Publications by David Smith
Applications of R presentations at Dataweek
I'm speaking at the DataWeek conference in San Francisco today. My talk follows Skylar Lyon from Accenture — I'm really looking forward to hearing how he uses Revolution R Enterprise with Teradata Database to run R in-database with 400 million rows of data. Update: Here are Skylar's slides. The slides for my talk on other companies' applicatio...
772 sym
Webinar September 25: Data Science with R
A quick heads up that if you'd like to get a great introduction to doing data science with the R language, Joe Rickert will be giving a free webinar next Thursday, September 25: Data Science with R. Regular readers of the blog will be familiar with Joe's posts on this topic. A few recent examples include posts on comparing machine learning models...
1553 sym
Around the world in 80k miles
You're probably familiar with the classic Travelling Salesman problem: given (say) 20 cities, what is shortest route you can take that passes through all 20 cities and returns to the starting point? It's a difficult problem to solve, because you need to try all possible routes to find the minimum, and there are a LOT of possibilities. For a 20-ci...
2174 sym 2 img
Become an effective data hacker with the R-Hadoop stack
In discussion with several data scientists, Will Stanton (a data scientist with Return Path) learned that a common concern is: what software should I be using? There are many options out there, but what is the best platform to be an effective “data hacker”? Will recommends using a technology stack with R and Hadoop, which allows data scientis...
1462 sym
Police militarization in the US, over time
The militarization of local police departments here in the US has been much in the news lately, and the New York Times published in June an in-depth article on how materiel from wars has ended up in the hands of US counties. Besides the traditional reporting it's a fantastic piece of data journalism: the Times submitted a freedom-of-information r...
1448 sym 2 img
Video introduction to data manipulation with dplyr
Hadley Wickham's dplyr package is a great toolkit for getting data ready for analysis in R. If you haven't yet taken the plunge to using dplyr, Kevin Markham has put together a great hands-on video tutorial for his Data School blog, which you can see below. The video covers the five main data-manipulation “verbs” that dplyr provides: filter, ...
1413 sym
New York Times approachably describes Bayesian Statistics
The New York Times published an article of interest to statisticians the other day: “The Odds, Continually Updated“. Surprisingly for a general-audience newspaper, this article goes into the the distinctions between Bayesian and frequentist statistics, and does so in a very approachable way. Here's an excerpt: The essence of the frequentist t...
2002 sym
R as a general-purpose language for creating DSLs
As a computer scientist, RStudio's Joe Cheng has some great insights into the R language and how it compares with other programming language. In the interview with DataScience.LA below, he notes that while R is often thought about as a domain-specific language (or DSL), the combination of a functional language with deferred evaluation of function...
1371 sym
In case you missed it: September 2014 Roundup
In case you missed them, here are some articles from September of particular interest to R users. Norm Matloff argues that T-tests shouldn't be part of the Statistics curriculum and questions the “star system” for p-values in R. A nice video introduction to the dplyr package and the %>% operator, presented by Kevin Markham. An animation of ...
2542 sym
14 Reasons Why R is better than Excel
The Fantasy Football Analytics blog shares these 14 reasons why R is better than Excel for data analysis: More powerful data manipulation capabilities Easier automation Faster computation It reads any type of data Easier project organization It supports larger data sets Reproducibility (important for detecting errors) Easier to find and fix erro...
1414 sym