— In the News —
Great article about why science is so easy to get wrong. This is very well written and with the p-value hacking simulator too, it's really a must-read.
Dr. DJ Patil, the U.S. Chief Data Scientist, has been doing a fantastic job of communicating his team's priorities and progress. Here's his latest six month update, which is a great overview that includes links to details and audio reports by key members of his staff.
IBM's “neuromorphic” chips are different than anything on the market today. Essentially, these chips provide deep learning at the hardware level and are potential game-changers for the industry. Here's an overview of the technology and its status.
— Sponsored Link —
Make HipChat Your Collaboration Command Center. Group Chat, Video Chat & Screensharing. $0/Unlimited Users. Get Started Today!
— Tools and Techniques —
This is a continuation of DataCamp's comprehensive tutorial for importing data into R. It's easy to follow and covers a wide variety of file types. In addition to a number of file types that weren't covered in Part 1, this part includes a section that specifically addresses large datasets.
Easy to follow introduction to eigenvectors and their relationship to matrices. For the most part, this is a plain English tutorial that continues with covariance, principal component analysis, and information entropy.
Practical guide to help software developers get started with machine learning.
IDEO is well-known for its human-centered approach to design. Here's an important read about how that relates to data.
— Resources —
This repo contains 101 web-scraping examples that were part of a recent Computational Journalism class at Stanford. Most of these scripts are simple and would be trivial to modify. The hard part is finding and interacting with the data sources, which these examples take care of for you.
Regardless of your skill level, you're likely to find something useful here. This is a combination cheatsheet/tutorial that's well organized and easy to search.
— Data Viz —
This 6-month review of news items, notable projects and articles is a MUST READ for data viz fans and practitioners. This article is by Andy Kirk of the super popular Visualising Data blog.
— About —
Data Elixir is curated and maintained by @lonriesberg. If you find this newsletter worthwhile, please help spread the word! Forward to your colleagues or use the links below to share to your favorite network: