Lab Manual

1. Implement A* Search Algorithm

A* Search Algorithm is a Path Finding Algorithm. It is similar to Breadth First

Search(BFS). It will search shortest path using heuristic value assigned to node
and actual cost from Source_node to Dest_node
Draw a polynomial regression line through the data points:
import numpy
import matplotlib.pyplot as plt
numpy.random.seed(2)

x = numpy.random.normal(3, 1, 100)
y = numpy.random.normal(150, 40, 100) / x

train_x = x[:80]
train_y = y[:80]

test_x = x[80:]
test_y = y[80:]

mymodel = numpy.poly1d(numpy.polyfit(train_x, train_y, 4))

myline = numpy.linspace(0, 6, 100)

plt.scatter(train_x, train_y)
plt.plot(myline, mymodel(myline))
plt.show()

output
 2. K means

from sklearn.cluster import KMeans

import matplotlib.pyplot as plt

x = [4, 5, 10, 4, 3, 11, 14 , 6, 10, 12]

y = [21, 19, 24, 17, 16, 25, 24, 22, 21, 21]

plt.scatter(x, y)
plt.show()
data = list(zip(x, y))
inertias = []

for i in range(1,11):
kmeans = KMeans(n_clusters=i)
kmeans.fit(data)
inertias.append(kmeans.inertia_)

plt.plot(range(1,11), inertias, marker='o')

plt.title('Elbow method')
plt.xlabel('Number of clusters')
plt.ylabel('Inertia')
plt.show()

Output
 3. Train data & test data accuracy

from sklearn import datasets

from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn.tree import DecisionTreeClassifier

data = datasets.load_wine(as_frame = True)

X = data.data
y = data.target

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25,

random_state = 22)

dtree = DecisionTreeClassifier(random_state = 22)

dtree.fit(X_train,y_train)

y_pred = dtree.predict(X_test)

print("Train data accuracy:",accuracy_score(y_true = y_train, y_pred =

dtree.predict(X_train)))
print("Test data accuracy:",accuracy_score(y_true = y_test, y_pred = y_pred))

output
Train data accuracy: 1.0
Test data accuracy: 0.8222222222222222
 4. AgglomerativeClustering
import numpy as np
import matplotlib.pyplot as plt
from sklearn.cluster import AgglomerativeClustering

x = [4, 5, 10, 4, 3, 11, 14 , 6, 10, 12]

y = [21, 19, 24, 17, 16, 25, 24, 22, 21, 21]

data = list(zip(x, y))

hierarchical_cluster = AgglomerativeClustering(n_clusters=2,
affinity='euclidean', linkage='ward')
labels = hierarchical_cluster.fit_predict(data)

plt.scatter(x, y, c=labels)
plt.show()

output

5. Dendrogram, linkage
import numpy as np
import matplotlib.pyplot as plt
from scipy.cluster.hierarchy import dendrogram, linkage

x = [4, 5, 10, 4, 3, 11, 14 , 6, 10, 12]

y = [21, 19, 24, 17, 16, 25, 24, 22, 21, 21]
data = list(zip(x, y))

linkage_data = linkage(data, method='ward', metric='euclidean')

dendrogram(linkage_data)

plt.show()

output

6. Implement k-nearest neighbours classification using python

''' Aim : Implement k-nearest neighbours classification using python.

=================================
Explanation:
=================================

===> To run this program you need to install the sklearn Module

===> Open Command propmt and then execute the following command to insta
ll sklearn Module

---> pip install scikit-learn

-----------------------------------------------
In this program, we are going to use iris dataset.And this dataset Split into
training(70%) and test set(30%).

The iris dataset conatins the following features

---> sepal length (cm)

---> sepal width (cm)
---> petal length (cm)
---> petal width (cm)

The Sample data in iris dataset format is [5.4 3.4 1.7 0.2]

Where 5.4 ---> sepal length (cm)

3.4 ---> sepal width (cm)
1.7 ---> petal length (cm)
0.2 ---> petal width (cm)

===============================
Source Code :
===============================

'''
# Import necessary modules
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import train_test_split
from sklearn.datasets import load_iris
import random

# Loading data
data_iris = load_iris()

# To get list of target names

label_target = data_iris.target_names
print()
print("Sample Data from Iris Dataset")
print("*"*30)
# to display the sample data from the iris dataset
for i in range(10):
rn = random.randint(0,120)
print(data_iris.data[rn],"===>",label_target[data_iris.target[rn]])

# Create feature and target arrays

X = data_iris.data
y = data_iris.target

# Split into training and test set

X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size = 0.3, random_state=1)

print("The Training dataset length: ",len(X_train))

print("The Testing dataset length: ",len(X_test))
try:
nn = int(input("Enter number of neighbors :"))
knn = KNeighborsClassifier(nn)

knn.fit(X_train, y_train)
# to display the score
print("The Score is :",knn.score(X_test, y_test))
# To get test data from the user
test_data = input("Enter Test Data :").split(",")
for i in range(len(test_data)):
test_data[i] = float(test_data[i])
print()

v = knn.predict([test_data])
print("Predicted output is :",label_target[v])
except:
print("Please supply valid input......")
output
 7. Given the following data, which specify classifications for nine
ombinationsof VAR1 and VAR2 predict a classification for a case
where VAR1=0.906and VAR2=0.606, using the result of k-means
clustering with 3 means (i.e., 3centroids

from sklearn.cluster import KMeans

import numpy as np
X = np.array([[1.713,1.586], [0.180,1.786], [0.353,1.240],
[0.940,1.566], [1.486,0.759], [1.266,1.106],[1.540,0.419],[0.459,1.799],[0.773,0
.186]])

y=np.array([0,1,1,0,1,0,1,1,1])
kmeans = KMeans(n_clusters=3, random_state=0).fit(X,y)
print("The input data is ")
print("VAR1 \t VAR2 \t CLASS")
i=0
for val in X:
print(val[0],"\t",val[1],"\t",y[i])
i+=1
print("="*20)
# To get test data from the user
print("The Test data to predict ")
test_data = []
VAR1 = float(input("Enter Value for VAR1 :"))
VAR2 = float(input("Enter Value for VAR2 :"))
test_data.append(VAR1)
test_data.append(VAR2)
print("="*20)
print("The predicted Class is : ",kmeans.predict([test_data]))
Output
The input data is
VAR1 VAR2 CLASS
1.713 1.586 0
0.18 1.786 1
0.353 1.24 1
0.94 1.566 0
1.486 0.759 1
1.266 1.106 0
1.54 0.419 1
0.459 1.799 1
0.773 0.186 1
====================
The Test data to predict
Enter Value for VAR1 :1.786
Enter Value for VAR2 :2.677
====================
The predicted Class is : [2]

8. The probability that it is Friday and that a student is absent is 3%

# The probability that it is Friday and that a student is absent is 3%

pAF=0.03
print("The probability that it is Friday and that a student is absent :",pAF)

# The probability that it is Friday is 20%

pF=0.2
print("The probability that it is Friday : ",pF)
# The probability that a student is absent given that today is Friday
pResult=(pAF/pF)

# Display the Result

print("The probability that a student is absent given that today is Friday :
",pResult * 100,"%")
output
The probability that it is Friday and that a student is absent : 0.03
The probability that it is Friday : 0.2
The probability that a student is absent given that today is Friday :
15.0 %