library(tidyverse)
library(tidyr)
library(leaflet)
library(sf)
library(knitr)
setwd("C:/Users/kmerv_6exilcx/Dropbox/SPRING 2024/Data 110/week10")
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>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 data for the state of California and geographical level City
mydata <- prevention |>
filter(StateAbbr=="CA")|>
filter(GeographicLevel == "City")
head(mydata)# A tibble: 6 × 18
Year StateAbbr StateDesc CityName GeographicLevel Category UniqueID Measure
<dbl> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
1 2017 CA California Concord City Prevent… 616000 "Visit…
2 2017 CA California Concord City Prevent… 616000 "Chole…
3 2017 CA California Fontana City Prevent… 624680 "Visit…
4 2017 CA California Stockton City Prevent… 675000 "Visit…
5 2017 CA California Vacaville City Prevent… 681554 "Curre…
6 2017 CA California Alhambra City Prevent… 600884 "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>2. Based on the GIS tutorial (Japan earthquakes), create one plot about something in your subsetted dataset.
First plot chunk here
ggplot(mydata, aes(lat))+
geom_density() +
theme_bw() +
labs(title = "Density Distribution of Latitude in California",
x = "Latitude",
caption = "Source: http://www.cdc.gov/500cities/
") 
3. Now create a map of your subsetted dataset.
First map chunk here
cal_long <- -119.417931
cal_lat <- 36.778259leaflet() |>
setView(lng = cal_long, lat = cal_lat, zoom = 6) |>
addProviderTiles("Esri.NatGeoWorldMap") |>
addCircles(
data = mydata,
radius = mydata$PopulationCount/100,
color = "brown",
fillColor = "orange",
fillOpacity = 0.5
)Assuming "long" and "lat" are longitude and latitude, respectively4. Refine your map to include a mousover tooltip
#Popup creation
pop <- paste0(
"<b>City: </b>", mydata$CityName, "<br>",
"<b>City FIPS: </b>", mydata$CityFIPS, "<br>",
"<b>Population Count: </b>", mydata$PopulationCount, "<br>",
"<b>Latitude: </b>", mydata$lat, "<br>",
"<b>Longitude: </b>", mydata$long, "<br>",
"<b>Data Value: </b>", mydata$Data_Value, "<br>",
"<b>Measure Id: </b>", mydata$MeasureId, "<br>",
"<b>Short Question Text: </b>", mydata$Short_Question_Text, "<br>"
)Refined map chunk here
leaflet() |>
setView(lng = cal_long, lat = cal_lat, zoom = 6) |>
addProviderTiles("Esri.NatGeoWorldMap") |>
addCircles(
data = mydata,
radius = mydata$PopulationCount/100,
color = "brown",
fillColor = "orange",
fillOpacity = 0.5,
#Add popup
popup = pop
)Assuming "long" and "lat" are longitude and latitude, respectively5. Write a paragraph
I have filtered the data to include only the state of California, at the geographical level of ‘City’. The density plot shows that most cities in California (in the subset) have latitudes around 34 or 38.
The largest circle on the Map represents Los Angeles, which has the highest population count in the dataset, followed by San Diego, San Jose, San Francisco, etc.