| Juan Pablo Olazaba STA-6233 |
Exercise 1
Assign the following values to a vector named Student: “Jack”, “Diana”, “Steve”, “Morgan”.
Student <- c("Jack", "Diana", "Steve", "Morgan")
Student## [1] "Jack" "Diana" "Steve" "Morgan"Exercise 2
Add one more student named “Vivian” to the vector Student
Student <- c(Student, "Vivian")
Student## [1] "Jack" "Diana" "Steve" "Morgan" "Vivian"Exercise 3
Print the 2nd and 5th names in the vector Student.
Student[c(2, 5)]## [1] "Diana" "Vivian"Exercise 4
In R, if V1 <- c(2, 4, 5), V2 <- seq(1, 10,2), what is the result of V1+V2?
V1 <- c(2, 4, 5)
V2 <- seq(1, 10,2)
V1+V2## Warning in V1 + V2: longer object length is not a multiple of shorter object
## length## [1] 3 7 10 9 13Exercise 5
If V3 <- c(3, 5, “Apple”, NA), what is the class of V3? What is the result of is.na(V3)?
V3 <- c(3, 5, "Apple", NA)
class(V3)## [1] "character"is.na(V3)## [1] FALSE FALSE FALSE TRUEExercise 6
For the vector size <- c(1,2,2,1,3,4,4,3), complete the following task: a. Convert it to a factor named size_factor. b. Print the levels of the data c. Label the levels as 1 for small, 2 for medium, 3 for large and 4 for xlarge d. Add a level xsmall as the first level to the current factor
size <- c(1,2,2,1,3,4,4,3)
#a
size_factor <- factor(size)
size_factor## [1] 1 2 2 1 3 4 4 3
## Levels: 1 2 3 4#b
levels(size_factor)## [1] "1" "2" "3" "4"#c
levels(size_factor) <- c("small", "meidum", "large", "xlarge")
#d
levels(size_factor) <- c("xsmall", levels(size_factor))
levels(size_factor)## [1] "xsmall" "small" "meidum" "large" "xlarge"Exercise 7
For the mtcars data frame, complete the following task: a. Create a new data frame named high_mpg which includes the rows where mpg is greater than 20 for all columns
Create a new data frame named high_mpg_4cyl which include which includes the rows where mpg > 20 and the cyl = 4 for all columns
Retrieve all elements of mpg column that the cyl = 4 or 6
str(mtcars)## 'data.frame': 32 obs. of 11 variables:
## $ mpg : num 21 21 22.8 21.4 18.7 18.1 14.3 24.4 22.8 19.2 ...
## $ cyl : num 6 6 4 6 8 6 8 4 4 6 ...
## $ disp: num 160 160 108 258 360 ...
## $ hp : num 110 110 93 110 175 105 245 62 95 123 ...
## $ drat: num 3.9 3.9 3.85 3.08 3.15 2.76 3.21 3.69 3.92 3.92 ...
## $ wt : num 2.62 2.88 2.32 3.21 3.44 ...
## $ qsec: num 16.5 17 18.6 19.4 17 ...
## $ vs : num 0 0 1 1 0 1 0 1 1 1 ...
## $ am : num 1 1 1 0 0 0 0 0 0 0 ...
## $ gear: num 4 4 4 3 3 3 3 4 4 4 ...
## $ carb: num 4 4 1 1 2 1 4 2 2 4 ...data(mtcars)
#a
high_mpg <- mtcars[mtcars$mpg > 20,]
#b
high_mpg_4cyl <- mtcars[mtcars$mpg > 20 & mtcars$cyl == 4,]
high_mpg_4cyl## mpg cyl disp hp drat wt qsec vs am gear carb
## Datsun 710 22.8 4 108.0 93 3.85 2.320 18.61 1 1 4 1
## Merc 240D 24.4 4 146.7 62 3.69 3.190 20.00 1 0 4 2
## Merc 230 22.8 4 140.8 95 3.92 3.150 22.90 1 0 4 2
## Fiat 128 32.4 4 78.7 66 4.08 2.200 19.47 1 1 4 1
## Honda Civic 30.4 4 75.7 52 4.93 1.615 18.52 1 1 4 2
## Toyota Corolla 33.9 4 71.1 65 4.22 1.835 19.90 1 1 4 1
## Toyota Corona 21.5 4 120.1 97 3.70 2.465 20.01 1 0 3 1
## Fiat X1-9 27.3 4 79.0 66 4.08 1.935 18.90 1 1 4 1
## Porsche 914-2 26.0 4 120.3 91 4.43 2.140 16.70 0 1 5 2
## Lotus Europa 30.4 4 95.1 113 3.77 1.513 16.90 1 1 5 2
## Volvo 142E 21.4 4 121.0 109 4.11 2.780 18.60 1 1 4 2#c
mtcars[mtcars$cyl == 4 | mtcars$cyl == 6, "mpg"]## [1] 21.0 21.0 22.8 21.4 18.1 24.4 22.8 19.2 17.8 32.4 30.4 33.9 21.5 27.3 26.0
## [16] 30.4 19.7 21.4Exercise 8
Working with the following vectors.
v1 <- c(1,3,4,6)
v2 <- c("A", "B", "C","D")
v3 <- factor(c(1, 2, 3, 4, 5))
#a Generate a list that contains the above vectors named list_data.
list_data <- list("v1", "v2", "v3")
list_data## [[1]]
## [1] "v1"
##
## [[2]]
## [1] "v2"
##
## [[3]]
## [1] "v3"#b Name each list as vec1, vec2, fac3.
list_data <- list(vec1 = v1, vec2 = v2, vec3 = v3)
names(list_data) <- c("vec1", "vec2", "vec3")
#c Retrieve v1 as a list.
list_data[1]## $vec1
## [1] 1 3 4 6#d Retrieve v2 as its original structure.
list_data[[2]]## [1] "A" "B" "C" "D"#e Retrieve the 2nd element in v1 from List.
list_data$vec1[2]## [1] 3Exercise 9
Use the data diamonds.csv to complete the following tasks.
#a
Data <- read.csv('C:\\Users\\Owner\\Documents\\diamonds.csv', header=TRUE, stringsAsFactors=FALSE)
#b
str(Data)## 'data.frame': 53940 obs. of 10 variables:
## $ carat : num 0.23 0.21 0.23 0.29 0.31 0.24 0.24 0.26 0.22 0.23 ...
## $ cut : chr "Ideal" "Premium" "Good" "Premium" ...
## $ color : chr "E" "E" "E" "I" ...
## $ clarity: chr "SI2" "SI1" "VS1" "VS2" ...
## $ depth : num 61.5 59.8 56.9 62.4 63.3 62.8 62.3 61.9 65.1 59.4 ...
## $ table : num 55 61 65 58 58 57 57 55 61 61 ...
## $ price : int 326 326 327 334 335 336 336 337 337 338 ...
## $ x : num 3.95 3.89 4.05 4.2 4.34 3.94 3.95 4.07 3.87 4 ...
## $ y : num 3.98 3.84 4.07 4.23 4.35 3.96 3.98 4.11 3.78 4.05 ...
## $ z : num 2.43 2.31 2.31 2.63 2.75 2.48 2.47 2.53 2.49 2.39 ...# There are 6 numerical variables & 3 categorical variables.
#c
names(Data)## [1] "carat" "cut" "color" "clarity" "depth" "table" "price"
## [8] "x" "y" "z"#d
Data$volume <- Data$x * Data$y * Data$z
#e
Data$clarity <- factor(Data$clarity, ordered = TRUE, levels = c("I1", "SI2", "SI1", "VS2", "VS1", "VVS2", "VVS1", "IF"))
#f
FourC <- Data[, c(1, 2, 3, 4)]
#g
Premium <- Data[Data$color == "D" & Data$cut == "Ideal",]
write.csv(Premium, "Premium.csv")
#h returns 7 rows
Premium[Premium$carat > 2,]## carat cut color clarity depth table price x y z volume
## 24448 2.12 Ideal D SI2 62.9 55 12707 8.17 8.14 5.13 341.1645
## 24785 2.75 Ideal D I1 60.9 57 13156 9.04 8.98 5.49 445.6738
## 26634 2.11 Ideal D SI2 62.7 56 16404 8.25 8.18 5.14 346.8729
## 26753 2.21 Ideal D SI2 62.0 57 16558 8.36 8.31 5.18 359.8629
## 27563 2.06 Ideal D SI2 60.3 56 18371 8.29 8.25 4.99 341.2786
## 27668 2.01 Ideal D SI2 62.1 56 18674 8.02 8.11 5.01 325.8614
## 27677 2.19 Ideal D SI2 61.8 57 18693 8.23 8.49 5.17 361.2419#i
Data[is.na(Data$carat),]## [1] carat cut color clarity depth table price x y
## [10] z volume
## <0 rows> (or 0-length row.names)#j
library(ggplot2)
ggplot(Data, aes(price)) +
geom_density(fill = "pink")
#k
ggplot(Data, aes(cut, fill = clarity)) +
geom_bar(position = "fill", alpha = 0.6)
#l
ggplot(Premium, aes(carat, price, color = clarity)) +
geom_point(size = 4) +
geom_smooth() +
labs(title = "Price of diamonds with difference carats", subtitle = "and different clairty", y = "Price in dollars") +
theme(legend.position = c(0.8, 0.2))## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
#m
ggplot(Premium, aes(carat, price)) + geom_point() + facet_wrap(~clarity)
Exercise 10
The working directory is the location where R will look to load files and it also uses it to write and export files.