Scribd
Upload
19 views

Ex 6

Uploaded by

senthil7111
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
19 views

Ex 6

Uploaded by

senthil7111
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
You are on page 1/ 2

Ex.No.

6 Naïve Bayesian Classifier

############### PROGRAM ###############


import csv
import random
import math
def loadcsv(filename):
with open(filename,"r") as file:
lines = csv.reader(file)
dataset = list(lines)
dataset = dataset[1:]
dataset = [[float(x)for x in row]for row in dataset]
return dataset
def splitdataset(dataset, splitratio):
trainsize = int(len(dataset) * splitratio);
trainset = []
copy = list(dataset);
while len(trainset) <trainsize:
index = random.randrange(len(copy));
trainset.append(copy.pop(index))
return [trainset, copy]
def separatebyclass(dataset):
separated = {}
for i in range(len(dataset)):
vector = dataset[i]
if (vector[-1] not in separated):
separated[vector[-1]] = []
separated[vector[-1]].append(vector)
return separated
def mean(numbers):
return sum(numbers)/float(len(numbers))
def stdev(numbers):
avg = mean(numbers)
variance = sum([pow(x-avg,2) for x in numbers])/float(len(numbers)-1)
return math.sqrt(variance)
def summarize(dataset):
summaries = [(mean(attribute), stdev(attribute)) for attribute in
zip(*dataset)];
del summaries[-1]
return summaries
def summarizebyclass(dataset):
separated = separatebyclass(dataset);
summaries = {}
for classvalue, instances in separated.items():
summaries[classvalue] = summarize(instances)
return summaries
def calculateprobability(x, mean, stdev):
exponent = math.exp(-(math.pow(x-mean,2)/(2*math.pow(stdev,2))))
return (1 / (math.sqrt(2*math.pi) * stdev)) * exponent
def calculateclassprobabilities(summaries, inputvector):
probabilities = {}
for classvalue, classsummaries in summaries.items():
probabilities[classvalue] = 1
for i in range(len(classsummaries)):
mean, stdev = classsummaries[i]
x = inputvector[i]
probabilities[classvalue] *= calculateprobability(x, mean, stdev)
return probabilities
def predict(summaries, inputvector):
probabilities = calculateclassprobabilities(summaries, inputvector)
bestLabel, bestProb = None, -1
for classvalue, probability in probabilities.items():
if bestLabel is None or probability >bestProb:
bestProb = probability
bestLabel = classvalue
return bestLabel
def getpredictions(summaries, testset):
predictions = []
for i in range(len(testset)):
result = predict(summaries, testset[i])
predictions.append(result)
return predictions
def getaccuracy(testset, predictions):
correct = 0
for i in range(len(testset)):
if testset[i][-1] == predictions[i]:
correct += 1
return (correct/float(len(testset))) * 100.0
def main():
filename = 'D:\\New folder\\Ex6.csv'
splitratio = 0.67
dataset = loadcsv(filename)
trainingset, testset = splitdataset(dataset, splitratio)
print('Split {0} rows into train={1} and test={2} rows'.format(len(dataset),
len(trainingset), len(testset)))
summaries = summarizebyclass(trainingset);
predictions = getpredictions(summaries, testset)
accuracy = getaccuracy(testset, predictions)
print('Accuracy of the classifier is : {0}%'.format(accuracy))
main()

############### OUTPUT ###############

Split 9 rows into train=6 and test=3 rows


Accuracy of the classifier is : 33.33333333333333%

You might also like