double checking target variables
ChosenVars <- filter(ProfileTables,name == "DP04_0063P"|
name == "DP02_0001")
print(ChosenVars$name)## [1] "DP02_0001" "DP04_0063P"print(ChosenVars$label)## [1] "Estimate!!HOUSEHOLDS BY TYPE!!Total households"
## [2] "Percent!!HOUSE HEATING FUEL!!Occupied housing units!!Utility gas"print(ChosenVars$concept)## [1] "Selected Social Characteristics in the United States"
## [2] "Selected Housing Characteristics"# Specifying target variables
VariableList =
c(Gas_ = "DP04_0063P",
Households_ = "DP02_0001")
# Fetching data
mydata <- get_acs(
geography = "county",
state = "TN",
variables = VariableList,
year = 2022,
survey = "acs5",
output = "wide",
geometry = TRUE)## Getting data from the 2018-2022 5-year ACS
## Downloading feature geometry from the Census website. To cache shapefiles for use in future sessions, set `options(tigris_use_cache = TRUE)`.
## Using the ACS Data Profile##
|
| | 0%
|
| | 1%
|
|= | 1%
|
|= | 2%
|
|== | 2%
|
|== | 3%
|
|=== | 4%
|
|=== | 5%
|
|==== | 6%
|
|===== | 7%
|
|===== | 8%
|
|====== | 8%
|
|====== | 9%
|
|======= | 9%
|
|======= | 10%
|
|======= | 11%
|
|======== | 11%
|
|======== | 12%
|
|========= | 12%
|
|========= | 13%
|
|========== | 14%
|
|========== | 15%
|
|=========== | 15%
|
|=========== | 16%
|
|============ | 17%
|
|============ | 18%
|
|============= | 18%
|
|============= | 19%
|
|============== | 19%
|
|============== | 20%
|
|============== | 21%
|
|=============== | 21%
|
|=============== | 22%
|
|================ | 22%
|
|================ | 23%
|
|================ | 24%
|
|================= | 24%
|
|================= | 25%
|
|================== | 26%
|
|=================== | 26%
|
|=================== | 27%
|
|=================== | 28%
|
|==================== | 28%
|
|==================== | 29%
|
|===================== | 29%
|
|===================== | 30%
|
|===================== | 31%
|
|====================== | 31%
|
|====================== | 32%
|
|======================= | 33%
|
|======================== | 34%
|
|======================== | 35%
|
|========================= | 35%
|
|========================= | 36%
|
|========================== | 37%
|
|========================== | 38%
|
|=========================== | 38%
|
|=========================== | 39%
|
|============================ | 39%
|
|============================ | 40%
|
|============================ | 41%
|
|============================= | 41%
|
|============================= | 42%
|
|============================== | 42%
|
|============================== | 43%
|
|=============================== | 44%
|
|=============================== | 45%
|
|================================ | 46%
|
|================================= | 47%
|
|================================= | 48%
|
|================================== | 48%
|
|================================== | 49%
|
|=================================== | 50%
|
|==================================== | 51%
|
|==================================== | 52%
|
|===================================== | 52%
|
|===================================== | 53%
|
|===================================== | 54%
|
|====================================== | 54%
|
|======================================= | 55%
|
|======================================= | 56%
|
|======================================== | 56%
|
|======================================== | 57%
|
|======================================== | 58%
|
|========================================= | 58%
|
|========================================= | 59%
|
|========================================== | 59%
|
|========================================== | 60%
|
|========================================== | 61%
|
|=========================================== | 61%
|
|=========================================== | 62%
|
|============================================ | 62%
|
|============================================ | 63%
|
|============================================= | 64%
|
|============================================= | 65%
|
|============================================== | 65%
|
|============================================== | 66%
|
|=============================================== | 66%
|
|=============================================== | 67%
|
|=============================================== | 68%
|
|================================================ | 68%
|
|================================================ | 69%
|
|================================================= | 70%
|
|================================================== | 71%
|
|================================================== | 72%
|
|=================================================== | 72%
|
|=================================================== | 73%
|
|==================================================== | 74%
|
|===================================================== | 75%
|
|========================================================= | 81%
|
|========================================================= | 82%
|
|========================================================== | 82%
|
|========================================================== | 83%
|
|=========================================================== | 84%
|
|=========================================================== | 85%
|
|============================================================ | 85%
|
|============================================================ | 86%
|
|============================================================= | 87%
|
|============================================================== | 88%
|
|============================================================== | 89%
|
|=============================================================== | 90%
|
|================================================================ | 91%
|
|================================================================ | 92%
|
|================================================================= | 93%
|
|================================================================== | 94%
|
|================================================================== | 95%
|
|=================================================================== | 95%
|
|=================================================================== | 96%
|
|==================================================================== | 97%
|
|===================================================================== | 98%
|
|===================================================================== | 99%
|
|======================================================================| 100%# Reformatting data
mydata <-
separate_wider_delim(mydata,
NAME,
delim = ", ",
names = c("County", "State"))
# Filtering data
filtereddata <- mydata %>%
filter(County == "Davidson County"|
County == "Rutherford County"|
County == "Williamson County"|
County == "Cheatham County"|
County == "Robertson County"|
County == "Sumner County"|
County == "Wilson County")
# Plotting data
ggplot(filtereddata, aes(x = Gas_E, y = reorder(County, Gas_E))) +
geom_errorbarh(aes(xmin = Gas_E - Gas_M, xmax = Gas_E + Gas_M)) +
geom_point(size = 3, color = "darkblue") +
theme_minimal(base_size = 12.5) +
labs(title = "Pct. households with gas heat",
subtitle = "Nashville-area counties. Brackets show error margins.",
x = "2018-2022 ACS estimate",
y = "")
# Mapping data
mapdata <- filtereddata %>%
rename(Gas = Gas_E,
Households = Households_E)
mapdata <- st_as_sf(mapdata)
mapviewOptions(basemaps.color.shuffle = FALSE)
mapview(mapdata, zcol = "Gas",
layer.name = "Pct. with gas heat",
popup = TRUE)# Exporting data in .csv format
CSVdata <- st_drop_geometry(mapdata)
write.csv(CSVdata, "mydata.csv", row.names = FALSE)