a. How many rows and columns of data are there in the data
set?
rows <- nrow(religiousdata)
columns <- ncol(religiousdata)
a <- list("rows" = rows, "columns" = columns)
a## $rows
## [1] 138
##
## $columns
## [1] 373b. Are there any missing values in the participants’ ages? What
is the average age of the participants? What is the most frequent
age?
religiousdata %>%
summarise(
missing_values = sum(is.na(age)),
mean_age = mean(age, na.rm = TRUE),
mode_age = age %>%
na.omit() %>%
table() %>%
which.max()
)## missing_values mean_age mode_age
## 1 0 23.5942 7c. In the data set, the variables depress1, depress2, …,
depress21 are measures of depression. Select these columns and save as a
subset called relig_depress.
relig_depress <- religiousdata %>%
select(starts_with("depress"))
glimpse(relig_depress)## Rows: 138
## Columns: 21
## $ depress1 <int> 2, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, …
## $ depress2 <int> 2, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 0, …
## $ depress3 <int> 1, 0, 0, 1, 0, 0, 0, 1, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 0, 0, …
## $ depress4 <int> 2, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 0, 1, 0, 0, 1, 1, 0, …
## $ depress5 <int> 2, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, …
## $ depress6 <int> 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 3, 0, 0, 1, 0, 0, 0, 0, …
## $ depress7 <int> 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 3, 0, 0, 0, 0, 0, 0, 0, …
## $ depress8 <int> 2, 3, 1, 0, 2, 0, 0, 0, 2, 1, 0, 1, 2, 0, 2, 0, 0, 1, 0, 0, …
## $ depress9 <int> 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, …
## $ depress10 <int> 5, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, …
## $ depress11 <int> 2, 0, 1, 0, 1, 0, 0, 1, 0, 0, 1, 1, 2, 0, 1, 0, 0, 1, 0, 0, …
## $ depress12 <int> 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 3, 0, 0, 0, 0, 1, 0, 0, …
## $ depress13 <int> 0, 3, 1, 0, 0, 0, 0, 0, 1, 0, 1, 1, 3, 1, 1, 0, 0, 1, 0, 0, …
## $ depress14 <int> 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 2, 0, 0, 0, 0, 0, 0, 0, …
## $ depress15 <int> 2, 1, 0, 0, 0, 0, 0, 1, 0, 0, 1, 1, 2, 0, 0, 0, 1, 2, 1, 1, …
## $ depress16 <int> 2, 3, 1, 1, 0, 0, 0, 1, 1, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, 1, …
## $ depress17 <int> 0, 0, 2, 0, 0, 0, 0, 2, 1, 1, 1, 1, 2, 1, 0, 0, 0, 2, 0, 0, …
## $ depress18 <int> 2, 1, 0, 0, 1, 0, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 0, 1, 0, 0, …
## $ depress19 <int> 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 1, 1, 2, 0, 2, 0, 1, 2, 0, 2, …
## $ depress20 <int> 1, 1, 0, 0, 0, 0, 0, 2, 1, 1, 1, 1, 3, 0, 0, 0, 0, 1, 1, 1, …
## $ depress21 <int> 2, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, …d. Calculate the total score of depression by adding the 21
depression variables together for each participant (set na.rm = TRUE)
and add this total score as a new variable to the relig_depress subset,
and save the new subset as relig_depress_total.
relig_depress_total <- relig_depress %>%
rowwise() %>%
mutate(depress_total = sum(c_across(everything()), na.rm = TRUE)) %>%
ungroup()
glimpse(relig_depress_total)## Rows: 138
## Columns: 22
## $ depress1 <int> 2, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0,…
## $ depress2 <int> 2, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0,…
## $ depress3 <int> 1, 0, 0, 1, 0, 0, 0, 1, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 0,…
## $ depress4 <int> 2, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 0, 1, 0, 0, 1, 1,…
## $ depress5 <int> 2, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0,…
## $ depress6 <int> 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 3, 0, 0, 1, 0, 0, 0,…
## $ depress7 <int> 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 3, 0, 0, 0, 0, 0, 0,…
## $ depress8 <int> 2, 3, 1, 0, 2, 0, 0, 0, 2, 1, 0, 1, 2, 0, 2, 0, 0, 1, 0,…
## $ depress9 <int> 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 1, 1, 0, 0, 0,…
## $ depress10 <int> 5, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0,…
## $ depress11 <int> 2, 0, 1, 0, 1, 0, 0, 1, 0, 0, 1, 1, 2, 0, 1, 0, 0, 1, 0,…
## $ depress12 <int> 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 3, 0, 0, 0, 0, 1, 0,…
## $ depress13 <int> 0, 3, 1, 0, 0, 0, 0, 0, 1, 0, 1, 1, 3, 1, 1, 0, 0, 1, 0,…
## $ depress14 <int> 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 2, 0, 0, 0, 0, 0, 0,…
## $ depress15 <int> 2, 1, 0, 0, 0, 0, 0, 1, 0, 0, 1, 1, 2, 0, 0, 0, 1, 2, 1,…
## $ depress16 <int> 2, 3, 1, 1, 0, 0, 0, 1, 1, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0,…
## $ depress17 <int> 0, 0, 2, 0, 0, 0, 0, 2, 1, 1, 1, 1, 2, 1, 0, 0, 0, 2, 0,…
## $ depress18 <int> 2, 1, 0, 0, 1, 0, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 0, 1, 0,…
## $ depress19 <int> 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 1, 1, 2, 0, 2, 0, 1, 2, 0,…
## $ depress20 <int> 1, 1, 0, 0, 0, 0, 0, 2, 1, 1, 1, 1, 3, 0, 0, 0, 0, 1, 1,…
## $ depress21 <int> 2, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 1, 0,…
## $ depress_total <int> 31, 15, 9, 2, 4, 0, 0, 14, 10, 6, 8, 17, 32, 2, 14, 4, 3…e. Save the relig_depress_total subset into .csv data file. [Use
write.csv function here.
write.csv(
relig_depress_total,
file = "relig_depress_total.csv",
row.names = FALSE
)In this case study, you’re going to work with a famous dataset, Iris.
Please use the Tidyverse to solve the following questions:
a.
The iris dataset is pre-installed in R. Please convert it to a tibble
and save the tibble as an object called iris_dat.
irisdat <- as_tibble(iris)
irisdat## # A tibble: 150 × 5
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## <dbl> <dbl> <dbl> <dbl> <fct>
## 1 5.1 3.5 1.4 0.2 setosa
## 2 4.9 3 1.4 0.2 setosa
## 3 4.7 3.2 1.3 0.2 setosa
## 4 4.6 3.1 1.5 0.2 setosa
## 5 5 3.6 1.4 0.2 setosa
## 6 5.4 3.9 1.7 0.4 setosa
## 7 4.6 3.4 1.4 0.3 setosa
## 8 5 3.4 1.5 0.2 setosa
## 9 4.4 2.9 1.4 0.2 setosa
## 10 4.9 3.1 1.5 0.1 setosa
## # ℹ 140 more rowsb. Keep only three variables–Sepal.Length, Petal.Length, and
Species–and arrange them in this order: Species, Sepal.Length,
Petal.Length. Save this subset as an object called iris_subset.
iris_subset <- irisdat %>%
dplyr::select(Species, Sepal.Length, Petal.Length)
iris_subset## # A tibble: 150 × 3
## Species Sepal.Length Petal.Length
## <fct> <dbl> <dbl>
## 1 setosa 5.1 1.4
## 2 setosa 4.9 1.4
## 3 setosa 4.7 1.3
## 4 setosa 4.6 1.5
## 5 setosa 5 1.4
## 6 setosa 5.4 1.7
## 7 setosa 4.6 1.4
## 8 setosa 5 1.5
## 9 setosa 4.4 1.4
## 10 setosa 4.9 1.5
## # ℹ 140 more rowsc. Within iris_subset, filter out rows where Sepal.Length is
greater than 6.
iris_subset <- iris_subset %>%
filter(Sepal.Length <= 6)
iris_subset## # A tibble: 89 × 3
## Species Sepal.Length Petal.Length
## <fct> <dbl> <dbl>
## 1 setosa 5.1 1.4
## 2 setosa 4.9 1.4
## 3 setosa 4.7 1.3
## 4 setosa 4.6 1.5
## 5 setosa 5 1.4
## 6 setosa 5.4 1.7
## 7 setosa 4.6 1.4
## 8 setosa 5 1.5
## 9 setosa 4.4 1.4
## 10 setosa 4.9 1.5
## # ℹ 79 more rowsd. Within iris_subset, compute average Petal.Length.
iris_mean <- iris_subset %>%
group_by(Species) %>%
summarize(mean_petal_length = mean(Petal.Length))
iris_mean## # A tibble: 3 × 2
## Species mean_petal_length
## <fct> <dbl>
## 1 setosa 1.46
## 2 versicolor 4.04
## 3 virginica 4.96e. Add the average Petal.Length as a new variable to
iris_subset
iris_subset <- iris_subset %>%
group_by(Species) %>%
mutate(mean_petal_length = mean(Petal.Length))
iris_subset## # A tibble: 89 × 4
## # Groups: Species [3]
## Species Sepal.Length Petal.Length mean_petal_length
## <fct> <dbl> <dbl> <dbl>
## 1 setosa 5.1 1.4 1.46
## 2 setosa 4.9 1.4 1.46
## 3 setosa 4.7 1.3 1.46
## 4 setosa 4.6 1.5 1.46
## 5 setosa 5 1.4 1.46
## 6 setosa 5.4 1.7 1.46
## 7 setosa 4.6 1.4 1.46
## 8 setosa 5 1.5 1.46
## 9 setosa 4.4 1.4 1.46
## 10 setosa 4.9 1.5 1.46
## # ℹ 79 more rows