xxxxxxxxxx
 
using CSV, Plots, Dates

171 s

Covid Cases per capita by state, against population density

I live in Rhode Island, which is one of the worst impacted states for covid per capita. We realized that, to be fair, it's also one of the densest states in the US (it's nearly a city-state around Providence - the metro population of Providence is twice the total population of Rhode Island because it bleeds over into Mass and Connecticut!).

But then, we wondered, is it actually fair to explain away our bad case rate by our high population density?

We found several articles arguing that in fact, no, there does not seem to be any correlation between cases per capita and population density:

However, most of the articles we found so far were using countries as data points, and we were interested in US states. So this notebook explores the data from states, and indeed draws the same conclusions:

There does not seem to be any correlation between population density and cases per capita.

The worst cases per capita are in fact mostly in the lowest-density, most rural states. However, among low-density states, there is no trend: some of the best states per capita are also in the lowest-density states. Rhode Island is an outlier, in that it is one of the worst states per capita, but also the second-most-dense state.

The color indicates how old the measurement is, with the darker colors most recent. You can see most states are getting worse over time (which makes sense because I'm plotting total historical cases per capita, so it can only increase).

The most-dense states are on the right, and the least-dense on the left.

39.0 μs

x
 
scatter(
    points_no_dc,
    marker_z = (a,b)->color[(a,b)],
    seriescolor = cgrad([:blue, :white]),
    markersize = 2,
    markerstrokewidth = 0,
    ylabel = "total cases per capita",
    xlabel = "population density",
    colorbar_title = "days ago",
    xticks = xticks_states,
    )

127 ms

I left DC out of the above plot, because it's so much more dense, it made the rest hard to read. Here's the plot that includes DC, in case you're interested:

7.7 μs

xxxxxxxxxx
 
scatter(
    points,
    marker_z = (a,b)->color[(a,b)],
    seriescolor = cgrad([:blue, :white]),
    markersize = 2,
    markerstrokewidth = 0,
    ylabel = "total cases per capita",
    xlabel = "population density",
    label = "days ago",
    xticks = xticks_states,
    )

143 ms

Implementation

The rest of this notebook includes the code to build the above plots.

I load the data from three separate CSVs, to get cases per state over time, area, and population, then combine them for the plots.

11.8 μs

xticks_states

1Float641

0.499385

37.2716

22.4108

24.2139

98.5878

21.1757

286.133

4453.22

192.427

153.45

70.7922

85.7465

21.8468

8.19388

88.7965

72.2028

13.7826

43.7304

41.8462

341.348

more42

4.47054

63.5083

42.4252

14.8453

83.3569

26.1388

43.752

41.4781

28.9609

2.28146

2String1

"AK"

"AL"

"AR"

"AZ"

"CA"

"CO"

"CT"

"DC"

"DE"

"FL"

"GA"

"HI"

"IA"

"ID"

"IL"

"IN"

"KS"

"KY"

"LA"

"MA"

more42

"SD"

"TN"

"TX"

"UT"

"VA"

"VT"

"WA"

"WI"

"WV"

"WY"

xxxxxxxxxx
 
xticks_states = (last.(state_densities), first.(state_densities))

8.9 μs

state_densities

Tuple{String,Float64}11

"AK"

0.499385

"AL"

37.2716

"AR"

22.4108

"AZ"

24.2139

"CA"

98.5878

"CO"

21.1757

"CT"

286.133

"DC"

4453.22

"DE"

192.427

101

"FL"

153.45

111

"GA"

70.7922

121

"HI"

85.7465

131

"IA"

21.8468

141

"ID"

8.19388

151

"IL"

88.7965

161

"IN"

72.2028

171

"KS"

13.7826

181

"KY"

43.7304

191

"LA"

41.8462

201

"MA"

341.348

more421

"SD"

4.47054

431

"TN"

63.5083

441

"TX"

42.4252

451

"UT"

14.8453

461

"VA"

83.3569

471

"VT"

26.1388

481

"WA"

43.752

491

"WI"

41.4781

501

"WV"

28.9609

511

"WY"

2.28146

xxxxxxxxxx
 
state_densities = sort([
    (abbr, density)
        for (state1, density) in state_population_density
        for (state2, abbr) in state_abbreviations_csv
            if state1==state2
], by=first)

212 ms

maxdays_ago

xxxxxxxxxx
 
maxdays_ago = 30

47.0 ns

points_no_dc

Tuple{Float64,Float64}11

21.1757

0.0657054

21.1757

0.0653492

21.1757

0.0582068

21.1757

0.0626491

21.1757

0.0547194

21.1757

0.0649479

21.1757

0.0640962

21.1757

0.055162

21.1757

0.0638304

101

21.1757

0.0631482

111

21.1757

0.065969

121

21.1757

0.0596692

131

21.1757

0.0610276

141

21.1757

0.0593154

151

21.1757

0.0610276

161

21.1757

0.0571792

171

21.1757

0.0556806

181

21.1757

0.0566815

191

21.1757

0.0574694

201

21.1757

0.0604192

more13911

43.752

0.0364745

13921

43.752

0.0340526

13931

43.752

0.0369885

13941

43.752

0.0319825

13951

43.752

0.035669

13961

43.752

0.0385017

13971

43.752

0.0315293

13981

43.752

0.0343623

13991

43.752

0.0360657

14001

43.752

0.0350588

xxxxxxxxxx
 
points_no_dc = [
    (density, cases_per_capita)
    for (state1, density) in state_population_density
        for ((date, state2), cases_per_capita) in state_cases_per_capita_over_time
    if state1 == state2
                && (today()-Date(date, "mm/dd/yyyy")).value < maxdays_ago &&
            state1 !== "District of Columbia"
]

1.2 s

points

Tuple{Float64,Float64}11

21.1757

0.0657054

21.1757

0.0653492

21.1757

0.0582068

21.1757

0.0626491

21.1757

0.0547194

21.1757

0.0649479

21.1757

0.0640962

21.1757

0.055162

21.1757

0.0638304

101

21.1757

0.0631482

111

21.1757

0.065969

121

21.1757

0.0596692

131

21.1757

0.0610276

141

21.1757

0.0593154

151

21.1757

0.0610276

161

21.1757

0.0571792

171

21.1757

0.0556806

181

21.1757

0.0566815

191

21.1757

0.0574694

201

21.1757

0.0604192

more14191

43.752

0.0364745

14201

43.752

0.0340526

14211

43.752

0.0369885

14221

43.752

0.0319825

14231

43.752

0.035669

14241

43.752

0.0385017

14251

43.752

0.0315293

14261

43.752

0.0343623

14271

43.752

0.0360657

14281

43.752

0.0350588

xxxxxxxxxx
 
points = [
    (density, cases_per_capita)
    for (state1, density) in state_population_density
        for ((date, state2), cases_per_capita) in state_cases_per_capita_over_time
    if state1 == state2
                && (today()-Date(date, "mm/dd/yyyy")).value < maxdays_ago
]

683 ms

color

Dict1

24.2139

0.0880896

14.8453

0.0980042

162.731

0.0270532

27.2904

0.0715187

22.4108

0.0711436

22.4108

0.0894532

21.1757

0.0638304

65.3623

0.0687934

42.4252

0.0617497

21.1757

0.0593154

16.7943

0.0216304

14.8453

0.0860748

192.427

0.0621234

88.7965

0.082965

26.1388

0.0124896

98.5878

0.0576358

286.133

0.0614643

27.2904

0.07379

162.731

0.0358948

43.752

0.030953

43.752

0.0376834

16.7943

0.0244331

286.133

0.0542361

396.457

0.0965281

110.663

0.0485301

70.7922

0.0686221

22.1801

0.0754136

14.8453

0.0996463

42.4252

0.0561969

88.7965

0.0805705

xxxxxxxxxx
 
color = Dict(
    (density, cases_per_capita) => (today()-Date(date, "mm/dd/yyyy")).value
    for (state1, density) in state_population_density
        for ((date, state2), cases_per_capita) in state_cases_per_capita_over_time
    if state1 == state2
                && (today()-Date(date, "mm/dd/yyyy")).value < maxdays_ago
)

885 ms

xxxxxxxxxx
 
length(state_population_density)

162 ns

state_population_density

Dict

"Colorado"

21.1757

"Texas"

42.4252

"Alabama"

37.2716

"Vermont"

26.1388

"Missouri"

34.4635

"Wyoming"

2.28146

"California"

98.5878

"Maine"

16.7943

"Tennessee"

63.5083

"Nevada"

10.7509

"Kentucky"

43.7304

"Delaware"

192.427

"Indiana"

72.2028

"South Carolina"

65.3623

"Nebraska"

9.71257

"Arizona"

24.2139

"Connecticut"

286.133

"Illinois"

88.7965

"Maryland"

241.811

"Kansas"

13.7826

"New York"

162.731

"Arkansas"

22.4108

"Minnesota"

27.2904

"South Dakota"

4.47054

"Wisconsin"

41.4781

"Ohio"

110.505

"Georgia"

70.7922

"New Hampshire"

58.2471

"Alaska"

0.499385

"Massachusetts"

341.348

xxxxxxxxxx
 
state_population_density = Dict(
    state1 => pop / parse(Int, replace(area, ','=>""))
    for (state1, pop) in state_populations_2018_csv
        for (state2, area) in state_land_area_csv
    if state1 !== missing && state2 !== missing &&
        area !== missing && pop !== missing &&
        state1 == state2
)

302 ms

xxxxxxxxxx
 
length(state_cases_per_capita_over_time)

55.0 ns

state_cases_per_capita_over_time

Dict1

"09/10/2020"

"Idaho"

0.0197376

"06/19/2020"

"Florida"

0.00411234

"10/12/2020"

"New Hampshire"

0.00681784

"09/03/2020"

"Kentucky"

0.0113779

"09/08/2020"

"Maryland"

0.0186813

"12/07/2020"

"Maryland"

0.0361802

"11/07/2020"

"Colorado"

0.0225127

"03/18/2020"

"Ohio"

7.5248e-6

"03/18/2020"

"Iowa"

1.20232e-5

"12/05/2020"

"Louisiana"

0.0527873

"06/13/2020"

"Connecticut"

0.0125377

"11/04/2020"

"Virginia"

0.0219576

"03/18/2020"

"Alabama"

1.04317e-5

"08/09/2020"

"Washington"

0.00837548

"07/13/2020"

"Wyoming"

0.00331695

"09/28/2020"

"Montana"

0.0116847

"05/27/2020"

"Hawaii"

0.000447282

"03/11/2020"

"Ohio"

2.56527e-7

"09/19/2020"

"Texas"

0.0239012

"01/08/2021"

"Maryland"

0.0498987

"12/17/2020"

"Rhode Island"

0.0727975

"08/06/2020"

"Nebraska"

0.014396

"09/15/2020"

"Kansas"

0.0170974

"02/27/2020"

"Arizona"

1.40373e-7

"10/03/2020"

"Ohio"

0.0135075

"04/12/2020"

"South Carolina"

0.000652202

"09/01/2020"

"New York"

0.010118

"04/02/2020"

"Vermont"

0.000541701

"01/07/2021"

"Ohio"

0.0643942

"02/16/2020"

"Alabama"

0.0

xxxxxxxxxx
 
state_cases_per_capita_over_time = Dict(
    (date, state1) => total_cases / pop
    for ((date, state1), total_cases) in state_cases_over_time
        for (state2, pop) in state_populations_2018_csv
    if state1 !== missing && state2 !== missing && pop !== missing &&
        state1 == state2
)

719 ms

state_cases_over_time

Dict1

"09/10/2020"

"Idaho"

"06/19/2020"

"Florida"

"10/12/2020"

"New Hampshire"

"09/03/2020"

"Kentucky"

"09/08/2020"

"Maryland"

"12/07/2020"

"Maryland"

"11/07/2020"

"Colorado"

"03/18/2020"

"Ohio"

"03/18/2020"

"Iowa"

"12/05/2020"

"Louisiana"

"06/13/2020"

"Connecticut"

"11/04/2020"

"Virginia"

"03/18/2020"

"Alabama"

"08/09/2020"

"Washington"

"07/13/2020"

"Wyoming"

"09/28/2020"

"Montana"

"05/27/2020"

"Hawaii"

"03/11/2020"

"Ohio"

"09/19/2020"

"Texas"

"01/08/2021"

"Maryland"

"12/17/2020"

"Rhode Island"

"08/06/2020"

"Nebraska"

"09/15/2020"

"Kansas"

"02/27/2020"

"Arizona"

"10/03/2020"

"Ohio"

"04/12/2020"

"South Carolina"

"09/01/2020"

"New York"

"04/02/2020"

"Vermont"

"01/07/2021"

"Ohio"

"02/16/2020"

"Alabama"

xxxxxxxxxx
 
state_cases_over_time = Dict(
    (date, state) => total_cases
    for (date, state_abbr1, total_cases) in covid_cases_by_state_over_time_csv
        for (state, state_abbr2) in state_abbreviations_csv
    if state !== missing && state_abbr1 !== missing &&
        date !== missing && total_cases !== missing &&
        state_abbr1 == state_abbr2
)

724 ms

Covid Cases and Deaths per State over Time

https://healthdata.gov/dataset/united-states-covid-19-cases-and-deaths-state-over-time

xxxxxxxxxx
 
md"""
## Covid Cases and Deaths per State over Time
https://healthdata.gov/dataset/united-states-covid-19-cases-and-deaths-state-over-time
"""

7.7 μs

covid_cases_by_state_over_time_csv

	submission_date	state	tot_cases	conf_cases	prob_cases	new_case	pnew_case	tot_death
	String	String	Int64			Int64		Int64
1	"05/04/2020"	"KY"	5245	5245	0	115	0	261
2	"12/08/2020"	"OK"	205999	171497	34502	0	0	1752
3	"08/21/2020"	"MD"	103523	missing	missing	624	0	3685
4	"03/05/2020"	"GA"	2	missing	missing	-5	missing	0
5	"02/08/2020"	"WA"	1	missing	missing	0	missing	0
6	"06/28/2020"	"PA"	85988	83529	2459	492	13	6614
7	"05/04/2020"	"WV"	1224	1224	0	29	0	50
8	"12/02/2020"	"NY"	346492	missing	missing	5775	0	10117
9	"01/23/2020"	"WY"	0	missing	missing	0	missing	0
10	"05/05/2020"	"GA"	28196	28182	14	602	1	1258
more
21720	"07/20/2020"	"NH"	6249	missing	missing	46	0	398

xxxxxxxxxx
 
covid_cases_by_state_over_time_csv = CSV.File(homedir()*"/Downloads/United_States_COVID-19_Cases_and_Deaths_by_State_over_Time.csv")

14.0 s

state_abbreviations_csv

	State/District	Postal Code
	String	String
1	"Alabama"	"AL"
2	"Alaska"	"AK"
3	"Arizona"	"AZ"
4	"Arkansas"	"AR"
5	"California"	"CA"
6	"Colorado"	"CO"
7	"Connecticut"	"CT"
8	"Delaware"	"DE"
9	"District of Columbia"	"DC"
10	"Florida"	"FL"
more
51	"Wyoming"	"WY"

xxxxxxxxxx
 
state_abbreviations_csv = CSV.File("state-abbreviations.csv")

156 ms

US State populations over time

https://www.kaggle.com/lucasvictor/us-state-populations-2018

xxxxxxxxxx
 
md"""
## US State populations over time
https://www.kaggle.com/lucasvictor/us-state-populations-2018
"""

7.9 μs

state_populations_2018_csv

	State	2018 Population
	String	Int64
1	"California"	39776830
2	"Texas"	28704330
3	"Florida"	21312211
4	"New York"	19862512
5	"Pennsylvania"	12823989
6	"Illinois"	12768320
7	"Ohio"	11694664
8	"Georgia"	10545138
9	"North Carolina"	10390149
10	"Michigan"	9991177
more
51	"Wyoming"	573720

xxxxxxxxxx
 
state_populations_2018_csv = CSV.File("State-Populations.csv")

229 ms

US State area

https://www.census.gov/geographies/reference-files/2010/geo/state-area.html

xxxxxxxxxx
 
md"""
## US State area
https://www.census.gov/geographies/reference-files/2010/geo/state-area.html
"""

7.0 μs

state_land_area_csv

	State and other areas2	Land Area Sq. Km.

1	"Total3"	"9,158,022"
2	"United States4"	"9,147,593"
3	"Alabama"	"131,171"
4	"Alaska"	"1,477,953"
5	"Arizona"	"294,207"
6	"Arkansas"	"134,771"
7	"California"	"403,466"
8	"Colorado"	"268,431"
9	"Connecticut"	"12,542"
10	"Delaware"	"5,047"
more
61	"U.S. Virgin Islands"	"348"

xxxxxxxxxx
 
state_land_area_csv = CSV.File("state-land-area.csv")

164 ms

Enter cell code...xxxxxxxxxx
 
​

48.0 ns