# vector x contains the value 3.
x <- 3
x
## [1] 3
# vector y stores the value 5
y <- 5
y
## [1] 5
# vector z is the result of x divided by y
z <- x/y
z
## [1] 0.6
# vector a has the value Applied Statistics
a <- "Applied Statistics"
a
## [1] "Applied Statistics"
# vector q stores the result of: 8 * 2 ^ 2
q <- 8 * 2 ^ 2
q
## [1] 32
# vector ‘message‘ stores “Hello World!”
message <- "Hello World"
message
## [1] "Hello World"
number <- c(4, -10, 33, 0, -121)
number
## [1] 4 -10 33 0 -121
number <- c(number, 8)
number
## [1] 4 -10 33 0 -121 8
reverse <- 100:75
reverse
## [1] 100 99 98 97 96 95 94 93 92 91 90 89 88 87 86 85 84 83 82
## [20] 81 80 79 78 77 76 75
ccny <- c("C", "C", "N", "Y")
ccny
## [1] "C" "C" "N" "Y"
v1 <- c(1,2,3)
v1
## [1] 1 2 3
v2 <- c(5,6,7)
v2
## [1] 5 6 7
v1 + v2
## [1] 6 8 10
v1 - v2
## [1] -4 -4 -4
v1 * v2
## [1] 5 12 21
fives <- c(1,2,3,4,5)
fives
## [1] 1 2 3 4 5
rep(fives, 10)
## [1] 1 2 3 4 5 1 2 3 4 5 1 2 3 4 5 1 2 3 4 5 1 2 3 4 5 1 2 3 4 5 1 2 3 4 5 1 2 3
## [39] 4 5 1 2 3 4 5 1 2 3 4 5
eLement <- 10:15
eLement
## [1] 10 11 12 13 14 15
rep(eLement, each=10)
## [1] 10 10 10 10 10 10 10 10 10 10 11 11 11 11 11 11 11 11 11 11 12 12 12 12 12
## [26] 12 12 12 12 12 13 13 13 13 13 13 13 13 13 13 14 14 14 14 14 14 14 14 14 14
## [51] 15 15 15 15 15 15 15 15 15 15
seq(0,100,20)
## [1] 0 20 40 60 80 100
seq(75, 20, -5)
## [1] 75 70 65 60 55 50 45 40 35 30 25 20
• “never married” is 0
• “married” is 1
• “divorced” is 2
• “widowed” is 3
marital_status <- c(0, 2, 1, 0, 1, 3, 0, 1, 1, 2, 1, 0, 3)
marital_status
## [1] 0 2 1 0 1 3 0 1 1 2 1 0 3
marital_status_factor <- factor(marital_status, labels= c("never-married", "married", "divorced", "widowed"))
marital_status_factor
## [1] never-married divorced married never-married married
## [6] widowed never-married married married divorced
## [11] married never-married widowed
## Levels: never-married married divorced widowed
• “small” is ‘s’
• “medium” is ‘m’
• “large” is ‘l’
drinks <- c("s", "m", "m", "s", "l", "s", "l", "l", "m", "s", "s", "l", "m", "l", "l")
drinks
## [1] "s" "m" "m" "s" "l" "s" "l" "l" "m" "s" "s" "l" "m" "l" "l"
drinks_factor <- factor(drinks, levels = c("s","m","l"), labels = c("small", "medium","large"), order=T)
drinks_factor
## [1] small medium medium small large small large large medium small
## [11] small large medium large large
## Levels: small < medium < large
# generate vector for each column
Guest <- c("Jennifer", "David", "Jack", "Joanna", "Victoria")
Age <- c(19,20,21,25,23)
Friend_Of <- c(1,2,1,2,2)
# check the length
length(Guest)
## [1] 5
length(Age)
## [1] 5
length(Friend_Of)
## [1] 5
# data-frame
wedding <- data.frame(Guest, Age, Friend_Of)
wedding
## Guest Age Friend_Of
## 1 Jennifer 19 1
## 2 David 20 2
## 3 Jack 21 1
## 4 Joanna 25 2
## 5 Victoria 23 2
typeof(wedding$Age)
## [1] "double"
typeof(wedding$Friend_Of)
## [1] "double"
wedding$Friend_Of <- factor(wedding$Friend_Of, labels = c("Groom", "Bride"))
wedding
## Guest Age Friend_Of
## 1 Jennifer 19 Groom
## 2 David 20 Bride
## 3 Jack 21 Groom
## 4 Joanna 25 Bride
## 5 Victoria 23 Bride
typeof(wedding$Friend_Of)
## [1] "integer"
They are different because we convert the original column into a factored column (integer data-type).
str(wedding)
## 'data.frame': 5 obs. of 3 variables:
## $ Guest : chr "Jennifer" "David" "Jack" "Joanna" ...
## $ Age : num 19 20 21 25 23
## $ Friend_Of: Factor w/ 2 levels "Groom","Bride": 1 2 1 2 2