library(tidyverse)
library(tidyr)
setwd("/Users/leikarayjoseph/Desktop/Data 110")
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>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>unique(md$CityName)[1] "Baltimore"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
fl <- prevention |>
filter(StateAbbr=="FL")|>
# filter(Short_Question_Text %in% c("Cholesterol Screening", "Health Insurance")) |>
filter(CityName %in%c("Miami", "Tampa")) |>
# Change long and lat to numeric
mutate(lat= as.numeric(lat),
long = as.numeric(long))
head(fl)# A tibble: 6 × 18
Year StateAbbr StateDesc CityName GeographicLevel Category UniqueID Measure
<dbl> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
1 2017 FL Florida Tampa City Prevention 1271000 "Chole…
2 2017 FL Florida Miami Census Tract Prevention 1245000… "Chole…
3 2017 FL Florida Miami Census Tract Prevention 1245000… "Chole…
4 2017 FL Florida Miami Census Tract Prevention 1245000… "Takin…
5 2017 FL Florida Miami Census Tract Prevention 1245000… "Curre…
6 2017 FL Florida Miami Census Tract Prevention 1245000… "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>#fl1 <- prevention |>
#filter(StateAbbr=="FL")|>
#filter(Short_Question_Text == "Cholesterol Screening")
#filter(CityName %in%c("Miami", "Tampa", "Jacksonville", "Orlando"))
#head(fl1)2. Based on the GIS tutorial (Japan earthquakes), create one plot about something in your subsetted dataset.
First plot chunk here
options(scipen = 999) # Make population count into normal notation instead of scientific notation.
ggplot(fl, aes(x=PopulationCount, y= Data_Value, color = Short_Question_Text)) +
geom_point(alpha = 0.05) +
scale_color_viridis_d()+
geom_jitter() +
#facet_wrap(~Short_Question_Text) +
labs(title = "Population vs Data_Value by Short_Question_Text") +
theme_bw() +
theme(axis.text.x = element_text(angle = 45, hjust = 1)) # Rotate x-axis labelsWarning: Removed 28 rows containing missing values or values outside the scale range
(`geom_point()`).
Removed 28 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() |>
setView( lng = mean(fl$long), lat = mean(fl$lat), zoom = 6) |>
addProviderTiles("Esri.WorldStreetMap") |>
addCircles(
data = fl,
radius = ~sqrt(Data_Value),
color= "darkblue",
fillColor = "red",
fillOpacity = 0.25
)Assuming "long" and "lat" are longitude and latitude, respectively# Set color pallette for my map
#color_palette <- colorFactor(palette = "pastel2", domain = fl$Short_Question_Text)
# Now let's make the map
#leaflet(data= fl) |>
#setView( lng = mean(fl$long), lat = mean(fl$lat), zoom = 6) |>
#addProviderTiles("Esri.WorldStreetMap") |>
#addCircles(
# radius = ~sqrt(Data_Value),
#color= ~color_palette(Short_Question_Text),
# fillColor = ~color_palette(Short_Question_Text),
#fillOpacity = 0.7)4. Refine your map to include a mouse-click tooltip
Refined map chunk here
popup <- paste0(
"<b>Prevalance: </b>", fl$Data_Value_Type, "<br>",
"<b>Population: </b>", fl$PopulationCount, "<br>",
"<b>Data_Value(%): </b>", fl$Data_Value, "<br>",
"<strong>reason: </strong>", fl$Short_Question_Text, "<br>"
)# filter data for only Cholesterol screening
fl1 <- fl |>
filter(Short_Question_Text == "Cholesterol Screening")
#create popup with fl1
popup <- paste0(
"<b>Prevalance: </b>", fl1$Data_Value_Type, "<br>",
"<b>Population: </b>", fl1$PopulationCount, "<br>",
"<b>Data_Value(%): </b>", fl1$Data_Value, "<br>",
"<strong>reason: </strong>", fl1$Short_Question_Text, "<br>"
)
leaflet() |>
setView( lng = mean(fl$long), lat = mean(fl$lat), zoom = 6) |>
addProviderTiles("Esri.WorldStreetMap") |>
addCircles(
data = fl1,
radius = fl$Data_Value*10, # multiply by 10 to increase the point size,
color= "darkblue",
fillColor = "red",
fillOpacity = 0.5,
popup = 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.
For my first plot, I created a scatter plot of Population vs. data value by Short_Question_Text. In my plot, I observed that Health Insurance, in green, has the most spread across the Data Value. All the points are clustered in one line, which makes the plot not really interesting.
For my map using leaflet, I filtered and chose Florida as the state I want to work with and I also filtered for the cityName and chose Tampa and Miami. I chose this state because I know and see among my research that its population is diverse and it’s a common place for tourism. I go further and add a popup on my map but this time I also filter the Short_Question_Text to only show the result for Cholesterol screening in the map we also observe that there are more points in than there are in Tampa than there are in Miami.