From the course: Data Science Foundations: Data Mining in Python

Unlock this course with a free trial

Join today to access over 25,500 courses taught by industry experts.

t-SNE

t-SNE

- [Instructor] At the risk of dating myself, I have to mention that some of these algorithms I'm demonstrating simply didn't exist when I started working with data many years ago. One of the more interesting ones to me is t-SNE or the t-distributed stochastic neighbor embedding, which is actually a method used for visualizing data that has very high dimensionality. And that means you have a lot of variables to go into it. And this is an exploratory way. Again, it's not for classification, so we don't do a training and testing split but it's a way of visualizing the data. Let's come down and let's start by loading a few packages, including the t-SNE function from sklearn, scikit-learn. And we're going to load and prepare the data but we're going to load all of it as opposed to the training and testing splits. We will split it into the attribute variables into x and the class variable, which indicates whether it's supposed…

Contents