Healthy Cities GIS Assignment

Author

Naomi Surendorj

Load the libraries and set the working directory

library(tidyverse)
library(tidyr)
setwd("~/Downloads/GIS")
cities500 <- read_csv("500CitiesLocalHealthIndicators.cdc.csv")
names(cities500)

 [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] "GeoLocation"                "CategoryID"                
[21] "MeasureId"                  "CityFIPS"                  
[23] "TractFIPS"                  "Short_Question_Text"

unique(cities500$Measure)[1:10]

 [1] "Arthritis among adults aged >=18 Years"                            
 [2] "Current smoking among adults aged >=18 Years"                      
 [3] "Coronary heart disease among adults aged >=18 Years"               
 [4] "Obesity among adults aged >=18 Years"                              
 [5] "Cholesterol screening among adults aged >=18 Years"                
 [6] "Binge drinking among adults aged >=18 Years"                       
 [7] "Chronic obstructive pulmonary disease among adults aged >=18 Years"
 [8] "Diagnosed diabetes among adults aged >=18 Years"                   
 [9] "Mammography use among women aged 50\x9674 Years"                   
[10] "All teeth lost among adults aged >=65 Years"

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 “latlong_clean2” is a manageable dataset now.

For your assignment, work with a cleaned dataset where you perform your own cleaning and filtering.

1. Once you run the above code and 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 through some inclusion/exclusion criteria.

Filter chunk here (you may need multiple chunks)

latlong_subset1 <- latlong_clean2 |>
  filter(Measure == "Obesity among adults aged >=18 Years") |>
  filter(Data_Value_Type == "Crude prevalence") |>
  filter(Year == 2017)

nrow(latlong_subset1)

[1] 228

head(latlong_subset1)

# 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 Hartford Census Tract    Unhealt… 0937000… Obesit…
5  2017 CT        Connecticut Waterbu… Census Tract    Unhealt… 0980000… Obesit…
6  2017 CT        Connecticut Hartford Census Tract    Unhealt… 0937000… 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>

latlong_subset2 <- latlong_subset1 |>
  filter(CityName %in% c("Hartford", "New Haven", "Bridgeport", "Waterbury", "Norwalk")) |>
  select(StateAbbr, CityName, Measure, Data_Value, lat, long)

nrow(latlong_subset2)

[1] 164

head(latlong_subset2)

# A tibble: 6 × 6
  StateAbbr CityName   Measure                            Data_Value   lat  long
  <chr>     <chr>      <chr>                                   <dbl> <dbl> <dbl>
1 CT        Bridgeport Obesity among adults aged >=18 Ye…       36    41.2 -73.2
2 CT        Norwalk    Obesity among adults aged >=18 Ye…       28.8  41.1 -73.4
3 CT        Hartford   Obesity among adults aged >=18 Ye…       45.2  41.8 -72.7
4 CT        Waterbury  Obesity among adults aged >=18 Ye…       39.7  41.6 -73.0
5 CT        Hartford   Obesity among adults aged >=18 Ye…       35.4  41.8 -72.7
6 CT        Norwalk    Obesity among adults aged >=18 Ye…       22.4  41.1 -73.4

2. Based on the GIS tutorial (Japan earthquakes), create one plot about something in your subsetted dataset.

First plot chunk here

ggplot(latlong_subset2, aes(x = reorder(CityName, Data_Value), 
                            y = Data_Value, 
                            fill = CityName)) +
  geom_col() +
  coord_flip() +
  labs(title = "Obesity Rates in Connecticut Cities (2017)",
       x = "City",
       y = "Percent Obese",
       caption = "Source: CDC 500 Cities") +
  theme_bw() +
  scale_fill_viridis_d()

3. Now create a map of your subsetted dataset.

First map chunk here

library(leaflet)

leaflet(latlong_subset2) |>
  setView(lng = -72.7, lat = 41.6, zoom = 7) |>
  addProviderTiles("Esri.WorldStreetMap") |>  
  addCircles(
    lng = ~long,
    lat = ~lat,
    radius = sqrt(latlong_subset2$Data_Value) * 1000,
    color = "#14010d",     
    fillColor = "#f2079c",  
    fillOpacity = 0.25)

4. Refine your map to include a mouse-click tooltip

Refined map chunk here

popup_city <- paste0(
  "<b>City:</b> ", latlong_subset2$CityName, "<br>",
  "<b>Obesity Rate:</b> ", round(latlong_subset2$Data_Value, 1), "%<br>",
  "<b>State:</b> ", latlong_subset2$StateAbbr
)

pal <- colorFactor(
  palette = c("#7538a1", "#3846a1", "#29b0d9", "#2f9c7b", "#3880a1"),
  domain = latlong_subset2$CityName
)

leaflet(latlong_subset2) |>
  setView(lng = -72.7, lat = 41.6, zoom = 7) |>
  addProviderTiles("Esri.WorldStreetMap") |>
  addCircles(
    lng = ~long,
    lat = ~lat,
    radius = sqrt(latlong_subset2$Data_Value) * 1000,
    color = ~pal(CityName),
    fillOpacity = 0.8,
    popup = popup_city )

5. Write a paragraph

In this project, I studied obesity rates in five cities in Connecticut using the CDC 500 Cities data from 2017. I made a bar chart to compare the obesity numbers in each city and a map to see where the cities are located. The bar chart showed that Bridgeport and Waterbury have the highest rates, while Hartford and Norwalk are lower. The map helped me see that the higher rates are in some of the inland areas.