Categorical Variable Assignment
Braden Baker
2/19/2021
This assignment is to practice good techniques for showing the distribution of a values of a categorical variable. To do the assignment, you need to select any categorical variable from any dataframe you have encountered in this class or elsewhere.
Problem 1
Load the libraries you need and the data, if necessary. Run str() and summary on the dataframe. Describe the source and point out your selected variable.
I am using the gss_sm dataset from the socviz package. The data contains a variety of demographics from a sample of people.
I will be working with the siblings variable
# Place your code here.
library(tidyverse)## -- Attaching packages ------------------------------------------------------------------------------------ tidyverse 1.3.0 --## v ggplot2 3.3.0 v purrr 0.3.4
## v tibble 3.0.0 v dplyr 0.8.5
## v tidyr 1.0.2 v stringr 1.4.0
## v readr 1.3.1 v forcats 0.5.0## -- Conflicts --------------------------------------------------------------------------------------- tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()library(socviz)
library(waffle)
a4data <- gss_sm
str(a4data)## tibble [2,867 x 32] (S3: tbl_df/tbl/data.frame)
## $ year : num [1:2867] 2016 2016 2016 2016 2016 ...
## ..- attr(*, "label")= chr "GSS YEAR FOR THIS RESPONDENT "
## ..- attr(*, "format.stata")= chr "%8.0g"
## $ id : num [1:2867] 1 2 3 4 5 6 7 8 9 10 ...
## ..- attr(*, "label")= chr "RESPONDNT ID NUMBER "
## ..- attr(*, "format.stata")= chr "%8.0g"
## $ ballot : 'labelled' num [1:2867] 1 2 3 1 3 2 1 3 1 3 ...
## ..- attr(*, "label")= chr "BALLOT USED FOR INTERVIEW"
## ..- attr(*, "format.stata")= chr "%8.0g"
## ..- attr(*, "labels")= Named num [1:5] 0 1 2 3 4
## .. ..- attr(*, "names")= chr [1:5] "iap" "BALLOT A" "BALLOT B" "BALLOT C" ...
## $ age : num [1:2867] 47 61 72 43 55 53 50 23 45 71 ...
## ..- attr(*, "label")= chr "AGE OF RESPONDENT"
## ..- attr(*, "format.stata")= chr "%8.0g"
## ..- attr(*, "labels")= Named num [1:3] 89 98 99
## .. ..- attr(*, "names")= chr [1:3] "89 OR OLDER" "dk" "na"
## $ childs : num [1:2867] 3 0 2 4 2 2 2 3 3 4 ...
## ..- attr(*, "label")= chr "NUMBER OF CHILDREN"
## ..- attr(*, "format.stata")= chr "%8.0g"
## ..- attr(*, "labels")= Named num [1:2] 8 9
## .. ..- attr(*, "names")= chr [1:2] "EIGHT OR MORE" "DK NA"
## $ sibs : 'labelled' num [1:2867] 2 3 3 3 2 2 2 6 5 1 ...
## ..- attr(*, "label")= chr "NUMBER OF BROTHERS AND SISTERS"
## ..- attr(*, "format.stata")= chr "%8.0g"
## ..- attr(*, "labels")= Named num [1:3] -1 98 99
## .. ..- attr(*, "names")= chr [1:3] "iap" "dk" "na"
## $ degree : Factor w/ 5 levels "Lt High School",..: 4 2 4 2 5 3 2 2 2 3 ...
## $ race : Factor w/ 3 levels "White","Black",..: 1 1 1 1 1 1 1 3 2 1 ...
## $ sex : Factor w/ 2 levels "Male","Female": 1 1 1 2 2 2 1 2 1 1 ...
## $ region : Factor w/ 9 levels "New England",..: 1 1 1 1 1 1 1 2 2 2 ...
## $ income16 : Factor w/ 26 levels "under $1 000",..: 26 19 21 26 26 20 26 16 20 20 ...
## $ relig : Factor w/ 13 levels "Protestant","Catholic",..: 4 4 2 2 4 4 4 2 1 4 ...
## $ marital : Factor w/ 5 levels "Married","Widowed",..: 1 5 1 1 1 1 1 1 1 3 ...
## $ padeg : Factor w/ 5 levels "Lt High School",..: 5 1 2 NA 4 NA 2 1 1 2 ...
## $ madeg : Factor w/ 5 levels "Lt High School",..: 2 2 1 2 2 2 2 1 1 2 ...
## $ partyid : Factor w/ 8 levels "Strong Democrat",..: 4 3 6 6 2 2 6 3 1 7 ...
## $ polviews : Factor w/ 7 levels "Extremely Liberal",..: 4 2 6 4 3 3 3 5 NA 6 ...
## $ happy : Factor w/ 3 levels "Very Happy","Pretty Happy",..: 2 2 1 2 1 1 2 1 2 2 ...
## $ partners : Factor w/ 9 levels "No Partners",..: NA 2 2 NA 2 2 NA 2 NA 4 ...
## $ grass : Factor w/ 2 levels "Legal","Not Legal": NA 1 2 NA 1 1 NA 2 NA 2 ...
## $ zodiac : Factor w/ 12 levels "Aries","Taurus",..: 11 8 12 4 8 8 10 11 NA 9 ...
## $ pres12 : 'labelled' num [1:2867] 3 1 2 2 1 1 NA NA NA 2 ...
## ..- attr(*, "label")= chr "VOTE OBAMA OR ROMNEY"
## ..- attr(*, "format.stata")= chr "%8.0g"
## ..- attr(*, "labels")= Named num [1:7] 0 1 2 3 4 8 9
## .. ..- attr(*, "names")= chr [1:7] "iap" "Obama" "Romney" "Other candidate (SPECIFY)" ...
## $ wtssall : num [1:2867] 0.957 0.478 0.957 1.914 1.435 ...
## ..- attr(*, "label")= chr "WEIGHT VARIABLE"
## ..- attr(*, "format.stata")= chr "%12.0g"
## ..- attr(*, "labels")= Named num -1
## .. ..- attr(*, "names")= chr "iap"
## $ income_rc : Factor w/ 16 levels "Gt $0","Gt $10000",..: 16 9 11 16 16 10 16 6 10 10 ...
## $ agegrp : Factor w/ 5 levels "Age 18-35","Age 35-45",..: 3 4 5 2 3 3 3 1 2 5 ...
## $ ageq : Factor w/ 4 levels "Age 18-34","Age 34-49",..: 2 3 4 2 3 3 3 1 2 4 ...
## $ siblings : Factor w/ 7 levels "0","1","2","3",..: 3 4 4 4 3 3 3 7 6 2 ...
## $ kids : Factor w/ 5 levels "0","1","2","3",..: 4 1 3 5 3 3 3 4 4 5 ...
## $ religion : Factor w/ 5 levels "Protestant","Catholic",..: 4 4 2 2 4 4 4 2 1 4 ...
## $ bigregion : Factor w/ 4 levels "Northeast","Midwest",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ partners_rc: Factor w/ 5 levels "0","1","2","3",..: NA 2 2 NA 2 2 NA 2 NA 4 ...
## $ obama : num [1:2867] 0 1 0 0 1 1 NA NA NA 0 ...Problem 2
Do a default bar plot of your variable.
# Place your code here.
ggplot(a4data, aes(x=siblings)) + geom_bar()
Problem 3
Use dplyr verbs to create a smaller dataframe that includes the counts of the categorical variable values in a variable count. Reorder the values of the variable according to count. Use geom_col() and put the categorical values on the vertical axis.
# Place your code here.
a4data <- a4data %>%
filter(!is.na(siblings)) %>%
group_by(siblings) %>%
summarise(count = n())
ggplot(a4data, aes(x=reorder(siblings, count), y=count)) + geom_col() + coord_flip() + labs(x='Siblings', y='Count', title = "Distribution of Siblings")
Problem 4
Create a pie chart to show the proportions of the categorical variable with its various values.
ggplot(a4data, aes(x=1, y=count, fill=siblings)) +
geom_col() +
coord_polar(theta = 'y') +
theme_void() +
labs(title="Distribution of Siblings")
Problem 5
As an alternative to the pie chart, create a waffle plot.
a4data <- a4data %>%
mutate(percent = round(count/sum(count)*100))
a4waffle <- as.numeric(a4data$percent)
names(a4waffle) <- a4data$siblings
waffle(a4waffle, title='Distribution of Siblings')