library(tidyverse)
library(tidyr)
setwd("C:/Users/senay/OneDrive/Desktop/Scoo/Spring 2025/DATA 110/Datasets")
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(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 CA California Hawthorne Census Tract BRFSS Health Outcom…
2 2017 CA California Hawthorne City BRFSS Unhealthy Beh…
3 2017 CA California Hayward City BRFSS Unhealthy Beh…
4 2017 CA California Indio Census Tract BRFSS Health Outcom…
5 2017 CA California Inglewood Census Tract BRFSS Health Outcom…
6 2017 CA California Lakewood City BRFSS Unhealthy Beh…
# 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 CA California Hawthorne Census Tract Health … 0632548… Arthri…
2 2017 CA California Hawthorne City Unhealt… 632548 Curren…
3 2017 CA California Hayward City Unhealt… 633000 Obesit…
4 2017 CA California Indio Census Tract Health … 0636448… Arthri…
5 2017 CA California Inglewood Census Tract Health … 0636546… Diagno…
6 2017 CA California Lakewood City Unhealt… 639892 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>#unique(md$CityName)The new dataset “Prevention” is a manageable dataset now.
For your assignment, work with a cleaned dataset.
1. Once you run the above code and learn how to filter in this format, filter this dataset however you choose so that you have a subset with no more than 900 observations.
Filter chunk here
names(latlong) <- tolower(names(latlong)) #cleaning
latlong3 <- latlong |>
filter(cityname == "Memphis", year == 2017, short_question_text == "Current Smoking", !geographiclevel == "City") latlong3 <- latlong3 |>
select(-datasource,-data_value_unit, -datavaluetypeid, -low_confidence_limit, -high_confidence_limit, -data_value_footnote_symbol, -data_value_footnote) #removing unnecessary columns 2. Based on the GIS tutorial (Japan earthquakes), create one plot about something in your subsetted dataset.
First plot chunk here
p1 <- latlong3 |>
ggplot(aes(x=populationcount, y = data_value)) +
geom_point() +
labs(x = "Population",
y = "Percentage of Smoking Adults",
title = "Percentage of Smoking Adults Vs Population for Census Tracts \n of Memphis,Tennessee")
p1Warning: Removed 3 rows containing missing values or values outside the scale range
(`geom_point()`).
3. Now create a map of your subsetted dataset.
First map chunk here
library(leaflet)Warning: package 'leaflet' was built under R version 4.4.3leaflet() |>
setView(lng = -90.051, lat = 35.148, zoom =11) |>
addProviderTiles("Esri.WorldStreetMap") |>
addCircles(data = latlong3,
radius = (latlong3$data_value^2)/2)Assuming "long" and "lat" are longitude and latitude, respectively4. Refine your map to include a mouse-click tooltip
Refined map chunk here
popup <- paste0(
"<b> Population: </b>", latlong3$populationcount, "<br>",
"<b> Percentage of Smoking Adults: </b>", latlong3$data_value, "<br>"
)
leaflet() |>
setView(lng = -90.051, lat = 35.148, zoom =11) |>
addProviderTiles("Esri.WorldStreetMap") |>
addCircles(data = latlong3,
color = "#0c0f0c",
fillColor = "#07de11",
fillOpacity = 0.5,
popup = popup,
radius = (latlong3$data_value^2)/2)Assuming "long" and "lat" are longitude and latitude, respectively5. Write a paragraph
In a paragraph, describe the plots you created and what they show.
For this assignment, I wanted to show smoking prevalence in Memphis,Tennessee. I chose this city because it is considered one of the cities with relatively high percentage of people who smoke, and I wanted to showcase that. I initially used the data set with the separated longitude and latitude to make a subset data set of the census tract of Memphis for only the year 2017. I also excluded 3 rows(geographic level = city) because they were huge outliers in my first scatter plot. The first scatter plot showed percentage of smokers vs population for each of the census tracts in Memphis Tennessee. Then, I used the leaflet package to make the map of census tracts. The size of the circles represent the percentage of smokers, which I exaggerated by doing some calculations.Finally, I added a tooltip to the map, allowing viewers to click on a specific point to get more information. The map showed that the closer the census tracts are to the Mississippi River, the bigger the percenatge of people who smoke.