Healthy Cities GIS Assignment
xutong
Load the libraries and set the working directory
library(tidyverse)
library(tidyr)
library(ggplot2)
library(maps)
setwd("/Users/xutongzhang/Desktop")
cities500 <- read_csv("500CitiesLocalHealthIndicators.cdc.csv")The GeoLocation variable has (lat, long) format
Split GeoLocation (lat, long) into two columns: lat and long
latlong <- tidyr::extract(cities500, GeoLocation, c('lat', 'long'),
regex = ',?\\s*\\((\\d+\\.\\d+).*(-?\\d+\\.\\d+)\\)')
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 <chr>, long <chr>, 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 <chr>, long <chr>, 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 <chr>, long <chr>, 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
# Filter "Cholesterol screening"
cholesterol_screening_subset <- prevention |>
filter(Measure == "Cholesterol screening among adults aged >=18 Years")2. Based on the GIS tutorial (Japan earthquakes), create one plot about something in your subsetted dataset.
First plot chunk here
# Create a scatter plot for cholesterol screening rates by city
ggplot(cholesterol_screening_subset, aes(x = long, y = lat, color = Data_Value)) +
geom_point() +
labs(title = "Cholesterol Screening Prevalence by City",
x = "Longitude",
y = "Latitude",
color = "Prevalence Rate (%)") +
theme_minimal()
3. Now create a map of your subsetted dataset.
First map chunk here
# Data cleaning and processing
cholesterol_screening_subset$long <- as.numeric(cholesterol_screening_subset$long)
cholesterol_screening_subset$lat <- as.numeric(cholesterol_screening_subset$lat)
cholesterol_screening_subset <- na.omit(cholesterol_screening_subset)
# Set up the base map layer
world_map <- map_data("world")
# Create the ggplot
ggplot() +
# Base map layer
geom_polygon(
data = world_map,
aes(x = long, y = lat, group = group),
fill = "lightgrey",
color = "white"
) +
# Data points layer
geom_point(
data = cholesterol_screening_subset,
aes(x = long, y = lat, color = Data_Value),
size = 2
) +
# Color gradient
scale_color_gradient(low = "blue", high = "red") +
# Labels
labs(
title = "Map of Cholesterol Screening Prevalence",
x = "Longitude",
y = "Latitude",
color = "Prevalence Rate (%)"
) +
# Setting the limits
xlim(
min(cholesterol_screening_subset$long, na.rm = TRUE) - 5,
max(cholesterol_screening_subset$long, na.rm = TRUE) + 5
) +
ylim(
min(cholesterol_screening_subset$lat, na.rm = TRUE) - 5,
max(cholesterol_screening_subset$lat, na.rm = TRUE) + 5
) +
# Themes and aesthetics
theme_minimal() +
theme(legend.position = "bottom") +
coord_fixed(1.3)
4. Refine your map to include a mousover tooltip
Refined map chunk here
library(leaflet)
# Assuming cholesterol_screening_subset is your data frame and it has 'lat', 'long', and 'Data_Value' columns
# Convert the columns to numeric if they're not already
cholesterol_screening_subset$lat <- as.numeric(cholesterol_screening_subset$lat)
cholesterol_screening_subset$long <- as.numeric(cholesterol_screening_subset$long)
# Create a leaflet map
leaflet(data = cholesterol_screening_subset) %>%
addTiles() %>% # Add the default OpenStreetMap map tiles
addCircles(
lng = ~long, lat = ~lat, weight = 1,
radius = 500,
color = ~colorNumeric(palette = "viridis", domain = cholesterol_screening_subset$Data_Value)(Data_Value),
label = ~paste("Prevalence Rate:", Data_Value, "%"),
popup = ~paste("City:", CityName, "<br>",
"Prevalence Rate:", Data_Value, "%")
) %>%
addLegend(
"bottomright",
pal = colorNumeric(palette = "viridis", domain = cholesterol_screening_subset$Data_Value),
values = ~Data_Value,
title = "Prevalence Rate",
labFormat = labelFormat(suffix = "%")
)5. Write a paragraph
In a paragraph, describe the plots you created and what they show.
The static map and interactive map we generated from the “Prevention” dataset show cholesterol screening rates across various locales. The static map uses a color gradient to indicate screening prevalence, with the intensity of color reflecting higher or lower rates. The interactive map, made with leaflet, adds functionality: clicking on a city shows a popup with the city name and its screening rate. Both visuals are practical for identifying areas with different levels of cholesterol health interventions, making it easier to target areas for improvement in public health initiatives.