program1

library(arules)

dataset=list(

c("Bread","Butter","Milk"),

c("Bread","Butter"),

c("Beer","Cookies","Diapers"),

c("Milk",'Diapers',"Bread","Butter"),

c("Beer","Diapers")

items1=transactions(dataset)

print(items1)

rules=apriori(items1,parameter=list(supp=0.4,conf=0.7,minlen=2,maxlen=10))

inspect(rules)

output

library(arules)
> dataset=list(
+ c("Bread","Butter","Milk"),
+ c("Bread","Butter"),
+ c("Beer","Cookies","Diapers"),
+ c("Milk",'Diapers',"Bread","Butter"),
+ c("Beer","Diapers")
+)
> items1=transactions(dataset)
> print(items1)
transactions in sparse format with
5 transactions (rows) and
6 items (columns)
> rules=apriori(items1,parameter=list(supp=0.4,conf=0.7,minlen=2,maxlen=10))
Apriori

Parameter specification:
confidence minval smax arem aval originalSupport maxtime support minlen maxlen target ext
0.7 0.1 1 none FALSE TRUE 5 0.4 2 10 rules TRUE

Algorithmic control:
filter tree heap memopt load sort verbose
0.1 TRUE TRUE FALSE TRUE 2 TRUE
Absolute minimum support count: 2

set item appearances ...[0 item(s)] done [0.00s].

set transactions ...[6 item(s), 5 transaction(s)] done [0.00s].
sorting and recoding items ... [5 item(s)] done [0.00s].
creating transaction tree ... done [0.00s].
checking subsets of size 1 2 3 done [0.00s].
writing ... [7 rule(s)] done [0.00s].
creating S4 object ... done [0.00s].
> inspect(rules)
lhs rhs support confidence coverage lift count
[1] {Beer} => {Diapers} 0.4 1 0.4 1.666667 2
[2] {Milk} => {Butter} 0.4 1 0.4 1.666667 2
[3] {Milk} => {Bread} 0.4 1 0.4 1.666667 2
[4] {Butter} => {Bread} 0.6 1 0.6 1.666667 3
[5] {Bread} => {Butter} 0.6 1 0.6 1.666667 3
[6] {Butter, Milk} => {Bread} 0.4 1 0.4 1.666667 2
[7] {Bread, Milk} => {Butter} 0.4 1 0.4 1.666667 2
>
>
>

Program2

library(cluster)

items <- read.csv("E:/kmeans.csv")

summary(items)

plot(items)

data <- kmeans(items,2)

print(data)

clusplot(items,data$cluster,color=TRUE,lines=0,labels = 2)

output:
library(cluster)
> items <- read.csv("E:/kmeans.csv")
> summary(items)
Dataset
Min. : 3.00
1st Qu.: 4.25
Median :10.00
Mean :12.83
3rd Qu.:18.75
Max. :30.00
> plot(items)
> data <- kmeans(items,2)
> print(data)
K-means clustering with 2 clusters of sizes 3, 3

Cluster means:
Dataset
1 21.66667
2 4.00000

Clustering vector:
[1] 2 2 1 2 1 1

Within cluster sum of squares by cluster:

[1] 116.6667 2.0000
(between_SS / total_SS = 79.8 %)

Available components:

[1] "cluster" "centers" "totss" "withinss" "tot.withinss" "betweenss"

[7] "size" "iter" "ifault"
> clusplot(items,data$cluster,color=TRUE,lines=0,labels = 2)
Program3

library(cluster)

items <- c(5,10,12,3,8)

summary(items)

plot(items)

data <- dist(items,method="euclidean")

hier <- hclust(data,method="complete")

plot(hier)

grps<-cutree(hier,k=2)

print(grps)

rect.hclust(hier,k=2,border="green")

output:

library(cluster)
> items <- c(5,10,12,3,8)
> summary(items)
Min. 1st Qu. Median Mean 3rd Qu. Max.
3.0 5.0 8.0 7.6 10.0 12.0
> plot(items)
> data <- dist(items,method="euclidean")
> hier <- hclust(data,method="complete")
> plot(hier)
> grps<-cutree(hier,k=2)
> print(grps)
[1] 1 2 2 1 2
> rect.hclust(hier,k=2,border="green")
Program4

library(e1071)

data<-read.csv("E:/mark.csv")

head(data)

str(data)

model<-naiveBayes(Dept~.,data=data)

predictions<-predict(model,data)
print(predictions)

model1<-naiveBayes(Dept~Maths+Science,data=data)

print(model1)

library(naivebayes)

model1<-naive_bayes(Dept~Maths+Science,usekernal=T,data=data)

print(model1)

output

library(e1071)
> data<-read.csv("E:/mark.csv")
> head(data)
Dept Maths Science
1 BCA 90 93
2 CS 98 78
3 BCA 60 50
4 Physics 95 67
5 CS 50 90
6 CS 65 70
> str(data)
'data.frame': 7 obs. of 3 variables:
$ Dept : chr "BCA" "CS" "BCA" "Physics" ...
$ Maths : int 90 98 60 95 50 65 87
$ Science: int 93 78 50 67 90 70 78

> model<-naiveBayes(Dept~.,data=data)
> predictions<-predict(model,data)
> print(predictions)
[1] CS Physics BCA Physics CS CS Physics
Levels: BCA CS Physics
> model1<-naiveBayes(Dept~Maths+Science,data=data)
>
> print(model1)

Naive Bayes Classifier for Discrete Predictors

Call:
naiveBayes.default(x = X, y = Y, laplace = laplace)

A-priori probabilities:
Y
BCA CS Physics
0.2857143 0.4285714 0.2857143

Conditional probabilities:
Maths
Y [,1] [,2]
BCA 75 21.213203
CS 71 24.556058
Physics 91 5.656854

Science
Y [,1] [,2]
BCA 71.50000 30.405592
CS 79.33333 10.066446
Physics 72.50000 7.778175

> library(naivebayes)
> model1<-naive_bayes(Dept~Maths+Science,usekernal=T,data=data)
> print(model1)

================================================ Naive Bayes ======================================

Call:
naive_bayes.formula(formula = Dept ~ Maths + Science, data = data,
usekernal = T)

--------------------------------------------------------------------------------------------------------------

Laplace smoothing: 0

--------------------------------------------------------------------------------------------------------------

A priori probabilities:

BCA CS Physics
0.2857143 0.4285714 0.2857143
 --------------------------------------------------------------------------------------------------------------

Tables:

--------------------------------------------------------------------------------------------------------------
::: Maths (Gaussian)
--------------------------------------------------------------------------------------------------------------

Maths BCA CS Physics

mean 75.000000 71.000000 91.000000
sd 21.213203 24.556058 5.656854

--------------------------------------------------------------------------------------------------------------
::: Science (Gaussian)
--------------------------------------------------------------------------------------------------------------

Science BCA CS Physics

mean 71.500000 79.333333 72.500000
sd 30.405592 10.066446 7.778175

--------------------------------------------------------------------------------------------------------------

>
Program5

library(party)

library(rpart)

data<-read.csv("E:/decision.csv")

head(data)

str(data)

plot(data)

data1<-as.data.frame(data)

tree<-
rpart(Play~data1$Whether+data1$Temperature+data1$Windy,data=data1,method="class",control=rpart.c
ontrol(minsplit=1,minbucket=1,cp=0))

plot(tree,main="Decision Tree")

text(tree)

output;
library(party)
> library(rpart)
> data<-read.csv("E:/decision.csv")
> head(data)
Day Whether Temperature Windy Play
1 1 Rain Mild Weak No
2 2 Normal Hot Weak Yes
3 3 Wind Mild Strong Yes
4 4 Normal Cool Weak No
5 5 Rain Hot Strong No
> str(data)
'data.frame': 5 obs. of 5 variables:
$ Day : int 1 2 3 4 5
$ Whether : chr "Rain" "Normal" "Wind" "Normal" ...
$ Temperature: chr "Mild" "Hot" "Mild" "Cool" ...
$ Windy : chr "Weak" "Weak" "Strong" "Weak" ...
$ Play : chr "No" "Yes" "Yes" "No" ...
> plot(data)
> data1<-as.data.frame(data)
> tree<-
rpart(Play~data1$Whether+data1$Temperature+data1$Windy,data=data1,method="class",control=rpart.c
ontrol(minsplit=1,minbucket=1,cp=0))
> plot(tree,main="Decision Tree")
> text(tree)
Program6

Age <- c(22,42,21,57)

Glosteral <- c(60,90,65,65)

relation <- lm(Glosteral~Age)

summary(relation)

a <- data.frame(Age = 54)

result <- predict(relation,a)

print(result)

output:

Age <- c(22,42,21,57)

> Glosteral <- c(60,90,65,65)
> relation <- lm(Glosteral~Age)
> summary(relation)

Call:
lm(formula = Glosteral ~ Age)

Residuals:
1 2 3 4
-6.538 18.333 -1.282 -10.513

Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 60.8974 20.1572 3.021 0.0943 .
Age 0.2564 0.5232 0.490 0.6725
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 15.67 on 2 degrees of freedom

Multiple R-squared: 0.1072, Adjusted R-squared: -0.3392
F-statistic: 0.2402 on 1 and 2 DF, p-value: 0.6725

> a <- data.frame(Age = 54)

> result <- predict(relation,a)
> print(result)
1
74.74359

Program7

#BAR PLOT

Age<-c(55,57,43,35,25)

BP<-c(140,141,130,120,120)

colors=c("red","yellow","green","violet","cyan")

barplot(Age,BP,col=colors,ylab='Age',xlab='BP,main=”Bar Plot')

#BOX PLOT

x<-c(12,24,50,33,28,43)

boxplot(x,horizontal=TRUE,main='Box Plot',xlab="Items")
#HISTOGRAM

x<-c(12,24,50,33,28,43)

hist(x)

colors=c("red","yellow","violet","green","cyan")

hist(x,col=colors,main="Histogram",xlab="Items")

#SCATTERPLOT

Age<-c(12,8,15,7,9)

Weight<-c(23,12,35,21,15)

plot(Age,Weight,ylab='Weight',xlab='Age',main='Scatter Plot')

#PIECHART

x<-c(10,30,12,23,21)

lbl<-c("US","UK","INDIA","JAPAN","FRANCE")

colors=c("red","yellow","violet","green","cyan")

pie(x,lbl,main="Pie Chart",col=colors)

output: