library(tidyverse)
library(tidyr)
setwd('C:/Users/Papad/Documents/MontCommunityCollege/Data110-Summer2024/Datasets')
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"mdsubset <- md |>
filter(PopulationCount > 2500)
mdsubset# A tibble: 504 × 18
Year StateAbbr StateDesc CityName GeographicLevel Category UniqueID Measure
<dbl> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
1 2017 MD Maryland Baltimore Census Tract Prevent… 2404000… "Visit…
2 2017 MD Maryland Baltimore Census Tract Prevent… 2404000… "Curre…
3 2017 MD Maryland Baltimore Census Tract Prevent… 2404000… "Curre…
4 2017 MD Maryland Baltimore Census Tract Prevent… 2404000… "Takin…
5 2017 MD Maryland Baltimore Census Tract Prevent… 2404000… "Chole…
6 2017 MD Maryland Baltimore Census Tract Prevent… 2404000… "Takin…
7 2017 MD Maryland Baltimore Census Tract Prevent… 2404000… "Visit…
8 2017 MD Maryland Baltimore Census Tract Prevent… 2404000… "Chole…
9 2017 MD Maryland Baltimore Census Tract Prevent… 2404000… "Curre…
10 2017 MD Maryland Baltimore Census Tract Prevent… 2404000… "Curre…
# ℹ 494 more rows
# 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
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 TRUElibrary(knitr)
mdsubset1 <- mdsubset |>
group_by(MeasureId);mdsubset1# A tibble: 504 × 18
# Groups: MeasureId [4]
Year StateAbbr StateDesc CityName GeographicLevel Category UniqueID Measure
<dbl> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
1 2017 MD Maryland Baltimore Census Tract Prevent… 2404000… "Visit…
2 2017 MD Maryland Baltimore Census Tract Prevent… 2404000… "Curre…
3 2017 MD Maryland Baltimore Census Tract Prevent… 2404000… "Curre…
4 2017 MD Maryland Baltimore Census Tract Prevent… 2404000… "Takin…
5 2017 MD Maryland Baltimore Census Tract Prevent… 2404000… "Chole…
6 2017 MD Maryland Baltimore Census Tract Prevent… 2404000… "Takin…
7 2017 MD Maryland Baltimore Census Tract Prevent… 2404000… "Visit…
8 2017 MD Maryland Baltimore Census Tract Prevent… 2404000… "Chole…
9 2017 MD Maryland Baltimore Census Tract Prevent… 2404000… "Curre…
10 2017 MD Maryland Baltimore Census Tract Prevent… 2404000… "Curre…
# ℹ 494 more rows
# 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(mdsubset1, aes(x=Data_Value, y=PopulationCount, color = MeasureId)) +
geom_point(alpha = 0.05) +
scale_color_viridis_d()+
geom_jitter() +
facet_wrap(~MeasureId) +
labs(title = "Data Value score of Baltimore,MD sites reporting for 2017",
caption = "Source: CDC.gov") +
theme_bw()
3. Now create a map of your subsetted dataset.
First map chunk here
baltimore_lon <- -76.6122
baltimore_lat <- 39.2904
leaflet() |>
setView(lng = baltimore_lon, lat = baltimore_lat, zoom =10) |>
addProviderTiles("Esri.WorldStreetMap") |>
addCircles(
data = mdsubset1,
radius = mdsubset1$Data_Value
)Assuming "long" and "lat" are longitude and latitude, respectively4. Refine your map to include a mousover tooltip
Refined map chunk here
popuphealth <- paste0(
"<b>Data_Value: </b>", mdsubset1$Data_Value, "<br>",
"<b>PopulationCount: </b>", mdsubset1$PopulationCount, "<br>",
"<b>MeasureId (km): </b>", mdsubset1$MeasureId, "<br>",
"<mdsubset1>CityName: </mdsubset1>", mdsubset1$CityName, "<br>"
)
leaflet() |>
setView(lng = baltimore_lon, lat = baltimore_lat, zoom =10) |>
addProviderTiles("Esri.WorldStreetMap") |>
addCircles(
data = mdsubset1,
radius = mdsubset1$Data_Value,
color = "yellow",
fillColor = "red",
fillOpacity = 0.25,
popup = popuphealth
)Assuming "long" and "lat" are longitude and latitude, respectively5. Write a paragraph
In a paragraph, describe the plots you created and what they show.
Both visualizations have a base of data from 2017 for only Baltimore, Maryland and prevention category and crude prevalence data value type. The first plot shows the population count of Baltimore, MD for 2017 based on the type of Measure Id. The second mapping plot shows a map of Baltimore, Maryland with all of the reported records for 2017, based on data value. The tooltip popup shows three variables and list Baltimore as the location.