Publications by David Smith
Revolution R, PMML and ADAPA: Webinar April 13
If you'd like to learn more about using the PMML package in R to export statistical models, or if you'd just like to learn more about building predictive models in Revolution R and creating predictions (scores) from them in other applications or in the cloud, I'll be co-presenter on a webinar next week that might be of interest. On Wednesday Apr...
1154 sym
New R User Group in St Louis, MO
The latest local R user group to join the fold is in St Louis, Missouri. Created by Josh Ulrich, their first meeting is on Monday, April 11. Check the link below for full details and to RSVP. Saint Louis R User Group: Inaugural Meeting Related To leave a comment for the author, please follow the link and comment on their blog: Revolutions. R-...
629 sym
Rstudio updates to beta 2
The folks over at Rstudio have released a new update to their open-source R GUI, currently in beta test. This Beta 2 release adds more customizable layouts, editor improvements and new editing themes. Also of interest is a new feature that allows creation of graphics that update under the control of sliders and checkboxes and such. See the full d...
820 sym
Journal of Statistical Software. Vol. 40
The latest edition of the Journal of Statistical Software is out, with plenty of interesting articles for R users. A must-read is Hadley Wickham's article on “The Split-Apply-Combine Strategy for Data Analysis“, which makes a compelling argument for the use of the plyr package to partition datasets and apply sub-group analyses. Also, anyone w...
1316 sym
R 2.13.0 released
The R Core Group has released the latest update to open-source R, R 2.13.0 is now available. You can download the new source distribution from the R Project website, and I see from the Download R tool at inside-R.org that binaries for Windows and Mac are already available at my local CRAN mirror (and, shortly, yours too). The (long) list of upd...
1744 sym
In case you missed it: March Roundup
In case you missed them, here are some articles from February of particular interest to R users. The doSMP package, which enables parallel processing for R on multiprocessor machines, is now available on CRAN. The Offensive Politics blog provided R code used to make a map of precinct returns in the Chicago mayoral election. A connector to integ...
3181 sym
Visualizing tax brackets
With Tax Day fast approaching here in the US, there's been a lot of discussion about tax policy and in particular the tax rates paid by the highest income earners. Like in many countries, here the income tax system is bracketed: Tax Bracket Single Married Filing Jointly 10% Bracket $0 – $8,375 $0 – $16,750 15% Bracket $8,375 – $34,000 $1...
3493 sym 2 img 1 tbl
Slides and replay for PMML webinar
If you missed Wednesday's webinar on Deploying Predictive Analytics with Revolution R, PMML and ADAPA, the presentation slides and the replay (in WMV, reg. req'd) format are now available for download. Here are some additional references, from the closing slide: How Revolution R and ADAPA work together The PMML Package reference White Paper: Dep...
1069 sym
How Kaggle competitors use R
The competitive data prediction competitions hosted by Kaggle require data scientists to bring their A game: the competition is intense, and competitors know in real time from the daily leaderboards how their predictions compare in accuracy to those of their rivals. So it's no surprise that open-source R, the most powerful statistics language, is...
2615 sym 4 img
250 years of Bayes’ Theorem
The Reverend Thomas Bayes died 250 years ago this month. His grave, located near epidemiological centre of excellence St Mary's College, remains a point of pilgrimage for statisticians (of both Bayesian and Frequentist stripes) visiting London to this day. Because since then, Bayes Theorem has been the underpinning of predictive analytics applica...
1257 sym