library(tidyverse)
library(tidyr)
library(leaflet)
setwd("/Users/janithrithilakasiri/Downloads")
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(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>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
unique(latlong_clean$StateAbbr) [1] "AL" "CA" "FL" "CT" "IL" "MN" "NY" "PA" "NC" "OH" "OK" "OR" "TX" "RI" "SC"
[16] "SD" "TN" "UT" "VA" "WA" "AK" "WI" "AZ" "AR" "CO" "DE" "NV" "DC" "GA" "ID"
[31] "HI" "MA" "MI" "IN" "KS" "KY" "IA" "LA" "MD" "ME" "NH" "NJ" "NM" "MO" "MS"
[46] "NE" "MT" "ND" "WV" "VT" "WY"VA_Alex <- prevention |>
filter(StateAbbr=="VA") |>
filter(CityName=="Alexandria")
head(VA_Alex)# A tibble: 6 × 18
Year StateAbbr StateDesc CityName GeographicLevel Category UniqueID Measure
<dbl> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
1 2017 VA Virginia Alexandria Census Tract Prevent… 5101000… "Takin…
2 2017 VA Virginia Alexandria Census Tract Prevent… 5101000… "Chole…
3 2017 VA Virginia Alexandria Census Tract Prevent… 5101000… "Curre…
4 2017 VA Virginia Alexandria Census Tract Prevent… 5101000… "Visit…
5 2017 VA Virginia Alexandria Census Tract Prevent… 5101000… "Visit…
6 2017 VA Virginia Alexandria Census Tract Prevent… 5101000… "Curre…
# 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>Chol_s <- VA_Alex |>
filter(MeasureId == "CHOLSCREEN")
Chol_s# A tibble: 39 × 18
Year StateAbbr StateDesc CityName GeographicLevel Category UniqueID Measure
<dbl> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
1 2017 VA Virginia Alexandr… Census Tract Prevent… 5101000… Choles…
2 2017 VA Virginia Alexandr… Census Tract Prevent… 5101000… Choles…
3 2017 VA Virginia Alexandr… Census Tract Prevent… 5101000… Choles…
4 2017 VA Virginia Alexandr… Census Tract Prevent… 5101000… Choles…
5 2017 VA Virginia Alexandr… Census Tract Prevent… 5101000… Choles…
6 2017 VA Virginia Alexandr… Census Tract Prevent… 5101000… Choles…
7 2017 VA Virginia Alexandr… Census Tract Prevent… 5101000… Choles…
8 2017 VA Virginia Alexandr… Census Tract Prevent… 5101000… Choles…
9 2017 VA Virginia Alexandr… Census Tract Prevent… 5101000… Choles…
10 2017 VA Virginia Alexandr… Census Tract Prevent… 5101000… Choles…
# ℹ 29 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>2. Based on the GIS tutorial (Japan earthquakes), create one plot about something in your subsetted dataset.
First plot chunk here
ggplot(VA_Alex, aes(x = MeasureId, y = Data_Value, fill = Short_Question_Text)) +
geom_boxplot() +
labs(title = "Data Value according to the Measure Id in Alexandria,VA",
x = "MeasureId",
y = "Data_Value")
3. Now create a map of your subsetted dataset.
First map chunk here
mean(Chol_s$lat)[1] 38.81839mean(Chol_s$long)[1] -77.08853leaflet() |>
setView(lng = -77.08853, lat = 38.81839, zoom = 10) |>
addProviderTiles("Esri.NatGeoWorldMap") |>
addCircles(
data= Chol_s,
radius = 5000*Chol_s$Data_Value/Chol_s$PopulationCount
)Assuming "long" and "lat" are longitude and latitude, respectively4. Refine your map to include a mousover tooltip
Refined map chunk here
Freq <- Chol_s$Data_Value/Chol_s$PopulationCount
tooltip <- paste0(
"<b>Visit type: </b>", Chol_s$Short_Question_Text, "<br>",
"<b>Raw Count: </b>", Chol_s$Data_Value, "<br>",
"<b>Population: </b>",Chol_s$PopulationCount, "<br>",
"<b>Relative Frequency: </b>", paste(100*round(Freq, digits = 4),"%"),"<br>")
leaflet() |>
setView(lng = -77.08853, lat =38.81839, zoom = 10) |>
addProviderTiles("Esri.NatGeoWorldMap") |>
addCircles(
data = VA_Alex,
radius = 5000*Chol_s$Data_Value/Chol_s$PopulationCount,
popup = tooltip
)Assuming "long" and "lat" are longitude and latitude, respectively5. Write a paragraph
My box plot that I did first, shows that there are different counts to different measure ID’s, it also shows that accesses to health insurance in Alexandria, VA in 2017 was low. It also shows that cholesterol screening has the highest data value compared to the other three.
The map visualizes the relative frequencies of Cholesterol Screening Alexandria,VA in 2017.
I would love to include the household incomes of Alexandria on the maps, and I will also check why was the health insurance rate was low in 2017 in the area.