ST.

MARY’S COLLEGE (AUTONOMOUS)

THOOTHUKUDI

M.Sc Computer Science(SSC)

(DATAMINING USING R)
2023-2024

Reg.No :

Name :

Semester :

Year :

ST.MARY’S COLLEGE (AUTONOMOUS)

 THOOTHUKUDI

DEPARTMENT OF COMPUTER SCIENCE (SSC)

BONAFIDE CERTIFICATE

Reg.No :

Name :

Sub.Code :

This is to certify that this is the bonafide record of the practical work done in
DATAMINING USING R at St .Mary’s College (Autonomous), during the year 2023-2024,
submitted for the M.Sc. Computer Science Practical Examination held on
at St. Mary’s College (Autonomous), Thoothukudi.

Date: Staff-in-charge

Head of the department External Examiner

 INDEX

EX.NO. DATE CONTENT PG. NO. SIGNATURE

1 27.11.2023 APRIORI ALGORITHM

2 06.12.2023 K-MEANS CLUSTERING

3 11.01.2024 HIERARCHICAL CLUSTERING

4 07.02.2024 CLASSIFICATION

5 13.02.2024 DECISION TREE

6 22.02.2024 LINEAR REGRESSION

7 06.03.2024 DATA VISUALIZATION

1. Apriori Algorithm
library(arules)

library(arulesViz)

library(RColorBrewer)

# import dataset

data("Groceries")

# using apriori() function

rules <- apriori(Groceries, parameter = list(supp = 0.01, conf = 0.2))

# using inspect() function

inspect(rules[1:10])

# using itemFrequencyPlot() function

arules::itemFrequencyPlot(Groceries, topN = 20,col = brewer.pal(8, 'Pastel2'),

main = 'Relative Item Frequency Plot',

type = "relative",

ylab = "Item Frequency (Relative)")

OUTPUT:

2. K- Means Clustering
set.seed(123)

data<- data.frame(x = c(rnorm(50, mean = 0), rnorm(50, mean = 5)),

y = c(rnorm(50, mean = 0), rnorm(50, mean = 5)))

plot(data$x, data$y, col = "blue", pch = 16, main = "Sample Data for K-Means Clustering")

kmeans_result<- kmeans(data, centers = 2, nstart = 20)

data$cluster<- kmeans_result$cluster

plot(data$x, data$y, col = data$cluster, pch = 16, main = "K-Means Clustering (K=2)")

points(kmeans_result$centers, col = 1:2, pch = 8, cex = 2)

cat("Cluster Centers:\n")

print(kmeans_result$centers)

OUTPUT:
3. Hierarchical Clustering
library(dplyr)

# Summary of dataset in package

head(mtcars)

# Finding distance matrix

distance_mat <- dist(mtcars, method = 'euclidean')

distance_mat

# Fitting Hierarchical clustering Model to training dataset

set.seed(240) # Setting seed

Hierar_cl <- hclust(distance_mat, method = "average")

Hierar_cl

# Plotting dendrogram

plot(Hierar_cl)

# Choosing no. of clusters

# Cutting tree by height

abline(h = 110, col = "green")

# Cutting tree by no. of clusters

fit <- cutree(Hierar_cl, k = 3 )

fit

table(fit)

rect.hclust(Hierar_cl, k = 3, border = "green")

OUTPUT:
 4. Classification Algorithm

library(party)
# Create the input data frame.

input.data <- readingSkills[c(1:105), ]

# Create the tree.

output.tree <- ctree(nativeSpeaker ~ age + shoeSize + score, data = input.data)

# Plot the tree.

plot(output.tree)

OUTPUT:

5. Decision Tree

library(dataset)
library(caTools)

library(party)

library(dplyr)

library(magrittr)

data("readingSkills")

head(readingSkills)

sample_data = sample.split(readingSkills, SplitRatio = 0.8)

train_data<- subset(readingSkills, sample_data == TRUE)

test_data<- subset(readingSkills, sample_data == FALSE)

model<- ctree(nativeSpeaker ~ ., train_data)

plot(model)

OUTPUT:

6. Linear Regression
x <-c(151,174,138,186,128,136,179,163,152,131)

y <-c(63,81,56,91,47,57,76,72,62,48)

# Apply the lm() function.

relation<- lm(y~x)

print(summary(relation))

# Plot the chart.

plot(y,x,col="blue",main="Height & Weight Regression",

abline(lm(x~y)),cex=1.3,pch =16,xlab ="Weight in Kg",ylab="Height in cm")

OUTPUT:

7. Data Visualization

barplot(airquality$Ozone, main = 'Ozone Concenteration in air', xlab = 'ozone levels', horiz = TRUE)
barplot(airquality$Ozone, main = 'Ozone Concenteration in air', xlab = 'ozone levels', col ='blue',
horiz = FALSE)
data(airquality)
hist(airquality$Temp, main ="La Guardia Airport's\ Maximum Temperature(Daily)",
xlab ="Temperature(Fahrenheit)",
xlim = c(50, 125), col ="yellow",
freq = TRUE)
boxplot(airquality[, 0:4],main ='Box Plots for Air Quality Parameters')
boxplot(airquality$Wind, main = "Average wind speed\ at La Guardia Airport",
xlab = "Miles per hour", ylab = "Wind",
col = "orange", border = "brown",
horizontal = TRUE, notch = TRUE)
plot(airquality$Ozone, airquality$Month, main ="Scatterplot Example",
xlab ="Ozone Concentration in parts per billion",
ylab =" Month of observation ",
pch = 19)

OUTPUT: