library(tidyverse)
library(tidyr)
setwd("C:/Users/bombshellnoir/Dropbox (Personal)/00000 Montgomery College/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.
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"dmv <- prevention %>%
filter(StateAbbr %in% c("DC", "MD", "VA"))
head(dmv)# 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… Taking…
2 2017 VA Virginia Lynchburg Census Tract Prevent… 5147672… Taking…
3 2017 VA Virginia Norfolk Census Tract Prevent… 5157000… Taking…
4 2017 VA Virginia Norfolk Census Tract Prevent… 5157000… Visits…
5 2017 VA Virginia Norfolk Census Tract Prevent… 5157000… Choles…
6 2017 VA Virginia Richmond City Prevent… 5167000 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>ggplot(quakes, aes(x=depth, y=mag, color = magType)) + geom_point(alpha = 0.1) + scale_color_viridis_d() + geom_jitter() + labs(title = “Earthquakes in Japan by Magnitude Type”, caption = “Source: USGS”) + theme_bw() ### 2. Based on the GIS tutorial (Japan earthquakes), create one plot about something in your subsetted dataset.
First plot chunk here
plot1 <- ggplot(dmv, aes(x= MeasureId, y= Data_Value, color = StateAbbr)) +
geom_point(alpha = 0.1) +
geom_jitter() +
labs(title = "Preventative Measures in the DMV",
caption = "Source: CDC",
color = "State") +
ylab("Population Percentage with High Blood Pressure\nTaking BP Meds") +
xlab("Preventative Measure")
plot1Warning: Removed 15 rows containing missing values (`geom_point()`).
Removed 15 rows containing missing values (`geom_point()`).
Virginia’s rates regarding blood pressure medication usage fluctuates widely. Let’s explore this more.
3. Now create a map of your subsetted dataset.
First map chunk here
library(leaflet)Warning: package 'leaflet' was built under R version 4.3.3library(sf)Warning: package 'sf' was built under R version 4.3.3Linking to GEOS 3.11.2, GDAL 3.8.2, PROJ 9.3.1; sf_use_s2() is TRUEbpmeds <- dmv %>%
filter(MeasureId == "BPMED") %>%
filter(StateAbbr == "VA") %>%
filter(Data_Value <= 55)
leaflet() %>%
setView(lat = 37.4316, lng = -77.0470, zoom = 7) %>%
addProviderTiles("Esri.NatGeoWorldMap") %>%
addCircles(
data = bpmeds,
radius = ~Data_Value*20,
color = "purple"
)Assuming "long" and "lat" are longitude and latitude, respectively4. Refine your map to include a mousover tooltip
Refined map chunk here
bp_popup <- paste0(
"<b>City: </b>", bpmeds$CityName, "<br>",
"<b>Level: </b>", bpmeds$GeographicLevel, "<br>",
"<b>BP Med Usage: </b>", bpmeds$Data_Value, "%<br>"
)
leaflet() %>%
setView(lat = 36.5049, lng = -76.1707, zoom = 9) %>%
addProviderTiles("Esri.NatGeoWorldMap") %>%
addCircles(
data = bpmeds,
radius = ~Data_Value*20,
color = "purple",
popup = bp_popup
)Assuming "long" and "lat" are longitude and latitude, respectively5. Write a paragraph
In a paragraph, describe the plots you created and what they show. ________________
My first plot is exploratory – are there any correlations in the DMV filtered dataset? In the scatterplot of the four preventative measures, most data points are clustered together – except for the trailing points regarding Virginia’s blood pressure med usage. According to the CDC, “approximately half (47%) of persons with high blood pressure have their condition under control” (1). My map examines the distribution of the half of the population that do not control their high blood pressure with medication. The initial plot suggests that there is an overlap with lack of access to health insurance and not taking high blood pressure medication. I do not know enough about Virginia to determine if the highlighted locations have a lower or higher cost of living than the locations with much higher compliance regarding high blood pressure medication.
- CDC. Vital signs: awareness and treatment of uncontrolled hypertension among adults—United States, 2003–2010. MMWR 2012;61:703–9.