Data 607 - Acquisition and Management - Assignment 1
Enid Roman
2022-09-04
In 2020 there was a high level of enthusiasm for voting in the general election. In the beginning of the year, voter registration had increased. Then COVID-19 pandemic hit and new registrations had suddenly decreased.
As per the data taken registration numbers were even stronger in early 2020 than early 2016. Things changed dramatically in March, at least in the 12 states that data were taken.
In this analysis we will focus on the comparison in Voter Registration in 2016 vs 2020. We will see the difference in numbers of Voter Registration.
This data was taken from the article Voter Registration Are Way, Way Down During The Pandemic, June 20, 2020 by Kaleigh Rogers and Nathaniel Rakich. https://fivethirtyeight.com/features/voter-registrations-are-way-way-down-during-the-pandemic/
This data was collected for https://electioninnovation.org/wp-content/uploads/2020/06/New_Voter_Registrations.pdf
The data and attached information was taken from https://github.com/fivethirtyeight/data/tree/master/voter-registration
The data contains total # of people registered to vote from early 2016 vs early 2020 from January to April in 11 states and to May in Washington, DC. Data was not available for the other states.
The data is broken down into four variables: Jurisdiction, Year, Month, New.registered.voters.
# I uploaded the libraries I might need.
library("pacman")
library("tidyverse")## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
## ✔ ggplot2 3.3.6 ✔ purrr 0.3.4
## ✔ tibble 3.1.8 ✔ dplyr 1.0.9
## ✔ tidyr 1.2.0 ✔ stringr 1.4.1
## ✔ readr 2.1.2 ✔ forcats 0.5.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()library("dplyr")
library("ggplot2")
library("scales")##
## Attaching package: 'scales'
##
## The following object is masked from 'package:purrr':
##
## discard
##
## The following object is masked from 'package:readr':
##
## col_factorI uploaded the csv dataset to my github where I created a repository for the dataset. I then uploaded the dataset to RStudio.
# I uploaded the csv dataset to my github where I created a repository for the dataset. I then uploaded the dataset to RStudio.
theUrl <- "https://raw.githubusercontent.com/enidroman/data607_acquisition_and_managent/main/new-voter-registrations.csv"
voter_registration <- read.table(file=theUrl, header=TRUE, sep=",")
voter_registration## Jurisdiction Year Month New.registered.voters
## 1 Arizona 2016 Jan 25852
## 2 Arizona 2016 Feb 51155
## 3 Arizona 2016 Mar 48614
## 4 Arizona 2016 Apr 30668
## 5 Arizona 2020 Jan 33229
## 6 Arizona 2020 Feb 50853
## 7 Arizona 2020 Mar 31872
## 8 Arizona 2020 Apr 10249
## 9 California 2016 Jan 87574
## 10 California 2016 Feb 103377
## 11 California 2016 Mar 174278
## 12 California 2016 Apr 185478
## 13 California 2020 Jan 151595
## 14 California 2020 Feb 238281
## 15 California 2020 Mar 176810
## 16 California 2020 Apr 38970
## 17 Colorado 2016 Jan 17024
## 18 Colorado 2016 Feb 20707
## 19 Colorado 2016 Mar 25627
## 20 Colorado 2016 Apr 22204
## 21 Colorado 2020 Jan 20260
## 22 Colorado 2020 Feb 33374
## 23 Colorado 2020 Mar 18990
## 24 Colorado 2020 Apr 6034
## 25 Delaware 2016 Jan 3007
## 26 Delaware 2016 Feb 3629
## 27 Delaware 2016 Mar 5124
## 28 Delaware 2016 Apr 3818
## 29 Delaware 2020 Jan 3276
## 30 Delaware 2020 Feb 3353
## 31 Delaware 2020 Mar 2535
## 32 Delaware 2020 Apr 589
## 33 District of Columbia 2016 Jan 2840
## 34 District of Columbia 2016 Feb 2954
## 35 District of Columbia 2016 Mar 4706
## 36 District of Columbia 2016 Apr 4157
## 37 District of Columbia 2016 May 5714
## 38 District of Columbia 2020 Jan 3334
## 39 District of Columbia 2020 Feb 3348
## 40 District of Columbia 2020 Mar 2225
## 41 District of Columbia 2020 Apr 1281
## 42 District of Columbia 2020 May 1925
## 43 Florida 2016 Jan 50231
## 44 Florida 2016 Feb 87351
## 45 Florida 2016 Mar 73627
## 46 Florida 2016 Apr 52508
## 47 Florida 2020 Jan 77466
## 48 Florida 2020 Feb 109859
## 49 Florida 2020 Mar 54872
## 50 Florida 2020 Apr 21031
## 51 Georgia 2016 Jan 34952
## 52 Georgia 2016 Feb 40976
## 53 Georgia 2016 Mar 44150
## 54 Georgia 2016 Apr 37028
## 55 Georgia 2020 Jan 38573
## 56 Georgia 2020 Feb 55386
## 57 Georgia 2020 Mar 26284
## 58 Georgia 2020 Apr 15484
## 59 Illinois 2016 Jan 44040
## 60 Illinois 2016 Feb 99674
## 61 Illinois 2016 Mar 52782
## 62 Illinois 2016 Apr 76098
## 63 Illinois 2020 Jan 44443
## 64 Illinois 2020 Feb 68455
## 65 Illinois 2020 Mar 47899
## 66 Illinois 2020 Apr 21332
## 67 Maryland 2016 Jan 19580
## 68 Maryland 2016 Feb 29122
## 69 Maryland 2016 Mar 40497
## 70 Maryland 2016 Apr 26655
## 71 Maryland 2016 May 5828
## 72 Maryland 2020 Jan 21532
## 73 Maryland 2020 Feb 20708
## 74 Maryland 2020 Mar 23864
## 75 Maryland 2020 Apr 10061
## 76 Maryland 2020 May 23488
## 77 North Carolina 2016 Jan 35213
## 78 North Carolina 2016 Feb 84357
## 79 North Carolina 2016 Mar 58272
## 80 North Carolina 2016 Apr 73341
## 81 North Carolina 2016 May 29374
## 82 North Carolina 2020 Jan 111990
## 83 North Carolina 2020 Feb 54053
## 84 North Carolina 2020 Mar 54807
## 85 North Carolina 2020 Apr 35484
## 86 North Carolina 2020 May 23517
## 87 Texas 2016 Jan 132860
## 88 Texas 2016 Feb 143795
## 89 Texas 2016 Mar 170607
## 90 Texas 2016 Apr 143199
## 91 Texas 2016 May 91205
## 92 Texas 2020 Jan 134559
## 93 Texas 2020 Feb 130080
## 94 Texas 2020 Mar 129424
## 95 Texas 2020 Apr 34694
## 96 Texas 2020 May 35678
## 97 Virginia 2016 Jan 20032
## 98 Virginia 2016 Feb 36911
## 99 Virginia 2016 Mar 44171
## 100 Virginia 2016 Apr 20460
## 101 Virginia 2016 May 26239
## 102 Virginia 2020 Jan 25934
## 103 Virginia 2020 Feb 29507
## 104 Virginia 2020 Mar 31492
## 105 Virginia 2020 Apr 5467
## 106 Virginia 2020 May 8239The data frame voter_registration has 106 observations and 4 variables.
The variables type, Jurisdiction, and Month are in character mode and Year and New.registered.voters that are integers.
# Checked the structure of the data with the function str():
str(voter_registration, vec.len = 1)## 'data.frame': 106 obs. of 4 variables:
## $ Jurisdiction : chr "Arizona" ...
## $ Year : int 2016 2016 ...
## $ Month : chr "Jan" ...
## $ New.registered.voters: int 25852 51155 ...In this dataset “Year” is actually a categorial data not an integer.
# I changed "Year" from integer to a factor.
voter_registration$Year <- as.factor(voter_registration$Year)
str(voter_registration, vec.len = 1)## 'data.frame': 106 obs. of 4 variables:
## $ Jurisdiction : chr "Arizona" ...
## $ Year : Factor w/ 2 levels "2016","2020": 1 1 ...
## $ Month : chr "Jan" ...
## $ New.registered.voters: int 25852 51155 ...The data is 106 lines in length and the “Year” are 2016 and 2020. The minimum of New Registered Voters is 589, Median is 33302, Mean is 48223, and Max New Registered Voters is 238381.
#I did a summary of the dataset.
summary(voter_registration)## Jurisdiction Year Month New.registered.voters
## Length:106 2016:53 Length:106 Min. : 589
## Class :character 2020:53 Class :character 1st Qu.: 19138
## Mode :character Mode :character Median : 33302
## Mean : 48223
## 3rd Qu.: 55258
## Max. :238281Since data was not available for all of states for the month of May, I removed the rows that contain the month of May from the data frame.
#I tried using the below code to remove the rows containing the month of May but I was not successful.
#voter_registration_to_remove <- subset(voter_registration, "Month" != "May") #I then went through the dataset and note down the index # of the rows that contained the month of May and I was able to remove those rows by the index #.
voter_registration_to_remain <- voter_registration[-c(37, 42, 71, 76, 81, 86, 91, 96, 101, 106),]
voter_registration_to_remain## Jurisdiction Year Month New.registered.voters
## 1 Arizona 2016 Jan 25852
## 2 Arizona 2016 Feb 51155
## 3 Arizona 2016 Mar 48614
## 4 Arizona 2016 Apr 30668
## 5 Arizona 2020 Jan 33229
## 6 Arizona 2020 Feb 50853
## 7 Arizona 2020 Mar 31872
## 8 Arizona 2020 Apr 10249
## 9 California 2016 Jan 87574
## 10 California 2016 Feb 103377
## 11 California 2016 Mar 174278
## 12 California 2016 Apr 185478
## 13 California 2020 Jan 151595
## 14 California 2020 Feb 238281
## 15 California 2020 Mar 176810
## 16 California 2020 Apr 38970
## 17 Colorado 2016 Jan 17024
## 18 Colorado 2016 Feb 20707
## 19 Colorado 2016 Mar 25627
## 20 Colorado 2016 Apr 22204
## 21 Colorado 2020 Jan 20260
## 22 Colorado 2020 Feb 33374
## 23 Colorado 2020 Mar 18990
## 24 Colorado 2020 Apr 6034
## 25 Delaware 2016 Jan 3007
## 26 Delaware 2016 Feb 3629
## 27 Delaware 2016 Mar 5124
## 28 Delaware 2016 Apr 3818
## 29 Delaware 2020 Jan 3276
## 30 Delaware 2020 Feb 3353
## 31 Delaware 2020 Mar 2535
## 32 Delaware 2020 Apr 589
## 33 District of Columbia 2016 Jan 2840
## 34 District of Columbia 2016 Feb 2954
## 35 District of Columbia 2016 Mar 4706
## 36 District of Columbia 2016 Apr 4157
## 38 District of Columbia 2020 Jan 3334
## 39 District of Columbia 2020 Feb 3348
## 40 District of Columbia 2020 Mar 2225
## 41 District of Columbia 2020 Apr 1281
## 43 Florida 2016 Jan 50231
## 44 Florida 2016 Feb 87351
## 45 Florida 2016 Mar 73627
## 46 Florida 2016 Apr 52508
## 47 Florida 2020 Jan 77466
## 48 Florida 2020 Feb 109859
## 49 Florida 2020 Mar 54872
## 50 Florida 2020 Apr 21031
## 51 Georgia 2016 Jan 34952
## 52 Georgia 2016 Feb 40976
## 53 Georgia 2016 Mar 44150
## 54 Georgia 2016 Apr 37028
## 55 Georgia 2020 Jan 38573
## 56 Georgia 2020 Feb 55386
## 57 Georgia 2020 Mar 26284
## 58 Georgia 2020 Apr 15484
## 59 Illinois 2016 Jan 44040
## 60 Illinois 2016 Feb 99674
## 61 Illinois 2016 Mar 52782
## 62 Illinois 2016 Apr 76098
## 63 Illinois 2020 Jan 44443
## 64 Illinois 2020 Feb 68455
## 65 Illinois 2020 Mar 47899
## 66 Illinois 2020 Apr 21332
## 67 Maryland 2016 Jan 19580
## 68 Maryland 2016 Feb 29122
## 69 Maryland 2016 Mar 40497
## 70 Maryland 2016 Apr 26655
## 72 Maryland 2020 Jan 21532
## 73 Maryland 2020 Feb 20708
## 74 Maryland 2020 Mar 23864
## 75 Maryland 2020 Apr 10061
## 77 North Carolina 2016 Jan 35213
## 78 North Carolina 2016 Feb 84357
## 79 North Carolina 2016 Mar 58272
## 80 North Carolina 2016 Apr 73341
## 82 North Carolina 2020 Jan 111990
## 83 North Carolina 2020 Feb 54053
## 84 North Carolina 2020 Mar 54807
## 85 North Carolina 2020 Apr 35484
## 87 Texas 2016 Jan 132860
## 88 Texas 2016 Feb 143795
## 89 Texas 2016 Mar 170607
## 90 Texas 2016 Apr 143199
## 92 Texas 2020 Jan 134559
## 93 Texas 2020 Feb 130080
## 94 Texas 2020 Mar 129424
## 95 Texas 2020 Apr 34694
## 97 Virginia 2016 Jan 20032
## 98 Virginia 2016 Feb 36911
## 99 Virginia 2016 Mar 44171
## 100 Virginia 2016 Apr 20460
## 102 Virginia 2020 Jan 25934
## 103 Virginia 2020 Feb 29507
## 104 Virginia 2020 Mar 31492
## 105 Virginia 2020 Apr 5467#Since I removed the rows that contained the month of May, I reset the index.
voter_registration_new <- voter_registration_to_remain
rownames(voter_registration_new) <- 1:nrow(voter_registration_new)
voter_registration_new ## Jurisdiction Year Month New.registered.voters
## 1 Arizona 2016 Jan 25852
## 2 Arizona 2016 Feb 51155
## 3 Arizona 2016 Mar 48614
## 4 Arizona 2016 Apr 30668
## 5 Arizona 2020 Jan 33229
## 6 Arizona 2020 Feb 50853
## 7 Arizona 2020 Mar 31872
## 8 Arizona 2020 Apr 10249
## 9 California 2016 Jan 87574
## 10 California 2016 Feb 103377
## 11 California 2016 Mar 174278
## 12 California 2016 Apr 185478
## 13 California 2020 Jan 151595
## 14 California 2020 Feb 238281
## 15 California 2020 Mar 176810
## 16 California 2020 Apr 38970
## 17 Colorado 2016 Jan 17024
## 18 Colorado 2016 Feb 20707
## 19 Colorado 2016 Mar 25627
## 20 Colorado 2016 Apr 22204
## 21 Colorado 2020 Jan 20260
## 22 Colorado 2020 Feb 33374
## 23 Colorado 2020 Mar 18990
## 24 Colorado 2020 Apr 6034
## 25 Delaware 2016 Jan 3007
## 26 Delaware 2016 Feb 3629
## 27 Delaware 2016 Mar 5124
## 28 Delaware 2016 Apr 3818
## 29 Delaware 2020 Jan 3276
## 30 Delaware 2020 Feb 3353
## 31 Delaware 2020 Mar 2535
## 32 Delaware 2020 Apr 589
## 33 District of Columbia 2016 Jan 2840
## 34 District of Columbia 2016 Feb 2954
## 35 District of Columbia 2016 Mar 4706
## 36 District of Columbia 2016 Apr 4157
## 37 District of Columbia 2020 Jan 3334
## 38 District of Columbia 2020 Feb 3348
## 39 District of Columbia 2020 Mar 2225
## 40 District of Columbia 2020 Apr 1281
## 41 Florida 2016 Jan 50231
## 42 Florida 2016 Feb 87351
## 43 Florida 2016 Mar 73627
## 44 Florida 2016 Apr 52508
## 45 Florida 2020 Jan 77466
## 46 Florida 2020 Feb 109859
## 47 Florida 2020 Mar 54872
## 48 Florida 2020 Apr 21031
## 49 Georgia 2016 Jan 34952
## 50 Georgia 2016 Feb 40976
## 51 Georgia 2016 Mar 44150
## 52 Georgia 2016 Apr 37028
## 53 Georgia 2020 Jan 38573
## 54 Georgia 2020 Feb 55386
## 55 Georgia 2020 Mar 26284
## 56 Georgia 2020 Apr 15484
## 57 Illinois 2016 Jan 44040
## 58 Illinois 2016 Feb 99674
## 59 Illinois 2016 Mar 52782
## 60 Illinois 2016 Apr 76098
## 61 Illinois 2020 Jan 44443
## 62 Illinois 2020 Feb 68455
## 63 Illinois 2020 Mar 47899
## 64 Illinois 2020 Apr 21332
## 65 Maryland 2016 Jan 19580
## 66 Maryland 2016 Feb 29122
## 67 Maryland 2016 Mar 40497
## 68 Maryland 2016 Apr 26655
## 69 Maryland 2020 Jan 21532
## 70 Maryland 2020 Feb 20708
## 71 Maryland 2020 Mar 23864
## 72 Maryland 2020 Apr 10061
## 73 North Carolina 2016 Jan 35213
## 74 North Carolina 2016 Feb 84357
## 75 North Carolina 2016 Mar 58272
## 76 North Carolina 2016 Apr 73341
## 77 North Carolina 2020 Jan 111990
## 78 North Carolina 2020 Feb 54053
## 79 North Carolina 2020 Mar 54807
## 80 North Carolina 2020 Apr 35484
## 81 Texas 2016 Jan 132860
## 82 Texas 2016 Feb 143795
## 83 Texas 2016 Mar 170607
## 84 Texas 2016 Apr 143199
## 85 Texas 2020 Jan 134559
## 86 Texas 2020 Feb 130080
## 87 Texas 2020 Mar 129424
## 88 Texas 2020 Apr 34694
## 89 Virginia 2016 Jan 20032
## 90 Virginia 2016 Feb 36911
## 91 Virginia 2016 Mar 44171
## 92 Virginia 2016 Apr 20460
## 93 Virginia 2020 Jan 25934
## 94 Virginia 2020 Feb 29507
## 95 Virginia 2020 Mar 31492
## 96 Virginia 2020 Apr 5467In order to compare each the Registered Voters for the month of Jan, Feb, Mar and April of each year, I made 2 columns with the total of Registered Voters for the Year 2016 and Year 2020.
voter_registration_new_wide <- pivot_wider(voter_registration_new, names_from = Year, values_from = New.registered.voters)
voter_registration_new_wide## # A tibble: 48 × 4
## Jurisdiction Month `2016` `2020`
## <chr> <chr> <int> <int>
## 1 Arizona Jan 25852 33229
## 2 Arizona Feb 51155 50853
## 3 Arizona Mar 48614 31872
## 4 Arizona Apr 30668 10249
## 5 California Jan 87574 151595
## 6 California Feb 103377 238281
## 7 California Mar 174278 176810
## 8 California Apr 185478 38970
## 9 Colorado Jan 17024 20260
## 10 Colorado Feb 20707 33374
## # … with 38 more rows#I renamed the columns.
colnames(voter_registration_new_wide)[1:4] = c("STATE", "MONTH", "REGISTERED_VOTERS_2016", "REGISTERED_VOTERS_2020")
voter_registration_new_wide## # A tibble: 48 × 4
## STATE MONTH REGISTERED_VOTERS_2016 REGISTERED_VOTERS_2020
## <chr> <chr> <int> <int>
## 1 Arizona Jan 25852 33229
## 2 Arizona Feb 51155 50853
## 3 Arizona Mar 48614 31872
## 4 Arizona Apr 30668 10249
## 5 California Jan 87574 151595
## 6 California Feb 103377 238281
## 7 California Mar 174278 176810
## 8 California Apr 185478 38970
## 9 Colorado Jan 17024 20260
## 10 Colorado Feb 20707 33374
## # … with 38 more rows# I then created a column for the difference of Registgered Voters in 2016 and 2019.
voter_registration_new_wide$REGISTERED_VOTERS_DIFF <- (voter_registration_new_wide$REGISTERED_VOTERS_2016 - voter_registration_new_wide$REGISTERED_VOTERS_2020)
voter_registration_new_wide## # A tibble: 48 × 5
## STATE MONTH REGISTERED_VOTERS_2016 REGISTERED_VOTERS_2020 REGISTERED_V…¹
## <chr> <chr> <int> <int> <int>
## 1 Arizona Jan 25852 33229 -7377
## 2 Arizona Feb 51155 50853 302
## 3 Arizona Mar 48614 31872 16742
## 4 Arizona Apr 30668 10249 20419
## 5 California Jan 87574 151595 -64021
## 6 California Feb 103377 238281 -134904
## 7 California Mar 174278 176810 -2532
## 8 California Apr 185478 38970 146508
## 9 Colorado Jan 17024 20260 -3236
## 10 Colorado Feb 20707 33374 -12667
## # … with 38 more rows, and abbreviated variable name ¹REGISTERED_VOTERS_DIFFNow the dataset is 48 rows in length. You can also see the Min, Median, Mean, Max for Registered Voters 2016, 2020, and the Regisgtered Voters Difference for the 12 States. For the Year 2016 the Min was 2840, the Median was 40737, the Mean was 54068, and the Max was 185478. For the Year 2020 the Min was 589, the Median was 31682, the Mean was 47192, and the Max was 238281. For the difference between the 2 years the Min was -134904, the Median was 3347 the Mean was 6877, and the Max was 146508.
With this summary you can already see that there is a big difference in drop of Registered Voters for the year 2020 in the 12 States. Even though we see that the Max of Registered Voters was in 2020 with a 238281 Registered Voters. This needs further investigation.
#I again did a new summary.
summary(voter_registration_new_wide)## STATE MONTH REGISTERED_VOTERS_2016
## Length:48 Length:48 Min. : 2840
## Class :character Class :character 1st Qu.: 20645
## Mode :character Mode :character Median : 40737
## Mean : 54068
## 3rd Qu.: 74245
## Max. :185478
## REGISTERED_VOTERS_2020 REGISTERED_VOTERS_DIFF
## Min. : 589 Min. :-134904
## 1st Qu.: 14175 1st Qu.: -2097
## Median : 31682 Median : 3347
## Mean : 47192 Mean : 6877
## 3rd Qu.: 54823 3rd Qu.: 17023
## Max. :238281 Max. : 146508I did a ggplot geometric line of the Registered Votes for each State per year.
# Viewing the unique values in the "Month" variable===
unique(voter_registration_new_wide$MONTH)## [1] "Jan" "Feb" "Mar" "Apr"# Identifying the class of the "Month" variable===
class(voter_registration_new_wide$MONTH)## [1] "character"# In order for the Months to be in sequential order in the X axes I had to convert the Month from Character to Factor and set the order.
voter_registration_new_wide <- voter_registration_new_wide %>%
mutate(MONTH = factor(MONTH, levels = c("Jan","Feb","Mar","Apr")))In this graph you can see in 2016 that the Total Registered Voters was increasing for the month of Jan and Feb for most states accept for Illinois, District of Columbia, Florida, and North Carolina, and Arizona. The only States that increased from Mar to Apr was Colorado, North Carolina, and Illinois. Delaware seem to maintain the same through all 4 months.
# I did a ggplot geometric line to compare the Registered Voters for each of the 12 State for 2016.
# I did notice that I would need to use different colors that is not colour because District of Columbia and Florida are the same shade of green.
ggplot(voter_registration_new_wide, aes(x = MONTH, y = REGISTERED_VOTERS_2016, colour = STATE, group = STATE)) +
geom_line() +
geom_point()
In this graph you can see in 2020 that the Total Registered Voters had increased somewhat for the month of Jan to Feb accept for Texas that decreased slightly and North Carolina dropped significantly. California had increased significantly. Feb to April they all decreased significantly accept for Texas, North Carolina, Virginia and Maryland had a slight borderline from Feb to Mar. Again Delaware maintained the same thought the 4 months.
# I did a ggplot geometric line to compare the Registered Voters for each of the 12 State for 2020
ggplot(voter_registration_new_wide, aes(x = MONTH, y = REGISTERED_VOTERS_2020, colour = STATE, group = STATE)) +
geom_line() +
geom_point()
In this graph you can see that Registered Voters difference were closed to or below 0 from Jan to Feb. California tremedously decreased from Jan to Feb. Feb to Mar all State increased slighly accept California that increased significantly. Mar to Apr all States increased a little accept for Texas that increased more and California increased significantly.
# I did a ggplot geometric line to compare the Registered Voters difference for each of the 12 State for 2016 vs 2020
ggplot(voter_registration_new_wide, aes(x = MONTH, y = REGISTERED_VOTERS_DIFF, colour = STATE, group = STATE)) +
geom_line() +
geom_point()
Based on these graphs and data further invesitigation needs to be done on the reason for the sudden increases and decreases in California.
Below I compare total 12 states for Jan, Feb, Mar, and April each year.
# Total all 12 states for Jan, Feb, Mar, and April in 2016.
voter_registration_new_2016 <-voter_registration_new_wide %>%
group_by(MONTH) %>%
summarise(REGISTERED_VOTERS_2016 = sum(REGISTERED_VOTERS_2016))
voter_registration_new_2016## # A tibble: 4 × 2
## MONTH REGISTERED_VOTERS_2016
## <fct> <int>
## 1 Jan 473205
## 2 Feb 704008
## 3 Mar 742455
## 4 Apr 675614Here you can see the tremedous increase and slight decrease for all 12 states from Jan to April in 2016.
ggplot(data=voter_registration_new_2016, aes(x=MONTH, y=REGISTERED_VOTERS_2016, group=1)) +
geom_line()+
geom_point()
# Total all 12 states for Jan, Feb, Mar, and April in 2020.
voter_registration_new_2020 <-voter_registration_new_wide %>%
group_by(MONTH) %>%
summarise(REGISTERED_VOTERS_2020 = sum(REGISTERED_VOTERS_2020))
voter_registration_new_2020## # A tibble: 4 × 2
## MONTH REGISTERED_VOTERS_2020
## <fct> <int>
## 1 Jan 666191
## 2 Feb 797257
## 3 Mar 601074
## 4 Apr 200676Here you can see the tremedous drop for all 12 states from Jan to April in 2020.
ggplot(data=voter_registration_new_2020, aes(x=MONTH, y=REGISTERED_VOTERS_2020, group=1)) +
geom_line()+
geom_point()