Assignment 2

#Given, 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 ) ) #Data frame

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

#Row add

new_row = c(6, "Santo", 22, 80 )
exam_score = rbind(exam_score, new_row)
new_r = c(7,"Shakhawat", 23, 79 )
exam_score = rbind(exam_score, new_r)
exam_score

NA

#Column add

Income = c(70000, 80000, 90000, 100000, 60000, 10000,12000 )
exam_score = cbind(exam_score, Income)
exam_score

NA

#Max

Income = c(70000, 80000, 90000, 100000, 60000, 10000,12000 )
max(Income)

[1] 1e+05

Age = c(20, 25, 30, 22, 18, 22, 23 )
max(Age)

[1] 30

Score = c(100, 78, 90, 55, 81, 80, 79 )
max(Score)

[1] 100

#Min

min(Income)

[1] 10000

min(Age)

[1] 18

min(Score)

[1] 55

#Median

median(Age)

[1] 22

median(Score)

[1] 80

median(Income)

[1] 70000

#Sum

sum(Age)

[1] 160

sum(Score)

[1] 563

sum(Income)

[1] 422000

#Mean

mean(Age)

[1] 22.85714

mean(Score)

[1] 80.42857

mean(Income)

[1] 60285.71

#SD

sd(Age)

[1] 3.848314

sd(Score)

[1] 13.72172

sd(Income)

[1] 36063.44

#Variance

var(Age)

[1] 14.80952

var(Score)

[1] 188.2857

var(Income)

[1] 1300571429

#Quantiles

quantile(Age)

  0%  25%  50%  75% 100% 
  18   21   22   24   30 

quantile(Score)

   0%   25%   50%   75%  100% 
 55.0  78.5  80.0  85.5 100.0 

quantile(Income)

    0%    25%    50%    75%   100% 
 10000  36000  70000  85000 100000 

#Correlation #a

cor(Age, Score)

[1] 0.08341482

Weak positive correlation

#b

cor(Age,Income)

[1] 0.2765528

Weak positive correlation

#c

cor(Score,Income)

[1] -0.1659946

Weak negative correlation

#Select row,Score >= 80

exam_score[exam_score$Score >=80 | exam_score$Score == 100 , ]

#Select rows with the age range of 20 to 30

exam_score[ exam_score$Age >= 20 | exam_score$Age == 30 , ]

#Select rows with age 22,25 and 30

exam_score[ exam_score$Age == 22 | exam_score$Age == 25 | exam_score$Age == 30 , ]