Report Overview

This report will help you use all of the skills you’ve been introduced to during this R workshop including:

BEFORE BEGINNING

Before trying to knit this document, you need the Fulton County Shapefiles. Here are the steps:

  1. Unzip the FultonCountyZipCodes.zip compressed file
  2. Put all of the files into a folder in your project called FultonCountyZipCodes.
    • for example on my PC, my project folder is C:\Rworkshop so the sub-folder is C:\Rworkshop\FultonCountyZipCodes
    • in this sub-folder I have the following files:
      • FultonCountyZipCodes.cpg
      • FultonCountyZipCodes.dbf
      • FultonCountyZipCodes.prj
      • FultonCountyZipCodes.sbn
      • FultonCountyZipCodes.sbx
      • FultonCountyZipCodes.shp
      • FultonCountyZipCodes.shp.xml
      • FultonCountyZipCodes.shx

Fulton County COVID Data

The dataset you will be working with has 82101 COVID cases from mostly the Fulton County, GA area. These data cover COVID cases reported from December 2019 to July 2021.

Table of Demographics

Overall (N=82101)
case_age
   N-Miss 48
   Mean (SD) 39.685 (19.159)
   Range -20.000 - 106.000
case_gender
   N-Miss 63
   Female 43299 (52.8%)
   Male 38393 (46.8%)
   Unknown 346 (0.4%)
case_race
   N-Miss 2630
   AMERICAN INDIAN/ALASKA NATIVE 84 (0.1%)
   ASIAN 3075 (3.9%)
   BLACK 35048 (44.1%)
   NATIVE HAWAIIAN/PACIFIC ISLANDER 79 (0.1%)
   OTHER 5863 (7.4%)
   UNKNOWN 3723 (4.7%)
   WHITE 31599 (39.8%)
case_eth
   N-Miss 2574
   HISPANIC/LATINO 8625 (10.8%)
   NON-HISPANIC/LATINO 62677 (78.8%)
   NOT SPECIFIED 8225 (10.3%)

Table of symptoms

Overall (N=82101)
sym_fever
   N-Miss 31577
   No 33951 (67.2%)
   Unk 1446 (2.9%)
   Yes 15127 (29.9%)
sym_subjfever
   N-Miss 37908
   No 30457 (68.9%)
   Unk 1024 (2.3%)
   Yes 12712 (28.8%)
sym_myalgia
   N-Miss 32137
   No 29210 (58.5%)
   Unk 1220 (2.4%)
   Yes 19533 (39.1%)
   YES 1 (0.0%)
sym_losstastesmell
   N-Miss 50724
   No 18109 (57.7%)
   Unk 534 (1.7%)
   Yes 12734 (40.6%)
sym_sorethroat
   N-Miss 32241
   No 36106 (72.4%)
   Unk 1238 (2.5%)
   Yes 12516 (25.1%)
sym_cough
   N-Miss 31630
   No 27474 (54.4%)
   Unk 1054 (2.1%)
   Yes 21943 (43.5%)
sym_headache
   N-Miss 32018
   No 27196 (54.3%)
   Unk 1212 (2.4%)
   Yes 21675 (43.3%)
sym_resolved
   N-Miss 42294
   No, still symptomatic 14466 (36.3%)
   Unknown symptom status 2076 (5.2%)
   Yes, date specified below 15304 (38.4%)
   Yes, date unknown 7961 (20.0%)

Clean up data and recode

Table of some symptoms after recoding

Overall (N=82101)
sym_fever.c
   No, unk, na 66974 (81.6%)
   Yes 15127 (18.4%)
sym_sorethroat.c
   No, unk, na 69585 (84.8%)
   Yes 12516 (15.2%)
sym_cough.c
   No, unk, na 60158 (73.3%)
   Yes 21943 (26.7%)
sym_headache.c
   No, unk, na 60426 (73.6%)
   Yes 21675 (26.4%)

Table of symptoms by race

Let’s also add some nicer labels and then make the table of these recoded symptoms by race.

Symptoms by race
Black (N=35048) Other, unknown or missing (N=15454) White (N=31599) Total (N=82101)
Fever
   No, unk, na 28725 (82.0%) 13017 (84.2%) 25232 (79.9%) 66974 (81.6%)
   Yes 6323 (18.0%) 2437 (15.8%) 6367 (20.1%) 15127 (18.4%)
Sore Throat
   No, unk, na 30356 (86.6%) 13393 (86.7%) 25836 (81.8%) 69585 (84.8%)
   Yes 4692 (13.4%) 2061 (13.3%) 5763 (18.2%) 12516 (15.2%)
Cough
   No, unk, na 25000 (71.3%) 12471 (80.7%) 22687 (71.8%) 60158 (73.3%)
   Yes 10048 (28.7%) 2983 (19.3%) 8912 (28.2%) 21943 (26.7%)
Headache
   No, unk, na 25909 (73.9%) 12415 (80.3%) 22102 (69.9%) 60426 (73.6%)
   Yes 9139 (26.1%) 3039 (19.7%) 9497 (30.1%) 21675 (26.4%)

Table of Symptoms by Race for People who Died

Symptoms by race - people who died
Black (N=1042) Other, unknown or missing (N=63) White (N=599) Total (N=1704)
Fever
   No, unk, na 848 (81.4%) 46 (73.0%) 485 (81.0%) 1379 (80.9%)
   Yes 194 (18.6%) 17 (27.0%) 114 (19.0%) 325 (19.1%)
Sore Throat
   No, unk, na 1020 (97.9%) 61 (96.8%) 581 (97.0%) 1662 (97.5%)
   Yes 22 (2.1%) 2 (3.2%) 18 (3.0%) 42 (2.5%)
Cough
   No, unk, na 839 (80.5%) 48 (76.2%) 482 (80.5%) 1369 (80.3%)
   Yes 203 (19.5%) 15 (23.8%) 117 (19.5%) 335 (19.7%)
Headache
   No, unk, na 1007 (96.6%) 61 (96.8%) 577 (96.3%) 1645 (96.5%)
   Yes 35 (3.4%) 2 (3.2%) 22 (3.7%) 59 (3.5%)

Maps with points and markers

Making maps with R is almost a whole other workshop in and of itself. But let’s try a few simple maps to get started.

In the exercises below you will be using these packages:

Make a Map of Atanta with leaflet

Learn more about the leaflet package.

Add data to the map - points/markers

Let’s look at the locations of the COVID deaths under review and color the points by gender.

Change the base layer if wanted to simplier road map

Learn more with basemaps at https://rstudio.github.io/leaflet/basemaps.html.

Add some data to the map

Aggregating data

In this part of the report, you will:

Load shapefiles for Fulton County Map

Read in the SHP shapefile for Fulton County, GA using the sf package. Then plot the map.

## Reading layer `FultonCountyZipCodes' from data source 
##   `C:\MyGithub\Emory_RWorkshop_11Nov2022\FultonCountyZipCodes\FultonCountyZipCodes.shp' 
##   using driver `ESRI Shapefile'
## Simple feature collection with 48 features and 4 fields
## Geometry type: MULTIPOLYGON
## Dimension:     XY
## Bounding box:  xmin: 2087952 ymin: 1274336 xmax: 2317492 ymax: 1522856
## Projected CRS: NAD83 / Georgia West (ftUS)

Pull data of interest and summarize by zipcode

Then merge and make a choropleth map

Another map option with ggplot2