library(tidyverse)
library(tidyr)
library(dplyr)
setwd("~/Telesphore/Personnel/Etudes/Montgomery_College/Data_Sciences_Certificate_program/Data_110/Week5")
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)
# Filter for obesity and smocking in Connecticut
library(dplyr)
kaya <- latlong_clean2 %>%
filter(Category == "Unhealthy Behaviors") %>%
filter(Measure == "Obesity among adults aged >=18 Years") %>%
filter(StateDesc == "Connecticut")
head(kaya)# 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 Hartford Census Tract Unhealt… 0937000… Obesit…
5 2017 CT Connecticut Waterbu… Census Tract Unhealt… 0980000… Obesit…
6 2017 CT Connecticut Hartford Census Tract Unhealt… 0937000… 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>2. Based on the GIS tutorial (Japan earthquakes), create one plot about something in your subsetted dataset.
#Create a side-by-side Box plot of Obesity among adults aged >=18 Years based on cities.
ggplot(kaya, aes(x= CityName, y = MeasureId, color = CityName)) +
geom_boxplot()+
geom_jitter(alpha = 0.2) +
theme(axis.text.x = element_text(angle = 45))
3. Now create a map of your subsetted dataset.
# Calculate the weighted obesity rates for each city and summarize it as a new variable for city-level obesity
city_smokers <- kaya |>
group_by(CityName) |>
summarize(
total_population = sum(PopulationCount),
weighted_smoking = sum(Data_Value * PopulationCount) / total_population,
lat = mean(lat, na.rm = TRUE),
long = mean(long, na.rm = TRUE)
) |>
arrange(desc(weighted_smoking))
head(city_smokers)# A tibble: 6 × 5
CityName total_population weighted_smoking lat long
<chr> <dbl> <dbl> <dbl> <dbl>
1 Hartford 249550 36.9 41.8 -72.7
2 Waterbury 220732 35.8 41.6 -73.0
3 New Haven 259558 34.5 41.3 -72.9
4 New Britain 146412 31.7 41.7 -72.8
5 Bridgeport 288458 29.4 41.2 -73.2
6 Norwalk 171206 23.5 41.1 -73.4# Calculate the weighted obesity rates for each city and summarize it as a new variable for city-level obesity
city_obesity <- kaya |>
group_by(CityName) |>
summarize(
total_population = sum(PopulationCount),
weighted_obesity = sum(Data_Value * PopulationCount) / total_population,
lat = mean(lat, na.rm = TRUE),
long = mean(long, na.rm = TRUE)
) |>
arrange(desc(weighted_obesity))
head(city_obesity)# A tibble: 6 × 5
CityName total_population weighted_obesity lat long
<chr> <dbl> <dbl> <dbl> <dbl>
1 Hartford 249550 36.9 41.8 -72.7
2 Waterbury 220732 35.8 41.6 -73.0
3 New Haven 259558 34.5 41.3 -72.9
4 New Britain 146412 31.7 41.7 -72.8
5 Bridgeport 288458 29.4 41.2 -73.2
6 Norwalk 171206 23.5 41.1 -73.4head(city_obesity)# A tibble: 6 × 5
CityName total_population weighted_obesity lat long
<chr> <dbl> <dbl> <dbl> <dbl>
1 Hartford 249550 36.9 41.8 -72.7
2 Waterbury 220732 35.8 41.6 -73.0
3 New Haven 259558 34.5 41.3 -72.9
4 New Britain 146412 31.7 41.7 -72.8
5 Bridgeport 288458 29.4 41.2 -73.2
6 Norwalk 171206 23.5 41.1 -73.4head(city_smokers)# A tibble: 6 × 5
CityName total_population weighted_smoking lat long
<chr> <dbl> <dbl> <dbl> <dbl>
1 Hartford 249550 36.9 41.8 -72.7
2 Waterbury 220732 35.8 41.6 -73.0
3 New Haven 259558 34.5 41.3 -72.9
4 New Britain 146412 31.7 41.7 -72.8
5 Bridgeport 288458 29.4 41.2 -73.2
6 Norwalk 171206 23.5 41.1 -73.4First map chunk here
library(leaflet)leaflet() |>
setView(lng = -73.0877, lat = 41.6032, zoom =7) |>
addProviderTiles("Esri.WorldStreetMap") |>
addCircles(
data = city_obesity,
lng = ~long, lat = ~lat,
radius = ~weighted_obesity * 150,
color = "red",
fillOpacity = 0.6,
group = "obesity"
) |>
addCircles(data = city_smokers,
lng = ~long + 0.10,, lat = ~lat,
radius = ~weighted_smoking * 150,
color = "blue",
fillOpacity = 0.6,
group = "smoking") |>
addLayersControl(overlayGroups = c("obesity", "smoking"),
options =
layersControlOptions(collapse = FALSE)
)4. Refine your map to include a mouse-click tooltip
# Create a popup using paste0
popupobesity <- paste0(
"<b>total_population: </b>", city_obesity, "<br>",
"<b>weighted_obesity: </b>", city_obesity, "<br>"
)# Create a popup using paste0
popupsmokers <- paste0(
"<b>total_population: </b>", city_smokers, "<br>",
"<b>weighted_smoking: </b>", city_smokers, "<br>"
)Refined map chunk here
leaflet() |>
setView(lng = -73.0877, lat = 41.6032, zoom = 8) |>
addProviderTiles("Esri.WorldStreetMap") |>
addCircles(
data = city_obesity,
lng = ~long, lat = ~lat,
radius = ~weighted_obesity * 150,
color = "red",
fillOpacity = 0.6,
popup = popupobesity,
group = "obesity"
) |>
addCircles(data = city_smokers,
lng = ~long + 0.10,, lat = ~lat,
radius = ~weighted_smoking * 150,
color = "blue",
fillOpacity = 0.6,
popup = popupsmokers,
group = "smoking") |>
addLayersControl(overlayGroups = c("obesity", "smoking"),
options =
layersControlOptions(collapse = FALSE)
)5. Write a paragraph
My plots are related to the visualization of obesity and smoking rate among adult population of 18 years and above per city in the state of Connecticut. The Red circles represent the obesity rate and the blue ones the smoking rate. Eight (8) major cities of the State of Connecticut are featured. I inserted for each city and behavior a popup presenting the total population and the rate of the behavior.