library(tidyverse)
library(tidyr)
library(plotly)
setwd("C:/Users/akais/OneDrive/Documents/500 Cities & local heath")
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(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>unique(md$CityName)[1] "Baltimore"The new dataset “Prevention” is a manageable dataset now.
For your assignment, work with a cleaned dataset.
1. Once you run the above code, filter this dataset one more time for any particular subset with no more than 900 observations.
Filter chunk here
subset_data <- prevention %>%
filter(StateAbbr == "SC" & Short_Question_Text == "Health Insurance")
subset_data# A tibble: 179 × 18
Year StateAbbr StateDesc CityName GeographicLevel Category UniqueID Measure
<dbl> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
1 2017 SC South Car… Rock Hi… Census Tract Prevent… 4561405… "Curre…
2 2017 SC South Car… Charles… Census Tract Prevent… 4513330… "Curre…
3 2017 SC South Car… North C… Census Tract Prevent… 4550875… "Curre…
4 2017 SC South Car… Rock Hi… Census Tract Prevent… 4561405… "Curre…
5 2017 SC South Car… Charles… Census Tract Prevent… 4513330… "Curre…
6 2017 SC South Car… North C… Census Tract Prevent… 4550875… "Curre…
7 2017 SC South Car… Columbia Census Tract Prevent… 4516000… "Curre…
8 2017 SC South Car… Columbia Census Tract Prevent… 4516000… "Curre…
9 2017 SC South Car… Charles… Census Tract Prevent… 4513330… "Curre…
10 2017 SC South Car… Columbia City Prevent… 4516000 "Curre…
# ℹ 169 more rows
# 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># Filtering for census tracts
tract_only <- subset_data %>%
filter(GeographicLevel == "Census Tract")
# Filtering for cities
city_only <- subset_data %>%
filter(GeographicLevel == "City")2. Based on the GIS tutorial (Japan earthquakes), create one plot about something in your subsetted dataset.
First plot chunk here
health_insurance_plot <- ggplot(tract_only, aes(CityName, Data_Value, color = CityName)) +
geom_point(shape = 17, size = 3) +
scale_color_brewer(palette = "Dark2") +
labs(
x = "City Name",
y = "Value (%)",
title = "Health Insurance Prevalence by City in Maryland (2017)",
subtitle = "Each point represents the prevalence of health insurance by city in Maryland.",
color = "City Name"
) +
theme(
plot.background = element_rect(fill = "lightgrey"),
panel.background = element_rect(fill = "grey"),
axis.title = element_text(face = 2),
legend.background = element_rect(fill = "lightgrey"),
legend.title = element_text(color = "black", size = 12),
legend.text = element_text(color = "black", size = 11),
legend.key.size = unit(0.75, units = "cm"),
panel.grid = element_line(color = "darkgrey"),
axis.text.x = element_text(angle = 45, hjust = 1) # Rotate x-axis text
)
health_insurance_plotWarning: Removed 7 rows containing missing values or values outside the scale range
(`geom_point()`).
3. Now create a map of your subsetted dataset.
Loading necessary libraries for the mapping
library(leaflet)
library(sf)Warning: package 'sf' was built under R version 4.4.2Linking to GEOS 3.12.2, GDAL 3.9.3, PROJ 9.4.1; sf_use_s2() is TRUElibrary(knitr)First map chunk here
map_plot <- leaflet() |>
setView(lat = 33.86, lng = -80.64, zoom = 7) |>
addProviderTiles("OpenStreetMap") |>
addCircles(
data = tract_only,
radius = sqrt(10^(tract_only$Data_Value/22)) * 5,
color = "blue"
)Assuming "long" and "lat" are longitude and latitude, respectivelymap_plot4. Refine your map to include a mouse-click tooltip
Refined map chunk here
# Define the popup content
map_popup <- paste0(
"<b>City: </b>", tract_only$CityName, "<br>",
"<b>Census Tract: </b>", tract_only$UniqueID, "<br>",
"<b>Data Value (%): </b>", tract_only$Data_Value, "<br>",
"<strong>Population: </strong>", tract_only$PopulationCount, "<br>"
)
# Create the map with popups
map_w_popup <- leaflet() |>
setView(lat = 33.86, lng = -80.64, zoom = 7) |>
addProviderTiles("OpenStreetMap") |>
addCircles(
data = tract_only,
radius = sqrt(10^(tract_only$Data_Value/23)) * 5,
color = "#ff7f50",
popup = map_popup
)Assuming "long" and "lat" are longitude and latitude, respectivelymap_w_popup5. Write a paragraph
In a paragraph, describe the plots you created and what they show.
The plots I created display health insurance prevalence data across cities and census tracts in South Carolina for 2017. The scatter plot visualizes the prevalence of health insurance by city, where each point represents a different city, colored by the city name. The map plot offers a geographic representation, with circle sizes proportional to health insurance prevalence, and tooltips provide additional city-specific data when clicked. These visualizations help to see the differences in health insurance rates across the state.