• Pandas DataFrames Tips and Tricks

    How do you iterate over the rows and columns of a Pandas DataFrame? How do you access the data in a format suitable for input for input to a modern machine learning framework? How do you one-hot-encode categorical data using a single line of code? Read this article to learn how!

    Published on Jul 31, 2022

  • Scalable graph representation learning with Graph Neural Networks

    Graph Neural Networks have received much attention recently due to the abundance of network data. The original spectral and spatial Graph Convolutional Networks scale poorly to large datasets. In this article we survey several approaches for scaling GCNs to handle graphs with 10s of millions and even billions of nodes.

    Published on Dec 11, 2021

  • The many kinds of data professionals

    Are you confused about all the different job titles assigned to those working in data analysis? What is the differerence between a data scientist and a statistician? Should one stay in school and earn a PhD if she wants to work as a data engineer? In this article, we provide an overview of the different types of data professionals. We explaing what the different job titles imply in terms of day-to-day work, educational requirements, skillset, and software tools.

    Published on Apr 02, 2021

  • How to keep up with machine learning research

    Every year, thousands of new machine learning papers are published. As a researcher, how can one keep up with so much information? Read our 4-step guide and never feel left behind again.

    Published on Feb 06, 2021