Exercise 6: tidycomm
After working through Exercise 6, you’ll…
- have practiced the most important functions of
tidycomm - have decided whether you prefer
tidycommordplyrto solve some problems in R
First, you’ll need to load the statwars_data:
Please, also activate the tidycomm package:
Task 1
How many characters are contained in the starwars_data that have no hair_color, i.e. hair_color that are equal to “none”?
Solve this task using tidycomm::tab_frequencies() and then keeping only the row that you are interested in by combining it with dplyr::filter().
Task 2
Replace all values of hair_color that are equal to “none” with NA, i.e., define them as missings. Remember to check the overwrite argument. :)
Task 3
Reverse the variable mass, and call the new variable “skinnyness”. Reverse the variable height, and call the new variable “tinyness”.
Task 4
Scale skinnyness to a new range from 0 to 1. The function should automatically create a variable called skinnyness_0to1. Display only the variables name, skinnyness, and skinnyness_0to1.
Task 5
Create two new variables: skinnyness_centered with center_scale() and skinnyness_z with z_scale().
Display all the variables name, skinnyness, skinnyness_0to1, skinnyness_centered, skinnyness_z.
Task 6
Visualize the variables skinnyness, skinnyness_0to1, skinnyness_centered, skinnyness_z using tidycomm::tab_frequencies) and tidycomm::visualize().
Task 7
Categorize skinnyness into three groups:
- “Heavy” for values ≤ 1200
- “Slim” for values > 1200 and ≤ 1300
- “Skinny” for values > 1300
Use tidycomm::categorize_scale(). The function should automatically create a variable called skinnyness_cat. Display the variables name, skinnyness, and skinnyness_cat.
Task 8
Use tidycomm::recode_cat_scale() to recode skinnyness_cat like this:
"Heavy"→"high_mass"
"Slim"→"medium_mass"
"Skinny"→"low_mass"
Do not overwrite the original variable. Instead, let recode_cat_scale() create a new variable automatically.
Display the variables name, skinnyness, skinnyness_cat, and the recoded variable.
Task 9
Create a mean index called smallness_index using the variables skinnyness and tinyness. Then display only the mean index and the original variables that were used to create it.