Building a linear classifier using Support Vector Machine (SVMs)

SVMs are supervised learning models that are used to build classifiers and regressors. An SVM finds the best separating boundary between the two sets of points by solving a system of mathematical equations. If you are not familiar with SVMs, here are a couple of good tutorials to get started:

• http://web.mit.edu/zoya/www/SVM.pdf

• http://www.support-vector.net/icml-tutorial.pdf

• http://www.svms.org/tutorials/Berwick2003.pdf

Let's see how to build a linear classifier using an SVM.

Getting ready

Let's visualize our data to understand the problem at hand. We will use svm.py that's already provided to you as a reference. Before we build the SVM, let's understand our data. We will use the data_multivar.txt file that's already provided to you. Let's see how to to visualize the data. Create a new Python file and add the following lines to it:

import numpy as np
import matplotlib.pyplot as plt

import utilities 

# Load input data
input_file...