Using Rapid Miner and R for Sports Analytics #rstats

Rapid Miner has been one of the oldest open source analytics software, long long before open source or even analytics was considered a fashion buzzword. The Rapid Miner software has been a pioneer in many areas (like establishing a marketplace for Rapid Miner Extensions) and the Rapid Miner -R extension was one of the most promising enablers of using R in an enterprise setting.
The following interview was taken with a manager of analytics for a sports organization. The sports organization considers analytics as a strategic differentiator , hence the name is confidential. No part of the interview has been edited or manipulated.

Ajay- Why did you choose Rapid Miner and R? What were the other software alternatives you considered and discarded?

Analyst- We considered most of the other major players in statistics/data mining or enterprise BI.  However, we found that the value proposition for an open source solution was too compelling to justify the premium pricing that the commercial solutions would have required.  The widespread adoption of R and the variety of packages and algorithms available for it, made it an easy choice.  We liked RapidMiner as a way to design structured, repeatable processes, and the ability to optimize learner parameters in a systematic way.  It also handled large data sets better than R on 32-bit Windows did.  The GUI, particularly when 5.0 was released, made it more usable than R for analysts who weren’t experienced programmers.

Ajay- What analytics do you do think Rapid Miner and R are best suited for?

 Analyst- We use RM+R mainly for sports analysis so far, rather than for more traditional business applications.  It has been quite suitable for that, and I can easily see how it would be used for other types of applications.

 Ajay- Any experiences as an enterprise customer? How was the installation process? How good is the enterprise level support?

Analyst- Rapid-I has been one of the most responsive tech companies I’ve dealt with, either in my current role or with previous employers.  They are small enough to be able to respond quickly to requests, and in more than one case, have fixed a problem, or added a small feature we needed within a matter of days.  In other cases, we have contracted with them to add larger pieces of specific functionality we needed at reasonable consulting rates.  Those features are added to the mainline product, and become fully supported through regular channels.  The longer consulting projects have typically had a turnaround of just a few weeks.

 Ajay- What challenges if any did you face in executing a pure open source analytics bundle ?

Analyst- As Rapid-I is a smaller company based in Europe, the availability of training and consulting in the USA isn’t as extensive as for the major enterprise software players, and the time zone differences sometimes slow down the communications cycle.  There were times where we were the first customer to attempt a specific integration point in our technical environment, and with no prior experiences to fall back on, we had to work with Rapid-I to figure out how to do it.  Compared to the what traditional software vendors provide, both R and RM tend to have sparse, terse, occasionally incomplete documentation.  The situation is getting better, but still lags behind what the traditional enterprise software vendors provide.

 Ajay- What are the things you can do in R ,and what are the things you prefer to do in Rapid Miner (comparison for technical synergies)

Analyst- Our experience has been that RM is superior to R at writing and maintaining structured processes, better at handling larger amounts of data, and more flexible at fine-tuning model parameters automatically.  The biggest limitation we’ve had with RM compared to R is that R has a larger library of user-contributed packages for additional data mining algorithms.  Sometimes we opted to use R because RM hadn’t yet implemented a specific algorithm.  The introduction the R extension has allowed us to combine the strengths of both tools in a very logical and productive way.

In particular, extending RapidMiner with R helped address RM’s weakness in the breadth of algorithms, because it brings the entire R ecosystem into RM (similar to how Rapid-I implemented much of the Weka library early on in RM’s development).  Further, because the R user community releases packages that implement new techniques faster than the enterprise vendors can, this helps turn a potential weakness into a potential strength.  However, R packages tend to be of varying quality, and are more prone to go stale due to lack of support/bug fixes.  This depends heavily on the package’s maintainer and its prevalence of use in the R community.  So when RapidMiner has a learner with a native implementation, it’s usually better to use it than the R equivalent.

2011 Analytics Recap

Events in the field of data that impacted us in 2011

1) Oracle unveiled plans for R Enterprise. This is one of the strongest statements of its focus on in-database analytics. Oracle also unveiled plans for a Public Cloud

2) SAS Institute released version 9.3 , a major analytics software in industry use.

3) IBM acquired many companies in analytics and high tech. Again.However the expected benefits from Cognos-SPSS integration are yet to show a spectacular change in market share.

2011 Selected acquisitions

Emptoris Inc. December 2011

Cúram Software Ltd. December 2011

DemandTec December 2011

Platform Computing October 2011

 Q1 Labs October 2011

Algorithmics September 2011

 i2 August 2011

Tririga March 2011

 

4) SAP promised a lot with SAP HANA- again no major oohs and ahs in terms of market share fluctuations within analytics.

http://www.sap.com/india/news-reader/index.epx?articleID=17619

5) Amazon continued to lower prices of cloud computing and offer more options.

http://aws.amazon.com/about-aws/whats-new/2011/12/21/amazon-elastic-mapreduce-announces-support-for-cc2-8xlarge-instances/

6) Google continues to dilly -dally with its analytics and cloud based APIs. I do not expect all the APIs in the Google APIs suit to survive and be viable in the enterprise software space.  This includes Google Cloud Storage, Cloud SQL, Prediction API at https://code.google.com/apis/console/b/0/ Some of the location based , translation based APIs may have interesting spin offs that may be very very commercially lucrative.

7) Microsoft -did- hmm- I forgot. Except for its investment in Revolution Analytics round 1 many seasons ago- very little excitement has come from MS plans in data mining- The plugins for cloud based data mining from Excel remain promising yet , while Azure remains a stealth mode starter.

8) Revolution Analytics promised us a GUI and didnt deliver (till yet 🙂 ) . But it did reveal a much better Enterprise software Revolution R 5.0 is one of the strongest enterprise software in the R /Stat Computing space and R’s memory handling problem is now an issue of perception than actual stuff thanks to newer advances in how it is used.

9) More conferences, more books and more news on analytics startups in 2011. Big Data analytics remained a strong buzzword. Expect more from this space including creative uses of Hadoop based infrastructure.

10) Data privacy issues continue to hamper and impede effective analytics usage. So does rational and balanced regulation in some of the most advanced economies. We expect more regulation and better guidelines in 2012.

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

http://support.sas.com/demosdownloads/downarea_t4.jsp?productID=110454&jmpflag=Y

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

Interview Zach Goldberg, Google Prediction API

Here is an interview with Zach Goldberg, who is the product manager of Google Prediction API, the next generation machine learning analytics-as-an-api service state of the art cloud computing model building browser app.
Ajay- Describe your journey in science and technology from high school to your current job at Google.

Zach- First, thanks so much for the opportunity to do this interview Ajay!  My personal journey started in college where I worked at a startup named Invite Media.   From there I transferred to the Associate Product Manager (APM) program at Google.  The APM program is a two year rotational program.  I did my first year working in display advertising.  After that I rotated to work on the Prediction API.

Ajay- How does the Google Prediction API help an average business analytics customer who is already using enterprise software , servers to generate his business forecasts. How does Google Prediction API fit in or complement other APIs in the Google API suite.

Zach- The Google Prediction API is a cloud based machine learning API.  We offer the ability for anybody to sign up and within a few minutes have their data uploaded to the cloud, a model built and an API to make predictions from anywhere. Traditionally the task of implementing predictive analytics inside an application required a fair amount of domain knowledge; you had to know a fair bit about machine learning to make it work.  With the Google Prediction API you only need to know how to use an online REST API to get started.

You can learn more about how we help businesses by watching our video and going to our project website.

Ajay-  What are the additional use cases of Google Prediction API that you think traditional enterprise software in business analytics ignore, or are not so strong on.  What use cases would you suggest NOT using Google Prediction API for an enterprise.

Zach- We are living in a world that is changing rapidly thanks to technology.  Storing, accessing, and managing information is much easier and more affordable than it was even a few years ago.  That creates exciting opportunities for companies, and we hope the Prediction API will help them derive value from their data.

The Prediction API focuses on providing predictive solutions to two types of problems: regression and classification. Businesses facing problems where there is sufficient data to describe an underlying pattern in either of these two areas can expect to derive value from using the Prediction API.

Ajay- What are your separate incentives to teach about Google APIs  to academic or researchers in universities globally.

Zach- I’d refer you to our university relations page

Google thrives on academic curiosity. While we do significant in-house research and engineering, we also maintain strong relations with leading academic institutions world-wide pursuing research in areas of common interest. As part of our mission to build the most advanced and usable methods for information access, we support university research, technological innovation and the teaching and learning experience through a variety of programs.

Ajay- What is the biggest challenge you face while communicating about Google Prediction API to traditional users of enterprise software.

Zach- Businesses often expect that implementing predictive analytics is going to be very expensive and require a lot of resources.  Many have already begun investing heavily in this area.  Quite often we’re faced with surprise, and even skepticism, when they see the simplicity of the Google Prediction API.  We work really hard to provide a very powerful solution and take care of the complexity of building high quality models behind the scenes so businesses can focus more on building their business and less on machine learning.

 

 

Product Review – Revolution R 5.0

So I got the email from Revolution R. Version 5.0 is ready for download, and unlike half hearted attempts by many software companies they make it easy for the academics and researchers to get their free copy. Free as in speech and free as in beer.

Some thoughts-

1) R ‘s memory problem is now an issue of marketing and branding. Revolution Analytics has definitely bridged this gap technically  beautifully and I quote from their documentation-

The primary advantage 64-bit architectures bring to R is an increase in the amount of memory available to a given R process.
The first benefit of that increase is an increase in the size of data objects you can create. For example, on most 32-bit versions of R, the largest data object you can create is roughly 3GB; attempts to create 4GB objects result in errors with the message “cannot allocate vector of length xxxx.”
On 64-bit versions of R, you can generally create larger data objects, up to R’s current hard limit of 231 􀀀 1 elements in a vector (about 2 billion elements). The functions memory.size and memory.limit help you manage the memory used byWindows versions of R.
In 64-bit Revolution R Enterprise, R sets the memory limit by default to the amount of physical RAM minus half a gigabyte, so that, for example, on a machine with 8GB of RAM, the default memory limit is 7.5GB:

2) The User Interface is best shown as below or at  https://docs.google.com/presentation/pub?id=1V_G7r0aBR3I5SktSOenhnhuqkHThne6fMxly_-4i8Ag&start=false&loop=false&delayms=3000

-(but I am still hoping for the GUI ,Revolution Analytics promised us for Christmas)

3) The partnership with Microsoft HPC is quite awesome given Microsoft’s track record in enterprise software penetration

but I am also interested in knowing more about the Oracle version of R and what it will do there.

Some future additions to Google Docs

1) More Presentation Templates

2) More HTML 5 clipart

3) Online Latex (lyx) GUI  (or a Chrome Extension)

4) Online Speech to Text dictation  (or a Chrome Extension)

5) Online Screen Capture software for audio and video editing  (or a Chrome Extension)

6) Some sharing of usage and statistics with world tech community

7) An on -site in house version for enterprise software customers (|?)

8) An easy to make HTML5 editor using just the browser

Seriously http://googledocs.blogspot.com/ needs to be challenged more.

Interview Mike Boyarski Jaspersoft

Here is an interview with Mike Boyarski , Director Product Marketing at Jaspersoft

.

 

the largest BI community with over 14 million downloads, nearly 230,000 registered members, representing over 175,000 production deployments, 14,000 customers, across 100 countries.

Ajay- Describe your career in science from Biology to marketing great software.
Mike- I studied Biology with the assumption I’d pursue a career in medicine. It took about 2 weeks during an internship at a Los Angeles hospital to determine I should do something else.  I enjoyed learning about life science, but the whole health care environment was not for me.  I was initially introduced to enterprise-level software while at Applied Materials within their Microcontamination group.  I was able to assist with an internal application used to collect contamination data.  I later joined Oracle to work on an Oracle Forms application used to automate the production of software kits (back when documentation and CDs had to be physically shipped to recognize revenue). This gave me hands on experience with Oracle 7, web application servers, and the software development process.
I then transitioned to product management for various products including application servers, software appliances, and Oracle’s first generation SaaS based software infrastructure. In 2006, with the Siebel and PeopleSoft acquisitions underway, I moved on to Ingres to help re-invigorate their solid yet antiquated technology. This introduced me to commercial open source software and the broader Business Intelligence market.  From Ingres I joined Jaspersoft, one of the first and most popular open source Business Intelligence vendors, serving as head of product marketing since mid 2009.
Ajay- Describe some of the new features in Jaspersoft 4.1 that help differentiate it from the rest of the crowd. What are the exciting product features we can expect from Jaspersoft down the next couple of years.
Mike- Jaspersoft 4.1 was an exciting release for our customers because we were able to extend the latest UI advancements in our ad hoc report designer to the data analysis environment. Now customers can use a unified intuitive web-based interface to perform several powerful and interactive analytic functions across any data source, whether its relational, non-relational, or a Big Data source.
 The reality is that most (roughly 70%) of todays BI adoption is in the form of reports and dashboards. These tools are used to drive and measure an organizations business, however, data analysis presents the most strategic opportunity for companies because it can identify new opportunities, efficiencies, and competitive differentiation.  As more data comes online, the difference between those companies that are successful and those that are not will likely be attributed to their ability to harness data analysis techniques to drive and improve business performance. Thus, with Jaspersoft 4.1, and our improved ad hoc reporting and analysis UI we can effectively address a broader set of BI requirements for organizations of all sizes.
Ajay-  What do you think is a good metric to measure influence of an open source software product – is it revenue or is it number of downloads or number of users. How does Jaspersoft do by these counts.
Mike- History has shown that open source software is successful as a “bottoms up” disrupter within IT or the developer market.  Today, many new software projects and startup ventures are birthed on open source software, often initiated with little to no budget. As the organization achieves success with a particular project, the next initiative tends to be larger and more strategic, often displacing what was historically solved with a proprietary solution. These larger deployments strengthen the technology over time.
Thus, the more proven and battle tested an open source solution is, often measured via downloads, deployments, community size, and community activity, usually equates to its long term success. Linux, Tomcat, and MySQL have plenty of statistics to model this lifecycle. This model is no different for open source BI.
The success to date of Jaspersoft is directly tied to its solid proven technology and the vibrancy of the community.  We proudly and openly claim to have the largest BI community with over 14 million downloads, nearly 230,000 registered members, representing over 175,000 production deployments, 14,000 customers, across 100 countries.  Every day, 30,000 developers are using Jaspersoft to build BI applications.  Behind Excel, its hard to imagine a more widely used BI tool in the market.  Jaspersoft could not reach these kind of numbers with crippled or poorly architected software.
Ajay- What are your plans for leveraging cloud computing, mobile and tablet platforms and for making Jaspersoft more easy and global  to use.