library(tidyverse)
library(tidyr)
X500CitiesLocalHealthIndicators_cdc_2_ <- read_csv("500CitiesLocalHealthIndicators.cdc (2).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 <- X500CitiesLocalHealthIndicators_cdc_2_|>
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.
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
Tes_filtered <- TX |>
filter(CityName %in% c("Dallas"))OX_filtered <- Tes_filtered |> filter(Short_Question_Text == "Cholesterol Screening")2. Based on the GIS tutorial (Japan earthquakes), create one plot about something in your subsetted dataset.
First plot chunk here
ggplot(OX_filtered, aes(x = PopulationCount, y = Data_Value)) +
geom_point(alpha = 0.5) +
labs(title = "Cholesterol Screening Prevalence in Dallas",
x = "Population Count",
y = "Crude Prevalence (%)") +
theme_bw()Warning: Removed 15 rows containing missing values or values outside the scale range
(`geom_point()`).
OX_filtered_clean <- OX_filtered |> filter(PopulationCount < 100000)
#filtered outlier.library(ggthemes)
# Re-create the plot without the outlier
ggplot(OX_filtered_clean, aes(x = PopulationCount, y = Data_Value)) +
geom_point(alpha = 0.8) +
labs(title = "Cholesterol Screening Prevalence in Dallas (Filtered)",
x = "Population Count",
y = "Crude Prevalence (%)") +
theme_calc()Warning: Removed 15 rows containing missing values or values outside the scale range
(`geom_point()`).
3. Now create a map of your subsetted dataset.
First map chunk here
library(leaflet)
#leaflet to map my dataset from earlier
leaflet(OX_filtered_clean) |>
setView(lng = -96.7970, lat = 32.7767, zoom = 10) |> #sets coordinates and zoom
addProviderTiles("Esri.WorldStreetMap") |> #using esri world street map
addCircles(
lng = ~long, lat = ~lat,
radius = ~sqrt(Data_Value) * 20, # Scale radius based on prevalence
color = "#0073C2FF",
fillColor = "#56B4E9",
fillOpacity = ~Data_Value / 20,
)4. Refine your map to include a mouse-click tooltip
Refined map chunk here
leaflet(OX_filtered_clean) |>
setView(lng = -96.7970, lat = 32.7767, zoom = 10) |> #sets coordinates and zoom
addProviderTiles("Esri.WorldStreetMap") |> #using esri world street map
addCircles(
lng = ~long, lat = ~lat,
radius = ~sqrt(Data_Value) * 20, # Scale radius based on prevalence
color = "#0073C2FF",
fillColor = "#56B4E9",
fillOpacity = ~Data_Value / 20,
popup = ~paste("<b>City:</b> Dallas<br>",
"<b>Prevalence:</b>", Data_Value, "%<br>",
"<b>Population:</b>", PopulationCount)
)5. Write a paragraph
In a paragraph, describe the plots you created and what they show.
This plot’s main focus was to analyze the cholesterol screening prevalence across various census tracts within Dallas, Texas. The plot displays data points clustered, indicating a strong prevalnce across these areas. The majority of prevalances percentages range between 70% and 90%. This plot helps visualize any patterns or anomalies in prevalence rates relative to population size, across different parts of Dallas and highlight areas that may benefit from increased screening efforts.