R Notebook

ID = c(1, 2, 3, 4, 5)
Name = c("Alice", "Bob", "David", "John", "Jenny")
Age = c(20, 25, 30, 22, 18)
Score = c(100, 78, 90, 55, 81)

Creat dataframe

exam_score = data.frame(
ID = c(1, 2, 3, 4, 5),
Name = c("Alice", "Bob", "David", "John", "Jenny"),
Age = c(20, 25, 30, 22, 18),
Score = c(100, 78, 90, 55, 81))
exam_score

Add 2 new rows & 1 new column

Add Rows

new_row_6 = c(6,"Jim",32,75)
new_row_7 = c(7,"Yao",28,60)
exam_score = rbind(exam_score, new_row_6, new_row_7)
exam_score

Add Column

Income = c(20000,25000,40000,35000,30000,45000,50000)
exam_score = cbind(exam_score, Income)
exam_score

Age= c(Age, 32,28)
Age

[1] 20 25 30 22 18 32 28

Score= c(Score,75,60)
Score

[1] 100  78  90  55  81  75  60

ID = c(ID,6,7)
ID

[1] 1 2 3 4 5 6 7

Name = c(Name, "Jim", "Yao")
Name

[1] "Alice" "Bob"   "David" "John"  "Jenny" "Jim"   "Yao"  

Simple Statistics

Min

min(Age)

[1] 18

min(Score)

[1] 55

min(Income)

[1] 20000

Max

max(Age)

[1] 32

max(Score)

[1] 100

max(Income)

[1] 50000

Mean

mean(Age)

[1] 25

mean(Score)

[1] 77

mean(Income)

[1] 35000

Median

median(Age)

[1] 25

median(Score)

[1] 78

median(Income)

[1] 35000

Standard deviation

sd(Age)

[1] 5.259911

sd(Score)

[1] 15.76917

sd(Income)

[1] 10801.23

Variance

var(Age)

[1] 27.66667

var(Score)

[1] 248.6667

var(Income)

[1] 116666667

Correlation

cor(Age,Score)

[1] -0.1547221

cor(Age,Income)

[1] 0.7333933

cor(Score,Income)

[1] -0.5724301

Select rows where the score is greater than or equal to 80

score_80 = exam_score[exam_score$Score >=80, ]
score_80

Select rows with the age range of 20 to 30

age_20_30 = exam_score[exam_score$Age >=20 & exam_score$Age <=30, ]
age_20_30