library(tidyverse)
library(tidyr)
library(leaflet)
setwd("C:/Users/Home/Desktop/DATA110 Data Visualization/Week 10")
cities500 <- read_csv("500CitiesLocalHealthIndicators.cdc.csv")Healthy Cities GIS Assignment
One Degree of Access
This dataset is part of the CDC’s 500 Cities Project.
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(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
long_access <- prevention |>
#Filter for "one degree"
filter(long < -82 & long > -83) |>
#Filter for lack of health insurance
filter(MeasureId == "ACCESS2")2. Based on the GIS tutorial (Japan earthquakes), create one plot about something in your subsetted dataset.
First plot chunk here
ggplot(long_access, aes(x=Data_Value, y=lat, color = CityName, na.rm = TRUE)) +
geom_point(alpha = 0.05) +
scale_color_manual(values =
c("#2f4f4f",
"#8b4513",
"#4b0082",
"#ff0000",
"#ffff54",
"#228b22",
"#00ffff",
"#0000ff",
"#ff00ff",
"#6495ed",
"#ff69b4",
"#ffe4c4",
"#00ff00"))+
geom_jitter() +
facet_wrap(~StateDesc) +
labs(title = "Percent Uninsured by Latitude",
subtitle = "Health Insurance - 2017",
caption = "Source: CDC",
color = "City") +
xlab("Percent Uninsured") +
ylab("Latitude") +
theme_bw() +
theme(legend.background = element_rect(fill = "grey",
color = "black"),
panel.background = element_rect(fill = "#c8cbcf")) Warning: Removed 17 rows containing missing values (`geom_point()`).
Removed 17 rows containing missing values (`geom_point()`).
3. Now create a map of your subsetted dataset.
First map chunk here
leaflet() |>
setView(lng = -82.5, lat = 36.4, zoom = 4.2) |>
addProviderTiles("OpenStreetMap.HOT") |>
addCircles(
data = long_access, radius = long_access$Data_Value * long_access$PopulationCount / 1000,
color = "#5D0E41",
fillColor = "#FF204E")Assuming "long" and "lat" are longitude and latitude, respectively4. Refine your map to include a mousover tooltip
Refined map chunk here
popup500cities <- paste0(
"<b>Uninsured Rate: </b>", long_access$Data_Value, "%","<br>",
"<strong>National Rate: </strong>", 10.8, "%","<br>",
"<b>Population: </b>", long_access$PopulationCount, "<br>",
"<b>Approximate Uninsured Residents: </b>", as.integer(long_access$Data_Value / 100 * long_access$PopulationCount), "<br>"
)
leaflet() |>
setView(lng = -82.5, lat = 36.4, zoom = 4.2) |>
addProviderTiles("OpenStreetMap.HOT") |>
addCircles(
data = long_access, radius = long_access$Data_Value * long_access$PopulationCount / 1000,
color = "#5D0E41",
fillColor = "#FF204E",
popup = popup500cities)Assuming "long" and "lat" are longitude and latitude, respectively5. Write a paragraph
In a paragraph, describe the plots you created and what they show.
The goal of this subset was to take a cross-section-like slice of the United States, one degree longitude in width, and observe any patterns in the cities that fall within this degree.
The facet wrap plot does not reveal any sort of linear relationship, but makes it simple to compare the general spread of rates of uninsured adults between states and cities.
The map illustrates hotspots within each city where the number of uninsured adults is high compared to surrounding areas. Florida cities have some of the biggest offenders.
The most uninsured portion of Tampa, at 23.6%, has a rate twice the national population estimate of 10.8%.
Gainesville is not much better:
Somewhat surprising was the lack of such a hotspot in Detroit:
