Skip to Content

Blogs

Detecting fraudulent transactions is a key applucation of statistical modeling, especially in an age of online transactions. R of course has many functions and packages suited to this purpose, including binary classification techniques such as logistic regression.

StackOverview is a popular Q&A site, and a go-to resource for developers of all languages to find answers to programming problems they may have: most of the time, the question has already been asked and answered, or you can always post a new question and wait for a reply. It's an excellent resource for R users, featuring answers to nearly 100,000 R questions.

Did you know that the charger for a modern MacBook has about as much computing power as the original Macintosh computer? That's one surprising lesson from this teardown of an Apple charger:

Buzzfeed isn't just listicles and cat videos these days. Science journalist Peter Aldhous recently joined Buzzfeed's editorial team, after stints at Nature, Science and New Scientist magazines. He brings with him his data journalism expertise and R programming skills to tell compelling stories with data on the site.

You may have heard that R and the big-data RevoScaleR package have been integrated with with SQL Server 2016 as SQL Server R Services.

In case you missed them, here are some articles from November of particular interest to R users. 

You can use emojis as plotting symbols in ggplot2 charts with the emoGG package.

A review of local R user group activity in 2015.

I was surprised to find that just five of the small particles in the video below, if arranged in just the right way, can jam the hopper:

 

Watch the coloured beads in the video as they ultimately join to form a perfect arch, which is apparently the only way the flow can be staunched. This Gizmodo article gives more background behind the research into solving this problem, which is apparently a common problem in some industrial settings.

David Smith's picture
December 11, 2015

Yesterday, the R Core Team released a new update to R (version 3.2.3, codenamed "Wooden Christmas Tree"), and the source distribution is now available for download on CRAN. Binary versions for Windows, Mac and Linux are also available for download from your local CRAN mirror.

This release makes a few small improvements and bug fixes to R, including: