getwd()[1] "C:/Users/cbash/OneDrive/Desktop/DATA 110"Healthy Cities GIS Assignment
Load the libraries and set the working directory
library(tidyverse)
library(tidyr)
setwd("C:/Users/cbash/OneDrive/Desktop/DATA 110")
cities500 <- read_csv("500CitiesLocalHealthIndicators.cdc.csv")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(Category == "Prevention") |>
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 AL Alabama Montgomery City BRFSS Prevention
2 2017 CA California Concord City BRFSS Prevention
3 2017 CA California Concord City BRFSS Prevention
4 2017 CA California Fontana City BRFSS Prevention
5 2017 CA California Richmond Census Tract BRFSS Prevention
6 2017 FL Florida Davie 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>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
prevention <- latlong_clean |>
select(-DataSource,-Data_Value_Unit, -DataValueTypeID, -Low_Confidence_Limit, -High_Confidence_Limit, -Data_Value_Footnote_Symbol, -Data_Value_Footnote)
head(prevention)# A tibble: 6 × 18
Year StateAbbr StateDesc CityName GeographicLevel Category UniqueID Measure
<dbl> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
1 2017 AL Alabama Montgome… City Prevent… 151000 Choles…
2 2017 CA California Concord City Prevent… 616000 Visits…
3 2017 CA California Concord City Prevent… 616000 Choles…
4 2017 CA California Fontana City Prevent… 624680 Visits…
5 2017 CA California Richmond Census Tract Prevent… 0660620… Choles…
6 2017 FL Florida Davie Census Tract Prevent… 1216475… Choles…
# 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>md <- prevention |>
filter(StateAbbr=="MD")
head(md)# A tibble: 6 × 18
Year StateAbbr StateDesc CityName GeographicLevel Category UniqueID Measure
<dbl> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
1 2017 MD Maryland Baltimore Census Tract Preventi… 2404000… "Chole…
2 2017 MD Maryland Baltimore Census Tract Preventi… 2404000… "Visit…
3 2017 MD Maryland Baltimore Census Tract Preventi… 2404000… "Visit…
4 2017 MD Maryland Baltimore Census Tract Preventi… 2404000… "Curre…
5 2017 MD Maryland Baltimore Census Tract Preventi… 2404000… "Curre…
6 2017 MD Maryland Baltimore Census Tract Preventi… 2404000… "Visit…
# 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 the cleaned “Prevention” dataset
1. Once you run the above code, filter this dataset one more time for any particular subset.
Filter chunk here
unique(latlong_clean$StateAbbr) [1] "AL" "CA" "FL" "CT" "IL" "MN" "NY" "PA" "NC" "OH" "OK" "OR" "TX" "RI" "SC"
[16] "SD" "TN" "UT" "VA" "WA" "AK" "WI" "AZ" "AR" "CO" "DE" "NV" "DC" "GA" "ID"
[31] "HI" "MA" "MI" "IN" "KS" "KY" "IA" "LA" "MD" "ME" "NH" "NJ" "NM" "MO" "MS"
[46] "NE" "MT" "ND" "WV" "VT" "WY"filtered_prevention <- prevention |>
filter(StateAbbr == "MD") |>
filter(Measure == "Current lack of health insurance among adults aged 18\x9664 Years")
head(filtered_prevention)# A tibble: 6 × 18
Year StateAbbr StateDesc CityName GeographicLevel Category UniqueID Measure
<dbl> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
1 2017 MD Maryland Baltimore Census Tract Preventi… 2404000… "Curre…
2 2017 MD Maryland Baltimore Census Tract Preventi… 2404000… "Curre…
3 2017 MD Maryland Baltimore Census Tract Preventi… 2404000… "Curre…
4 2017 MD Maryland Baltimore Census Tract Preventi… 2404000… "Curre…
5 2017 MD Maryland Baltimore Census Tract Preventi… 2404000… "Curre…
6 2017 MD Maryland Baltimore Census Tract Preventi… 2404000… "Curre…
# 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>2. Based on the GIS tutorial (Japan earthquakes), create one plot about something in your subsetted dataset.
First plot chunk here
library(ggplot2)
ggplot(filtered_prevention, aes(x = long, y = lat, size = Data_Value, color = Data_Value)) +
geom_point(alpha = 0.9) +
scale_size_continuous(range = c(3, 5)) +
scale_color_gradient(low = "hotpink", high = "black") +
labs(title = "Lack of Health Insurance in Maryland (2017)",
x = "Longitude",
y = "Latitude",
size = "Crude Prevalence",
color = "Crude Prevalence") +
theme_minimal()Warning: Removed 1 row containing missing values or values outside the scale range
(`geom_point()`).
3. Now create a map of your subsetted dataset.
First map chunk here
library(leaflet)Warning: package 'leaflet' was built under R version 4.4.1library(maps)Warning: package 'maps' was built under R version 4.4.1
Attaching package: 'maps'The following object is masked from 'package:purrr':
map# Set MD longtitude and latitude
Maryland_lon <- -76.641273
Maryland_lat <- 39.0458leaflet() |>
setView(lng = Maryland_lon, lat = Maryland_lat, zoom = 9) |>
addProviderTiles("Esri.WorldStreetMap") |>
addCircles(
data = filtered_prevention,
radius = (filtered_prevention$PopulationCount)/10
)Assuming "long" and "lat" are longitude and latitude, respectively4. Refine your map to include a mousover tooltip
popupquake <- paste0(
"<b>Year: </b>", iconv(filtered_prevention$Year, to = "UTF-8"), "<br>",
"<b>Geographic Level: </b>", iconv(filtered_prevention$GeographicLevel, to = "UTF-8"), "<br>",
"<b>Population Count: </b>", iconv(filtered_prevention$PopulationCount, to = "UTF-8"), "<br>",
"<b>Lack of Insurance Rate: </b>", iconv(filtered_prevention$Data_Value, to = "UTF-8"), "<br>",
"<b>Measure: </b>", iconv(filtered_prevention$Measure, to = "UTF-8"), "<br>")
# Create the leaflet map
leaflet() |>
setView(lng = Maryland_lon, lat = Maryland_lat, zoom = 10) |>
addProviderTiles("Esri.WorldStreetMap") |>
addCircles(data = filtered_prevention,
radius = filtered_prevention$PopulationCount / 10,
color = "#14010d",
fillColor = "#f2079c",
fillOpacity = 0.25,
popup = popupquake)Assuming "long" and "lat" are longitude and latitude, respectively5. Write a paragraph
In a paragraph, describe the plots you created and what they show.
In the first plot, scatter plot to visualize the distribution of the lack of health insurance among adults aged 18-64 years across different cities in Maryland for the year 2017. Each point on the scatter plot represents a city, with the size and color of the points indicating the crude prevalence of uninsured adults. Larger and more red-colored points indicate a higher prevalence, while smaller and pinker points indicate a lower prevalence. This plot effectively highlights the variation in health insurance coverage across different locations within the state.
In the second plot, we created a map of Maryland using the leaflet package. The map provides a geographical context, showing the boundaries of Maryland. Overlaid on the map are points representing the lactions within Baltimore county, with the size and color of these points corresponding to the crude prevalence of the lack of health insurance. This visual representation allows for an intuitive understanding of how health insurance coverage varies geographically across the state, pinpointing areas with higher or lower rates of uninsured adults. The combination of the map and the data points offers a clear and detailed view of health insurance disparities within Maryland, particularly in Baltimore area.