gis

Load the libraries and set the working directory

#|message: false
#|warning: false

library(tidyverse)

── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr     1.1.4     ✔ readr     2.1.5
✔ forcats   1.0.0     ✔ stringr   1.5.1
✔ ggplot2   3.5.1     ✔ tibble    3.2.1
✔ lubridate 1.9.4     ✔ tidyr     1.3.1
✔ purrr     1.0.4     
── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()
ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(leaflet)
library(tidyr)

setwd("~/Desktop/data 110")
cities500 <- read_csv("500CitiesLocalHealthIndicators.cdc.csv")

Rows: 810103 Columns: 24
── Column specification ────────────────────────────────────────────────────────
Delimiter: ","
chr (17): StateAbbr, StateDesc, CityName, GeographicLevel, DataSource, Categ...
dbl  (6): Year, Data_Value, Low_Confidence_Limit, High_Confidence_Limit, Cit...
num  (1): PopulationCount

ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

data(cities500)

Warning in data(cities500): data set 'cities500' not found

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)

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 Census Tract    BRFSS      Health Outcom…
2  2017 CA        California Hawthorne City            BRFSS      Unhealthy Beh…
3  2017 CA        California Hayward   City            BRFSS      Unhealthy Beh…
4  2017 CA        California Indio     Census Tract    BRFSS      Health Outcom…
5  2017 CA        California Inglewood Census Tract    BRFSS      Health Outcom…
6  2017 CA        California Lakewood  City            BRFSS      Unhealthy Beh…
# 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 Census Tract    Health … 0632548… Arthri…
2  2017 CA        California Hawthorne City            Unhealt… 632548   Curren…
3  2017 CA        California Hayward   City            Unhealt… 633000   Obesit…
4  2017 CA        California Indio     Census Tract    Health … 0636448… Arthri…
5  2017 CA        California Inglewood Census Tract    Health … 0636546… Diagno…
6  2017 CA        California Lakewood  City            Unhealt… 639892   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 in this format, filter this dataset however you choose so that you have a subset with no more than 900 observations.

Filter chunk here

mentalhealth <- latlong_clean2 |>
  filter(StateDesc == "Virginia") |>
  filter(Short_Question_Text == "Mental Health") |>
  filter(Data_Value_Type == "Crude prevalence")

head(mentalhealth)

# A tibble: 6 × 18
   Year StateAbbr StateDesc CityName   GeographicLevel Category UniqueID Measure
  <dbl> <chr>     <chr>     <chr>      <chr>           <chr>    <chr>    <chr>  
1  2017 VA        Virginia  Newport N… Census Tract    Health … 5156000… Mental…
2  2017 VA        Virginia  Newport N… Census Tract    Health … 5156000… Mental…
3  2017 VA        Virginia  Lynchburg  Census Tract    Health … 5147672… Mental…
4  2017 VA        Virginia  Chesapeake Census Tract    Health … 5116000… Mental…
5  2017 VA        Virginia  Hampton    Census Tract    Health … 5135000… Mental…
6  2017 VA        Virginia  Newport N… Census Tract    Health … 5156000… Mental…
# 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(mentalhealth, aes(x = CityName, y = Data_Value)) +
  geom_bar(stat = "identity", fill = "red") +
  labs(title = "Mental Health cases by City in Virginia",
       x = "City",
       y = "Data Value") +
  coord_flip() +
  theme_bw()

Warning: Removed 2 rows containing missing values or values outside the scale range
(`geom_bar()`).

3. Now create a map of your subsetted dataset.

names(mentalhealth)

 [1] "Year"                "StateAbbr"           "StateDesc"          
 [4] "CityName"            "GeographicLevel"     "Category"           
 [7] "UniqueID"            "Measure"             "Data_Value_Type"    
[10] "Data_Value"          "PopulationCount"     "lat"                
[13] "long"                "CategoryID"          "MeasureId"          
[16] "CityFIPS"            "TractFIPS"           "Short_Question_Text"

First map chunk here

mentalhealth$Data_Value <- as.numeric(mentalhealth$Data_Value)
head(mentalhealth$Data_Value)

[1] 12.2 12.5 17.7 12.6 16.1 17.2

leaflet() |>
  setView(lng = -78.6569, lat = 37.4316, zoom = 6) |>
  addProviderTiles("Esri.WorldStreetMap") |>
  addCircles(
    data = mentalhealth,
    lng = ~long,
    lat = ~lat,
    radius = ~Data_Value * 100
  )

4. Refine your map to include a mouse-click tooltip

Refined map chunk here

popupmental <- paste0(
  "<b>City: </b>", mentalhealth$CityName, "<br>",
  "<b>Mental Health %: </b>", mentalhealth$Data_Value, "<br>")

leaflet() |>
  setView(lng = -78.6569, lat = 37.4316, zoom = 7) |>
  addProviderTiles("Esri.WorldStreetMap") |>
  addCircles(
    data = mentalhealth,
    radius = ~Data_Value * 100,
    lng = ~long,
    lat = ~lat,
    color = "#1E88E5",  
    fillColor = "#42A5F5",
    fillOpacity = 0.4,
    popup = popupmental
  )

5. Write a paragraph

In a paragraph, describe the plots you created and what they show

so i was trying to display the mental health cases data across various cities in Virginia. Each city is represented by a circle, with the size of the circle proportional to the mental health cases percentage for that citys. These visualizations provide an interactive experience. The data allows us to understand the mental health trends across virgnia, highlighting areas with potentially higher or lower rates of mental health concerns.