Quiz 3: Superheroes
Kanitta Srichan Elder
4/7/2022
Download and load the Superheroes Dataset (heroes_information.csv) into a data frame.
Use any of the tools you currently have from Base R, the tidyverse and ggplot2 to answer the questions below.
library(tidyverse)## Warning: package 'tidyverse' was built under R version 4.1.3## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --## v ggplot2 3.3.5 v purrr 0.3.4
## v tibble 3.1.6 v dplyr 1.0.8
## v tidyr 1.2.0 v stringr 1.4.0
## v readr 2.1.2 v forcats 0.5.1## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()heroes_info <- read.csv("heroes_information.csv")
#heroes_info- Examine the data set with str, dim, etc. What do you notice about the data? Are there any potential problems? There are missing data such like “-” and some data such first column that we do not need. Negative Weight and Heights are the potential problems too
class(heroes_info)## [1] "data.frame"dim(heroes_info)## [1] 734 11summary(heroes_info)## X name Gender Eye.color
## Min. : 0.0 Length:734 Length:734 Length:734
## 1st Qu.:183.2 Class :character Class :character Class :character
## Median :366.5 Mode :character Mode :character Mode :character
## Mean :366.5
## 3rd Qu.:549.8
## Max. :733.0
##
## Race Hair.color Height Publisher
## Length:734 Length:734 Min. :-99.0 Length:734
## Class :character Class :character 1st Qu.:-99.0 Class :character
## Mode :character Mode :character Median :175.0 Mode :character
## Mean :102.3
## 3rd Qu.:185.0
## Max. :975.0
##
## Skin.color Alignment Weight
## Length:734 Length:734 Min. :-99.00
## Class :character Class :character 1st Qu.:-99.00
## Mode :character Mode :character Median : 62.00
## Mean : 43.86
## 3rd Qu.: 90.00
## Max. :900.00
## NA's :2str(heroes_info)## 'data.frame': 734 obs. of 11 variables:
## $ X : int 0 1 2 3 4 5 6 7 8 9 ...
## $ name : chr "A-Bomb" "Abe Sapien" "Abin Sur" "Abomination" ...
## $ Gender : chr "Male" "Male" "Male" "Male" ...
## $ Eye.color : chr "yellow" "blue" "blue" "green" ...
## $ Race : chr "Human" "Icthyo Sapien" "Ungaran" "Human / Radiation" ...
## $ Hair.color: chr "No Hair" "No Hair" "No Hair" "No Hair" ...
## $ Height : num 203 191 185 203 -99 193 -99 185 173 178 ...
## $ Publisher : chr "Marvel Comics" "Dark Horse Comics" "DC Comics" "Marvel Comics" ...
## $ Skin.color: chr "-" "blue" "red" "-" ...
## $ Alignment : chr "good" "good" "good" "bad" ...
## $ Weight : num 441 65 90 441 -99 122 -99 88 61 81 ...heroes_info <- as_tibble(heroes_info)
heroes_info <- select(heroes_info, -X)
sum(is.na(heroes_info))## [1] 2heroes_info[heroes_info == "-"] <- NA- How many superheroes are Human? What race has the second highest number of superheroes? Do not count rows where Race is not given. 208 superheroes are Human. Mutant has the second highest number of superheroes.
group_race <- heroes_info %>%
group_by(Race) %>%
summarise(n = n())
group_race %>% arrange(desc(n))## # A tibble: 62 x 2
## Race n
## <chr> <int>
## 1 <NA> 304
## 2 Human 208
## 3 Mutant 63
## 4 God / Eternal 14
## 5 Cyborg 11
## 6 Human / Radiation 11
## 7 Android 9
## 8 Symbiote 9
## 9 Alien 7
## 10 Kryptonian 7
## # ... with 52 more rows- Find the frequency of Gender values. How many female superheroes are there? 200 Female superheroes.
table(heroes_info$Gender)##
## Female Male
## 200 505- Create a contingency table for Gender and Alignment. What do you notice about this analysis?
I have noticed that there are higher-good superheroes than bad, both male and female. When comparing males and females, I see that males have a higher number in the same category in all aspects.
Gender_x_Alignment <- table(heroes_info$Gender, heroes_info$Alignment)
Gender_x_Alignment##
## bad good neutral
## Female 35 161 4
## Male 165 316 18- Filter the data to remove rows where Height is less than 0. Do the same for Weight. Use this filtered data for questions 6 through 10 below.
heroes_info <- heroes_info %>% filter(Height > 0 )
heroes_info <- heroes_info %>% filter(Weight > 0 )
heroes_info## # A tibble: 490 x 10
## name Gender Eye.color Race Hair.color Height Publisher Skin.color Alignment
## <chr> <chr> <chr> <chr> <chr> <dbl> <chr> <chr> <chr>
## 1 A-Bo~ Male yellow Human No Hair 203 Marvel C~ <NA> good
## 2 Abe ~ Male blue Icth~ No Hair 191 Dark Hor~ blue good
## 3 Abin~ Male blue Unga~ No Hair 185 DC Comics red good
## 4 Abom~ Male green Huma~ No Hair 203 Marvel C~ <NA> bad
## 5 Abso~ Male blue Human No Hair 193 Marvel C~ <NA> bad
## 6 Adam~ Male blue Human Blond 185 DC Comics <NA> good
## 7 Agen~ Female blue <NA> Blond 173 Marvel C~ <NA> good
## 8 Agen~ Male brown Human Brown 178 Marvel C~ <NA> good
## 9 Agen~ Male <NA> <NA> <NA> 191 Marvel C~ <NA> good
## 10 Air-~ Male blue <NA> White 188 Marvel C~ <NA> bad
## # ... with 480 more rows, and 1 more variable: Weight <dbl>- Calculate the mean, median and standard deviation of superhero Weight and Height.
#Weight
mean(heroes_info$Weight, na.rm = TRUE)## [1] 112.1796median(heroes_info$Weight, na.rm = TRUE)## [1] 81sd(heroes_info$Weight, na.rm = TRUE)## [1] 104.4227#Height
mean(heroes_info$Height, na.rm = TRUE)## [1] 187.1239median(heroes_info$Height, na.rm = TRUE)## [1] 183sd(heroes_info$Height, na.rm = TRUE)## [1] 58.99002- Create a histogram of Weight. Describe the distribution and what it tells us. The histogram is unimodal and right-skewed with two outliers at 600-700 and 800-900. It shows how many superheroes are lightweight because they weigh between 0-100 and 100-200. Only a couple of superheroes have a heavy weight with 600-700 and 800-900.
hist(heroes_info$Weight, main="Maximum weight of Superheroes",
xlab="Weight",xlim=c(0,1100),
col="lightskyblue"
)
- Plot Height vs. Weight. Do you see any correlation? Describe what you see. The points lie close to a straight line, which has a positive gradient. It shows that as one variable increases, the other increases. It is a positive correlation between height and weight. However, it is weak because it is slightly going up. In other words, taller superheroes seem to be a bit heavier than the ones shorter.
plot(heroes_info$Weight, heroes_info$Height , main = "Height vs. Weight",
xlab = "Weight", ylab = "Height")
abline(lm(Height ~ Weight, data = heroes_info), col = "blue")
- Calculate the five-number summary values for Height and Weight. Create a box plot of Weight for Alignment. What does this chart tell us?
The median weight for good superheroes is slightly less than bad and neutral. There is a greater variability for neutral than any other, but good superheroes have the largest outliers. The minimun number of bad superheroes is higher than others.
The chart tells us that good superheroes have the least average weight of all. The good superheroes have the less dispersed the weight, While the nuetral seems to have more dispersed weight. The minimum weight of bad superheroes is higher than other.
fivenum(heroes_info$Height)## [1] 15.2 173.0 183.0 188.0 975.0fivenum(heroes_info$Weight)## [1] 4 61 81 106 900boxplot(heroes_info$Weight ~ heroes_info$Alignment)
- Filter the data to include only the two largest publishers. Which publisher has a higher proportion of bad aligned superheroes? Hint: One way to do this is to use dplyr and group by the two columns Publisher and Alignment rather than a single column. The two largest publishers are Marvel Comics and DC Comics. Marvel Comics has a higher proportion of bad aligned superheroes by about 0.02.
#heroes_info %>% group_by(Publisher)
heroes_info %>% count(Publisher, sort = TRUE) ## # A tibble: 10 x 2
## Publisher n
## <chr> <int>
## 1 "Marvel Comics" 318
## 2 "DC Comics" 143
## 3 "Dark Horse Comics" 11
## 4 "George Lucas" 5
## 5 "Shueisha" 4
## 6 "Team Epic TV" 4
## 7 "Star Trek" 2
## 8 "" 1
## 9 "Image Comics" 1
## 10 "Sony Pictures" 1data_group <- filter(heroes_info, Publisher == "Marvel Comics" | Publisher == "DC Comics", na.rm = TRUE)
con_tab <- table(data_group$Publisher, data_group$Alignment)
con_tab##
## bad good neutral
## DC Comics 40 94 8
## Marvel Comics 92 215 9prop.table(con_tab, 1) ##
## bad good neutral
## DC Comics 0.28169014 0.66197183 0.05633803
## Marvel Comics 0.29113924 0.68037975 0.02848101