library(tidyverse)
library(tidyr)
setwd("C:/Users/sajut/OneDrive/Desktop/DATA_110")
cities500 <- read_csv("500CitiesLocalHealthIndicators.cdc.csv")
data(cities500)Healthy Cities GIS Assignment
Load the libraries and set the working directory
library(leaflet)Warning: package 'leaflet' was built under R version 4.5.2library(dplyr)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_clean2$Year <- as.numeric(latlong_clean2$Year)subset_data <- latlong_clean2 |>
filter(Year >= 2016 & Year <= 2019) |>
filter(Category == "Unhealthy Behaviors") |>
filter(!is.na(lat) & !is.na(long)) |>
slice_head(n = 900) |>
mutate(label = paste(CityName, Measure, sep = " - "))
head(subset_data)# A tibble: 6 × 19
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 11 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>, label <chr>2. Based on the GIS tutorial (Japan earthquakes), create one plot about something in your subsetted dataset.
First plot chunk here
# non map plot
ggplot(subset_data, aes(x = CityName, y = Data_Value, color = Category)) +
geom_point(alpha = 0.6, size = 3) +
geom_jitter(width = 0.4, alpha = 0.8) +
facet_wrap(~Category) +
scale_color_viridis_d() +
theme(axis.text.x = element_text(angle = 90))
labs(
title = "Health Indicators by Category and City (2016–2018)",
x = "City",
y = "Crude Prevalence (%)",
caption = "Source: CDC 500 Cities Local Health Indicators"
) +
theme_bw()NULL3. Now create a map of your subsetted dataset.
First map chunk here
# leaflet()
subset_data_clean <- subset_data |>
filter(!is.na(lat) & !is.na(long))
mypal <- colorNumeric( #Set the palette
palette = "YlOrRd",
domain = subset_data_clean$Data_Value
)
leaflet(subset_data_clean) |>
addProviderTiles("CartoDB.Positron") |>
addCircleMarkers( #Help from https://www.youtube.com/watch?v=8MQ3DgFp6q4&t=120s
lng = ~ long,
lat = ~ lat,
radius = 5,
color = ~ mypal(Data_Value),
fillOpacity = 0.7,
weight = 1
) |>
addLegend(
pal = mypal,
values = subset_data_clean$Data_Value,
position = "bottomright",
title = "Crude Prevalence (%)"
)4. Refine your map to include a mouse-click tooltip
Refined map chunk here
subset_data_clean <- subset_data |>
filter(!is.na(lat) & !is.na(long))
healthy_city_map <- subset_data_clean |>
leaflet() |>
addTiles() |>
addMarkers(
lng = ~long,
lat = ~lat ,
popup = ~paste( #Help from https://stackoverflow.com/questions/41940403/popup-on-a-shape-using-tmap
"City: ", CityName,
"\nState: ", StateAbbr,
"\nCrude Prevalence: ", Data_Value, "%"
),
label = ~CityName,
clusterOptions = markerClusterOptions()
)
healthy_city_map5. Write a paragraph
In a paragraph, describe the plots you created and the insights they show.
Paragraph: Description and Insights
The first plot shows the crude prevalence of unhealthy behaviors in selected Connecticut cities from 2016 to 2018. Each point represents a health indicator, colored by category, making it easy to compare behaviors across cities. The jittered points show that some cities, like Hartford and New Haven, have higher rates of unhealthy behaviors than others. The second plot is an interactive Leaflet map showing each city as a circle. Darker colors indicate higher prevalence rates, and the legend explains them. When it gives, it clicks on a city, and a pop-up shows its name, state, and data value. Together, these plots clearly show how health indicators vary by location and help identify cities with greater health concerns.