Machine Learning Project.(CS403)
				   Malicious URL Detection


To run the code:

Simply type python SVM.py

The first answer comes that of SVM, then perceptron and then Neural Network.
The dataset used is named Day0.svm (it is in the svm format). 
For the train and test data :

We have chosen a part of the data for training and the a part of the data for testing(But they are disjoint).
The number of points used here are less(16000) but they can be easily extended to extremely large datasets.

Explanation:

In the SVM.py in the main function first the SVM code is executed.

Then the csv is created from the svm file by executing the Dimentionality_Reduction.py by the command os.system('python Dimentionality_Reduction.py').

Then perceptron update algorithm is executed by executing the file Perceptron.py.

And finally the neural network code is run.

Note that we have ourselves implemented the perceptron and neural network code.