Created
November 9, 2017 17:10
-
-
Save hoenirvili/d9bef7fa2b4e6c9611fc5b7a24ee5b6a to your computer and use it in GitHub Desktop.
naive bayes
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
x1 | x2 | y | |
---|---|---|---|
0 | 0 | 0 | |
0 | 0 | 0 | |
0 | 0 | 1 | |
0 | 0 | 1 | |
0 | 0 | 1 | |
0 | 0 | 1 | |
0 | 0 | 1 | |
0 | 0 | 1 | |
0 | 0 | 1 | |
0 | 0 | 1 | |
0 | 0 | 1 | |
0 | 0 | 1 | |
0 | 0 | 1 | |
0 | 0 | 1 | |
0 | 0 | 1 | |
0 | 0 | 1 | |
0 | 0 | 1 | |
0 | 0 | 1 | |
0 | 0 | 1 | |
0 | 0 | 1 | |
1 | 0 | 0 | |
1 | 0 | 0 | |
1 | 0 | 0 | |
1 | 0 | 0 | |
1 | 0 | 1 | |
0 | 1 | 0 | |
0 | 1 | 0 | |
0 | 1 | 0 | |
0 | 1 | 0 | |
0 | 1 | 1 | |
1 | 1 | 0 | |
1 | 1 | 0 | |
1 | 1 | 1 | |
1 | 1 | 1 | |
1 | 1 | 1 | |
1 | 1 | 1 | |
1 | 1 | 1 | |
1 | 1 | 1 | |
1 | 1 | 1 | |
1 | 1 | 1 | |
1 | 1 | 1 | |
1 | 1 | 1 | |
1 | 1 | 1 | |
1 | 1 | 1 | |
1 | 1 | 1 | |
1 | 1 | 1 | |
1 | 1 | 1 | |
1 | 1 | 1 | |
1 | 1 | 1 | |
1 | 1 | 1 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python3 | |
import csv | |
import sys | |
def main(): | |
if len(sys.argv) < 2: | |
raise ValueError('Requires path to *.csv file') | |
name = sys.argv[1] | |
data = [] # the hole csv data | |
with open(name, 'r') as fd: | |
r = csv.reader(fd) | |
data = [d for d in r] | |
print("Attributes = {}".format(data[0][:-1])) | |
print("Classifier = {}".format(data[0][-1])) | |
instance_to_classify = ['0', '0'] | |
y = naive_bayes(data[1:], instance_to_classify) | |
print("Instance to classify = {}".format(instance_to_classify)) | |
print("Bayes naive decision for y = {}".format(y)) | |
y = joint_bayes(data[1:], instance_to_classify) | |
print("Joint bayes decision for y = {}".format(y)) | |
def column(data, column): | |
return [row[column] for row in data] | |
def naive_bayes(data, instance): | |
target_names = list(set(column(data, -1))) | |
mle = {} | |
for target_name in target_names: | |
targets = column(data, -1).count(target_name) | |
maximum_likelihood = 0 | |
p = 1 | |
for index, element in enumerate(instance): | |
nominator = 0 | |
for row in data: | |
if (target_name == row[-1] and | |
element == row[index]): | |
nominator += 1 | |
p = (p * (nominator / targets)) | |
maximum_likelihood += (p * (targets/len(data))) | |
mle[target_name] = maximum_likelihood | |
return max(mle, key=mle.get) | |
def compare(one, two): | |
if len(one) != len(two): | |
raise ValueError("Lists needs to have the same length") | |
for i, j in zip(one, two): | |
if i != j: | |
return False | |
return True | |
def joint_bayes(data, instance): | |
target_names = list(set(column(data, -1))) | |
mle = {} | |
for target_name in target_names: | |
targets = column(data, -1).count(target_name) | |
maximum_likelihood = 0 | |
nominator = 0 | |
for row in data: | |
if (target_name == row[-1] and | |
compare(instance, row[:-1])): | |
nominator += 1 | |
mle[target_name] = ((nominator/targets) * (targets/len(data))) | |
return max(mle, key=mle.get) | |
if __name__ == '__main__': | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment