library(tidyverse)
library(tidyr)
library(leaflet)
library(knitr)
library(webshot2)
setwd("C:/Users/gitar/Documents")
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(Data_Value_Type == "Crude prevalence") |>
filter(Year == 2017) |>
filter(StateAbbr == "CT") |>
filter(Category == "Unhealthy Behaviors")
head(latlong_clean)# A tibble: 6 × 25
Year StateAbbr StateDesc CityName GeographicLevel DataSource Category
<dbl> <chr> <chr> <chr> <chr> <chr> <chr>
1 2017 CT Connecticut Bridgeport Census Tract BRFSS Unhealthy B…
2 2017 CT Connecticut Danbury City BRFSS Unhealthy B…
3 2017 CT Connecticut Norwalk Census Tract BRFSS Unhealthy B…
4 2017 CT Connecticut Bridgeport Census Tract BRFSS Unhealthy B…
5 2017 CT Connecticut Hartford Census Tract BRFSS Unhealthy B…
6 2017 CT Connecticut Waterbury Census Tract BRFSS Unhealthy B…
# 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 CT Connecticut Bridgep… Census Tract Unhealt… 0908000… Obesit…
2 2017 CT Connecticut Danbury City Unhealt… 918430 Obesit…
3 2017 CT Connecticut Norwalk Census Tract Unhealt… 0955990… Obesit…
4 2017 CT Connecticut Bridgep… Census Tract Unhealt… 0908000… Curren…
5 2017 CT Connecticut Hartford Census Tract Unhealt… 0937000… Obesit…
6 2017 CT Connecticut Waterbu… Census Tract Unhealt… 0980000… Obesit…
# 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 this complicated dataset, perform your own investigation by filtering this dataset however you choose so that you have a subset with no more than 900 observations.
Filter chunk here (you may need multiple chunks)
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
smoking_data <- latlong |>
filter(Measure == "Current smoking among adults aged >=18 Years") |>
filter(Data_Value_Type == "Crude prevalence") |>
filter(StateDesc != "United States") |>
filter(StateAbbr == "CA") |>
filter(GeographicLevel == "Census Tract") |>
filter(Year == 2017) |>
filter(CityName == "Los Angeles") |>
filter(Data_Value >= 10.0)
head(smoking_data)# A tibble: 6 × 25
Year StateAbbr StateDesc CityName GeographicLevel DataSource Category
<dbl> <chr> <chr> <chr> <chr> <chr> <chr>
1 2017 CA California Los Angeles Census Tract BRFSS Unhealthy B…
2 2017 CA California Los Angeles Census Tract BRFSS Unhealthy B…
3 2017 CA California Los Angeles Census Tract BRFSS Unhealthy B…
4 2017 CA California Los Angeles Census Tract BRFSS Unhealthy B…
5 2017 CA California Los Angeles Census Tract BRFSS Unhealthy B…
6 2017 CA California Los Angeles Census Tract BRFSS Unhealthy B…
# 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># Select useful columns
smoking_data_final <- smoking_data |>
select(-DataSource,-Data_Value_Unit, -DataValueTypeID, -Low_Confidence_Limit, -Data_Value_Footnote_Symbol, -Data_Value_Footnote)
head(smoking_data_final)# A tibble: 6 × 19
Year StateAbbr StateDesc CityName GeographicLevel Category UniqueID Measure
<dbl> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
1 2017 CA California Los Ange… Census Tract Unhealt… 0644000… Curren…
2 2017 CA California Los Ange… Census Tract Unhealt… 0644000… Curren…
3 2017 CA California Los Ange… Census Tract Unhealt… 0644000… Curren…
4 2017 CA California Los Ange… Census Tract Unhealt… 0644000… Curren…
5 2017 CA California Los Ange… Census Tract Unhealt… 0644000… Curren…
6 2017 CA California Los Ange… Census Tract Unhealt… 0644000… Curren…
# ℹ 11 more variables: Data_Value_Type <chr>, Data_Value <dbl>,
# High_Confidence_Limit <dbl>, PopulationCount <dbl>, lat <dbl>, long <dbl>,
# CategoryID <chr>, MeasureId <chr>, CityFIPS <dbl>, TractFIPS <dbl>,
# Short_Question_Text <chr># Remove rows with missing values and shorten long names
smoking_data_final <- na.omit(smoking_data_final)
head(smoking_data_final)# A tibble: 6 × 19
Year StateAbbr StateDesc CityName GeographicLevel Category UniqueID Measure
<dbl> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
1 2017 CA California Los Ange… Census Tract Unhealt… 0644000… Curren…
2 2017 CA California Los Ange… Census Tract Unhealt… 0644000… Curren…
3 2017 CA California Los Ange… Census Tract Unhealt… 0644000… Curren…
4 2017 CA California Los Ange… Census Tract Unhealt… 0644000… Curren…
5 2017 CA California Los Ange… Census Tract Unhealt… 0644000… Curren…
6 2017 CA California Los Ange… Census Tract Unhealt… 0644000… Curren…
# ℹ 11 more variables: Data_Value_Type <chr>, Data_Value <dbl>,
# High_Confidence_Limit <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
# non map plot
ggplot(smoking_data, aes(x = Data_Value)) +
geom_density(fill = "grey", alpha = 0.7) +
labs(title = "Density Plot of Smoking Prevalence in L.A. Census",
x = "Smoking Rate (%)",
y = "Density (proportion per %)") +
theme_classic()
ggplot(smoking_data, aes(x = Data_Value)) +
geom_histogram(binwidth = 0.5, fill = "grey", color = "white") +
labs(title = "Distribution of Smoking Prevalence Above 10%",
x = "Smoking Rate (%)",
y = "Number of Census Tracts") +
theme_classic()
3. Now create a map of your subsetted dataset.
First map chunk here
library(leaflet)
smoking_prevelance <- smoking_data_final |>
filter(Data_Value >= 10)
leaflet(smoking_data) |>
setView(lng = -118.35, lat = 34.13, zoom = 9.5) |>
addProviderTiles("Esri.WorldStreetMap") |>
addCircles(
data = smoking_prevelance,
radius = sqrt(1.7^smoking_prevelance$Data_Value),
color = "red",
fillColor = "black",
fillOpacity = 0.15
)Assuming "long" and "lat" are longitude and latitude, respectively4. Refine your map to include a mouse-click tooltip
Refined map chunk here
popupsmoke <- paste0(
"<b>Population: </b>", smoking_prevelance$PopulationCount, "<br>",
"<b>Estimated Percent Smokers(%): </b>", smoking_prevelance$Data_Value, "<br>",
"<b>Highest Estimate(%): </b>", smoking_prevelance$High_Confidence_Limit, "<br>",
"<b>Estimated Smokers: </b>", smoking_prevelance$PopulationCount*(0.01*smoking_prevelance$Data_Value), "<br>"
)smoking_prevelance <- smoking_data_final |>
filter(Data_Value >= 10)
leaflet(smoking_data) |>
setView(lng = -118.35, lat = 34.13, zoom = 9.5) |>
addProviderTiles("Esri.WorldStreetMap") |>
addCircles(
data = smoking_prevelance,
radius = sqrt(1.7^smoking_prevelance$Data_Value),
color = "red",
fillColor = "black",
fillOpacity = 0.15,
popup = popupsmoke
)Assuming "long" and "lat" are longitude and latitude, respectively5. Write a paragraph
For the first non-map plot I made, I chose to do a density plot showing how smoking prevalence is distributed across census tracts. The plot shows that the most common percentage of smokers in an area of Los Angeles is around 14-16 percent. However the density plot is a little confusing to follow for somebody who doesn’t know how it works, so below it I made a similar plot, this time showing the most common percentages by the amount of times that percentage was logged by a census tract. This plot is easier to follow since it shows the amount of times a percentage was found in a neighborhood of Los Angeles, instead of how prevalent it was in dataset itself. The maps I made are pretty self explanitory, each circle represents a neighborhood, the bigger it is the more smokers there are in the neighborhood, with central LA being by far the biggest concentration with 31.3 % of people living there being smokers. I also added a raw representation of the percentage by calculating and displaying the number of smokers based on the population of the neighborhood.