library(leaflet)
library(tidyverse)
library(tidyr)
setwd("C:/Users/Owner/OneDrive/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(GeographicLevel != "Census Tract") |>
filter(Data_Value_Type == "Crude prevalence") |>
filter(Year == 2017)
# Convert variable names to lowercase
names(latlong_clean) <- tolower(names(latlong_clean))
# Display the first few rows
head(latlong_clean)# A tibble: 6 × 25
year stateabbr statedesc cityname geographiclevel datasource category
<dbl> <chr> <chr> <chr> <chr> <chr> <chr>
1 2017 CA California Hawthorne City BRFSS Unhealthy Be…
2 2017 CA California Hayward City BRFSS Unhealthy Be…
3 2017 CA California Lakewood City BRFSS Unhealthy Be…
4 2017 CA California Livermore City BRFSS Health Outco…
5 2017 AL Alabama Hoover City BRFSS Health Outco…
6 2017 AL Alabama Huntsville City BRFSS Health Outco…
# 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
latlong_clean2 <- latlong_clean |>
select(-datasource,-data_value_unit, -datavaluetypeid, -low_confidence_limit, -high_confidence_limit, -data_value_footnote_symbol, -data_value_footnote)
head(latlong_clean2)# A tibble: 6 × 18
year stateabbr statedesc cityname geographiclevel category uniqueid measure
<dbl> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
1 2017 CA California Hawthorne City Unhealt… 632548 Curren…
2 2017 CA California Hayward City Unhealt… 633000 Obesit…
3 2017 CA California Lakewood City Unhealt… 639892 Obesit…
4 2017 CA California Livermore City Health … 641992 Curren…
5 2017 AL Alabama Hoover City Health … 135896 Chroni…
6 2017 AL Alabama Huntsvil… City Health … 137000 Corona…
# 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 a cleaned dataset.
1. Once you run the above code and learn how to filter in this format, filter this dataset however you choose so that you have a subset with no more than 900 observations.
Filter chunk here
latlong_clean3 <- latlong_clean2 |>
filter(category== "Prevention")
# Display the first few rows
head(latlong_clean3)# 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 "Chole…
2 2017 CA California Concord City Prevent… 616000 "Visit…
3 2017 CA California Concord City Prevent… 616000 "Chole…
4 2017 CA California Fontana City Prevent… 624680 "Visit…
5 2017 FL Florida Palm Coa… 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>Filter out the state of california.
latlong_clean3_CA <- latlong_clean3|>
filter(stateabbr== "CA")
head(latlong_clean3_CA)# 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(latlong_clean3_CA, aes(x = data_value, fill = short_question_text)) +
geom_density(alpha = 0.5) +
labs(
title = "Density Distribution of \nCrude Prevalence by Prevention",
x = "Crude Prevalence",
fill = "category",
caption = "source:cdc.gov/places",
) +
theme_minimal()
## Set the lat and long values for California
lat is + : north of the equator lat is - : south of the equator long +: east of the prime meridian long - : west of the prime meridian First map chunk here
california_lon <- -119.417931
california_lat <- 36.778259Create a popup using paste0
create a line break using < br >
surround text with < b > makes it bold
popupplot <- paste0(
"<b>cityname: </b>", latlong_clean3_CA$cityname, "<br>",
"<b>data_value: </b>", latlong_clean3_CA$data_value, "<br>",
"<b>measureid: </b>", latlong_clean3_CA$measureid, "<br>",
"<b>shortquestiontext", latlong_clean3_CA$short_question_text,"<br>" )3. Now create a map of your subsetted dataset.
leaflet() |>
setView(lng = -119.4, lat = 36.7, zoom =6) |>
addProviderTiles("Esri.WorldStreetMap") |>
addCircles(
data = latlong_clean3_CA,
lng = ~long,
lat = ~lat,
radius = 500, # Fixed radius in meters
color = "#14010d",
fillColor = "#f2079c",
fillOpacity = 0.3,
popup = popupplot
)5. Write a paragraph
In a paragraph, describe the plots you created and what they show.
Density Distribution of Crude Prevalence by Prevention – California Focus
I created a density plot to illustrate the distribution of crude prevalence across different health prevention categories in California. To ensure I captured less than 900 observation, I filtered out census tract data and focused specifically on data related to California.
Crude prevalence refers to the overall proportion of a population that has a specific condition or characteristic at a given point in time, without accounting for specific subgroups or risk factors.
This density plot visualizes the distribution for four preventive health categories:
Annual Checkup
Cholesterol Screening
Health Insurance
Taking Blood Pressure (BP) Medication
Each density curve shows how the prevalence values are distributed—indicating both the concentration of observations and the variability within each category.
Insights from the Plot:
Cholesterol Screening (Green) has the highest crude prevalence, centered around 80%, and displays a relatively broad distribution, suggesting it’s a common and widely accessed preventive service.
Annual Checkup (Pink) and Taking BP Medication (Purple) both center around 65–70%, with Annual Checkup showing a narrower peak, implying more consistent participation across the population.
Health Insurance (Blue) displays a much lower and broader distribution, peaking between 10–20%, which may reflect regional disparities or data anomalies within the filtered sample.
Overall, this plot provides valuable insights into how preventive health behaviors are adopted across California, highlighting potential areas for public health intervention or resource allocation.