library(tidyverse)
library(tidyr)
setwd("/Users/ashleyramirez/Desktop/data110")
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(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>tx <- prevention |>
filter(StateAbbr=="TX")
head(tx)# A tibble: 6 × 18
Year StateAbbr StateDesc CityName GeographicLevel Category UniqueID Measure
<dbl> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
1 2017 TX Texas Houston Census Tract Prevention 4835000… "Chole…
2 2017 TX Texas Houston Census Tract Prevention 4835000… "Chole…
3 2017 TX Texas Irving Census Tract Prevention 4837000… "Chole…
4 2017 TX Texas Abilene Census Tract Prevention 4801000… "Visit…
5 2017 TX Texas Austin Census Tract Prevention 4805000… "Curre…
6 2017 TX Texas Austin Census Tract Prevention 4805000… "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>unique(tx$CityName) [1] "Houston" "Irving" "Abilene" "Austin"
[5] "Beaumont" "Brownsville" "Carrollton" "Dallas"
[9] "Denton" "El Paso" "Fort Worth" "Garland"
[13] "Grand Prairie" "Tyler" "Laredo" "Lewisville"
[17] "Longview" "Lubbock" "McKinney" "Odessa"
[21] "San Antonio" "Arlington" "Amarillo" "Allen"
[25] "Missouri City" "Mesquite" "Bryan" "Corpus Christi"
[29] "College Station" "Baytown" "Midland" "McAllen"
[33] "Killeen" "Edinburg" "Frisco" "Pasadena"
[37] "Mission" "Pearland" "League City" "Plano"
[41] "Richardson" "Sugar Land" "Wichita Falls" "Waco"
[45] "Pharr" "San Angelo" "Round Rock" The new dataset “Prevention” is a manageable dataset now.
For your assignment, work with a cleaned dataset.
-Ashley Ramirez
1. Once you run the above code, filter this dataset one more time for any particular subset with no more than 900 observations.
Filter chunk here
texas_data <- tx %>%
filter(StateAbbr == "TX",GeographicLevel == "Census Tract", PopulationCount < 2000 )Bp_medication <- texas_data %>%
filter(MeasureId == "BPMED")2. Based on the GIS tutorial (Japan earthquakes), create one plot about something in your subsetted dataset.
First plot chunk here
ggplot(Bp_medication, aes(x = CityName, y = PopulationCount)) +
geom_bar(stat = "identity", fill = "red", color = "black", size = 0.3) +
theme_minimal() +
labs(
title = "Population Taking Blood Pressure Medication by City in Texas",
x = "City",
y = "Population Count",
caption = "Data source: 500CitiesLocalHealthIndicators.cdc.csv"
) +
theme(axis.text.x = element_text(angle = 90, hjust = 1))Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
ℹ Please use `linewidth` instead.
3. Now create a map of your subsetted dataset.
First map chunk here
#Load leaflet
library(leaflet)# Create the map
texas_map <- leaflet(Bp_medication) |>
setView(lng = -99.9018, lat = 31.9686, zoom = 6) |>
addProviderTiles("Esri.WorldStreetMap") |>
addCircles(
data = Bp_medication,
lat = ~lat,
lng = ~long,
radius = 8,
color = "purple",
fillOpacity = 0.6
)
# Display the map
texas_map4. Refine your map to include a mouse-click tooltip
Refined map chunk here
library(leaflet)map <- leaflet(Bp_medication) %>%
addTiles() %>%
addCircleMarkers(~long, ~lat,
radius = 8,
color = "purple",
fillOpacity = 0.2,
popup = ~paste(
"City: ", CityName, "<br>",
"City FIPS: ", CityFIPS, "<br>",
"Population: ", PopulationCount, "<br>",
"Category: ", Category, "<br>",
"Year: ", Year, "<br>",
"Measure: ", Measure, "<br>",
"Data Value: ", Data_Value))
map5. Write a paragraph
In a paragraph, describe the plots you created and what they show.
My work is based around census tracked geographical level of the population in Texas that are 18 or older that take blood pressure medication in order to prevent it. With the previous context in mind the first plot I created was to show how many people across the cities of Texas take blood pressure medication to prevent blood pressure in doing so the results were that Houston have the most people taking bloop pressure medication, followed by Dallas and San Antonio. In that same concept with the previous plot, i wanted to create a map that showed the density in the population of each city in the map of peopel taking the medication, plus extra details the dataset provided to give extra context of the many reasons they might’ve taken it or extra information of their geographical locations. My final thoughts are that the most populated cities consume more medication due to having high population.