What will you learn?

Hello and welcome to Advanced Data Mining with Weka. I’m Ian Witten, and I’m going to be giving some of the lessons in this course, which is brought to you by the entire data mining team at the University of Waikato in New Zealand. This is the third in a series of online courses on practical data mining and the use of the Weka workbench, and this course is going to look at the use of some popular packages in Weka, specialist packages for specialist jobs in data mining. And also, we’re going to look at some specific application areas in this course to give some example applications.

As you know, a weka is a bird found only on the islands of New Zealand, but, as far as this course is concerned, it’s a data mining workbench – the Waikato Environment for Knowledge Analysis – that contains a bunch of machine learning algorithms for various data mining tasks like classification, preprocessing, feature selection, clustering, association rule mining – things like that. So what are you going to learn in this course? Well, we’re going to look at the time series forecasting package and how to do time series forecasting with Weka. We’re going to look

at data stream mining: incremental classifiers in Weka, and we’re looking at the MOA system for Massive Online Analysis. There’s a MOA package for Weka, which we’ll install and look at, and then also the MOA system itself, you’ll install that – it’s got a very similar interface to Weka – and look at some its facilities for stream-oriented data mining. We’re going to be looking at Weka’s interface to the R data mining system. You can use facilities in R, which is a pretty advanced data mining system from Weka, getting all that extra functionality right inside your Weka. We’re going to look at distributed processing using the Apache SPARK system. We’re going to be looking at scripting Weka in Python.

There’s a package which allows you to script Weka right from the Explorer. You can write little Python scripts, and also you can install the Python Weka wrapper, where you install a full version of Python with access to all of the things that Python gives you access to plus Weka besides. And we’re going to look at some applications. We’re going to look at analyzing soil samples. We’re going to look at neuroimaging with functional MRI data. We’re going to look at classifying tweets and classifying images and signal peptide prediction. The aim of this course is to equip you to use Weka on your own data and most importantly to understand what it is that you’re doing. This is the team.

These are the Weka people at Waikato, and you’ll meet all of these people as we go through this course. They’re all experienced Weka users. They’ve lived with Weka for many years. Before I go, let me just show you that this is where I am at the moment. I’m sitting here in New Zealand. This is the world as we see it. New Zealand’s at the top, in the middle, where the red arrow is, and you’re probably down at the bottom somewhere. This is where Weka is from. I’ve turned this map of New Zealand around so that north is at the top, which is probably more familiar to you, and we’re right there.

The home of Weka at the University of Waikato in the center of the North Island of New Zealand. I’m really looking forward to giving this course, and looking forward to seeing you in the next lesson. Bye for now!