Here are some things that caught our attention last week:
-
If you’re anything like me, you’re a sucker for algorithm visualization. These sorting algorithm animations and Mike Bostock’s visualizations of sampling, shuffling, sorting and maze generation are among my favorites. So I was delighted to find R2D3’s Visual Introduction to Machine Learning.
-
Dat is like Git for data - a “version-controlled, decentralized data tool for collaboration between data people and data systems.” It’s a much-needed tool and the development team just announced that it’s hit beta status - do check it out.
-
Hot on the heels of last week’s coverage of the Worm Wars The Economist has a superb “Clinical Trial Simulator” that brings home the consequences of pharmaceutical companies selectively publishing trial data. All Trails is the campaign for all past and present clinical trials to be registered and their full methods and summary results reported.
-
If you’ve used the open source statistics software R, the chances are that you’ve encountered the “Hadleyverse” - the R packages written by the prolific Hadley Wickham. Priceonomics has a fine profile of “The Man who Revolutionized R”
-
Finally, if you like mathematical brain teasers, Nick Berry’s Blog “Data Genetics” is essential reading. In a recent post he asks: I have a set containing three numbers {1,2,3}, what number can I add to this set so that the standard deviation remains the same? Hint: use a whiteboard...
Join the Conversation