In this course, you'll learn about clustering and dimension reduction, the two fundamental techniques of unsupervised learning and you'll learn to apply them using Python 3 and industry standard, freely available software libraries like scikit-learn and SciPy. You're going to learn to use the fundamental tools of unsupervised learning that professional data scientists use everyday.
So who is this course for? Perhaps you're an IT professional, an analyst, a scientist or an academic, and you're looking to make the transition to data science, or you're a student, and you want to learn what data science is all about.
In this course I'm going to share with you not only what I learnt but also the joy and the fascination of discovering patterns in data - the wonder of finding hidden structure in datasets that seemed at first too large and too complex. Each lecture is going to be followed by 3 or 4 short exercises where you'll practice what you've learnt on some real-world data. You'll experience this sense of discovery for yourself. You'll cluster Italian wines, you'll visualise the voting behaviour at the Eurovision, you'll analyse the stock market, build a low-dimensional map of Wikipedia, you'll find themes in collections of newspaper articles and common patterns in collections of images and you'll build a recommender system for recommending music based on user behaviour.