EXPERIMENT – 8

AIM: Write a java program to prepare a simulated data set with unique instances.

SOURCE CODE:
import java.io.FileWriter; // Import the FileWriter class

import java.io.IOException; // Import the IOException class to handle errors

import java.util.*;

class dataset {

public static void main(String[] args) {

int noOfInstances, noOfAtributes, i;

String temp_str, class_attributes, data;

System.out.print("Enter no of attributes (columns) : ");

Scanner sc = new Scanner(System.in);

noOfAtributes = sc.nextInt();

System.out.print("Enter no of Instances (rows) : ");

noOfInstances = sc.nextInt();

try {

FileWriter myWriter = new FileWriter("exp8.arff");

myWriter.write("@RELATION DWDM \n");

for(i=0; i < noOfAtributes; i++){

System.out.println("Enter Attribute name " + (i+1) + " : ");

temp_str = sc.next();

myWriter.write("@ATTRIBUTE " + temp_str + " REAL \n");

System.out.println("Enter class labels with comma separated values");

sc.nextLine();

class_attributes = sc.nextLine();

myWriter.write("@ATTRIBUTE class {" +class_attributes + "}\n");

myWriter.write("@DATA\n");

System.out.println("Enter data (rows) line by line with comma separated values");

 for(i=1; i <= noOfInstances; i++){

System.out.println("Enter row " + i + " : ");

data = sc.nextLine();

myWriter.write(data + "\n");

myWriter.close();

System.out.println("Successfully wrote to the file.");

} catch (IOException e) {

System.out.println("An error occurred.");

e.printStackTrace();

Output:

Enter no of attributes (columns) : 2

Enter no of Instances (rows) : 4

Enter Attribute name 1 :

Mid1

Enter Attribute name 2 :

Mid2

Enter class labels with comma separated values

abc,def,pqr,xyz

Enter data (rows) line by line with comma separated values

Enter row 1 :

25,28

Enter row 2 :

21,23

Enter row 3 :
14,24Enter row 4 : 19,22[Successfully wrote to the file.]
EXPERIMENT – 9
AIM: Write a Python program to generate frequent item sets / association rules using
Apriori algorithm.

Program:
from mlxtend.frequent_patterns import apriori, association_rules
import matplotlib.pyplot as plt import pandas as pd import numpy
as np
# df =
pd.read_csv('/content/retail_dataset.csv')
## Print first 10 rows
df.head(10) items = set() for col
in df:
items.update(df[col].unique())
print(items) itemset = set(items)
encoded_vals = [] for index, row
in df.iterrows():
rowset = set(row) labels = {}
uncommons = list(itemset - rowset) commons =
list(itemset.intersection(rowset)) for uc in
uncommons: labels[uc] = 0 for com in
commons: labels[com] = 1
encoded_vals.append(labels)
#encoded_vals[0] ohe_df =
pd.DataFrame(encoded_vals)
freq_items = apriori(ohe_df, min_support=0.1, use_colnames=True,
verbose=1)
freq_items.head(7)

OUTPUT:
Pencil', 'Eggs', 'Diaper', 'Bread', 'Milk', 'Bagel', 'Wine', 'Cheese',
'Meat'}
{'Pencil', 'Eggs', 'Diaper', nan, 'Bread', 'Milk', 'Bagel', 'Wine',
'Cheese', 'Meat'}
{'Pencil', 'Eggs', 'Diaper', nan, 'Bread', 'Milk', 'Bagel', 'Wine',
'Cheese', 'Meat'}
{'Pencil', 'Eggs', 'Diaper', nan, 'Bread', 'Milk', 'Bagel', 'Wine',
'Cheese', 'Meat'}
{'Pencil', 'Eggs', 'Diaper', nan, 'Bread', 'Milk', 'Bagel', 'Wine',
'Cheese', 'Meat'}
{'Pencil', 'Eggs', 'Diaper', nan, 'Bread', 'Milk', 'Bagel', 'Wine',
'Cheese', 'Meat'}
{'Pencil', 'Eggs', 'Diaper', nan, 'Bread', 'Milk', 'Bagel', 'Wine',
'Cheese', 'Meat'}
Processing 6 combinations | Sampling itemset size 6
/usr/local/lib/python3.10/distpackages/mlxtend/frequent_patterns/fpcommon.p
y:110:
support itemsets

0 1.0 (Eggs)

1 1.0 (nan)

2 1.0 (Bread)

3 1.0 (Bagel)

4 1.0 (Wine)

5 1.0 (Meat)

6 1.0 (Eggs, nan)

EXPERIMENT – 10
AIM: Write a program to calculate chi-square value using Python. Report your observation.

Program:
from scipy.stats import chi2_contingency

# defining the table data = [[207, 282, 241],

[234, 242, 232]] stat, p, dof, expected =

chi2_contingency(data)

# interpret p-value alpha

= 0.05 print("p value is"+

str(p)) if p <= alpha:

print('Dependent (reject H0)') else:

print('Independent (H0 holds true)')

OUTPUT:

p value is0.1031971404730939
Independent (H0 holds true)
EXPERIMENT – 11
AIM: Write a program of Naive Bayesian classification using Python programming language.

Program:
import pandas as pd
import numpy as np
from sklearn import datasets
iris = datasets.load_iris() # importing the dataset
iris.data # showing the iris data
X=iris.data #assign the data to the X
y=iris.target #assign the target/flower type to the y
print (X.shape)
print (y.shape)
from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.2,random_
state=9)
from sklearn.naive_bayes import GaussianNB
nv = GaussianNB() # create a classifier
nv.fit(X_train,y_train) # fitting the data
from sklearn.metrics import accuracy_score
y_pred = nv.predict(X_test) # store the prediction data
accuracy_score(y_test,y_pred)

OUTPUT:
/usr/local/lib/python3.10/dist-packages/ipykernel/ipkernel.py:283:
(150, 4)
(150,)
1.0
EXPERIMENT – 12
AIM: Implement a Java program to perform Apriori algorithm.

SOURCE CODE:

import java.util.*;

public class MainClass {

public static void main(String[] args) {

Scanner scanner = new Scanner(System.in);

System.out.println("Enter the number of transactions:");

int n = scanner.nextInt();

String[] itemNames = {"Milk", "Bread", "Coffee", "Juice", "Cookies", "Jam", "Tea", "Butter",
"Sugar", "Water"};

// Display all the listed items

System.out.println("List of items:");

for (int i = 0; i < itemNames.length; i++) {

System.out.println((i + 1) + "--" + itemNames[i]);

int[][] items = new int[n][10];

for (int i = 0; i < n; i++) {

System.out.println("Transaction " + (i + 1) + ":");

for (int j = 0; j < 10; j++) {

System.out.println("Is Item " + itemNames[j] + " present in this transaction? (1/0):");

items[i][j] = scanner.nextInt();

int[] nt = new int[10];

int[] q = new int[10];

 for (int j = 0; j < 10; j++) {

for (int i = 0; i < n; i++) {

if (items[i][j] == 1) {

nt[j]++;

System.out.println("Number of " + itemNames[j] + ": " + nt[j]);

System.out.println("Items selected after threshold calculation (>=50%):");

int t1 = 0;

for (int j = 0; j < 10; j++) {

float percentage = (nt[j] / (float) n) * 100;

if (percentage >= 50) {

q[j] = 1;

t1++;

System.out.println(itemNames[j] + " is selected ");

int[][] nt1 = new int[10][10];

for (int j = 0; j < 10; j++) {

for (int m = j + 1; m < 10; m++) {

for (int i = 0; i < n; i++) {

if (items[i][j] == 1 && items[i][m] == 1) {

nt1[j][m]++;

System.out.println("Number of Items of " + itemNames[j] + " & " + itemNames[m] + ": " +
nt1[j][m]);

}
 }

System.out.println("2-frequency itemsets with frequency >= 50%:");

for (int j = 0; j < 10; j++) {

for (int m = j + 1; m < 10; m++) {

float percentage = (nt1[j][m] / (float) n) * 100;

if (percentage >= 50) {

System.out.println(itemNames[j] + " & " + itemNames[m] + " is selected ");

output:
Enter the number of transactions:

List of items:

1--Milk2--Bread3--Coffee

4--Juice

5--Cookies

6--Jam

7--Tea

8--Butter

9--Sugar

10--Water

Transaction 1:

Is Item Milk present in this transaction? (1/0):

Is Item Bread present in this transaction? (1/0):

0
Is Item Coffee present in this transaction? (1/0):

Is Item Juice present in this transaction? (1/0):0

Is Item Cookies present in this transaction? (1/0):

Is Item Jam present in this transaction? (1/0):

Is Item Tea present in this transaction? (1/0):

Is Item Butter present in this transaction? (1/0):0

Is Item Sugar present in this transaction? (1/0):

Is Item Water present in this transaction? (1/0):0

Transaction 2:

Is Item Milk present in this transaction? (1/0):

Is Item Bread present in this transaction? (1/0):0

Is Item Coffee present in this transaction? (1/0):

Is Item Juice present in this transaction? (1/0):

Is Item Cookies present in this transaction? (1/0):0

Is Item Jam present in this transaction? (1/0):

Is Item Tea present in this transaction? (1/0):

Is Item Butter present in this transaction? (1/0):

Is Item Sugar present in this transaction? (1/0):

Is Item Water present in this transaction? (1/0):0

Number of Milk: 2

Number of Bread: 0

Number of Coffee: 2

Number of Juice: 0

Number of Cookies: 1

Number of Jam: 0

Number of Tea: 1

Number of Butter: 0

Number of Sugar: 2

Number of Water: 0

Items selected after threshold calculation (>=50%):

Milk is selected

Coffee is selected

Cookies is selected

Tea is selected

Sugar is selected

Number of Items of Milk & Bread: 0Number of Items of Milk & Coffee: 2

Number of Items of Milk & Juice: 0

Number of Items of Milk & Cookies: 1

Number of Items of Milk & Jam: 0

Number of Items of Milk & Tea: 1

Number of Items of Milk & Butter: 0

Number of Items of Milk & Sugar: 2

Number of Items of Milk & Water: 0

Number of Items of Bread & Coffee: 0

Number of Items of Bread & Juice: 0

Number of Items of Bread & Cookies: 0

Number of Items of Bread & Jam: 0

Number of Items of Bread & Tea: 0

Number of Items of Bread & Butter: 0

Number of Items of Bread & Sugar: 0

Number of Items of Bread & Water: 0

Number of Items of Coffee & Juice: 0

Number of Items of Coffee & Cookies: 1

Number of Items of Coffee & Jam: 0

Number of Items of Coffee & Tea: 1

Number of Items of Coffee & Butter: 0

Number of Items of Coffee & Sugar: 2

Number of Items of Coffee & Water: 0

Number of Items of Juice & Cookies: 0

Number of Items of Juice & Jam: 0

Number of Items of Juice & Tea: 0

Number of Items of Juice & Butter: 0

Number of Items of Juice & Sugar: 0

Number of Items of Juice & Water: 0

Number of Items of Cookies & Jam: 0

Number of Items of Cookies & Tea: 1

Number of Items of Cookies & Butter: 0

Number of Items of Cookies & Sugar: 1

Number of Items of Cookies & Water: 0

Number of Items of Jam & Tea: 0

Number of Items of Jam & Butter: 0

Number of Items of Jam & Sugar: 0

Number of Items of Jam & Water: 0

Number of Items of Tea & Butter: 0

Number of Items of Tea & Sugar: 1

Number of Items of Tea & Water: 0

Number of Items of Butter & Sugar: 0

Number of Items of Butter & Water: 0

Number of Items of Sugar & Water: 0

2-frequency itemsets with frequency >= 50%:

Milk & Coffee is selected

Milk & Cookies is selected

Milk & Tea is selected

Milk & Sugar is selected

Coffee & Cookies is selected

Coffee & Tea is selected

Coffee & Sugar is selected

Cookies & Tea is selected

Cookies & Sugar is selected

Tea & Sugar is selected

EXPERIMENT - 13
AIM: Write a program to cluster your choice of data using simple k-means algorithm using
JDK.

SOURCE CODE:

import java.util.*;

class KmeansJ {

public static void main(String args[]) {

int dataset[][] = {

{2,1},

{5,2},

{2,2},

{4,1},

{4,3},

{7,5},

{3,6},

{5,7},

{1,4},

{4,1}

};

int i,j,k=2;

int part1[][] = new int[10][2];

int part2[][] = new int[10][2];

float mean1[][] = new float[1][2];

float mean2[][] = new float[1][2];

float temp1[][] = new float[1][2], temp2[][] = new float[1][2];

int sum11 = 0, sum12 = 0, sum21 = 0, sum22 = 0;

double dist1, dist2;

int i1 = 0, i2 = 0, itr = 0;

// Printing the dataset

 System.out.println("Dataset: ");

for(i=0;i<10;i++) {

System.out.println(dataset[i][0]+" "+dataset[i][1]);

System.out.println("\nNumber of partitions: "+k);

// Assuming (2,2) and (5,7) are random means

mean1[0][0] = 2;

mean1[0][1] = 2;

mean2[0][0] = 5;

mean2[0][1] = 7;

// Loop till the new mean and previous mean are same

while(!Arrays.deepEquals(mean1, temp1) || !Arrays.deepEquals(mean2, temp2)) {

//Empting the partitions

for(i=0;i<10;i++) {

part1[i][0] = 0;

part1[i][1] = 0;

part2[i][0] = 0;

part2[i][1] = 0;

i1 = 0; i2 = 0;

//Finding distance between mean and data point and store the data point in
the corresponding partition

for(i=0;i<10;i++) {

dist1 = Math.sqrt(Math.pow(dataset[i][0] - mean1[0][0],2) +

Math.pow(dataset[i][1] - mean1[0][1],2));

dist2 = Math.sqrt(Math.pow(dataset[i][0] - mean2[0][0],2) +

Math.pow(dataset[i][1] - mean2[0][1],2));

if(dist1 < dist2) {

part1[i1][0] = dataset[i][0];

part1[i1][1] = dataset[i][1];

i1++;
 }

else {

part2[i2][0] = dataset[i][0];

part2[i2][1] = dataset[i][1];

i2++;

//Storing the previous mean

temp1[0][0] = mean1[0][0];

temp1[0][1] = mean1[0][1];

temp2[0][0] = mean2[0][0];

temp2[0][1] = mean2[0][1];

//Finding new mean for new partitions

sum11 = 0; sum12 = 0; sum21 = 0; sum22 = 0;

for(i=0;i<i1;i++) {

sum11 += part1[i][0];

sum12 += part1[i][1];

for(i=0;i<i2;i++) {

sum21 += part2[i][0];

sum22 += part2[i][1];

mean1[0][0] = (float)sum11/i1;

mean1[0][1] = (float)sum12/i1;

mean2[0][0] = (float)sum21/i2;

mean2[0][1] = (float)sum22/i2;

itr++;

System.out.println("\nFinal Partition: ");

System.out.println("Part1:");
 for(i=0;i<i1;i++) {

System.out.println(part1[i][0]+" "+part1[i][1]);

System.out.println("\nPart2:");

for(i=0;i<i2;i++) {

System.out.println(part2[i][0]+" "+part2[i][1]);

System.out.println("\nFinal Mean: ");

System.out.println("Mean1 : "+mean1[0][0]+" "+mean1[0][1]);

System.out.println("Mean2 : "+mean2[0][0]+" "+mean2[0][1]);

System.out.println("\nTotal Iteration: "+itr);

Output:
Dataset: 2 1

52

22

41

43

75

36

57

14

41

Number of partitions: 2

Final Partition:

Part1:

2 15 2
22

4 14 3

1 44 1

Part2:

75

36

57

Final Mean:

Mean1 : 3.142857 2.0Mean2 : 5.0 6.0

Total Iteration: 2
EXPERIMENT – 14
AIM:Write a program of cluster analysis using simple k-means algorithm Python
programming language.

Program:
importnumpy as np
import pandas as pd
import statsmodels.api as sm
import matplotlib.pyplot as plt
import seaborn as sns
sns.set()
from sklearn.cluster import KMeans
data = pd.read_csv('/content/cluster.csv')
data
plt.scatter(data['Longitude'],data['Latitude'])
plt.xlim(-180,180)
plt.ylim(-90,90)
plt.show()
x = data.iloc[:,1:3] # 1t for rows and second for columns
x
kmeans = KMeans(3)
kmeans.fit(x)
identified_clusters = kmeans.fit_predict(x)
identified_clusters
data_with_clusters = data.copy()
data_with_clusters['Clusters'] = identified_clusters
plt.scatter(data_with_clusters['Longitude'],data_with_clusters['Latitude
'],c=data_with_clusters['Clusters'],cmap='rainbow')
print(data_with_clusters)

OUTPUT:

/usr/local/lib/python3.10/dist-packages/ipykernel/ipkern el.py:283:
/usr/local/lib/python3.10/dist-packages/sklearn/cluster/_kmeans.py:870:
 /content/kmeans.csv.docx Latitude Longitude LANGUAGE Clusters
0 USA 44.97 -103.77 ENGLISH NaN 1
1 CANADA 62.40 -96.80 ENGLISH NaN 1
2 UK 66.25 2.40 FRENCH NaN 0
3 GERMANY 96.88 -2.53 ENGLISH NaN 0
4 AUSTRALIA 33.74 10.40 GERMAN NaN 0
5 INDIA 22.36 133.11 ENGLISH NaN 2
6 EUROPE 66.44 2.40 FRENCH NaN 0
7 IRAN 72.66 -96.80 ENGLISH NaN 1
8 IRAQ 46.75 54.07 ENGLISH NaN 0
9 SRILANA 22.58 22.77 FRENCH NaN 0
10 USA 44.97 -103.77 ENGLISH NaN 1
11 CANADA 62.40 -96.80 ENGLISH NaN 1
12 UK 66.25 2.40 FRENCH NaN 0
13 GERMANY 96.88 -2.53 ENGLISH NaN 0
14 AUSTRALIA 33.74 10.40 GERMAN NaN 0
15 INDIA 22.36 133.11 ENGLISH NaN 2
16 EUROPE 66.44 2.40 FRENCH NaN 0
17 IRAN 72.66 -96.80 ENGLISH NaN 1
18 IRAQ 46.75 54.07 ENGLISH NaN 0
19 SRILANA 22.58 22.77 FRENCH NaN 0
20 USA 44.97 -103.77 ENGLISH NaN 1
21 CANADA 62.40 -96.80 ENGLISH NaN 1
22 UK 66.25 2.40 FRENCH NaN 0
23 GERMANY 96.88 -2.53 ENGLISH NaN 0
24 AUSTRALIA 33.74 10.40 GERMAN NaN 0
25 INDIA 22.36 133.11 ENGLISH NaN 2
26 EUROPE 66.44 2.40 FRENCH NaN 0
27 IRAN 72.66 -96.80 ENGLISH NaN 1
28 IRAQ 46.75 54.07 ENGLISH NaN 0
29 SRILANA 22.58 22.77 FRENCH NaN 0
30 USA 44.97 -103.77 ENGLISH NaN 1
31 CANADA 62.40 -96.80 ENGLISH NaN 1
32 UK 66.25 2.40 FRENCH NaN 0
33 GERMANY 96.88 -2.53 ENGLISH NaN 0
34 AUSTRALIA 33.74 10.40 GERMAN NaN 0
35 INDIA 22.36 133.11 ENGLISH NaN 2
36 EUROPE 66.44 2.40 FRENCH NaN 0
37 IRAN 72.66 -96.80 ENGLISH NaN 1
38 IRAQ 46.75 54.07 ENGLISH NaN 0
39 SRILANA 22.58 22.77 FRENCH NaN 0
40 USA 44.97 -103.77 ENGLISH NaN 1
41 CANADA 62.40 -96.80 ENGLISH NaN 1
42 UK 66.25 2.40 FRENCH NaN 0
43 GERMANY 96.88 -2.53 ENGLISH NaN 0
44 AUSTRALIA 33.74 10.40 GERMAN NaN 0
45 INDIA 22.36 133.11 ENGLISH NaN 2
46 EUROPE 66.44 2.40 FRENCH NaN 0
47 IRAN 72.66 -96.80 ENGLISH NaN 1
48 IRAQ 46.75 54.07 ENGLISH NaN 0
49 SRILANA 22.58 22.77 FRENCH NaN 0
50 USA 44.97 -103.77 ENGLISH NaN 1
51 CANADA 62.40 -96.80 ENGLISH NaN 1
52 UK 66.25 2.40 FRENCH NaN 0
53 GERMANY 96.88 -2.53 ENGLISH NaN 0
54 AUSTRALIA 33.74 10.40 GERMAN NaN 0
55 INDIA 22.36 133.11 ENGLISH NaN 2
56 EUROPE 66.44 2.40 FRENCH NaN 0
57 IRAN 72.66 -96.80 ENGLISH NaN 1
58 IRAQ 46.75 54.07 ENGLISH NaN 0
59 SRILANA 22.58 22.77 FRENCH NaN 0

0
EXPERIMENT – 15
AIM: Write a program to compute/display dissimilarity matrix (for your own dataset
containing at least four instances with two attributes) using Python.

Program:
import numpy as np
import matplotlib.pyplot as plt
from scipy.stats import pearsonr
np.random.seed(42)
x=np.random.randn(15)
y=x+np.random.randn(15)
plt.scatter(x,y)
plt.plot(np.unique(x),np.poly1d(np.polyfit(x,y,1))(np.unique(x)))
plt.xlabel('x')
plt.ylabel('y')
plt.show()
corr,_=pearsonr(x,y)
print('pearsons correlation:%.3f'%corr)
from sklearn.metrics.pairwise import cosine_similarity
cos_sin=cosine_similarity(x.reshape(1,-1),y.reshape(1,-1))
print('cosine similarity:%.3f'%cos_sin)
from sklearn.metrics import jaccard_score
a=[1,1,1,0]
b=[1,1,0,1]
jacc=jaccard_score(a,b)
print("Jaccard score:%.3f"%jacc)
from scipy.spatial import distance
dat=distance.euclidean(x,y)
print("Euclidean distance:%.3f"%dat)
dst=distance.cityblock(x,y)
print("Manhattan Distance:%.3f"%dst)

OUTPUT:
/usr/local/lib/python3.10/dist-packages/ipykernel/ipkernel.py:283:
pearsons correlation:0.810
cosine similarity:0.773
Jaccard score:0.500
Euclidean distance:3.273
Manhattan Distance:10.468
EXPERIMENT – 16
AIM: Visualize the datasets using matplotlib in python.(Histogram, Box plot, Bar chart, Pie
chart etc.,)
Program:
import numpy as np
x = np.random.normal(20, 10, 30)
print(x)
import matplotlib.pyplot as plt
import numpy as np
x = np.random.normal(170, 10, 250)
plt.hist(x)
plt.show()
import matplotlib.pyplot as plt
import numpy as np
# Creating dataset
np.random.seed(10)
data = np.random.normal(100, 20, 200)
fig = plt.figure(figsize =(10, 7))
# Creating plot
plt.boxplot(data)

import numpy as np
import matplotlib.pyplot as plt
# creating the dataset
data = {'C':20, 'C++':15, 'Java':30,'Python':35}
courses = list(data.keys())
values = list(data.values())
fig1 = plt.figure(figsize = (10, 5))

# creating the bar plot

plt.bar(courses, values, color ='maroon',
width = 0.4)
plt.xlabel("Courses offered")
plt.ylabel("No. of students enrolled")
plt.title("Students enrolled in different courses")
plt.show()
# Import libraries
from matplotlib import pyplot as plt
import numpy as np
# Creating dataset
cars = ['AUDI', 'BMW', 'FORD',
'TESLA', 'JAGUAR', 'MERCEDES']
data = [23, 17, 35, 29, 12, 41]
# Creating plot
fig = plt.figure(figsize =(10, 7))
plt.pie(data, labels = cars)
# show plot
plt.show()
# show plot
plt.show()

OUTPUT:

/usr/local/lib/python3.10/dist-packages/ipykernel/ipkernel.py:283:
[13.98293388 38.52278185 19.86502775 9.42289071 28.22544912 7.7915635
22.08863595 0.40329876 6.71813951 21.96861236 27.3846658 21.71368281
18.84351718 16.98896304 5.2147801 12.80155792 15.39361229 30.57122226
23.4361829 2.36959845 23.24083969 16.1491772 13.23078 26.11676289
30.30999522 29.31280119 11.60782477 16.90787624 23.31263431 29.75545127]