library(tidyverse)
library(tidyr)
library(leaflet)
library(knitr)
library(webshot2)
setwd("C:/Users/pickl/OneDrive")
cities500 <- read_csv("500CitiesLocalHealthIndicators.cdc.csv")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(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)
lat_long_clean <- latlong |>
filter(Data_Value_Type == "Crude prevalence")|>
filter(Year == 2017)|>
filter(StateAbbr == "TN")|>
filter(CityName == "Nashville")|>
filter(Category == "Unhealthy Behaviors")
head(lat_long_clean)# A tibble: 6 × 25
Year StateAbbr StateDesc CityName GeographicLevel DataSource Category
<dbl> <chr> <chr> <chr> <chr> <chr> <chr>
1 2017 TN Tennessee Nashville Census Tract BRFSS Unhealthy Beha…
2 2017 TN Tennessee Nashville Census Tract BRFSS Unhealthy Beha…
3 2017 TN Tennessee Nashville Census Tract BRFSS Unhealthy Beha…
4 2017 TN Tennessee Nashville Census Tract BRFSS Unhealthy Beha…
5 2017 TN Tennessee Nashville Census Tract BRFSS Unhealthy Beha…
6 2017 TN Tennessee Nashville Census Tract BRFSS Unhealthy Beha…
# 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>names(lat_long_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" lat_long_clean_2 <- lat_long_clean |>
select(-DataSource,-Data_Value_Unit, -DataValueTypeID, -Low_Confidence_Limit, -High_Confidence_Limit, -Data_Value_Footnote_Symbol, -Data_Value_Footnote)
head(lat_long_clean_2)# A tibble: 6 × 18
Year StateAbbr StateDesc CityName GeographicLevel Category UniqueID Measure
<dbl> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
1 2017 TN Tennessee Nashville Census Tract Unhealth… 4752006… Binge …
2 2017 TN Tennessee Nashville Census Tract Unhealth… 4752006… No lei…
3 2017 TN Tennessee Nashville Census Tract Unhealth… 4752006… Obesit…
4 2017 TN Tennessee Nashville Census Tract Unhealth… 4752006… Curren…
5 2017 TN Tennessee Nashville Census Tract Unhealth… 4752006… No lei…
6 2017 TN Tennessee Nashville Census Tract Unhealth… 4752006… Binge …
# 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
ggplot(lat_long_clean_2, aes(x = Data_Value, y = reorder(Measure, Data_Value))) +
geom_point(size = 1, color = "red") +
labs(
title = "Crude Prevalence of Unhealthy Behaviors by Measure in Nashville, TN (2017)",
x = "Crude Prevalence (%)",
y = "Health Measure",
color = "Measure Type",
caption = "Source: 500 Cities Local Health Indicators (CDC)"
) +
theme_bw() Ignoring unknown labels:
• colour : "Measure Type"
3. Now create a map of your subsetted dataset.
First map chunk here
# leaflet()
leaflet(lat_long_clean_2) |>
setView(lng = -86.78, lat = 36.16, zoom = 10) |>
addProviderTiles("CartoDB.Positron") |>
addCircles(
radius = ~Data_Value * 50,
color = "darkred" ,
fillColor = "red",
fillOpacity = 0.005,
stroke = TRUE
)Assuming "long" and "lat" are longitude and latitude, respectively4. Refine your map to include a mouse-click tooltip
Refined map chunk here
popup_health <- paste0(
"<b>Measure: </b>", lat_long_clean_2$Measure, "<br>",
"<b>Prevalence: </b>", lat_long_clean_2$Data_Value, "%"
)
leaflet(lat_long_clean_2) |>
setView(lng = -86.78, lat = 36.16, zoom = 10) |>
addProviderTiles("Esri.WorldStreetMap") |>
addCircles(
lng = ~long,
lat = ~lat,
radius = ~Data_Value * 50,
color = "darkblue",
fillColor = "blue",
fillOpacity = 0.05,
stroke = FALSE,
popup = popup_health
)5. Write a paragraph
For my tutorial, I decided to look at the crude prevalence of unhealthy behaviors in Nashville, TN in 2017. For the filtering I just got data for the year (2017), State (Tennessee), City (Nashville), Category (Unhealthy behavior), and data type (Crude Prevalance). For graph 2, some insights I can take away is that obesity and not getting enough exercise are the 2 bigger variables in comparison to smoking and binge drinking. I can also see that obesity and not getting enough exercise is pretty similar leading me to think there is a correlation and possibly even causation since the 2 go hand and hand basically. For the other 2 graphs, the only major insight I can see is that in the inner city, the unhealthy behaviors are more common and as you start going to the outskirts, it slowly stops becoming as prevelant.