library(tidyverse)
library(tidyr)
setwd("C:/Users/user/Downloads")
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) |>
filter(StateAbbr == "CT") |>
filter(Category == "Unhealthy Behaviors")
head(latlong_clean)# A tibble: 6 × 25
Year StateAbbr StateDesc CityName GeographicLevel DataSource Category
<dbl> <chr> <chr> <chr> <chr> <chr> <chr>
1 2017 CT Connecticut Bridgeport Census Tract BRFSS Unhealthy B…
2 2017 CT Connecticut Danbury City BRFSS Unhealthy B…
3 2017 CT Connecticut Norwalk Census Tract BRFSS Unhealthy B…
4 2017 CT Connecticut Bridgeport Census Tract BRFSS Unhealthy B…
5 2017 CT Connecticut Hartford Census Tract BRFSS Unhealthy B…
6 2017 CT Connecticut Waterbury Census Tract BRFSS Unhealthy B…
# 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 CT Connecticut Bridgep… Census Tract Unhealt… 0908000… Obesit…
2 2017 CT Connecticut Danbury City Unhealt… 918430 Obesit…
3 2017 CT Connecticut Norwalk Census Tract Unhealt… 0955990… Obesit…
4 2017 CT Connecticut Bridgep… Census Tract Unhealt… 0908000… Curren…
5 2017 CT Connecticut Hartford Census Tract Unhealt… 0937000… Obesit…
6 2017 CT Connecticut Waterbu… Census Tract Unhealt… 0980000… 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 this complicated dataset, perform your own investigation by filtering this dataset however you choose so that you have a subset with no more than 900 observations.
Filter chunk here (you may need multiple chunks)
# Filter for California + Prevention + Crude prevalence in 2017
latlong_subset <- latlong |>
filter(StateDesc != "United States") |>
filter(Data_Value_Type == "Crude prevalence") |>
filter(Year == 2017) |>
filter(StateAbbr == "CA") |>
filter(Category == "Prevention")
# Limit to max 900 observations
latlong_subset <- latlong_subset |>
slice_sample(n = 900)
head(latlong_subset)# A tibble: 6 × 25
Year StateAbbr StateDesc CityName GeographicLevel DataSource Category
<dbl> <chr> <chr> <chr> <chr> <chr> <chr>
1 2017 CA California Upland Census Tract BRFSS Prevention
2 2017 CA California Escondido Census Tract BRFSS Prevention
3 2017 CA California Irvine Census Tract BRFSS Prevention
4 2017 CA California San Diego Census Tract BRFSS Prevention
5 2017 CA California Pomona Census Tract BRFSS Prevention
6 2017 CA California Los Angeles Census Tract BRFSS Prevention
# 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>2. Based on the GIS tutorial (Japan earthquakes), create one plot about something in your subsetted dataset.
First plot chunk here
# Histogram of Crude Prevalence Values
ggplot(latlong_subset, aes(x = Data_Value)) +
geom_histogram(binwidth = 4, fill = "blue", color = "red") +
labs(title = "Distribution of Crude Prevalence Across California",
x = "Crude Prevalence (%)",
y = "Frequency") +
theme_minimal()Warning: Removed 10 rows containing non-finite outside the scale range
(`stat_bin()`).
3. Now create a map of your subsetted dataset.
First map chunk here
library(leaflet)
leaflet(latlong_subset) |>
addTiles() |>
addCircleMarkers(~long, ~lat,
radius = 4,
stroke = FALSE,
fillOpacity = 0.7)4. Refine your map to include a mouse-click tooltip
Refined map chunk here
latlong_subset <- latlong_subset |>
mutate(
popup_info = paste0(
"City: ", iconv(CityName, "latin1", "UTF-8", sub = ""), "<br/>",
"Measure: ", iconv(Measure, "latin1", "UTF-8", sub = ""), "<br/>",
"Value: ", round(Data_Value, 1), "%"
)
)# Create leaflet map with tooltips
leaflet(data = latlong_subset) |>
addTiles() |>
addCircleMarkers(
lng = ~long,
lat = ~lat,
radius = 4,
stroke = FALSE,
fillOpacity = 0.7,
popup = ~popup_info
)5. Write a paragraph
In a paragraph, describe the plots you created and what they show.
In this assignment, I investigated preventive health behavior data for cities in California using the 500 Cities dataset from the CDC. Before anything, I filtered the dataset to include only records from 2017 and the prevention category in California. Then I created a histogram to explore the distribution of crude prevalence values across cities in California. The histogram showed a moderately right-skewed distribution, with most values clustering between 60% and 80%. This indicated that a large portion of people in the cities reported participation in preventive health behaviors such as cholesterol screening, routine check-ups, or vaccinations. Thus, indicating a relatively strong engagement with preventive care measures in urban areas across California, even though some cities showed lower prevalence rates. I also created an interactive map using the Leaflet library in R. The map displays each observation as a circular marker. When clicked, each marker reveals a tooltip showing the city name, the specific health measure, and the corresponding crude prevalence value. This visualization revealed that while many cities had high preventive health values, there were spatial clusters where lower participation was evident. This information could be useful for targeting public health interventions in areas with lower performance.