— In the News —
"Holy crap" is right. The recent acquisitions of Looker and Tableau are head-spinning and are just part of a wave of major acquisitions this year. In this post, Tristan Handy offers some perspective on what it means for the future of the data stack.
Apparently, "litigation analytics and prediction" is an emerging field and the courts in France, at least, don't like it. This article in an online publication called "Artificial Lawyer" describes a new law that's designed to undermine the practice. Regardless of whether the law actually accomplishes anything or not, the fear behind it is an interesting descent for analytics.
— Sponsored Link —
Mode Studio combines a SQL editor, native Python & R notebooks, HTML/JS editor, and visualization builder in one platform. Connect data from anywhere and analyze with your preferred language. Make custom viz (D3.js, HTML/CSS) or use out-of-the-box charts.
— Tools and Techniques —
This post by Alex Hayes will help you evaluate whether a statistical package is worth using and if you write software, it will help you confirm the correctness of the code that you write. Covers key test types and considerations.
"Lost demand" is hard to measure but is crucial to understanding the inefficiencies in a business. This post on the Instacart Tech Blog explores the problem and how they approach it with machine learning.
Kedro is an open-source workflow development tool that helps you build data pipelines that are robust, scalable, deployable, reproducible and versioned. This post introduces the project and for details, here's the code repo >>
Vettery specializes in tech roles and is completely free for job seekers. Interested? Submit your profile, and if accepted onto the platform, you can receive interview requests directly from top companies growing their data science teams.
— Projects —
Kyle McDonald calls himself "an artist that works with code." He works with data too and this interactive essay is a fascinating exploration of seven terabytes of data from what's essentially, an alien life form. The story starts in the 60s, with a well-known whale researcher named Roger Payne...
— Resources —
This curated list of resources is a great place to get started for learning data engineering skills. Includes sections for SQL, Databases, Algorithms & Data Structures, Programming, Cloud Platforms, Tools, etc.
Sebastian Raschka recently uploaded this collection of 80 Jupyter notebooks that he uses for teaching TensorFlow and PyTorch. There are a variety of deep learning architectures, models, and tips here. This collection has been up for about a week and has ~5,000 stars already!
— Data Viz —
Uncertainty + Visualization, Explained
Matthew Kay and Jessica Hullman are collaborating on a series of posts about uncertainty visualization. The first one covers the basics and from there, they'll be exploring techniques from visualization research and beyond:
If you haven't used Plotly Express yet, you may not realize that it's inspired by Hadley Wickham’s layered grammar of graphics. That makes it easy to work with and gives users a lot of control, in spite of its terse code. This post shows how that works and includes a variety of examples to get started with.