EX NO : 1

TO PERFORM VECTOR OPERATIONS

DATE:

1
CODE

#To set the working directory

setwd("D:/ ")

#To remove an environment

rm(list=ls())

#creating vector using ':' operator

A = 1:4;

B = 5:8;

writeLines("The Vector A is:")

print(A)

writeLines("The Vector B is:")

print(B)

#creating vector using seq function

C=seq(from=1, to=10, by=2);

writeLines("The Vector C using seq is:")

print(C)

#Access Elements of a Vector

writeLines("Accessing Elements of a Vector")

writeLines("A[3] is:")

A[3]

writeLines("A[1:3] is:")

A[1:3]

2
#Performing Vector Arithmetic

writeLines("Vector Arithmetic")

c = A + B;

writeLines("A+B:")

print(c)

c = A - B;

writeLines("A-B:")

print(c)

c =A * B;

writeLines("A*B:")

print(c)

c = A / B;

writeLines("A/B:")

print(c)

c = A + (B)^2;

writeLines("A+B^2:")

print(c)

c = 2+A; print(c)

c =2+3*B; print(c)

c =(2+3)*B; print(c)

#Vector Repetition

e=rep(5,4) ;

writeLines("Vector Repetition of (5,4) is :")

print(e)

3
#Replace/Delete a Vector

# Replace single element

e[1]=10

#Delete single element

e=e[-3]

print(e)

writeLines("Vector e after Replace/Delete Operation:")

print(e)

#Delete Entire Vector

e= NULL

print(e)

4
OUTPUT

The Vector A is:

[1] 1 2 3 4

The Vector B is:

[1] 5 6 7 8

The Vector C using seq is:

[1] 1 3 5 7 9

Accessing Elements of a Vector

A[3] is:
[1] 3
A[1:3] is:
[1] 1 2 3

Vector Arithmetic
A+B:
[1] 6 8 10 12

A-B:
[1] -4 -4 -4 -4

A*B:
[1] 5 12 21 32

A/B:
[1] 0.2000000 0.3333333 0.4285714 0.5000000

A+B^2:
[1] 26 38 52 68

Vector Repetition of (5,4) is :

[1] 5 5 5 5

Vector e after Replace/Delete Operation:

[1] 10 5 5

5
6
EX NO : 2

TO PERFORM MATRIX OPERATIONS

DATE:

7
CODE

#To set the working directory

setwd("D:/ ")

#To remove an environment

rm(list=ls())

#A matrix is a two-dimensional array

#Creating a Matrix

A=matrix(1:9, nrow = 3);

writeLines("Matrix A is:")

print(A)

B=matrix(1:9, nrow=3, byrow=TRUE);

writeLines("Matrix B is:")

print(B)

#Access Elements of a matrix

writeLines("Accessing Elements of a Matrix :")

A[2, 3]

A[2, ]

A[ ,3]

#Combining Matrices

a = matrix(1:9, 3,3);

b = matrix(10:18, 3,3);

writeLines("Combining Matrices")

printc(a)

printc(b)

writeLines("Column-Wise:")

8
cbind(a,b)

writeLines("Row-Wise:")

rbind(a,b)

#Matrix Arithmetic

writeLines("Matrix Arithmetic:")

c = a+b;

writeLines("A+B:")

printc(c)

c = a-b; writeLines("A-B:")

printc(c)

c = a*b; writeLines("A*B:")

printc(c)

c = a/b; writeLines("A/B:")

printc(c)

#Modify Matrix Elements

a[3,3] = 0;

a[a > 5] = 0;

writeLines("Matrix A after Modification:")

printc(a)

9
OUTPUT

Matrix A is:
[,1] [,2] [,3]
[1,] 1 4 7
[2,] 2 5 8
[3,] 3 6 9

Matrix B is:
[,1] [,2] [,3]
[1,] 1 2 3
[2,] 4 5 6
[3,] 7 8 9

Accessing Elements of a Matrix :

[1] 8
[1] 2 5 8
[1] 7 8 9

Combining Matrices
>a
[,1] [,2] [,3]
[1,] 1 4 7
[2,] 2 5 8
[3,] 3 6 9

>b
[,1] [,2] [,3]
[1,] 10 13 16
[2,] 11 14 17
[3,] 12 15 18

Column-Wise:
[,1] [,2] [,3] [,4] [,5] [,6]
[1,] 1 4 7 10 13 16
[2,] 2 5 8 11 14 17
[3,] 3 6 9 12 15 18

Row-Wise:
[,1] [,2] [,3]
[1,] 1 4 7
[2,] 2 5 8
[3,] 3 6 9
[4,] 10 13 16
[5,] 11 14 17
[6,] 12 15 18

10
Matrix Arithmetic:
A+B:
[,1] [,2] [,3]
[1,] 11 17 23
[2,] 13 19 25
[3,] 15 21 27

A-B:
[,1] [,2] [,3]
[1,] -9 -9 -9
[2,] -9 -9 -9
[3,] -9 -9 -9

A*B:
[,1] [,2] [,3]
[1,] 10 52 112
[2,] 22 70 136
[3,] 36 90 162

A/B:
[,1] [,2] [,3]
[1,] 0.1000000 0.3076923 0.4375000
[2,] 0.1818182 0.3571429 0.4705882
[3,] 0.2500000 0.4000000 0.5000000

Matrix A after Modification:

[,1] [,2] [,3]
[1,] 1 4 0
[2,] 2 5 0
[3,] 3 0 0

11
12
EX NO : 3

TO PERFORM LIST OPERATIONS

DATE:

13
CODE

#To set the working directory

setwd("D:/ ")

#To remove an environment

rm(list=ls())

# A list contain elements of different types like − numbers, strings, vectors

#List contents can be accessed either by index or by name.

mylist= list( c(1, 1, 2, 5, 14, 42), [Link], matrix(c(3, -8, 1, -3), nrow = 2))

writeLines("Creating myList:")

mylist

#Naming list elements

names(mylist) = c("numbers", "months", "matrix")

writeLines("Naming list elements")

mylist

#A list’s length is the number of top-level elements that it contains

writeLines("The Length of the List is:")

length(mylist)

writeLines("Arithmetic operations on list L1 and L2")

#Arithmetic operations on list

L1 = list(1:5);

writeLines("L1:")

print(L1)

L2 = list(6:10);

writeLines("L2:")

14
print(L2)

writeLines("List Addition:")

L1[[1]] + L2[[1]]

writeLines("List Subtraction:")

L1[[1]] - L2[[1]]

writeLines("List Multiplication:")

L1[[1]] * L2[[1]]

writeLines("List Division:")

L1[[1]] / L2[[1]]

writeLines("Indexing List")

#Indexing Lists

l = list( first = 1, second = 2, third = list(alpha = 3.1, beta = 3.2))

writeLines("L[2:3] is:")

l[2:3]

l[c(FALSE, FALSE, TRUE)]

#Converting Between Vectors / Lists

writeLines("Converting Between Vectors / Lists")

b = c(1, 6, 21, 107);

[Link](b)

print(b)

#Combining Lists

a = c(list (1:3, pi), list("periyar", "university"), list(matrix(1:9, 3,3)))

writeLines("Combining Lists")

writeLines("List A:")

print(a)

15
#Insert/ Remove elements in list

writeLines("Insert/ Remove elements in list:")

writeLines("List A:")

a = list(1, 3, 5)

print(a)

a[[4]] = 7

a[-3]

a[[2]] = NULL

16
OUTPUT

Creating myList:
[[1]]
[1] 1 1 2 5 14 42

[[2]]
[1] "Jan" "Feb" "Mar" "Apr" "May" "Jun" "Jul" "Aug" "Sep" "Oct" "Nov" "Dec"

[[3]]
[,1] [,2]
[1,] 3 1
[2,] -8 -3

Naming list elements

$numbers
[1] 1 1 2 5 14 42

$months
[1] "Jan" "Feb" "Mar" "Apr" "May" "Jun" "Jul" "Aug" "Sep" "Oct" "Nov" "Dec"

$matrix
[,1] [,2]
[1,] 3 1
[2,] -8 -3

The Length of the List is:

[1] 3

Arithmetic operations on list L1 and L2

L1:
[[1]]
[1] 1 2 3 4 5
L2[[1]]
[1] 6 7 8 9 10

List Addition:
[1] 7 9 11 13 15

List Subtraction:
[1] -5 -5 -5 -5 -5

List Multiplication:
[1] 6 14 24 36 50

List Division:
[1] 0.1666667 0.2857143 0.3750000 0.4444444 0.5000000

17
Indexing List
L[2:3] is:
$second
[1] 2
$third
$third$alpha

[1] 3.1

$third$beta
[1] 3.2
Converting Between Vectors / Lists
[[1]]
[1] 1

[[2]]
[1] 6

[[3]]
[1] 21

[[4]]
[1] 107

Combining Lists
List A:
[[1]]
[1] 1 2 3

[[2]]
[1] 3.141593

[[3]]
[1] "periyar"

[[4]]
[1] "university"

[[5]]
[,1] [,2] [,3]
[1,] 1 4 7
[2,] 2 5 8
[3,] 3 6 9

18
Insert/ Remove elements in list:
List A:
[[1]]
[1] 1

[[2]]
[1] 3

[[3]]
[1] 5
List A:
[[1]]
[1] 1

[[2]]
[1] 3
[[3]]
[1] 7

19
20
EX NO : 4

TO PERFORM DATA-FRAME OPERATIONS

DATE:

21
CODE

#Data frame is a two dimensional data structure in R

#hold different type of data

#A data frame is created with the [Link]() function

#mydata <- [Link](col1, col2,.,colN)

#where col1, col2, col3, . are column vectors of any type (such as character, numeric, or logical)

#Creating a Data Frame

patientID <- c(1, 2, 3, 4)

age <- c(25, 34, 28, 52)

diabetes <- c("Type1", "Type2", "Type1", "Type1")

status <- c("Poor", "Improved", "Excellent", "Poor")

patientdata <- [Link](patientID, age, diabetes, status)

writeLines("Creating a Dataframe: patientdata")

patientdata

#Data Frame Properties

writeLines("Number of rows in patientdata:")

nrow(patientdata)

writeLines("Number of columns in patientdata:")

ncol(patientdata)

writeLines("Order patientdata by Age")

patientdata[order(patientdata$age),]

patientdata[order(patientdata$age, decreasing=T),]

#Accessing of a elements in Data Frame

writeLines("Access Elements in patientdata:")

patientdata[1:2]

22
patientdata[c("diabetes", "status")]

patientdata$age

writeLines("Modify Elements in patientdata:")

#Modifying elements in Data Frame

patientdata[1, "age"] <- 30

patientdata

#Adding elements to a Data Frame

patientdata <- rbind(patientdata, list(5, 40, "Type2", "Improved"))

patientdata

writeLines("Add Elements to patientdata:")

cbind(patientdata, gender=c("Male", "Male", "Female", "Male", "Female"))

#Deleting Components from Data Frame

patientdata$gender <- NULL

patientdata

writeLines("Delete Elements from patientdata:")

patientdata[-5,]

23
OUTPUT

Creating a Dataframe: patientdata

patientID age diabetes status

1 1 25 Type1 Poor
2 2 34 Type2 Improved
3 3 28 Type1 Excellent
4 4 52 Type1 Poor

Number of rows in patientdata:

[1] 4
Number of columns in patientdata:
[1] 4

Order patientdata by Age

patientID age diabetes status

1 1 25 Type1 Poor
3 3 28 Type1 Excellent
2 2 34 Type2 Improved
4 4 52 Type1 Poor

Access Elements in patientdata:

patientID age
1 1 25
2 2 34
3 3 28
4 4 52

diabetes status
1 Type1 Poor
2 Type2 Improved
3 Type1 Excellent
4 Type1 Poor

Modify Elements in patientdata:

patientID age diabetes status

1 1 30 Type1 Poor
2 2 34 Type2 Improved
3 3 28 Type1 Excellent
4 4 52 Type1 Poor

24
Add Elements to patientdata:

patientID age diabetes status gender

1 1 30 Type1 Poor Male
2 2 34 Type2 Improved Male
3 3 28 Type1 Excellent Female
4 4 52 Type1 Poor Male
5 5 40 Type2 Improved Female

Delete Records from patientdata:

patientID age diabetes status

1 1 30 Type1 Poor
2 2 34 Type2 Improved
3 3 28 Type1 Excellent
4 4 52 Type1 Poor

25
26
EX NO : 5
TO PERFORM STRINGS AND FACTOR
DATE:
OPERATIONS

27
CODE

# String Operations

# Creating Strings

a<-"First"

b<-'String'

c<-"Program in R"

writeLines("Creating Strings")

writeLines("String A:")

print(a)

writeLines("String B:")

print(b)

writeLines("String C:")

print(c)

#Concatenating Strings - paste() function

MyString<-paste(a,b,c,sep=" ", collapse = NULL)

writeLines("Concatenating A, B and C to MyString")

MyString

#Counting number of characters in a string - nchar() function

writeLines("Number of Characters in the String:")

nchar(MyString)

#Changing the case - toupper() & tolower() functions

writeLines("Changing to Upper and Lower case:")

toupper(MyString)

tolower(MyString)

28
#Extracting parts of a string - substring() function

writeLines("Extracting parts of a string:")

substring(MyString,1,5)

# Factor Operations

#Given the vector status <- c("Poor", "Improved", "Excellent", "Poor")

#the statement status <- factor(status, ordered=TRUE) will encode the vector as (3, 2, 1, 3) and

#associate these values internally as 1=Excellent, 2=Improved, and 3=Poor

#By default, factor levels for character vectors are created in alphabetical order.

writeLines("Factor Operations")

patientID <- c(1, 2, 3, 4)

age <- c(25, 34, 28, 52)

diabetes <- c("Type1", "Type2", "Type1", "Type1")

status <- c("Poor", "Improved", "Excellent", "Poor")

diabetes <- factor(diabetes)

status <- factor(status, order=TRUE)

writeLines("Creating Factor: Patient")

patientdata <- [Link](patientID, age, diabetes, status)

patientdata

writeLines("Srting in Patient:")

str(patientdata)

writeLines("Summary of Patient")

summary(patientdata)

29
OUTPUT

Creating Strings
String A:
[1] "First"

String B:
[1] "String"

String C:
[1] "Program in R"

Concatenating A, B and C to MyString

[1] "First String Program in R"

Number of Characters in the String:

Changing to Upper and Lower case:

[1] "FIRST STRING PROGRAM IN R"
[1] "first string program in r"

Extracting parts of a string:

[1] "First"
[1] 25

Factor Operations
Creating Factor: Patient
patientID age diabetes status
1 1 25 Type1 Poor
2 2 34 Type2 Improved
3 3 28 Type1 Excellent
4 4 52 Type1 Poor

Srting in Patient:
'[Link]': 4 obs. of 4 variables:
$ patientID: num 1 2 3 4
$ age : num 25 34 28 52
$ diabetes : Factor w/ 2 levels "Type1","Type2": 1 2 1 1
$ status : [Link] w/ 3 levels "Excellent"<"Improved"<..: 3 2 1 3

Summary of Patient
patientID age diabetes status
Min. :1.00 Min. :25.00 Type1:3 Excellent:1
1st Qu.:1.75 1st Qu.:27.25 Type2:1 Improved :1
Median :2.50 Median :31.00 Poor :2
Mean :2.50 Mean :34.75
3rd Qu.:3.25 3rd Qu.:38.50
Max. :4.00 Max. :52.00

30
31
EX NO : 6
TO PERFORM CONTROL STATEMENT
DATE:
OPERATIONS

32
CODE

#A series of numbers in which each number ( Fibonacci number )

#is the sum of the two preceding numbers.

#The simplest is the series 0, 1, 1, 2, 3, 5, 8, etc.

# Create a function Fibonacci

# take input from the user

nterms = [Link](readline(prompt="How many terms? "))

# first two terms

n1 = 0

n2 = 1

count = 2

# check if the number of terms is valid

if(nterms <= 0)

print("Plese enter a positive integer")

} else

if(nterms == 1)

print("Fibonacci sequence:")

print(n1)

} else

print("Fibonacci sequence:")

print(n1)

print(n2)

while(count < nterms)

33
 nth = n1 + n2

print(nth)

# update values

n1 = n2

n2 = nth

count = count + 1

34
OUTPUT

Fibonacci(25)

[1] 0 1 1 2 3 5 8 13 21 34 55 89 144
[16] 233 377 610 987 1597 2584 4181 6765 10946 17711
28657 46368

35
36
EX NO : 7
TO PERFORM DATA IMPORT/EXPORT
DATE:
OPERATIONS

37
CODE

#set the working directory

setwd("H:/ ")

#to remove an environment

rm(list=ls())

#to get the student marks

m1=c(23,56,78,90,76)

m2=c(45,67,84,35,67)

m3=c(23,56,78,54,89)

m4=c(67,98,65,43,56)

m5=c(45,67,89,76,54)

var2=(1:5)/10

var3=c("R","Python","Data Mining","Big Data","C++")

#to create an [Link] method

df1=[Link](m1,m2,m3,m4,m5,var2,var3)

View(df1)

names(df1)=c("int1","int2","int3","int4","int5","float","char")

View(df1)\

#to create an .csv file

[Link](df1,"H:/PU - GL 2018/R - Supportive/2018-19-Odd

Sem/[Link]",[Link]=FALSE)

df2=[Link]("H:/PU - GL 2018/R - Supportive/2018-19-Odd Sem/[Link]")

print(df2)

View(df2)

38
#to convert an matrix format

DM=[Link](df1)

#to create an .txt file

write(DM,file="[Link]")

[Link]("[Link]")

df3=[Link]("[Link]",header=FALSE,sep="/",[Link] = TRUE,[Link] =

"EMPTY")

View(df3)

#to create an .xlsx file

#[Link]("xlsx")

library("xlsx")

[Link](df1,"H:/PU - GL 2018/R - Supportive/2018-19-Odd

Sem/[Link]",[Link]=FALSE,sheetName = "Data Frame")

df4=[Link]("H:/PU - GL 2018/R - Supportive/2018-19-Odd Sem/[Link]",sheetIndex = 1)

View(df4)

39
OUTPUT

CSV File:
int1 int2 int3 int4 int5 float char
1 23 45 23 67 45 0.1 R
2 56 67 56 98 67 0.2 Python
3 78 84 78 65 89 0.3 Data Mining
4 90 35 54 43 76 0.4 Big Data
5 76 67 89 56 54 0.5 C++
Text File:

Excel File:

40
41
EX NO : 8

TO PERFORM PRE-PROCESSING OPERATIONS

DATE:

42
CODE

#data set

aq=airquality;

#install packages

library("Amelia")

#identifying missing columns

missmap(aq)

#identifying missing position

mpos=which([Link](aq),[Link]=TRUE)

print(sprintf("total number of missing values of the airquality dataset is:%d",nrow=mpos))

print("the position of the missing value is:")

print(mpos)

a=mpos[,2]

matt=unique(a)

writeLines("the attributes having missing columns are:")

print(matt)

#find an mean value and replace NA values

writeLines("the MEAN value replacing the NA values")

aq$Ozone[[Link](aq$Ozone)]=mean(aq$Ozone,[Link]=TRUE)

aq$Solar.R[[Link](aq$Solar.R)]=mean(aq$Solar.R,[Link]=TRUE)

print(aq)

writeLines("the summary of airquality dataset is:")

print(summary(aq))

43
#find min-max normalization

writeLines("the MIN-MAX NORMALIZATION of airquality dataset is:")

aqmm=(aq-min(aq))/(max(aq)-min(aq))

print(aqmm)

44
OUTPUT

The position of the missing value is:

row col
[1,] 5 1
[2,] 10 1
[3,] 25 1
[4,] 26 1
[5,] 27 1
[6,] 32 1
[7,] 33 1
[8,] 34 1
[9,] 35 1
[10,] 36 1
[11,] 37 1
[12,] 39 1
[13,] 42 1
[14,] 43 1
[15,] 45 1
[16,] 46 1
[17,] 52 1
[18,] 53 1
[19,] 54 1
[20,] 55 1
[21,] 56 1
[22,] 57 1
[23,] 58 1
[24,] 59 1
[25,] 60 1
[26,] 61 1
[27,] 65 1
[28,] 72 1
[29,] 75 1
[30,] 83 1
[31,] 84 1
[32,] 102 1
[33,] 103 1
[34,] 107 1
[35,] 115 1
[36,] 119 1
[37,] 150 1
[38,] 5 2
[39,] 6 2
[40,] 11 2
[41,] 27 2
[42,] 96 2
[43,] 97 2
[44,] 98 2

The attributes having missing columns are:

[1] 1 2

45
the MEAN value replacing the NA values
Ozone Solar.R Wind Temp Month Day
1 41.00000 190.0000 7.4 67 5 1
2 36.00000 118.0000 8.0 72 5 2
3 12.00000 149.0000 12.6 74 5 3
4 18.00000 313.0000 11.5 62 5 4
5 42.12931 185.9315 14.3 56 5 5
6 28.00000 185.9315 14.9 66 5 6
7 23.00000 299.0000 8.6 65 5 7
8 19.00000 99.0000 13.8 59 5 8
9 8.00000 19.0000 20.1 61 5 9
10 42.12931 194.0000 8.6 69 5 10
11 7.00000 185.9315 6.9 74 5 11
12 16.00000 256.0000 9.7 69 5 12
13 11.00000 290.0000 9.2 66 5 13
14 14.00000 274.0000 10.9 68 5 14
15 18.00000 65.0000 13.2 58 5 15
………………..

…………………

the summary of airquality dataset is:

Ozone Solar.R Wind Temp Month
Min. : 1.00 Min. : 7.0 Min. : 1.700 Min. :56.00 Min. :5.000
1st Qu.: 21.00 1st Qu.:120.0 1st Qu.: 7.400 1st Qu.:72.00 1st Qu.:6.000
Median : 42.13 Median :194.0 Median : 9.700 Median :79.00 Median :7.000
Mean : 42.13 Mean :185.9 Mean : 9.958 Mean :77.88 Mean :6.993
3rd Qu.: 46.00 3rd Qu.:256.0 3rd Qu.:11.500 3rd Qu.:85.00 3rd Qu.:8.000
Max. :168.00 Max. :334.0 Max. :20.700 Max. :97.00 Max. :9.000
Day
Min. : 1.0
1st Qu.: 8.0
Median :16.0
Mean :15.8
3rd Qu.:23.0
Max. :31.0

46
The MIN-MAX NORMALIZATION of airquality dataset is:

Ozone Solar.R Wind Temp Month Day

1 0.120120120 0.56756757 0.019219219 0.1981982 0.01201201 0.000000000
2 0.105105105 0.35135135 0.021021021 0.2132132 0.01201201 0.003003003
3 0.033033033 0.44444444 0.034834835 0.2192192 0.01201201 0.006006006
4 0.051051051 0.93693694 0.031531532 0.1831832 0.01201201 0.009009009
5 0.123511442 0.55534987 0.039939940 0.1651652 0.01201201 0.012012012
6 0.081081081 0.55534987 0.041741742 0.1951952 0.01201201 0.015015015
7 0.066066066 0.89489489 0.022822823 0.1921922 0.01201201 0.018018018
8 0.054054054 0.29429429 0.038438438 0.1741742 0.01201201 0.021021021
9 0.021021021 0.05405405 0.057357357 0.1801802 0.01201201 0.024024024
10 0.123511442 0.57957958 0.022822823 0.2042042 0.01201201 0.027027027
11 0.018018018 0.55534987 0.017717718 0.2192192 0.01201201 0.030030030
12 0.045045045 0.76576577 0.026126126 0.2042042 0.01201201 0.033033033
13 0.030030030 0.86786787 0.024624625 0.1951952 0.01201201 0.036036036
14 0.039039039 0.81981982 0.029729730 0.2012012 0.01201201 0.039039039
15 0.051051051 0.19219219 0.036636637 0.1711712 0.01201201 0.042042042
…………………

…………………

47
48
EX NO : 9
TO PERFORM BASIC STATISTICAL
DATE:
OPERATIONS ON DATASET

49
CODE

#STATISTICAL OPERATIONS(MEAN,MEDIAN,STANDARD DEVIATION)

#to get the iris dataset

dm=iris[,-5]

#dataset to convert into matrix

dm=[Link](dm)

#to find a MEAN value

writeLines("@@@ MEAN VALUE @@@")

meandm=mean(dm)

writeLines("******* MEAN OF IRIS DATASET *******")

writeLines(sprintf("the mean of iris dataset is:%f", meandm))

writeLines("*********MEAN OF CONDITIONAL ATTRIBUTES********")

sl=mean(dm[,1])

writeLines(sprintf("The mean of [Link] is:%f",sl))

sw=mean(dm[,2])

writeLines(sprintf("The mean of [Link] is:%f",sw))

pl=mean(dm[,3])

writeLines(sprintf("The mean of [Link] is:%f",pl))

pw=mean(dm[,4])

writeLines(sprintf("The mean of [Link] is:%f",pw))

ca=c(sl,sw,pl,pw)

50
meanca=mean(ca)

writeLines(sprintf("The mean of conditional attribute is:%f",meanca))

#to find a MEDIAN value

writeLines(sprintf("@@@ THE CALCULATION OF MEDIAN VALUE @@@"))

mediandm=median(dm)

writeLines("*******MEDIAN OF IRIS DATASET*******")

writeLines(sprintf("The median of iris dataset is:%f", mediandm))

writeLines("*********MEDIAN OF CONDITIONAL ATTRIBUTES********")

sl=median(dm[,1])

writeLines(sprintf("The median of [Link] is:%f",sl))

sw=median(dm[,2])

writeLines(sprintf("The median of [Link] is:%f",sw))

pl=median(dm[,3])

writeLines(sprintf("the median of [Link] is:%f",pl))

pw=median(dm[,4])

writeLines(sprintf("The median of [Link] is:%f",pw))

ca=c(sl,sw,pl,pw)

medianca=median(ca)

writeLines(sprintf("The median of conditional attribute is:%f",medianca))

51
#to find the STANDARD DEVIATION value

writeLines("@ THE CALCULATION OF STANDARD DEVIATION VALUE @")

sddm=sd(dm)

writeLines("******* STANDARD DEVIATION OF IRIS DATASET *******")

writeLines(sprintf("the standard deviation of iris dataset is:%f", sddm))

writeLines("*STANDARD DEVIATION OF CONDIOTIONAL ATTRIBUTES *")

sl=sd(dm[,1])

writeLines(sprintf("The standard deviation of [Link] is:%f",sl))

sw=sd(dm[,2])

writeLines(sprintf("The standard deviation of [Link] is:%f",sw))

pl=sd(dm[,3])

writeLines(sprintf("The standard deviation of [Link] is:%f",pl))

pw=sd(dm[,4])

writeLines(sprintf("The standard deviation of [Link] is:%f",pw))

ca=c(sl,sw,pl,pw)

sdca=sd(ca)

writeLines(sprintf("The standard deviation of conditional attribute is:%f",sdca))

52
OUTPUT

@@@ MEAN VALUE @@@

******* MEAN OF IRIS DATASET *******
The mean of iris dataset is:3.464500
*********MEAN OF CONDITIONAL ATTRIBUTES********
The mean of [Link] is:5.843333
The mean of [Link] is:3.057333
The mean of [Link] is:3.758000
The mean of [Link] is:1.199333
The mean of conditional attribute is:3.464500

@@@ THE CALCULATION OF MEDIAN VALUE @@@

*******MEDIAN OF IRIS DATASET*******
The median of iris dataset is:3.200000
*********MEDIAN OF CONDITIONAL ATTRIBUTES********
The median of [Link] is:5.800000
The median of [Link] is:3.000000
The median of [Link] is:4.350000
The median of [Link] is:1.300000
The median of conditional attribute is:3.675000

@ THE CALCULATION OF STANDARD DEVIATION VALUE @

The standard deviation of iris dataset is:1.975490
*STANDARD DEVIATION OF CONDIOTIONAL ATTRIBUTES *
The standard deviation of [Link] is:0.828066
The standard deviation of [Link] is:0.435866
The standard deviation of [Link] is:1.765298
The standard deviation of [Link] is:0.762238
The standard deviation of conditional attribute is:0.571299

53
54
EX NO : 10
TO PERFORM DATA EXPLORATION
DATE:
OPERATIONS

55
CODE

N=readline("Enter the number of students:")

#Variable declaration

s=0

# Using for loop

for (i in 1:N)

s[i]=readline("Enter the mark of Students:");

# To declare the data type

s=[Link](s)

#to find the maximum value

maximum=max(s)

print(sprintf( "The maximum mark obtained: %d",maximum))

#to find the minimum value

minimum=min(s)

print(sprintf("The minimum mark obtained : %d",minimum))

#to find the total value

writeLines("The total value of marks :")

total=sum(s)

print(total)

56
# to find the average value

writeLines("The average value of marks :")

average=ave(s)

print(average[1])

# to find the square root value

writeLines("The squareroot value of marks :")

squareroot=sqrt(s)

print(squareroot)

# to find the round value

writeLines("The round value of squareroot marks :")

round=round(squareroot)

print(round)

57
OUTPUT

Enter the number of students:6

Enter the mark of Students:80
Enter the mark of Students:90
Enter the mark of Students:60
Enter the mark of Students:30
Enter the mark of Students:20
Enter the mark of Students:50

[1] "The maximum mark obtained: 90"

[1] "The minimum mark obtained : 20"

The total value of marks :

[1] 330

The average value of marks :

[1] 55

The squareroot value of marks :

[1] 8.944272 9.486833 7.745967 5.477226 4.472136 7.071068

The round value of squareroot marks :

[1] 9 9 8 5 4 7

58
59
EX NO : 11
TO PERFORM DATA VISUALIZATION
DATE:
OPERATIONS

60
CODE

#Visualization of Average Rainfall in India for Last 10 Years

writeLines("Visualization of Average Rainfall in India for Last 10 Years")

Year=c(2009,2010,2011,2012,2013,2014,2015,2016,2017,2018);
Rainfall=c(69.43,43.15,35.23,50.03,60.02,47.62,48.38,38.69,52.48,58.18);

writeLines("Rainfall Data from 2009-2018")

names(Rainfall)=Year
Rainfall

#Histograms
writeLines("Histogram for Rainfall Data")
hist(Rainfall,col="yellow", border="blue")

#Pie Chart
writeLines("Pie Chart for Rainfall Data")
pie(Rainfall,col=Year,main="Average Rainfall in India for Last 10 Years")

#Bar Chart
writeLines("Bar Chart for Rainfall Data")
barplot(Rainfall,col=Year, main="Average Rainfall in India for Last 10 Years")

#Boxplot
writeLines("Box Plot for Rainfall Data")
boxplot(Rainfall,main="Boxplot of Rainfall")

#Line Graph
writeLines("Line Graph for Rainfall Data")
plot(Year,Rainfall,type='o', col="blue", main="Average Rainfall in India for Last 10 Years")

#Scatterplot
writeLines("Scatterplot for Rainfall Data")
plot(Year, Rainfall, col="red", main="Average Rainfall in India for Last 10 Years")

61
OUTPUT

Visualization of Average Rainfall in India for Last 10 Years

Rainfall Data from 2009-2018

2009 2010 2011 2012 2013 2014 2015 2016 2017 2018
69.43 43.15 35.23 50.03 60.02 47.62 48.38 38.69 52.48 58.18

Histogram for Rainfall Data

62
Pie Chart for Rainfall Data

Bar Chart for Rainfall Data

63
Box Plot for Rainfall Data

Line Graph for Rainfall Data

64
Scatterplot for Rainfall Data

65
66
EX NO : 12

TO PERFORM T-TEST
DATE:

67
CODE

# Performing t-Tests

writeLines("Perform t-Tests ")

# One-Sample t Test

rnorm=rnorm(50,500,100)

writeLines("Summary of Data ")

summary(rnorm)

writeLines("One-Sample t-Tests ")

[Link](rnorm,mu=500)

#Paired-samples t Test

Pretest=c(25.0,41.7,41.7,54.2,29.2,50.0,54.2,45.8,54.2,33.3,33.3,54.2,37.5,12.5)

Posttest=c(41.7,66.7,91.7,70.8,70.8,54.2,87.5,54.2,70.8,50.0,58.3,79.2,87.5,45.8)

writeLines("Paired-samples t Test ")

[Link](Pretest,Posttest,paired=TRUE)

# Relationship between One-Sample and Paired-Sample t-Test

Differences=Posttest-Pretest;

writeLines("Relationship between One-Sample and Paired-Sample t-Test")

[Link](Differences)

#Two-Sample t Test

n=length(Pretest)

Pretest1=Pretest[1:(n/2)]

Pretest2=Pretest[((n/2)+1):n]

writeLines("Two-Sample t Test")

[Link](Pretest1,Pretest2);

68
OUTPUT

Perform t-Tests
Summary of Data
Min. 1st Qu. Median Mean 3rd Qu. Max.
280.9 406.4 481.7 486.5 550.4 799.8

One Sample t-test

data: rnorm
t = -0.84971, df = 49, p-value = 0.3996
alternative hypothesis: true mean is not equal to 500
95 percent confidence interval:
454.5055 518.4547
sample estimates:
mean of x
486.4801

Paired t-test
data: Pretest and Posttest
t = -6.7973, df = 13, p-value = 1.268e-05
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
-34.11287 -17.65856
sample estimates:
mean of the differences
-25.88571

Relationship between One-Sample and Paired-Sample t-Test

One Sample t-test
data: Differences
t = 6.7973, df = 13, p-value = 1.268e-05
alternative hypothesis: true mean is not equal to 0
95 percent confidence interval:
17.65856 34.11287
sample estimates:
mean of x
25.88571

Two-Sample t Test
Welch Two Sample t-test
data: Pretest1 and Pretest2
t = 0.51018, df = 11.439, p-value = 0.6196
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
-11.85835 19.05835
sample estimates:
mean of x mean of y
42.28571 38.68571

69
70
EX NO : 13

TO PERFORM ANOVA
DATE:

71
CODE

#ANOVA - Analysis of Variance

writeLines("Perform ANOVA-Analysis of Variance")

mpg=c(34,35,34.3,35.5,35.8,35.5,36.5,36.4,37,37.6,33.3,34,34.7,33,34.9)

brand=c("A","A","A","A","A","B","B","B","B","B","C","C","C","C","C")

mileage=[Link](mpg=mpg,brand=brand)

attach(mileage)

factor(brand)

writeLines("Create a Dataset - Automobile Mileage of Three Brands")

mileage

writeLines("Box Plot of Dataset")

boxplot(mpg~brand)

group=factor(brand)

# Use aov() to perform ANOVA

results=aov(mpg~group)

# To display the result

writeLines("ANOVA Test")

summary(results)

[Link](results,type="means")

72
OUTPUT

Create a Dataset - Automobile Mileage of Three Brands

mpg brand
1 34.0 A
2 35.0 A
3 34.3 A
4 35.5 A
5 35.8 A
6 35.5 B
7 36.5 B
8 36.4 B
9 37.0 B
10 37.6 B
11 33.3 C
12 34.0 C
13 34.7 C
14 33.0 C
15 34.9 C
Box Plot of Dataset

ANOVA Test
Df Sum Sq Mean Sq F value Pr(>F)
group 2 17.617 8.809 13.99 0.000731 ***
Residuals 12 7.556 0.630
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Tables of means
Grand mean

35.16667

group
A B C
34.92 36.60 33.98

73
74
EX NO : 14
TO PERFORM LINEAR REGRESSION AND
DATE:
LOGISTIC REGRESSION

75
CODE

X=[Link]("H:/PU - GL 2018/R - Supportive/2018-19-Odd Sem/[Link]")

str(x)

# PARTITION OF DATA

[Link](1234)

ind =sample(2,nrow(x),replace = T,prob = c(0.8,0.2))

train = x[ind==1,]

test = x[ind==2,]

plot(x$RESULT,x$AVG)

#logistic model

Logistic=glm(AVG~T_C01+T_C02+T_C03+T_C04+T_C05+T_C06,data = x)

summary(logistic)

# prediction

p1=predict(logistic,train,type ='response')

head(p1)

head(train)

p2=predict(logistic,test,type ='response')

head(p2)

head(test)

# Missclassification Error

cm=table(predict(logistic), x$AVG)

print(cm)

76
a = c( x$AVG < 50)

print(sprintf(" the student will not get seat",a))

View(a)

b=c( x$AVG > 40 || x$AVG < 80)

View(b)

c = c( x$AVG > 80)

print(sprintf(" the student will get seat",c))

View(c)

77
OUTPUT

*******Simple Linear Regression*******

Coefficients:
(Intercept) UNEM
3957 1134
[1] "The predicted fall enrollment, given a 9 Percent of unemployment rate is 14161 students"
Residuals:
Min 1Q Median 3Q Max
-7640.0 -1046.5 602.8 1934.3 4187.2

Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 3957.0 4000.1 0.989 0.3313
UNEM 1133.8 513.1 2.210 0.0358
---

*******Multiple Linear Regression*******

Coefficients:
(Intercept) UNEM HGRAD INC
-9153.2545 450.1245 0.4065 4.2749
[1] "The predicted fall enrollment, given a 9 Percent of unemployment rate,spring high school
graduating class (HGRAD) of 100,000, and a per capita income (INC) of $30,000 is 163792
students"
Residuals:
Min 1Q Median 3Q Max
-1148.84 -489.71 -1.88 387.40 1425.75

Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -9.153e+03 1.053e+03 -8.691 5.02e-09 ***
UNEM 4.501e+02 1.182e+02 3.809 0.000807 ***
HGRAD 4.065e-01 7.602e-02 5.347 1.52e-05 ***
INC 4.275e+00 4.947e-01 8.642 5.59e-09 ***

*******Logistic Regression*******
Deviance Residuals:
Min 1Q Median 3Q Max
-8.4601 -0.2188 0.2048 0.5724 1.4485

Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 3.81462 4.36362 0.874 0.38973
T_C01 0.13812 0.03396 4.068 0.00037 ***
T_C02 0.11006 0.08167 1.348 0.18900
T_C03 0.15764 0.07939 1.986 0.05731 .
T_C04 0.17885 0.06284 2.846 0.00835 **
T_C05 0.19952 0.05515 3.617 0.00121 **
T_C06 0.16188 0.02510 6.449 6.53e-07 ***
---

78
79
EX NO : 15
TO PERFORM CORRELATION AND MULTI-
DATE:
CORRELATION COEFFICIENT

80
CODE

#To compute correlation between age and glucose level

writeLines("Compute correlation between age and glucose level")

age=c(43,21,25,42,57,59);

writeLines("Age")

age

glucose_level=c(99,65,79,75,87,81);

writeLines("Glucose_level")

glucose_level

# Pearson Correlation

writeLines("Pearson Correlation")

Pearson_cor=cor(age, glucose_level, method = c("pearson"))

Pearson_cor

# Kendall Correlation

writeLines("Kendall Correlation")

Kendall_cor=cor(age, glucose_level, method = c("kendall"))

Kendall_cor

# Spearman Correlation

writeLines("Spearman Correlation")

Spearman_cor=cor(age, glucose_level, method = c("spearman"))

Spearman_cor

#TO compute multicorrelation between age, weight and glucose level

writeLines("Compute multicorrelation between age, weight and glucose level")

weight=c(55,40,42,55,70,65);

81
#correlation between age and glucose

a_g=cor(age, glucose_level, method = c("pearson"));

#correlation between age and weight

a_w=cor(age, weight, method = c("pearson"));

#correlation between weight and glucose

w_g=cor(weight, glucose_level,method = c("pearson"));

#Multiple Correlation

writeLines("Multiple Correlation")

Multiple_Correlation=sqrt(((a_g)^2+(w_g)^2-2*a_g*a_w*w_g)/(1-(w_g)^2));

Multiple_Correlation

82
OUTPUT

Compute correlation between age and glucose level

Age
[1] 43 21 25 42 57 59

Glucose_level
[1] 99 65 79 75 87 81

Pearson Correlation
[1] 0.5298089

Kendall Correlation
[1] 0.4666667

Spearman Correlation
[1] 0.7142857

Compute multicorrelation between age, weight and glucose level

Multiple Correlation
[1] 0.1103142

83
84