#Plot hyperplan how to#

There exist many debates about the value of C, as well as how to calculate the value for C. The machine learning field is relatively new, and experimental. What is C you ask? Don't worry about it for now, but, if you must know, C is a valuation of 'how badly' you want to properly classify, or fit, everything. Our kernel is going to be linear, and C is equal to 1.0. We're going to be using the SVC (support vector classifier) SVM (support vector machine). Moving along, we are now going to define our classifier: In the case of our project, we will wind up having a list of numerical features that are various statistics about stock companies, and then the 'label' will be either a 0 or a 1, where 0 is under-perform the market and a 1 is out-perform the market. We've then assigned 0 to the lower coordinate pairs and 1 to the higher feature pairs. Just by looking at our data set, we can see we have coordinate pairs that are 'low' numbers and coordinate pairs that are 'higher' numbers.

There are forms of machine learning called 'unsupervised learning,' where data labeling isn't used, as is the case with clustering, though this example is a form of supervised learning.įor our labels, sometimes referred to as 'targets,' we're going to use 0 or 1. Now that we have this array, we need to label it for training purposes. Let's translate our above x and y coordinates into an array that is compiled of the x and y coordinates, where x is a feature and y is a feature. Generally, you will see the feature list being stored in a capital X variable. Now, in order to feed data into our machine learning algorithm, we first need to compile an array of the features, rather than having them as x and y coordinate values. With that in mind, we're going to go ahead and continue with our two-featured example. Now you can start to understand the power of machine learning, seeing and analyzing a number of dimensions imperceptible to us. The problem occurs when we have four features, or four-thousand features. The 3D graph would be a little more challenging for us to visually group and divide, but still do-able. If we had three features, we could have a 3D graph. So this is with two features, and we see we have a 2D graph.

Now, of course, we can see with our own eyes how these groups should be divided, though exactly where we might draw the dividing line might be debated: These features will be visualized as axis on our graph. Next, let's consider that we have two features to consider. Other than the visualization packages we're using, you will just need to import svm from sklearn and numpy for array conversion. Typically, you wont be able to visualize as many dimensions as you will have features, but, it's worth visualizing at least once to understand how linear svc works.

The reason why we're using it here is for the eventual data visualization. Matplotlib here is not truly necessary for Linear SVC. Let's get started.įirst, we're going to need some basic dependencies: This makes this specific algorithm rather suitable for our uses, though you can use this for many situations. From there, after getting the hyperplane, you can then feed some features to your classifier to see what the 'predicted' class is. The objective of a Linear SVC (Support Vector Classifier) is to fit to the data you provide, returning a 'best fit' hyperplane that divides, or categorizes, your data. Before hopping into Linear SVC with our data, we're going to show a very simple example that should help solidify your understanding of working with Linear SVC. The most applicable machine learning algorithm for our problem is Linear SVC.

Plot hyperplan