library(tidyverse)
library(tidyr)
setwd("~/Desktop/DATA/Data Visualization 110/DataSets")
cities500 <- read_csv("500CitiesLocalHealthIndicators.cdc.csv")
data(cities500)Healthy Cities GIS Assignment
Load the libraries and set the working directory
The GeoLocation variable has (lat, long) format
Split GeoLocation (lat, long) into two columns: lat and long
latlong <- cities500|>
mutate(GeoLocation = str_replace_all(GeoLocation, "[()]", ""))|>
separate(GeoLocation, into = c("lat", "long"), sep = ",", convert = TRUE)
head(latlong)# A tibble: 6 × 25
Year StateAbbr StateDesc CityName GeographicLevel DataSource Category
<dbl> <chr> <chr> <chr> <chr> <chr> <chr>
1 2017 CA California Hawthorne Census Tract BRFSS Health Outcom…
2 2017 CA California Hawthorne City BRFSS Unhealthy Beh…
3 2017 CA California Hayward City BRFSS Health Outcom…
4 2017 CA California Hayward City BRFSS Unhealthy Beh…
5 2017 CA California Hemet City BRFSS Prevention
6 2017 CA California Indio Census Tract BRFSS Health Outcom…
# ℹ 18 more variables: UniqueID <chr>, Measure <chr>, Data_Value_Unit <chr>,
# DataValueTypeID <chr>, Data_Value_Type <chr>, Data_Value <dbl>,
# Low_Confidence_Limit <dbl>, High_Confidence_Limit <dbl>,
# Data_Value_Footnote_Symbol <chr>, Data_Value_Footnote <chr>,
# PopulationCount <dbl>, lat <dbl>, long <dbl>, CategoryID <chr>,
# MeasureId <chr>, CityFIPS <dbl>, TractFIPS <dbl>, Short_Question_Text <chr>Filter the dataset
Remove the StateDesc that includes the United Sates, select Prevention as the category (of interest), filter for only measuring crude prevalence and select only 2017.
latlong_clean <- latlong |>
filter(StateDesc != "United States") |>
filter(Data_Value_Type == "Crude prevalence") |>
filter(Year == 2017)
head(latlong_clean)# A tibble: 6 × 25
Year StateAbbr StateDesc CityName GeographicLevel DataSource Category
<dbl> <chr> <chr> <chr> <chr> <chr> <chr>
1 2017 CA California Hawthorne Census Tract BRFSS Health Outcom…
2 2017 CA California Hawthorne City BRFSS Unhealthy Beh…
3 2017 CA California Hayward City BRFSS Unhealthy Beh…
4 2017 CA California Indio Census Tract BRFSS Health Outcom…
5 2017 CA California Inglewood Census Tract BRFSS Health Outcom…
6 2017 CA California Lakewood City BRFSS Unhealthy Beh…
# ℹ 18 more variables: UniqueID <chr>, Measure <chr>, Data_Value_Unit <chr>,
# DataValueTypeID <chr>, Data_Value_Type <chr>, Data_Value <dbl>,
# Low_Confidence_Limit <dbl>, High_Confidence_Limit <dbl>,
# Data_Value_Footnote_Symbol <chr>, Data_Value_Footnote <chr>,
# PopulationCount <dbl>, lat <dbl>, long <dbl>, CategoryID <chr>,
# MeasureId <chr>, CityFIPS <dbl>, TractFIPS <dbl>, Short_Question_Text <chr>What variables are included? (can any of them be removed?)
names(latlong_clean) [1] "Year" "StateAbbr"
[3] "StateDesc" "CityName"
[5] "GeographicLevel" "DataSource"
[7] "Category" "UniqueID"
[9] "Measure" "Data_Value_Unit"
[11] "DataValueTypeID" "Data_Value_Type"
[13] "Data_Value" "Low_Confidence_Limit"
[15] "High_Confidence_Limit" "Data_Value_Footnote_Symbol"
[17] "Data_Value_Footnote" "PopulationCount"
[19] "lat" "long"
[21] "CategoryID" "MeasureId"
[23] "CityFIPS" "TractFIPS"
[25] "Short_Question_Text" Remove the variables that will not be used in the assignment
latlong_clean2 <- latlong_clean |>
select(-DataSource,-Data_Value_Unit, -DataValueTypeID, -Low_Confidence_Limit, -High_Confidence_Limit, -Data_Value_Footnote_Symbol, -Data_Value_Footnote)
head(latlong_clean2)# A tibble: 6 × 18
Year StateAbbr StateDesc CityName GeographicLevel Category UniqueID Measure
<dbl> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
1 2017 CA California Hawthorne Census Tract Health … 0632548… Arthri…
2 2017 CA California Hawthorne City Unhealt… 632548 Curren…
3 2017 CA California Hayward City Unhealt… 633000 Obesit…
4 2017 CA California Indio Census Tract Health … 0636448… Arthri…
5 2017 CA California Inglewood Census Tract Health … 0636546… Diagno…
6 2017 CA California Lakewood City Unhealt… 639892 Obesit…
# ℹ 10 more variables: Data_Value_Type <chr>, Data_Value <dbl>,
# PopulationCount <dbl>, lat <dbl>, long <dbl>, CategoryID <chr>,
# MeasureId <chr>, CityFIPS <dbl>, TractFIPS <dbl>, Short_Question_Text <chr>The new dataset “Prevention” is a manageable dataset now.
For your assignment, work with a cleaned dataset.
1. Once you run the above code and learn how to filter in this format, filter this dataset however you choose so that you have a subset with no more than 900 observations.
Filter chunk here
subset_prevention <- latlong_clean2 |>
filter(Category == "Unhealthy Behaviors") |>
filter(Measure %in% c("Obesity among adults aged >=18 Years",
"Current smoking among adults aged >=18 Years",
"No leisure-time physical activity among adults aged >=18 Years",
"Binge drinking among adults aged >=18 Years")) |>
slice_head(n = 900) # Only show 900 obs2. Based on the GIS tutorial (Japan earthquakes), create one plot about something in your subsetted dataset.
First plot chunk here
unhealthy_by_state <- subset_prevention |>
group_by(StateDesc, Measure) |>
summarise(AvgPrevalence = mean(Data_Value, na.rm = TRUE), .groups = "drop")# Add region info for better visualization
state_regions <- data.frame(
StateDesc = c("Alabama", "Alaska", "Arizona", "Arkansas", "California", "Colorado",
"Connecticut", "Delaware", "Florida", "Georgia", "Hawaii", "Idaho",
"Illinois", "Indiana", "Iowa", "Kansas", "Kentucky", "Louisiana",
"Maine", "Maryland", "Massachusetts", "Michigan", "Minnesota",
"Mississippi", "Missouri", "Montana", "Nebraska", "Nevada",
"New Hampshire", "New Jersey", "New Mexico", "New York", "North Carolina",
"North Dakota", "Ohio", "Oklahoma", "Oregon", "Pennsylvania",
"Rhode Island", "South Carolina", "South Dakota", "Tennessee", "Texas",
"Utah", "Vermont", "Virginia", "Washington", "West Virginia",
"Wisconsin", "Wyoming"),
Region = c("South", "West", "West", "South", "West", "West",
"Northeast", "South", "South", "South", "West", "West",
"Midwest", "Midwest", "Midwest", "Midwest", "South", "South",
"Northeast", "South", "Northeast", "Midwest", "Midwest",
"South", "Midwest", "West", "Midwest", "West",
"Northeast", "Northeast", "West", "Northeast", "South",
"Midwest", "Midwest", "South", "West", "Northeast",
"Northeast", "South", "Midwest", "South", "South",
"West", "Northeast", "South", "West", "South",
"Midwest", "West")
)
# Join with unhealthy_by_state
unhealthy_by_state <- left_join(unhealthy_by_state, state_regions, by = "StateDesc")ggplot(unhealthy_by_state, aes(x = Region, y = AvgPrevalence, fill = Region)) +
geom_col(position = "dodge") +
facet_wrap(~Measure) +
labs(
title = "Average Crude Prevalence by Region for Each Unhealthy Behavior",
x = "Region",
y = "Average Crude Prevalence (%)",
fill = "Region",
caption = "Source: CDC - 500 Cities (2017)"
) +
scale_fill_manual(values = c(
"South" = "#7538a1",
"Northeast" = "#3846a1",
"Midwest" = "#29b0d9",
"West" = "#2f9c7b" )) +
theme_bw(base_size = 10) +
theme(
axis.text.x = element_text(angle = 45, hjust = 1),
legend.position = "none"
)
3. Now create a map of your subsetted dataset.
First map chunk here
# Load leaflet
library(leaflet)# Color palette for unhealthy behaviors
colors_behavior <- colorFactor(
palette = c("#7538a1", "#3846a1", "#29b0d9", "#2f9c7b"),
levels = c(
"Current smoking among adults aged >=18 Years",
"Obesity among adults aged >=18 Years",
"No leisure-time physical activity among adults aged >=18 Years",
"Binge drinking among adults aged >=18 Years"), subset_prevention$Measure
)leaflet(subset_prevention) |>
setView(lng = -97, lat = 38, zoom = 4) |> #Had to Google the lat and long
addProviderTiles("Esri.WorldPhysical") |>
addCircles(
lng = ~long,
lat = ~lat,
radius = ~Data_Value * 500, #Size of the circles
weight = 1,
color = ~colors_behavior(subset_prevention$Measure),
fillOpacity = 0.6,
)4. Refine your map to include a mouse-click tooltip
Refined map chunk here
unique(subset_prevention$Measure)[1] "Current smoking among adults aged >=18 Years"
[2] "Obesity among adults aged >=18 Years"
[3] "No leisure-time physical activity among adults aged >=18 Years"
[4] "Binge drinking among adults aged >=18 Years" popupunhealthy = ~paste0(
"<b>City:</b> ", CityName, "<br>",
"<b>State:</b> ", StateDesc, "<br>",
"<b>Measure:</b> ", Measure, "<br>",
"<b>Value:</b> ", Data_Value, "%" #Add "%" to the value
)leaflet(subset_prevention) |>
setView(lng = -97, lat = 38, zoom = 4) |>
addProviderTiles("Esri.WorldPhysical") |>
addCircles(
lng = ~long,
lat = ~lat,
radius = ~Data_Value * 500,
weight = 1,
color = ~colors_behavior(subset_prevention$Measure),
fillOpacity = 0.6,
popup = popupunhealthy) |>
# Add legend https://rstudio.github.io/leaflet/articles/legends.html#:~:text=Use%20the%20addLegend()%20function,colors%20and%20labels%20for%20you.
addLegend("bottomright",
pal = colors_behavior,
values = ~Measure,
title = "Unhealthy Behavior",
opacity = 1
)5. Write a paragraph
In a paragraph, describe the plots you created and what they show.
In this project, I analyzed data from the CDC’s 500 Cities dataset, focusing on four unhealthy behaviors: smoking, obesity, physical inactivity, and binge drinking. I filtered and cleaned the dataset to include only relevant observations, limiting the data to 900 entries for clarity. Using ggplot2, I created a faceted bar plot that displays the average crude prevalence of each behavior across U.S. regions—South, Northeast, Midwest, and West—revealing that the South consistently shows higher prevalence rates. I also created an interactive map using leaflet, where each city is represented by a circle whose size corresponds to the prevalence and color to the specific behavior. A legend was added to improve readability. These visualizations make it easier to analyze geographic patterns of unhealthy behaviors and raise questions for deeper investigation, such as why certain behaviors are more common in specific regions and what strategies high-prevalence states might be implementing to mitigate these health risks.
Sources:
https://www.cdc.gov/places/about/500-cities-2016-2019/index.html
https://rstudio.github.io/leaflet/articles/legends.html#:~:text=Use%20the%20addLegend()%20function,colors%20and%20labels%20for%20you..