library(tidyverse)
library(tidyr)
library(leaflet)
library(ggplot2)
library(ggthemes)
setwd("C:/Users/micha/OneDrive/Documents/DATA 110")
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.
Lowercase the names of columns
names(prevention) <- tolower(names(prevention))
names(prevention) <- gsub(" ","_",names(prevention))
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>Additional filter to highlight cholesterol screening among adults older than 18
measure <- prevention |>
filter(measure == "Cholesterol screening among adults aged >=18 Years")
head(measure)# 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 Choles…
3 2017 CA California Richmond Census Tract Prevent… 0660620… Choles…
4 2017 FL Florida Davie Census Tract Prevent… 1216475… Choles…
5 2017 FL Florida Hialeah Census Tract Prevent… 1230000… Choles…
6 2017 FL Florida Miami Be… Census Tract Prevent… 1245025… 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>unique(latlong_clean$StateAbbr) [1] "AL" "CA" "FL" "CT" "IL" "MN" "NY" "PA" "NC" "OH" "OK" "OR" "TX" "RI" "SC"
[16] "SD" "TN" "UT" "VA" "WA" "AK" "WI" "AZ" "AR" "CO" "DE" "NV" "DC" "GA" "ID"
[31] "HI" "MA" "MI" "IN" "KS" "KY" "IA" "LA" "MD" "ME" "NH" "NJ" "NM" "MO" "MS"
[46] "NE" "MT" "ND" "WV" "VT" "WY"2. Based on the GIS tutorial (Japan earthquakes), create one plot about something in your subsetted dataset.
First plot chunk here
ggplot(measure, aes(x = stateabbr, y = populationcount, color = stateabbr)) +
geom_point(aes(size=data_value)) +
labs(title = "Test", x = "State", y = "Population") +
theme_light() +
scale_fill_viridis_b(name = "Measure") +
theme(axis.text.x = element_text(angle = 50, hjust = 1))Warning: Removed 794 rows containing missing values or values outside the scale range
(`geom_point()`).
Remove outlier New York, NY
measure2 <- measure[measure$cityname != "New York",]p2 <- ggplot(measure2, aes(x = stateabbr, y = populationcount, color = stateabbr, head(data(, 10)))) +
geom_point(aes(size=data_value)) +
labs(title = "Test", x = "State", y = "Population") +
theme_light() +
scale_fill_viridis_b(name = "Measure") +
theme(axis.text.x = element_text(angle = 90, hjust = 1))
options(scipen = 999)
p2 + geom_point() # add the pointsWarning: Removed 771 rows containing missing values or values outside the scale range
(`geom_point()`).
fl <- prevention |>
filter(stateabbr == "FL")
head(fl)# A tibble: 6 × 18
year stateabbr statedesc cityname geographiclevel category uniqueid measure
<dbl> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
1 2017 FL Florida Davie Census Tract Prevent… 1216475… "Chole…
2 2017 FL Florida Hialeah Census Tract Prevent… 1230000… "Visit…
3 2017 FL Florida Hialeah Census Tract Prevent… 1230000… "Chole…
4 2017 FL Florida Miami Bea… Census Tract Prevent… 1245025… "Chole…
5 2017 FL Florida Palm Coast City Prevent… 1254200 "Curre…
6 2017 FL Florida Tampa City Prevent… 1271000 "Chole…
# 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>florida_cities <- fl |>
filter(geographiclevel == "City")
head(florida_cities)# A tibble: 6 × 18
year stateabbr statedesc cityname geographiclevel category uniqueid measure
<dbl> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
1 2017 FL Florida Palm Coast City Prevent… 1254200 "Curre…
2 2017 FL Florida Tampa City Prevent… 1271000 "Chole…
3 2017 FL Florida Coral Spr… City Prevent… 1214400 "Curre…
4 2017 FL Florida Deerfield… City Prevent… 1216725 "Visit…
5 2017 FL Florida Deltona City Prevent… 1217200 "Curre…
6 2017 FL Florida Hollywood City Prevent… 1232000 "Takin…
# 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>p4 <- ggplot(florida_cities, aes(x = cityname, y = populationcount, fill = short_question_text)) +
geom_bar(stat = "identity", position = "Dodge") +
labs(title = "Florida Prevention Broken Down by City", x = "City", y = "Population") +
theme_stata() +
scale_fill_brewer(name = "Measure") +
theme(axis.text.x = element_text(angle = 70, hjust = 1)) +
theme(axis.text.y = element_text(angle = 70, hjust = 1))
p4 + geom_point() # add the points
3. Now create a map of your subsetted dataset.
First map chunk here
leaflet(data = florida_cities) |>
setView(lng = -83.0, lat = 28.0, zoom = 12) |>
addProviderTiles("Esri.WorldStreetMap") |>
addCircles()Assuming "long" and "lat" are longitude and latitude, respectively4. Refine your map to include a mousover tooltip
Refined map chunk here
color_palette <- colorFactor(viridis::viridis_pal()(length(unique(florida_cities$short_question_text))), domain = florida_cities$short_question_text)
leaflet(data = florida_cities) |>
setView(lng = -82.72448, lat = 27.78623, zoom = 12) |>
addProviderTiles("Esri.WorldStreepMap") |>
addCircles(
data = florida_cities,
radius = florida_cities$data_value* 3,
color = color_palette(florida_cities$short_question_text),
fillOpacity = 0.5,
weight = 1.5,
popup = ~paste("<b>City: ", cityname, "<br>",
"<b>Population Count: ", populationcount, "<br>",
"<b>Measure: ", short_question_text, "<br>",
"<b>Data Value: ", data_value))Assuming "long" and "lat" are longitude and latitude, respectively5. Write a paragraph
In a paragraph, describe the plots you created and what they show.
The plots created in this document came from the 500 Healthy Cities dataset. First I filtered the data to include only cholesterol screening among adults ages 18 and up. From implementing that filter, I initially wanted to create a visualization that plotted just the states in this dataset with their population size. Realizing that this was not turning out to be the most interesting plot, I altered my code to instead focus solely on cities within the state of Florida. I also added the fill function to include the short question text column within each of these cities. The four possible options, annual checkup, cholesterol screening, health insurance and taking BP medication, are color coded on each city bar. Unfortunately, there are several cities within Florida in this dataset, so it is difficult to see the distribution of each short question text within each city since the data appears so zoomed out. That said, I find it intriguing that Jacksonville, FL has more than double a population size than Miami, the next highest. Perhaps removing Jacksonville as an outlier would have been wise to help create some space between each bar. It was also challenging picking an appropriate latitude and longitude as well as zoom function since you must click on the “-” symbol to find my plotted points on the map.