Experiment No 8

Que 1:
Create a Vector
age=c(10,12,14,16,18,20,22,19)
a=age[age>15]
a

## [1] 16 18 20 22 19

b=age[age<20]
b

## [1] 10 12 14 16 18 19

c=intersect(a,b)
c

## [1] 16 18 19

d=length(c)
d

## [1] 3

#b)Access the element numbered 3 to 6

age[3:6]

## [1] 14 16 18 20

#c)Accesssll the element expect 5th and 7th

age[-c(5,7)]

## [1] 10 12 14 16 20 19

#d)Access element numbered 2,4,6amd &

age[c(2,4,6,8)]

## [1] 12 16 20 19

#e)Argument age with adding 18 in beginning and 21,24 in the end

age1=c(18,age,21,24)
age1

## [1] 18 10 12 14 16 18 20 22 19 21 24
Que 2:
Create a data frame.
x=c("Soham", "Rohan", "Mohan", "Arnav","Aryan")
y=c(12500,9000,7500,5600,3200)
d=data.frame("Employee_name"=x,"basicpay"=y)
d

## Employee_name basicpay
## 1 Soham 12500
## 2 Rohan 9000
## 3 Mohan 7500
## 4 Arnav 5600
## 5 Aryan 3200

#find employee with basicpay>7000

d1=subset(d,basicpay>7000)
d1

## Employee_name basicpay
## 1 Soham 12500
## 2 Rohan 9000
## 3 Mohan 7500

Que 3:
Create a,b,c,d variables
a=c(10,20,30,40)
b=c("Book", "Pen", "Textbook", "Pencil_case")
c=c("True", "False","True", "False")
d=c(2.5,8,10,7)

#a)joint the variables to create data frame > df=data.frame(a,b,c,d)

df=data.frame(a,b,c,d)

#b)print the column headers

d1=colnames(df)
d1

## [1] "a" "b" "c" "d"

#c)change the column names with the function names

names(df)=c("ID", "items","store","price")
df

## ID items store price

## 1 10 Book True 2.5
## 2 20 Pen False 8.0
## 3 30 Textbook True 10.0
## 4 40 Pencil_case False 7.0

#d)print the structure

str(df)

## 'data.frame': 4 obs. of 4 variables:

## $ ID : num 10 20 30 40
## $ items: chr "Book" "Pen" "Textbook" "Pencil_case"
## $ store: chr "True" "False" "True" "False"
## $ price: num 2.5 8 10 7

#e) select the row 1 in column 2

df[1,2]

## [1] "Book"

#f) select row 1 to 2

df[1:2,]

## ID items store price

## 1 10 Book True 2.5
## 2 20 Pen False 8.0

#g)select column 1
df[1]

## ID
## 1 10
## 2 20
## 3 30
## 4 40

#h) select rows 1to 3 and column 3 to 4

df[1:3,3:4]

## store price
## 1 True 2.5
## 2 False 8.0
## 3 True 10.0

#i) slice with column name(extract the first two columns using their names)
df[,c("ID", "items")]

## ID items
## 1 10 Book
## 2 20 Pen
## 3 30 Textbook
## 4 40 Pencil_case

#j) create a new vector quantity

quantity=c(10,35,40,5)
#k) Append quantity to data frame
df$quantity=quantity
df

## ID items store price quantity

## 1 10 Book True 2.5 10
## 2 20 Pen False 8.0 35
## 3 30 Textbook True 10.0 40
## 4 40 Pencil_case False 7.0 5

#I)select column ID from data frame

df$ID

## [1] 10 20 30 40

#m)Reutrn only items with price and above 10

subset(df,subset=price>10)

## [1] ID items store price quantity

## <0 rows> (or 0-length row.names)

#n) Return only items with price and above 10

subset(df,subset=price>5)

## ID items store price quantity

## 2 20 Pen False 8 35
## 3 30 Textbook True 10 40
## 4 40 Pencil_case False 7 5

Que 4:
Create data frame
x=data.frame("SN"=1:2,"Age"=c(21,15), "Name"=c("John", "Dora"),stringsAsFacto
rs=TRUE)
x

## SN Age Name
## 1 1 21 John
## 2 2 15 Dora

#a) Check type of x using typeof function

typeof(x)

## [1] "list"

#b) Check if x is a data frame or not, using class function

class(x)

## [1] "data.frame"
#c)Print names of vectors in x
names(x)

## [1] "SN" "Age" "Name"

#d)Print number of columns in x

ncol(x)

## [1] 3

#e)Print number of rows in x

nrow(x)

## [1] 2

#f)check structure of x
str(x)

## 'data.frame': 2 obs. of 3 variables:

## $ SN : int 1 2
## $ Age : num 21 15
## $ Name: Factor w/ 2 levels "Dora","John": 2 1

#g)The third colum"Name"is of type factor change this type to character

x=data.frame("SN"=1:2,"Age"=c(21,15), "Name"=c("John", "Dora"),stringsAsFacto
rs=FALSE)
x

## SN Age Name
## 1 1 21 John
## 2 2 15 Dora

typeof(x$Name)

## [1] "character"

Que 5:
Represent data by bar chart
Year=c(2014,2015,2016,2017,2018,2019)
Annual_sales=c(15.0,25.0,27.0,28.0,26.0,26.6)
barplot(Annual_sales,names.arg=Year,xlab="Year",ylab="Sales",col="Blue")
Que 6:
Barplot of frequencies and proportion.
x=c(3,4,1,1,3,4,3,3,1,3,2,1,2,1,2,3,2,3,1,1,1,1,4,3,1)
t=table(x)
t

## x
## 1 2 3 4
## 10 4 8 3

#i)Barplot of frequencies
barplot(t,xlab="Soft-drink",ylab="Frequency of Preferences", main="Barplot",c
ol="Sky blue")
#ii) Barplot of proportion
barplot(t/length(x),xlab="Soft-drink",ylab="Frequency of Preferences",main="B
arplot",col="yellow")
Que 7:
Represent data as a subdivided barplot
study=matrix(c(2810,890,540,3542,1363,471,4301,1632,652,5362,2071,895,6593,27
52,1113),byrow=TRUE,ncol=3)
study

## [,1] [,2] [,3]

## [1,] 2810 890 540
## [2,] 3542 1363 471
## [3,] 4301 1632 652
## [4,] 5362 2071 895
## [5,] 6593 2752 1113

rownames(study)=c(2015,2016,2017,2018,2019)
colnames(study)=c("Humanity","Science", "Commerce")
study

## Humanity Science Commerce

## 2015 2810 890 540
## 2016 3542 1363 471
## 2017 4301 1632 652
## 2018 5362 2071 895
## 2019 6593 2752 1113

barplot(t(study),col=c("white", "Sky blue","Blue"),main="Sub-divided barplot"

,beside=FALSE)
Que 8:
Represent data as a Multiple bar diagram
donation=matrix(c(1154,526,775,155,1700,1125,1280,560), byrow=TRUE, ncol=4);
donation

## [,1] [,2] [,3] [,4]

## [1,] 1154 526 775 155
## [2,] 1700 1125 1280 560

rownames(donation)=c("2014","2019")
colnames(donation)=c("O","A", "B","AB")
barplot(t(donation), col=c("white", "Sky blue", "Blue", "Black"), main="Multi
ple barplot", beside=TRUE)

Que 9:
Represent the data by pie chart
tax=c(6526,7108,2568,560,763)
names(tax)=c("Excise","Custom","Corporation tax","Income tax", "Other")
pie(tax,main="The tax revenue of INDIA",col=c("red", "yellow", "blue", "orang
e","green"))
Que 10:
Draw stem and leaf diagram
hotels=c(20,14,21,29,43,17,15,26,8,14,39,23,16,46,28,11,26,35,26,28,30,22,23,
7,32,19,22,18,27,9)
hotels

## [1] 20 14 21 29 43 17 15 26 8 14 39 23 16 46 28 11 26 35 26 28 30 22 23
7 32
## [26] 19 22 18 27 9

stem(hotels)

##
## The decimal point is 1 digit(s) to the right of the |
##
## 0 | 789
## 1 | 144
## 1 | 56789
## 2 | 012233
## 2 | 6667889
## 3 | 02
## 3 | 59
## 4 | 3
## 4 | 6

Que 11:
Histogram of the data.
xi=c(12.5,37.5,62.5,87.5,112.5)
fi=c(5,8,13,11,3)
y=rep(xi,fi)
brk=seq(0,125,25)
hist(y,breaks=brk,xlab="Sales", main="Histogram",col="Brown")