Tech news site The Register has just published an in-depth profile of Revolution Analytics. It was great meeting the author Dan Olds at Revolution HQ a couple of weeks ago, and sharing with him why we think the R language is the way forward for data science: modern, applied, large-scale ... [Read more...]

In some work that I am currently involved in, we have to decide which GUI engine we should use. As an obvious starter, we decided to have a look at what other people are using in their packages. While cran helpfully displays all the R packages that are available, it ... [Read more...]

[Read more...]

I finally got around to organizing and packaging my complete set of extended model support for mtable in Martin Elff’s memisc library. Here is a list of the models supported: coxph, survreg – Cox proportional hazards models and parametric survival … Continue reading → [Read more...]

Bob Muenchen, author of R for SAS and SPSS Users and co-author of R for Stata Users, has updated his in-depth analysis of the popularity of data analysis software. Determining "popularity" for software is a tricky task, but this analysis looks at several different metrics: mailing list traffic, blogs, search ... [Read more...]

[Read more...]

Feature NumPy R contiguous (virtual) memory ✔ ✔ 'view' memory model ✔ ✘ subset-assignment ✔ ✔ vectorized operations ✔ ✔ memory-mapping ✔ ✘* broadcasting rules ✔ ✔ index arrays ✔ ✔ This comparison is current as of R 2.13.0, NumPy version 1.4.1, and other web resources to date. Because this post was motivated by a [...] [Read more...]

I’m not sure how I missed this package, but I am sure glad I’ve found it. The data.table package for R provides something of a reconceptualization of the standard data.frame object. Though it remains (mostly) compatible with data.frame. The advantage … Continue reading → [Read more...]

I came up with an idea to draw correlation network to get a grasp about relationship between a list of stocks. An alternative way to show correlation matrix would be head map, which can have limitations with big matrices (__100). Unfortunately,  ggplot2 package doesn’t have a easy way to draw ... [Read more...]

[Read more...]

Thanks to this post, I found OpenClassroom. In addition, thanks to Andrew Ng and his lectures, I took my first course in machine learning. These videos are quite easy to follow. Exercise 2 requires implementing gradient descent algorithm to model data with linear regression. Read More: 243 Words Totally [Read more...]

For its 20th anniversary, JCGS offers free access to papers, including Andrew’s discussion paper Why tables are really much better than graphs. (Another serious ending for an April fool joke!) Incidentally (or rather coincidentally), I received today the great news that our Using parallel computation to improve Independent Metropolis-Hastings ... [Read more...]

[Read more...]

[Read more...]

Recently, the good folks at Infochimps.com rolled out a series of new APIs to add to their already impressive set of data resources. I have been in a perpetual state of catch-up since the new year, so I have only now got around to adding some of these new ... [Read more...]

Exercise 5.2 Improves the Logistic Regression implementation done in Exercise 4 by adding a regularization parameter that reduces the problem of over-fitting. We will be using Newton's Method. Data Here's the data we want to fit. # linear regression # load the data mydata = read.csv("http://spreadsheets.google.com/pub?key=0AnypY27pPCJydHZPN2... [Read more...]

In lattice, there is a function called splom for the display of scatter plot matrices. For large datasets, the panel.hexbinplot from the hexbin package is a better option than the default panel. As an example, let’s use some meteorological data from MAPA-SIAR: library(solaR) library(hexbin) aranjuez [Read more...]

If there is ever a time to learn R and web application development, it is now...in the age of Big Data. The upcoming release of R 2.13 will provide basic functionality for developing R web applications on the desktop via the internal HTTP server, but t... [Read more...]

A couple of quick notes about some upcoming R courses: In Vancouver, Canada, R trainer Isabella Ghement is presenting two R courses: An Introduction to the Statistical Software Package R, 8:30am-4:30pm, March 30-31, 2011, Vancouver, B.C., Canada (http://www.ghement.ca/RworkshopMarch30and31_2011.html) Advanced Statistical Modeling Using the ... [Read more...]

Exercise 5.1 Improves the Linear Regression implementation done in Exercise 3 by adding a regularization parameter that reduces the problem of over-fitting. Over-fitting occurs especially when fitting a high-order polynomial, that we will try to do here. Data Here's the points we will make a model from: # linear regression mydata = read.csv("... [Read more...]