Facebook and R

Part 1 How do people at Facebook use R?

tamar Rosenn, Facebook

Itamar conveyed how Facebook’s Data Team used R in 2007 to answer two questions about new users: (i) which data points predict whether a user will stay? and (ii) if they stay, which data points predict how active they’ll be after three months?

For the first question, Itamar’s team used recursive partitioning (via the rpartpackage) to infer that just two data points are significantly predictive of whether a user remains on Facebook: (i) having more than one session as a new user, and (ii) entering basic profile information.

For the second question, they fit the data to a logistic model using a least angle regression approach (via the lars package), and found that activity at three months was predicted by variables related to three classes of behavior: (i) how often a user was reached out to by others, (ii) frequency of third party application use, and (iii) what Itamar termed “receptiveness” — related to how forthcoming a user was on the site.


and cute graphs like the famous




studying baseball on facebook


by counting the number of posts that occurred the day after a team lost divided by the total number of wins, since losses for great teams are remarkable and since winning teams’ fans just post more.


But mostly at

https://www.facebook.com/data?sk=notes and https://www.facebook.com/data?v=app_4949752878


and creating new packages

1. jjplot (not much action here!)



I liked the promise of JJplot at


2. ising models



3. R pipe



even the FB interns are cool



Part 2 How do people with R use Facebook?

Using the API at https://developers.facebook.com/tools/explorer

and code mashes from




but the wonderful troubleshooting code from http://www.brocktibert.com/blog/2012/01/19/358/

which needs to be added to the code first


and using network package


Annoyingly the Facebook token can expire after some time, this can lead to huge wait and NULL results with Oauth errors

If that happens you need to regenerate the token

What we need
> require(RCurl)
> require(rjson)
> download.file(url=”http://curl.haxx.se/ca/cacert.pem”, destfile=”cacert.pem”)

Roman’s Famous Facebook Function (altered)

> facebook <- function( path = “me”, access_token , options){
+ if( !missing(options) ){
+ options <- sprintf( “?%s”, paste( names(options), “=”, unlist(options), collapse = “&”, sep = “” ) )
+ } else {
+ options <- “”
+ }
+ data <- getURL( sprintf( “https://graph.facebook.com/%s%s&access_token=%s&#8221;, path, options, access_token ), cainfo=”cacert.pem” )
+ fromJSON( data )
+ }


Now getting the friends list
> friends <- facebook( path=”me/friends” , access_token=access_token)
> # extract Facebook IDs
> friends.id <- sapply(friends$data, function(x) x$id)
> # extract names
> friends.name <- sapply(friends$data, function(x) iconv(x$name,”UTF-8″,”ASCII//TRANSLIT”))
> # short names to initials
> initials <- function(x) paste(substr(x,1,1), collapse=””)
> friends.initial <- sapply(strsplit(friends.name,” “), initials)

This matrix can take a long time to build, so you can change the value of N to say 40 to test your network. I needed to press the escape button to cut short the plotting of all 400 friends of mine.
> # friendship relation matrix
> N <- length(friends.id)
> friendship.matrix <- matrix(0,N,N)
> for (i in 1:N) {
+ tmp <- facebook( path=paste(“me/mutualfriends”, friends.id[i], sep=”/”) , access_token=access_token)
+ mutualfriends <- sapply(tmp$data, function(x) x$id)
+ friendship.matrix[i,friends.id %in% mutualfriends] <- 1
+ }


Plotting using Network package in R (with help from the  comments at http://applyr.blogspot.in/2012/01/mining-facebook-data-most-liked-status.html)

> require(network)

>net1<- as.network(friendship.matrix)

> plot(net1, label=friends.initial, arrowhead.cex=0)

(Rgraphviz is tough if you are on Windows 7 like me)

but there is an alternative igraph solution at https://github.com/sciruela/facebookFriends/blob/master/facebook.r


After all that-..talk.. a graph..of my Facebook Network with friends initials as labels..


Opinion piece-

I hope plans to make the Facebook R package get fulfilled (just as the twitteR  package led to many interesting analysis)

and also Linkedin has an API at http://developer.linkedin.com/apis

I think it would be interesting to plot professional relationships across social networks as well. But I hope to see a LinkedIn package (or blog code) soon.

As for jjplot, I had hoped ggplot and jjplot merged or atleast had some kind of inclusion in the Deducer GUI. Maybe a Google Summer of Code project if people are busy!!

Also the geeks at Facebook.com can think of giving something back to the R community, as Google generously does with funding packages like RUnit, Deducer and Summer of Code, besides sponsoring meet ups etc.


(note – this is part of the research for the upcoming book ” R for Business Analytics”)



but didnt get time to download all my posts using R code at


or do specific Facebook Page analysis using R at



 #access token from https://developers.facebook.com/tools/explorer
# download the file needed for authentication http://www.brocktibert.com/blog/2012/01/19/358/
download.file(url="http://curl.haxx.se/ca/cacert.pem", destfile="cacert.pem")
# http://romainfrancois.blog.free.fr/index.php?post/2012/01/15/Crawling-facebook-with-R
facebook <- function( path = "me", access_token = token, options){
if( !missing(options) ){
options <- sprintf( "?%s", paste( names(options), "=", unlist(options), collapse = "&", sep = "" ) )
} else {
options <- ""
data <- getURL( sprintf( "https://graph.facebook.com/%s%s&access_token=%s", path, options, access_token ), cainfo="cacert.pem" )
fromJSON( data )

 # see http://applyr.blogspot.in/2012/01/mining-facebook-data-most-liked-status.html

# scrape the list of friends
friends <- facebook( path="me/friends" , access_token=access_token)
# extract Facebook IDs
friends.id <- sapply(friends$data, function(x) x$id)
# extract names 
friends.name <- sapply(friends$data, function(x)  iconv(x$name,"UTF-8","ASCII//TRANSLIT"))
# short names to initials 
initials <- function(x) paste(substr(x,1,1), collapse="")
friends.initial <- sapply(strsplit(friends.name," "), initials)

# friendship relation matrix
#N <- length(friends.id)
N <- 200
friendship.matrix <- matrix(0,N,N)
for (i in 1:N) {
  tmp <- facebook( path=paste("me/mutualfriends", friends.id[i], sep="/") , access_token=access_token)
  mutualfriends <- sapply(tmp$data, function(x) x$id)
  friendship.matrix[i,friends.id %in% mutualfriends] <- 1
net1<- as.network(friendship.matrix)
plot(net1, label=friends.initial, arrowhead.cex=0)

Created by Pretty R at inside-R.org

JMP and R – #rstats

An amazing example of R being used sucessfully in combination (and not is isolation) with other enterprise software is the add-ins functionality of JMP and it’s R integration.

See the following JMP add-ins which use R


JMP Add-in: Multidimensional Scaling using R

This add-in creates a new menu command under the Add-Ins Menu in the submenu R Add-ins. The script will launch a custom dialog (or prompt for a JMP data table is one is not already open) where you can cast columns into roles for performing MDS on the data table. The analysis results in a data table of MDS dimensions and associated output graphics. MDS is a dimension reduction method that produces coordinates in Euclidean space (usually 2D, 3D) that best represent the structure of a full distance/dissimilarity matrix. MDS requires that input be a symmetric dissimilarity matrix. Input to this application can be data that is already in the form of a symmetric dissimilarity matrix or the dissimilarity matrix can be computed based on the input data (where dissimilarity measures are calculated between rows of the input data table in R).

Submitted by: Kelci Miclaus SAS employee Initiative: All
Application: Add-Ins Analysis: Exploratory Data Analysis

Chernoff Faces Add-in

One way to plot multivariate data is to use Chernoff faces. For each observation in your data table, a face is drawn such that each variable in your data set is represented by a feature in the face. This add-in uses JMP’s R integration functionality to create Chernoff faces. An R install and the TeachingDemos R package are required to use this add-in.

Submitted by: Clay Barker SAS employee Initiative: All
Application: Add-Ins Analysis: Data Visualization

Support Vector Machine for Classification

By simply opening a data table, specifying X, Y variables, selecting a kernel function, and specifying its parameters on the user-friendly dialog, you can build a classification model using Support Vector Machine. Please note that R package ‘e1071’ should be installed before running this dialog. The package can be found from http://cran.r-project.org/web/packages/e1071/index.html.

Submitted by: Jong-Seok Lee SAS employee Initiative: All
Application: Add-Ins Analysis: Exploratory Data Analysis/Mining

Penalized Regression Add-in

This add-in uses JMP’s R integration functionality to provide access to several penalized regression methods. Methods included are the LASSO (least absolutee shrinkage and selection operator, LARS (least angle regression), Forward Stagewise, and the Elastic Net. An R install and the “lars” and “elasticnet” R packages are required to use this add-in.

Submitted by: Clay Barker SAS employee Initiative: All
Application: Add-Ins Analysis: Regression

MP Addin: Univariate Nonparametric Bootstrapping

This script performs simple univariate, nonparametric bootstrap sampling by using the JMP to R Project integration. A JMP Dialog is built by the script where the variable you wish to perform bootstrapping over can be specified. A statistic to compute for each bootstrap sample is chosen and the data are sent to R using new JSL functionality available in JMP 9. The boot package in R is used to call the boot() function and the boot.ci() function to calculate the sample statistic for each bootstrap sample and the basic bootstrap confidence interval. The results are brought back to JMP and displayed using the JMP Distribution platform.

Submitted by: Kelci Miclaus SAS employee Initiative: All
Application: Add-Ins Analysis: Basic Statistics


GNU General Public License
Image via Wikipedia


GrapheR is a Graphical User Interface created for simple graphs.

Depends: R (>= 2.10.0), tcltk, mgcv
Description: GrapheR is a multiplatform user interface for drawing highly customizable graphs in R. It aims to be a valuable help to quickly draw publishable graphs without any knowledge of R commands. Six kinds of graphs are available: histogram, box-and-whisker plot, bar plot, pie chart, curve and scatter plot.
License: GPL-2
LazyLoad: yes
Packaged: 2011-01-24 17:47:17 UTC; Maxime
Repository: CRAN
Date/Publication: 2011-01-24 18:41:47

More information about GrapheR at CRAN
Path: /cran/newpermanent link

Advantages of using GrapheR

  • It is bi-lingual (English and French) and can import in text and csv files
  • The intention is for even non users of R, to make the simple types of Graphs.
  • The user interface is quite cleanly designed. It is thus aimed as a data visualization GUI, but for a more basic level than Deducer.
  • Easy to rename axis ,graph titles as well use sliders for changing line thickness and color

Disadvantages of using GrapheR

  • Lack of documentation or help. Especially tips on mouseover of some options should be done.
  • Some of the terms like absicca or ordinate axis may not be easily understood by a business user.
  • Default values of color are quite plain (black font on white background).
  • Can flood terminal with lots of repetitive warnings (although use of warnings() function limits it to top 50)
  • Some of axis names can be auto suggested based on which variable s being chosen for that axis.
  • Package name GrapheR refers to a graphical calculator in Mac OS – this can hinder search engine results

Using GrapheR

  • Data Input -Data Input can be customized for CSV and Text files.
  • GrapheR gives information on loaded variables (numeric versus Factors)
  • It asks you to choose the type of Graph 
  • It then asks for usual Graph Inputs (see below). Note colors can be customized (partial window). Also number of graphs per Window can be easily customized 
  • Graph is ready for publication

R for Predictive Modeling:Workshop

A view of the Oakland-San Francisco Bay Bridge...
Image via Wikipedia

A workshop on using R for Predictive Modeling, by the Director, Non Clinical Stats, Pfizer. Interesting Bay Area Event- part of next edition of Predictive Analytics World

Sunday, March 13, 2011 in San Francisco

R for Predictive Modeling:
A Hands-On Introduction

Intended Audience: Practitioners who wish to learn how to execute on predictive analytics by way of the R language; anyone who wants “to turn ideas into software, quickly and faithfully.”

Knowledge Level: Either hands-on experience with predictive modeling (without R) or hands-on familiarity with any programming language (other than R) is sufficient background and preparation to participate in this workshop.

Workshop Description

This one-day session provides a hands-on introduction to R, the well-known open-source platform for data analysis. Real examples are employed in order to methodically expose attendees to best practices driving R and its rich set of predictive modeling packages, providing hands-on experience and know-how. R is compared to other data analysis platforms, and common pitfalls in using R are addressed.

The instructor, a leading R developer and the creator of CARET, a core R package that streamlines the process for creating predictive models, will guide attendees on hands-on execution with R, covering:

  • A working knowledge of the R system
  • The strengths and limitations of the R language
  • Preparing data with R, including splitting, resampling and variable creation
  • Developing predictive models with R, including decision trees, support vector machines and ensemble methods
  • Visualization: Exploratory Data Analysis (EDA), and tools that persuade
  • Evaluating predictive models, including viewing lift curves, variable importance and avoiding overfitting

Hardware: Bring Your Own Laptop
Each workshop participant is required to bring their own laptop running Windows or OS X. The software used during this training program, R, is free and readily available for download.

Attendees receive an electronic copy of the course materials and related R code at the conclusion of the workshop.


  • Workshop starts at 9:00am
  • Morning Coffee Break at 10:30am – 11:00am
  • Lunch provided at 12:30 – 1:15pm
  • Afternoon Coffee Break at 2:30pm – 3:00pm
  • End of the Workshop: 4:30pm


Max Kuhn, Director, Nonclinical Statistics, Pfizer

Max Kuhn is a Director of Nonclinical Statistics at Pfizer Global R&D in Connecticut. He has been apply models in the pharmaceutical industries for over 15 years.

He is a leading R developer and the author of several R packages including the CARET package that provides a simple and consistent interface to over 100 predictive models available in R.

Mr. Kuhn has taught courses on modeling within Pfizer and externally, including a class for the India Ministry of Information Technology.




Multi State Models

Arc de Triomphe

A special issue of the Journal of Statistical Software has come out devoted to Multi State Models and Competing Risks. It is a must read for anyone with interest in Pharma Analytics or Survival Analysis- even if you dont know much R

Here is an extract from “mstate: An R Package for the Analysis ofCompeting Risks and Multi-State Models”

Multi-state models are a very useful tool to answer a wide range of questions in sur-vival analysis that cannot, or only in a more complicated way, be answered by classicalmodels. They are suitable for both biomedical and other applications in which time-to-event variables are analyzed. However, they are still not frequently applied. So far, animportant reason for this has been the lack of available software. To overcome this prob-lem, we have developed the mstate package in R for the analysis of multi-state models.The package covers all steps of the analysis of multi-state models, from model buildingand data preparation to estimation and graphical representation of the results. It canbe applied to non- and semi-parametric (Cox) models. The package is also suitable forcompeting risks models, as they are a special category of multi-state models.




Issues for JSS Special Volume 38: Competing Risks and Multi-State Models

Special Issue about Competing Risks and Multi-State Models

Hein Putter
Vol. 38, Issue 1, Jan 2011
Submitted 2011-01-03, Accepted 2011-01-03

Analyzing Competing Risk Data Using the R timereg Package

Thomas H. Scheike, Mei-Jie Zhang
Vol. 38, Issue 2, Jan 2011
Submitted 2009-05-25, Accepted 2010-06-22

p3state.msm: Analyzing Survival Data from an Illness-Death Model

Luís Filipe Meira Machado, Javier Roca-Pardiñas
Vol. 38, Issue 3, Jan 2011
Submitted 2009-06-30, Accepted 2010-03-02

Empirical Transition Matrix of Multi-State Models: The etm Package

Arthur Allignol, Martin Schumacher, Jan Beyersmann
Vol. 38, Issue 4, Jan 2011
Submitted 2009-01-08, Accepted 2010-03-11

Lexis: An R Class for Epidemiological Studies with Long-Term Follow-Up

Martyn Plummer, Bendix Carstensen
Vol. 38, Issue 5, Jan 2011
Submitted 2010-02-09, Accepted 2010-09-16

Using Lexis Objects for Multi-State Models in R

Bendix Carstensen, Martyn Plummer
Vol. 38, Issue 6, Jan 2011
Submitted 2010-02-09, Accepted 2010-09-16

mstate: An R Package for the Analysis of Competing Risks and Multi-State Models

Liesbeth C. de Wreede, Marta Fiocco, Hein Putter
Vol. 38, Issue 7, Jan 2011
Submitted 2010-01-17, Accepted 2010-08-20

Multi-State Models for Panel Data: The msm Package for R

Christopher Jackson
Vol. 38, Issue 8, Jan 2011
Submitted 2009-07-21, Accepted 2010-08-18

JSS-Announce mailing list


Trying out Google Prediction API from R

Ubuntu Login
Image via Wikipedia

So I saw the news at NY R Meetup and decided to have a go at Prediction API Package (which first started off as a blog post at


1)My OS was Ubuntu 10.10 Netbook

Ubuntu has a slight glitch plus workaround for installing the RCurl package on which the Google Prediction API is dependent- you need to first install this Ubuntu package for RCurl to install libcurl4-gnutls-dev

Once you install that using Synaptic,

Simply start R

2) Install Packages rjson and Rcurl using install.packages and choosing CRAN

Since GooglePredictionAPI is not yet on CRAN


3) Download that package from


You need to copy this downloaded package to your “first library ” folder

When you start R, simply run


and thats the folder you copy the GooglePredictionAPI package  you downloaded.

5) Now the following line works

  1. Under R prompt,
  2. > install.packages("googlepredictionapi_0.1.tar.gz", repos=NULL, type="source")

6) Uploading data to Google Storage using the GUI (rather than gs util)

Just go to https://sandbox.google.com/storage/

and thats the Google Storage manager

Notes on Training Data-

Use a csv file

The first column is the score column (like 1,0 or prediction score)

There are no headers- so delete headers from data file and move the dependent variable to the first column  (Note I used data from the kaggle contest for R package recommendation at

http://kaggle.com/R?viewtype=data )

6) The good stuff:

Once you type in the basic syntax, the first time it will ask for your Google Credentials (email and password)

It then starts showing you time elapsed for training.

Now you can disconnect and go off (actually I got disconnected by accident before coming back in a say 5 minutes so this is the part where I think this is what happened is why it happened, dont blame me, test it for yourself) –

and when you come back (hopefully before token expires)  you can see status of your request (see below)

> library(rjson)
> library(RCurl)
Loading required package: bitops
> library(googlepredictionapi)
> my.model <- PredictionApiTrain(data="gs://numtraindata/training_data")
The request for training has sent, now trying to check if training is completed
Training on numtraindata/training_data: time:2.09 seconds
Training on numtraindata/training_data: time:7.00 seconds


Note I changed the format from the URL where my data is located- simply go to your Google Storage Manager and right click on the file name for link address  ( https://sandbox.google.com/storage/numtraindata/training_data.csv)

to gs://numtraindata/training_data  (that kind of helps in any syntax error)

8) From the kind of high level instructions at  https://code.google.com/p/google-prediction-api-r-client/, you could also try this on a local file


## Load googlepredictionapi and dependent libraries

## Make a training call to the Prediction API against data in the Google Storage.
## Replace MYBUCKET and MYDATA with your data.
my.model <- PredictionApiTrain(data="gs://MYBUCKET/MYDATA")

## Alternatively, make a training call against training data stored locally as a CSV file.
## Replace MYPATH and MYFILE with your data.
my.model <- PredictionApiTrain(data="MYPATH/MYFILE.csv")

At the time of writing my data was still getting trained, so I will keep you posted on what happens.

Nice BI Tutorials

Tutorials screenshot.
Image via Wikipedia

Here is a set of very nice, screenshot enabled tutorials from SAP BI. They are a bit outdated (3 years old) but most of it is quite relevant- especially from a Tutorial Design Perspective –

Most people would rather see screenshot based step by step powerpoints, than cluttered or clever presentations , or even videos that force you to sit like a TV zombie. Unfortunately most tutorial presentations I see especially for BI are either slides with one or two points, that abruptly shift to “concepts” or videos that are atleast more than 10 minutes long. That works fine for scripting tutorials or hands on workshops, but cannot be reproduced for later instances of study.

The mode of tutorials especially for GUI software can vary, it may be Slideshare, Scribd, Google Presentation,Microsoft Powerpoint but a step by step screenshot by screenshot tutorial is much better for understanding than commando line jargon/ Youtub   Videos presentations, or Powerpoint with Points.

Have a look at these SAP BI 7 slideshares


Speaking of BI, the R Package called Brew is going to brew up something special especially combined with R Apache. However I wish R Apache, or R Web, or RServe had step by step install screenshot tutorials to increase their usage in Business Intelligence.

I tried searching for JMP GUI Tutorials too, but I believe putting all your content behind a registration wall is not so great. Do a Pareto Analysis of your training material, surely you can share a couple more tutorials without registration. It also will help new wanna-migrate users to get a test and feel for the installation complexities as well as final report GUI.