Top Talks and Tutorials From PyData London

Get some insight into the most recent Python data science talks and presentations with this eclectic mix of videos from PyData London 2016.

PyData London 2016 took place this past weekend, from May 6-8, hosted by Bloomberg. For those unfamiliar with PyData, it is a data analysis conference for both users and developers which focuses on the Python ecosystem, but which is also R and Julia friendly. Directly from the organizers:

PyData conferences bring together users and developers of data analysis tools to share ideas and learn from each other. The PyData community gathers to discuss how best to apply Python tools, as well as tools using R and Julia, to meet evolving challenges in data management, processing, analytics, and visualization.

We aim to be an accessible, community-driven conference, with tutorials for novices, advanced topical workshops for practitioners, and opportunities for package developers and users to meet in person.

You can find out everything about PyData here.

PyData London 2016

PyData London 2016 boasted a packed schedule, and has made many of the talks and tutorials available for interested parties (be sure to check out previous PyData conference playlists as well). For busy readers without time to watch or comb through all the videos, the following are the top 5 most promising talks and tutorials from the recently-wrapped PyData London 2016 conference, in no particular order.

Update: It seems as though some of these videos have already been removed for some reason, and so I add in the following additional talk links as replacements:

A Gentle Introduction to Neural Networks

The first talk is presented by Tariq Rashid, and is intended as an introductory treatment of neural networks for those with little to no previous (hands-on) experience. The accompanying slides are available here, and the corresponding code is available here.

Probablistic Programming Data Science with PyMC3

This talk is given by Thomas Wiecki. The talks begins with an overview of probabilistic programming, and then moves to a more advanced treatment of the subject in the second half. The presentation slides are available here; code can be found here.

Assessing the Quality of a Clustering

Christian Hennig presents this talk, which first outlines clustering and clustering techniques, and then goes on to discuss result assessment techniques. The slides of the presentation are available here.

Building Data Pipelines in Python

This talk is by Marco Bonzanini, and discusses building data pipelines, and all the steps needed for data preparation when creating a data product. The slides from the talk are available here.

Finding Needles in Haystacks with Deep Neural Networks

Calvin Giles gives this presentation, which focuses on leveraging advanced deep learning techniques in a practical setting, with a focus on computer vision and image processing. The corresponding slides are available here.