Week 11 Challenge Problem

Preparation Instructions

• Be sure to change the author in the YAML to your name. Remember to keep it inside the quotes.

• Questions that require the use of R will have an R code chunk below it.

• Download the datasets about word count in the Lord of the Rings trilogy (titled The_Fellowship_Of_The_Ring.csv, The_Two_Towers.csv, and The_Return_Of_The_King.csv) and LOTR-Table.png from the Canvas page for this assignment and save these files to the folder where the RMD file is located.

• There is less hand-holding in this assignment.

  • The packages that need to be loaded will no longer be provided in the setup code chunk. You are responsible for loading the appropriate packages for the assignment.
  • Questions on examining the data will no longer be provided. You are responsible for getting a sense of the data prior to completing the analyses.

THE DATASETS

For this Challenge Problem assignment, you are going to be using data from the Lord of the Rings Trilogy on total number of words spoken, by characters of different races and sexes. The data provided are stored by movie (1st movie: The Fellowship of the Ring; 2nd movie: The Two Towers; 3rd movie: The Return of the King).

EXERCISES

Practice Problems

Now let’s practice data wrangling (in particular, reshaping).

1. Based on how the datasets are right now, identify two things that make the data untidy.

• The column headers contain values (female and male) rather than the variable name (sex), and a single observational unit is stored in multiple tables.

2. Merge the three datasets together to create a single dataset. Save this new dataset in an object called lotr1 (for “Lord of The Rings”). Hint: Because these three datasets all have completely different observations (no overlap between datasets), you can just use the bind_rows() function to do this.

lotr1 <- bind_rows(fellowship, two_towers, return_king)

lotr1

3. Reshape the lotr1 dataset so that Sex is a single column and word count, Words, is a single column. Save this new dataset in an object called lotr2. The following image shows the first 6 rows of the desired dataset (there should be 18 rows in the actual dataset):

lotr2 <- lotr1 %>%
  pivot_longer(cols = c(Female, Male),
               names_to = "Sex",
               values_to = "Words")
lotr2

4. Reshape the lotr2 dataset so that the columns the number of words spoken in each movie by each race (still separate rows for male and female, i.e. Sex as a variable). The following image shows the desired dataset:

reshaped_lotr2 <- lotr2 %>%
  pivot_wider(id_cols = c(Film, Sex),
              names_from = Race,
              values_from = Words)
reshaped_lotr2

Putting It All Together

Now let’s put the reshaped datasets to use (in addition to other data verbs and data visualization) to answer questions.

Question #1: Of all the words spoken, what is the total number and proportion of words spoken by female elves in Lord of the Rings?

5. Create a data visualization or a “pretty” table to answer the posed question in Question #1. Be sure to take into account meaningful design elements as you create your plot or table.

female_words <- lotr2 %>%
  filter(Race == "Elf", Sex == "Female") %>%
  summarise(word_count = sum(Words)) %>%
  pull(word_count)

total_words <- lotr2 %>%
  summarise(word_count = sum(Words)) %>%
pull(word_count)

female_proportion <- female_words / total_words

tibble(
  Category = c("Female Elves", "Total"),
  Word_count = c(female_words, total_words),
  Proportion = c(female_proportion, 1)) %>%
  gt() %>%
  tab_header(title = "Female Eleves in Lord of the Rings:",
             subtitle = "Total number and proportion of words spoken ") %>%
  cols_label(
    Word_count = "Word Count",
    Proportion = "Proportion") %>%
  fmt_percent(columns = Proportion, decimals = 2)

Female Eleves in Lord of the Rings:
Total number and proportion of words spoken
Category	Word Count	Proportion
Female Elves	1743	8.20%
Total	21245	100.00%

Question #2: Does a certain race dominate the words spoken a single movie? Does the dominant race differ across movies?

6. Create a data visualization or a “pretty” table to answer the posed question in Question #2. Be sure to take into account meaningful design elements as you create your plot or table.

race_movie <- lotr2 %>%
  group_by(Film, Race) %>%
  summarise(word_count = sum(Words), .groups = "drop")

ggplot(race_movie, aes(x = Race, y = word_count, fill = Race)) +
  geom_col() +
  facet_wrap(~ Film, scales = "free_y") +
  scale_fill_paletteer_d("ggsci::default_ucscgb") +   
  labs(
    title = "Lord of the Ring Movies: Total Words Spoken",
    subtitle = "Comparing which race speaks the most",
    x = "Race", y = "Total Words Spoken") +
  theme_minimal() +
  theme(
    legend.position = "none", 
    plot.title = element_text(face ="bold", size = 16, hjust = 0.5),
    plot.subtitle = element_text(hjust = 0.5))

7. Wrangle the data to reproduce the following table (Hint: think about what 7 columns you need to have in your data before making your gt table):

sex <- lotr2 %>%
  pivot_wider(id_cols = c(Film, Race),
              names_from = "Sex",
              values_from= "Words")

race_sex <- sex %>%
    pivot_wider(id_cols = Film,
              names_from = Race,
              values_from= c(Female, Male)) 

race_sex %>%
  gt() %>%
  tab_header(title = "Words Spoken by Characters (Sex, Race) in LOTR") %>%
  tab_spanner(label = "Female Characters", columns = c(Female_Elf, Female_Hobbit, Female_Man)) %>%
  tab_spanner(label = "Male Characters", columns = c(Male_Elf, Male_Hobbit, Male_Man)) %>%
  cols_label(
    Film = "Film",
    Female_Elf = "Elf",
    Female_Hobbit = "Hobbit",
    Female_Man = "Human",
    Male_Elf = "Elf",
    Male_Hobbit = "Hobbit",
    Male_Man = "Human")

Words Spoken by Characters (Sex, Race) in LOTR
Film	Female Characters			Male Characters
	Elf	Hobbit	Human	Elf	Hobbit	Human
The Fellowship Of The Ring	1229	14	0	971	3644	1995
The Two Towers	331	0	401	513	2463	3589
The Return Of The King	183	2	268	510	2673	2459