Now, linear is just one of many kernels that you can use, like I said there are many different kernels you can use. One of them is a polynomial model, so you might want to play with that. Please do go ahead and look up the documentation. It's good practice for you to looking at the docs. If you're going to be using scikit-learn in any sort of depth, there's a lot of different capabilities and options that you have available to you. So, go look up scikit-learn online, find out what the other kernels are for the SVC method, and try them out, see if you actually get better results or not.

This is a little exercise, not just in playing with SVM and different kinds of SVC, but also in familiarizing yourself with how to learn more on your own about SVC. And, honestly, a very important trait of any data scientist or engineer is going to be the ability to go and look up information yourself when you don't know the answers.

So, you know, I'm not being lazy by not telling you what those other kernels are, I want you to get used to the idea of having to look this stuff up on your own, because if you have to ask someone else about these things all the time you're going to get really annoying, really fast in a workplace. So, go look that up, play around it, see what you come up with.

So, that's SVM/SVC, a very high power technique that you can use for classifying data, in supervised learning. Now you know how it works and how to use it, so keep that in your bag of tricks!