Even though exploring data visually is an integral part of the data analytic pipeline, we struggle to do so once the number of dimensions go beyond three. I get a lot of questions on how we can visualise data beyond the normal bar and line charts to show many dimensions. I decided to give a talk at The Fifth Elephant conference focussed on showcasing techniques to visually explore multi dimensional data (p > 3).
The talks start with visualising a very small dataset to teach about the grammar of graphics and then goes to explore visualising large and big datasets. Then it moves to exploring wide datasets and showcases different techniques - Standard 2D/3D Approaches, Glyph based Approaches, Geometric Transformation Approaches, Stacked based Approaches and Pixel based Approaches - to do so. It also explores the role of interaction - annotation, pan & zoom, brushing & linking etc. - to improve our ability to successfully conduct EDA.
I thought the video came out nice and I was quite happy with the talk. If you don’t want the narrative and want to quickly run through the slides, then feel free to browse the slideshare below.
24 July 2015