EX.

NO: 1 Implementation of Uninformed search algorithms (BFS, DFS)

GRAPH:

PROGRAM: BFS

graph = {
'1': ['2','3','4'],
'2': ['5', '6'],
'3':[],
'5': ['9','10'],
'4': ['7','8'],
'7': ['11','12'],
'6':[],
'8':[],
'9':[],
'10':[],
'11':[],
'12':[]
}
visited = [] # List for visited nodes.
queue = [] #Initialize a queue

def bfs(visited, graph, node): #function for BFS

visited.append(node)
queue.append(node)

while queue: # Creating loop to visit each node

m = queue.pop(0)
print (m, end = " ")

for neighbour in graph[m]:

if neighbour not in visited:
visited.append(neighbour)
queue.append(neighbour)

# Driver Code
print("Following is the Breadth-First Search")
bfs(visited, graph, '5') # function calling

OUTPUT:
Following is the Breadth-First Search
1 2 3 4 5 6 7 8 9 10 11 12
GRAPH:

PROGRAM: DFS

# Using a Python dictionary to act as an adjacency list

graph = {
'1': ['2','3','4'],
'2': ['5', '6'],
'3':[],
'5': ['9','10'],
'4': ['7','8'],
'7': ['11','12'],
'6':[],
'8':[],
'9':[],
'10':[],
'11':[],
'12':[]
}
visited = set() # Set to keep track of visited nodes of graph.

def dfs(visited, graph, node): #function for dfs

if node not in visited:
print (node)
visited.add(node)
for neighbour in graph[node]:
dfs(visited, graph, neighbour)
# Driver Code
print("Following is the Depth-First Search")
dfs(visited, graph, '5')

OUTPUT:
Following is the Depth-First Search
1
2
5
9
10
6
3
4
7
11
12
8
EX.NO: 2 Implementation of Informed search algorithms (A*,
memory-bounded A*)
GRAPH: A*

PROGRAM:
def aStarAlgo(start_node, stop_node):

open_set = set(start_node)

closed_set = set()

g = {} #store distance from starting node

parents = {} # parents contains an adjacency map of all nodes

#distance of starting node from itself is zero

g[start_node] = 0

#start_node is root node i.e it has no parent nodes

#so start_node is set to its own parent node

parents[start_node] = start_node

while len(open_set) > 0:

n = None

#node with lowest f() is found

for v in open_set:

if n == None or g[v] + heuristic(v) < g[n] + heuristic(n):

n=v

if n == stop_node or Graph_nodes[n] == None:

pass

else:

for (m, weight) in get_neighbors(n):

#nodes 'm' not in first and last set are added to first
 #n is set its parent

if m not in open_set and m not in closed_set:

open_set.add(m)

parents[m] = n

g[m] = g[n] + weight

#for each node m,compare its distance from start i.e g(m) to the

#from start through n node

else:

if g[m] > g[n] + weight:

#update g(m)

g[m] = g[n] + weight

#change parent of m to n

parents[m] = n

#if m in closed set,remove and add to open

if m in closed_set:

closed_set.remove(m)

open_set.add(m)

if n == None:

print('Path does not exist!')

return None

# if the current node is the stop_node

# then we begin reconstructin the path from it to the start_node

if n == stop_node:

path = []

while parents[n] != n:

path.append(n)

n = parents[n]

path.append(start_node)

path.reverse()

print('Path found: {}'.format(path))

return path

# remove n from the open_list, and add it to closed_list

# because all of his neighbors were inspected

open_set.remove(n)

closed_set.add(n)
 print('Path does not exist!')

return None

#define fuction to return neighbor and its distance

#from the passed node

def get_neighbors(v):

if v in Graph_nodes:

return Graph_nodes[v]

else:

return None

def heuristic(n):

H_dist = {

'A': 11,

'B': 6,

'C': 99,

'D': 1,

'E': 7,

'G': 0,

return H_dist[n]

#Describe your graph here

Graph_nodes = {

'A': [('B', 2), ('E', 3)],

'B': [('A', 2), ('C', 1), ('G', 9)],

'C': [('B', 1)],

'D': [('E', 6), ('G', 1)],

'E': [('A', 3), ('D', 6)],

'G': [('B', 9), ('D', 1)]

aStarAlgo('A', 'G')

OUTPUT:

Path found: ['A', 'E', 'D', 'G']

['A', 'E', 'D', 'G']

 EX.NO:4 Implementing Naive Bayes algorithm from scratch
using Python

PROGRAM:
# Importing library
import math
import random
import csv

# the categorical class names are changed to numberic data

# eg: yes and no encoded to 1 and 0
def encode_class(mydata):
classes = []
for i in range(len(mydata)):
if mydata[i][-1] not in classes:
classes.append(mydata[i][-1])
for i in range(len(classes)):
for j in range(len(mydata)):
if mydata[j][-1] == classes[i]:
mydata[j][-1] = i
return mydata

# Splitting the data

def splitting(mydata, ratio):
train_num = int(len(mydata) * ratio)
train = []
 # initially testset will have all the dataset
test = list(mydata)
while len(train) < train_num:
# index generated randomly from range 0
# to length of testset
index = random.randrange(len(test))
# from testset, pop data rows and put it in train
train.append(test.pop(index))
return train, test

# Group the data rows under each class yes or

# no in dictionary eg: dict[yes] and dict[no]
def groupUnderClass(mydata):
dict = {}
for i in range(len(mydata)):
if (mydata[i][-1] not in dict):
dict[mydata[i][-1]] = []
dict[mydata[i][-1]].append(mydata[i])
return dict

# Calculating Mean
def mean(numbers):
return sum(numbers) / float(len(numbers))

# Calculating Standard Deviation

def std_dev(numbers):
avg = mean(numbers)
variance = sum([pow(x - avg, 2) for x in numbers]) /
float(len(numbers) - 1)
return math.sqrt(variance)

def MeanAndStdDev(mydata):
info = [(mean(attribute), std_dev(attribute)) for attribute in
zip(*mydata)]
# eg: list = [ [a, b, c], [m, n, o], [x, y, z]]
# here mean of 1st attribute =(a + m+x), mean of 2nd attribute
= (b + n+y)/3
# delete summaries of last class
del info[-1]
return info

# find Mean and Standard Deviation under each class

def MeanAndStdDevForClass(mydata):
info = {}
dict = groupUnderClass(mydata)
for classValue, instances in dict.items():
info[classValue] = MeanAndStdDev(instances)
return info

# Calculate Gaussian Probability Density Function

def calculateGaussianProbability(x, mean, stdev):
 expo = math.exp(-(math.pow(x - mean, 2) / (2 *
math.pow(stdev, 2))))
return (1 / (math.sqrt(2 * math.pi) * stdev)) * expo

# Calculate Class Probabilities

def calculateClassProbabilities(info, test):
probabilities = {}
for classValue, classSummaries in info.items():
probabilities[classValue] = 1
for i in range(len(classSummaries)):
mean, std_dev = classSummaries[i]
x = test[i]
probabilities[classValue] *=
calculateGaussianProbability(x, mean, std_dev)
return probabilities

# Make prediction - highest probability is the prediction

def predict(info, test):
probabilities = calculateClassProbabilities(info, test)
bestLabel, bestProb = None, -1
for classValue, probability in probabilities.items():
if bestLabel is None or probability > bestProb:
bestProb = probability
bestLabel = classValue
return bestLabel
# returns predictions for a set of examples
def getPredictions(info, test):
predictions = []
for i in range(len(test)):
result = predict(info, test[i])
predictions.append(result)
return predictions

# Accuracy score
def accuracy_rate(test, predictions):
correct = 0
for i in range(len(test)):
if test[i][-1] == predictions[i]:
correct += 1
return (correct / float(len(test))) * 100.0

# driver code

# add the data path in your system

filename = r'E:\user\MACHINE LEARNING\machine learning algos\
Naive bayes\filedata.csv'

# load the file and store it in mydata list

mydata = csv.reader(open(filename, "rt"))
mydata = list(mydata)
mydata = encode_class(mydata)
for i in range(len(mydata)):
mydata[i] = [float(x) for x in mydata[i]]

# split ratio = 0.7

# 70% of data is training data and 30% is test data used for testing
ratio = 0.7
train_data, test_data = splitting(mydata, ratio)
print('Total number of examples are: ', len(mydata))
print('Out of these, training examples are: ', len(train_data))
print("Test examples are: ", len(test_data))

# prepare model
info = MeanAndStdDevForClass(train_data)

# test model
predictions = getPredictions(info, test_data)
accuracy = accuracy_rate(test_data, predictions)
print("Accuracy of your model is: ", accuracy)
OUTPUT:
Total number of examples are: 200
Out of these, training examples are: 140
Test examples are: 60
Accuracy of your model is: 71.2376788
 EX.NO:5 Implement Bayesian Networks

PROGRAM:
import numpy as np
import pandas as pd
import csv
from pgmpy.estimators import MaximumLikelihoodEstimator
from pgmpy.models import BayesianModel
from pgmpy.inference import VariableElimination

heartDisease = pd.read_csv('heart.csv')
heartDisease = heartDisease.replace('?',np.nan)

print('Sample instances from the dataset are given below')

print(heartDisease.head())

print('\n Attributes and datatypes')

print(heartDisease.dtypes)

model= BayesianModel([('age','heartdisease'),('sex','heartdisease'),
('exang','heartdisease'),('cp','heartdisease'),('heartdisease','restecg'),
('heartdisease','chol')])
print('\nLearning CPD using Maximum likelihood estimators')
model.fit(heartDisease,estimator=MaximumLikelihoodEstimator)

print('\n Inferencing with Bayesian Network:')

HeartDiseasetest_infer = VariableElimination(model)
print('\n 1. Probability of HeartDisease given evidence= restecg')
q1=HeartDiseasetest_infer.query(variables=['heartdisease'],evidence
={'restecg':1})
print(q1)

print('\n 2. Probability of HeartDisease given evidence= cp ')

q2=HeartDiseasetest_infer.query(variables=['heartdisease'],evidence
={'cp':2})
print(q2)

OUTPUT:
EX.NO:6 Build Regression models

PROGRAM: LINEAR REGRESSION MODELS

import numpy as np
import matplotlib.pyplot as plt

def estimate_coef(x, y):

# number of observations/points
n = np.size(x)

# mean of x and y vector

m_x = np.mean(x)
m_y = np.mean(y)

# calculating cross-deviation and deviation about x

SS_xy = np.sum(y*x) - n*m_y*m_x
SS_xx = np.sum(x*x) - n*m_x*m_x

# calculating regression coefficients

b_1 = SS_xy / SS_xx
b_0 = m_y - b_1*m_x

return (b_0, b_1)

def plot_regression_line(x, y, b):

# plotting the actual points as scatter plot
plt.scatter(x, y, color = "m",
 marker = "o", s = 30)

# predicted response vector

y_pred = b[0] + b[1]*x

# plotting the regression line

plt.plot(x, y_pred, color = "g")

# putting labels
plt.xlabel('x')
plt.ylabel('y')

# function to show plot

plt.show()

def main():
# observations / data
x = np.array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])
y = np.array([1, 3, 2, 5, 7, 8, 8, 9, 10, 12])

# estimating coefficients
b = estimate_coef(x, y)
print("Estimated coefficients:\nb_0 = {} \
\nb_1 = {}".format(b[0], b[1]))

# plotting regression line

plot_regression_line(x, y, b)
if __name__ == "__main__":
main()

OUTPUT:
Estimated coefficients:
b_0 = 1.2363636363636363
b_1 = 1.1696969696969697