Income across Nashville-area counties

This project uses American Community Survey data from the U.S. Census Bureau to show what the median household income across Davidson County and the counties that surround it.

Census Data Analysis

############################################################
# STEP 1: Load Packages
############################################################

if (!require("tidycensus")) install.packages("tidycensus")
if (!require("tidyverse")) install.packages("tidyverse")
if (!require("kableExtra")) install.packages("kableExtra")
if (!require("sf")) install.packages("sf")
if (!require("leaflet")) install.packages("leaflet")
if (!require("htmlwidgets")) install.packages("htmlwidgets")
if (!require("plotly")) install.packages("plotly")

library(tidycensus)
library(tidyverse)
library(kableExtra)
library(sf)
library(leaflet)
library(htmlwidgets)
library(plotly)

############################################################
# STEP 2: Verify Census API Key
############################################################

if (!nzchar(Sys.getenv("CENSUS_API_KEY"))) {

  stop(
    paste(
      "\nNo Census API key was found.",
      "\n\nTo obtain a free Census API key, visit:",
      "\nhttps://api.census.gov/data/key_signup.html",
      "\n\nAfter obtaining your key, run the",
      "\none-time setup code shown above.",
      "\n"
    )
  )

}

############################################################
# STEP 3: Configure Your Analysis
############################################################

# ACS year

acs_year <- 2024

# State abbreviation

state_abbrev <- "TN"

# ACS variable

# Examples:
# DP05_0001  = Total population
# DP03_0062  = Median Household Income
# DP03_0128P = Poverty Rate
# DP02_0068P = Bachelor's Degree or Higher Rate
# DP05_0018  = Median Age
# DP04_0046P = Homeownership Rate
# DP04_0134  = Median Gross Rent
# DP04_0142P = Rent Burden Rate
# DP05_0090P = Hispanic or Latino Population Percentage
# DP02_0094P = Foreign-Born Percentage
# DP03_0009P = Unemployment Rate
# DP03_0025  = Average Commute Time

my_variable <- "DP03_0062"

# Geography level

# Recommended ACS geography options:
# "county"
# "county subdivision"
# "tract"

geography_level <- "county"

# County filter

# Use NULL to include all counties in the state.

# Examples:
# selected_counties <- NULL
# selected_counties <- "Rutherford"
# selected_counties <- c(
#   "Davidson",
#   "Rutherford",
#   "Williamson",
#   "Cheatham",
#   "Robertson",
#   "Sumner",
#   "Wilson"
# )

selected_counties <- c(
  "Davidson",
  "Rutherford",
  "Williamson",
  "Cheatham",
  "Robertson",
  "Sumner",
  "Wilson"
)

############################################################
# STEP 4: Explore ACS Codebooks (Optional)
############################################################

ProfileTables <- load_variables(
  acs_year,
  "acs5/profile"
)

# DetailedTables <- load_variables(
#   acs_year,
#   "acs5"
# )

# SubjectTables <- load_variables(
#   acs_year,
#   "acs5/subject"
# )

############################################################
# STEP 5: Download ACS Data
############################################################

if (is.null(selected_counties)) {

  mydata <- get_acs(
    geography = geography_level,
    state = state_abbrev,
    year = acs_year,
    survey = "acs5",
    variables = my_variable,
    geometry = TRUE
  )

} else {

  mydata <- get_acs(
    geography = geography_level,
    state = state_abbrev,
    county = selected_counties,
    year = acs_year,
    survey = "acs5",
    variables = my_variable,
    geometry = TRUE
  )

}

############################################################
# STEP 6: Keep Needed Variables and Geometry
############################################################

mydata <- mydata |>
  select(
    Area = NAME,
    Variable = variable,
    Estimate = estimate,
    Margin_of_Error = moe,
    geometry
  )

############################################################
# STEP 7: Transform Coordinates for Leaflet
############################################################

mydata <- st_transform(
  mydata,
  crs = 4326
)

############################################################
# STEP 8: Download County Boundaries (Optional Overlay)
############################################################

if (is.null(selected_counties)) {

  county_boundaries <- get_acs(
    geography = "county",
    state = state_abbrev,
    year = acs_year,
    survey = "acs5",
    variables = my_variable,
    geometry = TRUE
  )

} else {

  county_boundaries <- get_acs(
    geography = "county",
    state = state_abbrev,
    county = selected_counties,
    year = acs_year,
    survey = "acs5",
    variables = my_variable,
    geometry = TRUE
  )

}

county_boundaries <- st_transform(
  county_boundaries,
  4326
)

############################################################
# STEP 9: Sort Results from Highest to Lowest
############################################################

mydata <- mydata |>
  arrange(desc(Estimate))

############################################################
# STEP 10: Display Results as a Table
############################################################

ResultsTable <- mydata |>
  st_drop_geometry() |>
  kbl(
    col.names = c(
      "Area",
      "Variable",
      "Estimate",
      "Margin of Error"
    ),
    format.args = list(big.mark = ",")
  ) |>
  kable_styling(
    bootstrap_options = c("striped", "hover"),
    full_width = FALSE
  )

############################################################
# STEP 11: Create Pop-Up Content
############################################################

mydata$popup <- paste0(
  "<strong>", mydata$Area, "</strong>",
  "<br><br>",
  "Estimate: ",
  format(mydata$Estimate, big.mark = ","),
  "<br>",
  "Plus/Minus: ",
  format(mydata$Margin_of_Error, big.mark = ",")
)

############################################################
# STEP 12: Build Color Palette
############################################################

qs <- unique(
  quantile(
    mydata$Estimate,
    probs = seq(0, 1, length.out = 6),
    na.rm = TRUE
  )
)

pal <- colorBin(
  palette = "Blues",
  domain = mydata$Estimate,
  bins = qs,
  pretty = FALSE
)

############################################################
# STEP 13: Create Choropleth Map
############################################################

AreaMap <- leaflet(mydata) |>
  addProviderTiles(
    providers$Esri.WorldTopoMap
  ) |>
  addPolygons(
    fillColor = ~pal(Estimate),
    fillOpacity = 0.5,
    color = "black",
    weight = 1,
    popup = ~popup
  )

# Optional county boundary overlay for
# sub-county geographies

if (geography_level != "county") {

  AreaMap <- AreaMap |>
    addPolygons(
      data = county_boundaries,
      fill = FALSE,
      color = "black",
      weight = 2,
      opacity = 1,
      group = "County Boundaries"
    )

}

AreaMap <- AreaMap |>
  addLegend(
    pal = pal,
    values = ~Estimate,
    title = "Estimate",
    labFormat = labelFormat(
      big.mark = ","
    )
  )

############################################################
# STEP 14: Create Plotly Dot Plot
############################################################

plotdf <- mydata |>
  st_drop_geometry() |>
  mutate(
    point_color = pal(Estimate),

    y_ordered = reorder(
      Area,
      Estimate
    ),

    hover_text = paste0(
      Area,
      "\nEstimate: ",
      format(Estimate, big.mark = ","),
      "\nPlus/Minus: ",
      format(Margin_of_Error, big.mark = ",")
    )
  )

DotPlot <- plot_ly(
  data = plotdf,
  x = ~Estimate,
  y = ~as.character(y_ordered),
  type = "scatter",
  mode = "markers",
  showlegend = FALSE,
  marker = list(
    color = ~point_color,
    size = 8,
    line = list(
      color = "rgba(120,120,120,0.9)",
      width = 0.5
    )
  ),
  error_x = list(
    type = "data",
    array = ~Margin_of_Error,
    arrayminus = ~Margin_of_Error,
    color = "rgba(0,0,0,0.65)",
    thickness = 1
  ),
  text = ~hover_text,
  hovertemplate = "%{text}"
) |>
  layout(
    title = list(
      text = paste0(
        "ACS Estimates by Geography",
        "\nError bars show ACS margins of error."
      )
    ),
    xaxis = list(
      title = "Estimate",
      tickformat = ",.0f",
      automargin = TRUE
    ),
    yaxis = list(
      title = "",
      automargin = TRUE,
      categoryorder = "array",
      categoryarray = levels(plotdf$y_ordered)
    ),
    margin = list(
      l = 200,
      r = 20,
      b = 60,
      t = 60,
      pad = 2
    )
  )

############################################################
# STEP 15: Export Dot Plot (Optional)
############################################################

saveWidget(
  widget = as_widget(DotPlot),
  file = "ACSGraph.html",
  selfcontained = TRUE
)

############################################################
# STEP 16: Export Map (Optional)
############################################################

saveWidget(
  widget = AreaMap,
  file = "ACSMap.html",
  selfcontained = TRUE
)

############################################################
# STEP 17: Show output
############################################################

DotPlot # The dot plot with error bars
AreaMap # The map
# Display the results table

ResultsTable
Area Variable Estimate Margin of Error
Williamson County, Tennessee DP03_0062 135,594 4,044
Wilson County, Tennessee DP03_0062 95,839 3,023
Sumner County, Tennessee DP03_0062 90,301 2,629
Cheatham County, Tennessee DP03_0062 89,852 6,619
Rutherford County, Tennessee DP03_0062 85,470 1,909
Robertson County, Tennessee DP03_0062 83,047 4,193
Davidson County, Tennessee DP03_0062 77,853 1,253

R Code

The following R code was used.

Click to view the complete R code
# Step 1: Load packages

library(tidycensus)
library(tidyverse)
library(kableExtra)
library(sf)
library(leaflet)
library(htmlwidgets)
library(plotly)


# Step 2: Verify Census API key

Sys.getenv("CENSUS_API_KEY")


# Step 3: Configure analysis

acs_year <- 2024

selected_counties <- c(
  "Davidson",
  "Rutherford",
  "Williamson",
  "Cheatham",
  "Robertson",
  "Sumner",
  "Wilson"
)


# Step 4: Load ACS variable information

acs_variables <- load_variables(
  acs_year,
  "acs5/profile"
)


# Step 5: Download ACS data

CountyData <- get_acs(
  geography = "county",
  variables = "DP03_0062",
  year = acs_year,
  survey = "acs5/profile",
  state = "TN",
  county = selected_counties,
  geometry = TRUE
)


# Step 6: Select and rename columns

CountyData <- CountyData %>%
  select(
    NAME,
    estimate,
    moe,
    geometry
  ) %>%
  rename(
    County = NAME,
    MedianIncome = estimate,
    MarginOfError = moe
  )


# Step 7: Transform coordinate reference system

CountyData <- st_transform(
  CountyData,
  crs = 4326
)


# Step 8: Download county boundaries

CountyBoundaries <- CountyData %>%
  select(County, geometry)


# Step 9: Arrange counties by median household income

CountyData <- CountyData %>%
  arrange(desc(MedianIncome))


# Step 10: Create results table

ResultsTable <- CountyData %>%
  st_drop_geometry() %>%
  select(
    County,
    MedianIncome,
    MarginOfError
  ) %>%
  kbl(
    caption = "Median Household Income by County",
    col.names = c(
      "County",
      "Median Household Income",
      "Margin of Error"
    ),
    digits = 0
  ) %>%
  kable_styling(
    bootstrap_options = c(
      "striped",
      "hover",
      "condensed"
    ),
    full_width = FALSE
  )


# Step 11: Create map popup content

CountyData$popup <- paste0(
  "<strong>",
  CountyData$County,
  "</strong><br>",
  "Median Household Income: $",
  format(
    CountyData$MedianIncome,
    big.mark = ","
  )
)


# Step 12: Create color palette

pal <- colorBin(
  palette = "YlGnBu",
  domain = CountyData$MedianIncome,
  bins = 5
)


# Step 13: Create interactive county map

AreaMap <- leaflet(CountyData) %>%
  addProviderTiles("CartoDB.Positron") %>%
  addPolygons(
    fillColor = ~pal(MedianIncome),
    weight = 2,
    opacity = 1,
    color = "white",
    fillOpacity = 0.7,
    popup = ~popup
  ) %>%
  addLegend(
    pal = pal,
    values = ~MedianIncome,
    title = "Median Household Income",
    position = "bottomright",
    labFormat = labelFormat(
      prefix = "$",
      big.mark = ","
    )
  )


# Step 14: Create interactive dot plot

DotPlot <- plot_ly(
  data = CountyData,
  x = ~MedianIncome,
  y = ~reorder(County, MedianIncome),
  type = "scatter",
  mode = "markers",
  error_x = list(
    type = "data",
    array = ~MarginOfError,
    visible = TRUE
  )
) %>%
  layout(
    title = "Median Household Income by County",
    xaxis = list(
      title = "Median Household Income",
      tickprefix = "$",
      separatethousands = TRUE
    ),
    yaxis = list(
      title = "County"
    )
  )


# Step 15: Save interactive dot plot

saveWidget(
  DotPlot,
  "ACSGraph.html",
  selfcontained = TRUE
)


# Step 16: Save interactive county map

saveWidget(
  AreaMap,
  "ACSMap.html",
  selfcontained = TRUE
)


# Step 17: Display results

DotPlot

AreaMap

ResultsTable