Interview John Myles White , Machine Learning for Hackers

Here is an interview with one of the younger researchers  and rock stars of the R Project, John Myles White,  co-author of Machine Learning for Hackers.

Ajay- What inspired you guys to write Machine Learning for Hackers. What has been the public response to the book. Are you planning to write a second edition or a next book?

John-We decided to write Machine Learning for Hackers because there were so many people interested in learning more about Machine Learning who found the standard textbooks a little difficult to understand, either because they lacked the mathematical background expected of readers or because it wasn’t clear how to translate the mathematical definitions in those books into usable programs. Most Machine Learning books are written for audiences who will not only be using Machine Learning techniques in their applied work, but also actively inventing new Machine Learning algorithms. The amount of information needed to do both can be daunting, because, as one friend pointed out, it’s similar to insisting that everyone learn how to build a compiler before they can start to program. For most people, it’s better to let them try out programming and get a taste for it before you teach them about the nuts and bolts of compiler design. If they like programming, they can delve into the details later.

We once said that Machine Learning for Hackers  is supposed to be a chemistry set for Machine Learning and I still think that’s the right description: it’s meant to get readers excited about Machine Learning and hopefully expose them to enough ideas and tools that they can start to explore on their own more effectively. It’s like a warmup for standard academic books like Bishop’s.
The public response to the book has been phenomenal. It’s been amazing to see how many people have bought the book and how many people have told us they found it helpful. Even friends with substantial expertise in statistics have said they’ve found a few nuggets of new information in the book, especially regarding text analysis and social network analysis — topics that Drew and I spend a lot of time thinking about, but are not thoroughly covered in standard statistics and Machine Learning  undergraduate curricula.
I hope we write a second edition. It was our first book and we learned a ton about how to write at length from the experience. I’m about to announce later this week that I’m writing a second book, which will be a very short eBook for O’Reilly. Stay tuned for details.

Ajay-  What are the key things that a potential reader can learn from this book?

John- We cover most of the nuts and bolts of introductory statistics in our book: summary statistics, regression and classification using linear and logistic regression, PCA and k-Nearest Neighbors. We also cover topics that are less well known, but are as important: density plots vs. histograms, regularization, cross-validation, MDS, social network analysis and SVM’s. I hope a reader walks away from the book having a feel for what different basic algorithms do and why they work for some problems and not others. I also hope we do just a little to shift a future generation of modeling culture towards regularization and cross-validation.

Ajay- Describe your journey as a science student up till your Phd. What are you current research interests and what initiatives have you done with them?

John-As an undergraduate I studied math and neuroscience. I then took some time off and came back to do a Ph.D. in psychology, focusing on mathematical modeling of both the brain and behavior. There’s a rich tradition of machine learning and statistics in psychology, so I got increasingly interested in ML methods during my years as a grad student. I’m about to finish my Ph.D. this year. My research interests all fall under one heading: decision theory. I want to understand both how people make decisions (which is what psychology teaches us) and how they should make decisions (which is what statistics and ML teach us). My thesis is focused on how people make decisions when there are both short-term and long-term consequences to be considered. For non-psychologists, the classic example is probably the explore-exploit dilemma. I’ve been working to import more of the main ideas from stats and ML into psychology for modeling how real people handle that trade-off. For psychologists, the classic example is the Marshmallow experiment. Most of my research work has focused on the latter: what makes us patient and how can we measure patience?

Ajay- How can academia and private sector solve the shortage of trained data scientists (assuming there is one)?

John- There’s definitely a shortage of trained data scientists: most companies are finding it difficult to hire someone with the real chops needed to do useful work with Big Data. The skill set required to be useful at a company like Facebook or Twitter is much more advanced than many people realize, so I think it will be some time until there are undergraduates coming out with the right stuff. But there’s huge demand, so I’m sure the market will clear sooner or later.

The changes that are required in academia to prepare students for this kind of work are pretty numerous, but the most obvious required change is that quantitative people need to be learning how to program properly, which is rare in academia, even in many CS departments. Writing one-off programs that no one will ever have to reuse and that only work on toy data sets doesn’t prepare you for working with huge amounts of messy data that exhibit shifting patterns. If you need to learn how to program seriously before you can do useful work, you’re not very valuable to companies who need employees that can hit the ground running. The companies that have done best in building up data teams, like LinkedIn, have learned to train people as they come in since the proper training isn’t typically available outside those companies.
Of course, on the flipside, the people who do know how to program well need to start learning more about theory and need to start to have a better grasp of basic mathematical models like linear and logistic regressions. Lots of CS students seem not to enjoy their theory classes, but theory really does prepare you for thinking about what you can learn from data. You may not use automata theory if you work at Foursquare, but you will need to be able to reason carefully and analytically. Doing math is just like lifting weights: if you’re not good at it right now, you just need to dig in and get yourself in shape.
John Myles White is a Phd Student in  Ph.D. student in the Princeton Psychology Department, where he studies human decision-making both theoretically and experimentally. Along with the political scientist Drew Conway, he is  the author of a book published by O’Reilly Media entitled “Machine Learning for Hackers”, which is meant to introduce experienced programmers to the machine learning toolkit. He is also working with Mark Hansenon a book for laypeople about exploratory data analysis.John is the lead maintainer for several R packages, including ProjectTemplate and log4r.

(TIL he has played in several rock bands!)

You can read more in his own words at his blog at
He can be contacted via social media at Google Plus at or twitter at

Who made Who in #Rstats

While Bob M, my old mentor and fellow TN man maintains the website how popular R is across various forums, I am interested in who within R community of 3 million (give or take a few) is contributing more. I am very sure by 2014, we can have a new fork of R called Hadley R, in which all packages would be made by Hadley Wickham and you wont need anything else.

But jokes apart, since I didnt have the time to

1) scrape CRAN for all package authors

2) scrape for lines of code across all packages

3) allocate lines of code (itself a dubious software productivity metric) to various authors of R packages-


1) scraping the entire and 2011’s R help list

2) determine who is the most frequent r question and answer user (ala SAS-L’s annual MVP and rookie of the year awards)

I did the following to atleast who is talking about R across easily scrapable Q and A websites

Stack Overflow still rules over all. shows the statistics on who made whom in R on Stack Overflow

All in all, initial ardour seems to have slowed for #Rstats on Stack Overflow ? or is it just summer?

No the answer- credit to Rob J Hyndman is most(?) activity is shifting to Stats Exchange

You could also paste this in Notepad and some graphs on Average Score / Answer or even make a social network graph if you had the time.

Do NOT (Go/Bi) search for Stack Overflow API or web scraping stack overflow- it gives you all the answers on the website but 0 answers on how to scrape these websites.

I have added a new website called Meta Optimize to this list based on Tal G’s interview of Joseph Turian,  at

There are only 17 questions tagged R but it seems a lot of views is being generated.

I also decided to add views from Quora since it is Q and A site (and one which I really like)

Again very few questions but lot many followers

FaceBook IPO- Who hacked whom?

Some thoughts on the FB IPO-

1) Is Zuck reading emails on his honeymoon? Where is he?

2) In 3 days FB lost 34 billion USD in market valuation. Thats enough to buy AOL,Yahoo, LinkedIn and Twitter (combined)

3) People are now shorting FB based on 3-4 days of trading performance. Maybe they know more ARIMA !

4) Who made money on the over-pricing in terms on employees who sold on 1 st day, financial bankers who did the same?

5) Who lost money on the first three days due to Nasdaq’s problems?

6) What is the exact technical problem that Nasdaq had?

7) The much deplored FaceBook Price/Earnings ratio (99) is still comparable to AOL’s (85) and much less than LI (620!). see

8) Maybe FB can stop copying Google’s ad model (which Google invented) and go back to the drawing table. Like a FB kind of Paypal

9) There are more experts on the blogosphere than experts in Wall Street.

10) No blogger is willing to admit that they erred in the optimism on the great white IPO hope.

I did. Mea culpa. I thought FB is a good stock. I would buy it still- but the rupee tanked by 10% since past 1 week against the dollar.


I am now waiting for Chinese social network market to open with IPO’s. Thats walled gardens within walled gardens of Jade and Bamboo.

Related- Art Work of Another 100 billion dollar company (2006)

Book Review- Machine Learning for Hackers

This is review of the fashionably named book Machine Learning for Hackers by Drew Conway and John Myles White (O’Reilly ). The book is about hacking code in R.


The preface introduces the reader to the authors conception of what machine learning and hacking is all about. If the name of the book was machine learning for business analytsts or data miners, I am sure the content would have been unchanged though the popularity (and ambiguity) of the word hacker can often substitute for its usefulness. Indeed the many wise and learned Professors of statistics departments through out the civilized world would be mildly surprised and bemused by their day to day activities as hacking or teaching hackers. The book follows a case study and example based approach and uses the GGPLOT2 package within R programming almost to the point of ignoring any other native graphics system based in R. It can be quite useful for the aspiring reader who wishes to understand and join the booming market for skilled talent in statistical computing.

Chapter 1 has a very useful set of functions for data cleansing and formatting. It walks you through the basics of formatting based on dates and conditions, missing value and outlier treatment and using ggplot package in R for graphical analysis. The case study used is an Infochimps dataset with 60,000 recordings of UFO sightings. The case study is lucid, and done at a extremely helpful pace illustrating the powerful and flexible nature of R functions that can be used for data cleansing.The chapter mentions text editors and IDEs but fails to list them in a tabular format, while listing several other tables like Packages used in the book. It also jumps straight from installation instructions to functions in R without getting into the various kinds of data types within R or specifying where these can be referenced from. It thus assumes a higher level of basic programming understanding for the reader than the average R book.

Chapter 2 discusses data exploration, and has a very clear set of diagrams that explain the various data summary operations that are performed routinely. This is an innovative approach and will help students or newcomers to the field of data analysis. It introduces the reader to type determination functions, as well different kinds of encoding. The introduction to creating functions is quite elegant and simple , and numerical summary methods are explained adequately. While the chapter explains data exploration with the help of various histogram options in ggplot2 , it fails to create a more generic framework for data exploration or rules to assist the reader in visual data exploration in non standard data situations. While the examples are very helpful for a reader , there needs to be slightly more depth to step out of the example and into a framework for visual data exploration (or references for the same). A couple of case studies however elaborately explained cannot do justice to the vast field of data exploration and especially visual data exploration.

Chapter 3 discussed binary classification for the specific purpose for spam filtering using a dataset from SpamAssassin. It introduces the reader to the naïve Bayes classifier and the principles of text mining suing the tm package in R. Some of the example codes could have been better commented for easier readability in the book. Overall it is quite a easy tutorial for creating a naïve Bayes classifier even for beginners.

Chapter 4 discusses the issues in importance ranking and creating recommendation systems specifically in the case of ordering email messages into important and not important. It introduces the useful grepl, gsub, strsplit, strptime ,difftime and strtrim functions for parsing data. The chapter further introduces the reader to the concept of log (and affine) transformations in a lucid and clear way that can help even beginners learn this powerful transformation concept. Again the coding within this chapter is sparsely commented which can cause difficulties to people not used to learn reams of code. ( it may have been part of the code attached with the book, but I am reading an electronic book and I did not find an easy way to go back and forth between the code and the book). The readability of the chapters would be further enhanced by the use of flow charts explaining the path and process followed than overtly verbose textual descriptions running into multiple pages. The chapters are quite clearly written, but a helpful visual summary can help in both revising the concepts and elucidate the approach taken further.A suggestion for the authors could be to compile the list of useful functions they introduce in this book as a sort of reference card (or Ref Card) for R Hackers or atleast have a chapter wise summary of functions, datasets and packages used.

Chapter 5 discusses linear regression , and it is a surprising and not very good explanation of regression theory in the introduction to regression. However the chapter makes up in practical example what it oversimplifies in theory. The chapter on regression is not the finest chapter written in this otherwise excellent book. Part of this is because of relative lack of organization- correlation is explained after linear regression is explained. Once again the lack of a function summary and a process flow diagram hinders readability and a separate section on regression metrics that help make a regression result good or not so good could be a welcome addition. Functions introduced include lm.

Chapter 6 showcases Generalized Additive Model (GAM) and Polynomial Regression, including an introduction to singularity and of over-fitting. Functions included in this chapter are transform, and poly while the package glmnet is also used here. The chapter also introduces the reader formally to the concept of cross validation (though examples of cross validation had been introduced in earlier chapters) and regularization. Logistic regression is also introduced at the end in this chapter.

Chapter 7 is about optimization. It describes error metric in a very easy to understand way. It creates a grid by using nested loops for various values of intercept and slope of a regression equation and computing the sum of square of errors. It then describes the optim function in detail including how it works and it’s various parameters. It introduces the curve function. The chapter then describes ridge regression including definition and hyperparameter lamda. The use of optim function to optimize the error in regression is useful learning for the aspiring hacker. Lastly it describes a case study of breaking codes using the simplistic Caesar cipher, a lexical database and the Metropolis method. Functions introduced in this chapter include .Machine$double.eps .

Chapter 8 deals with Principal Component Analysis and unsupervised learning. It uses the ymd function from lubridate package to convert string to date objects, and the cast function from reshape package to further manipulate the structure of data. Using the princomp functions enables PCA in R.The case study creates a stock market index and compares the results with the Dow Jones index.

Chapter 9 deals with Multidimensional Scaling as well as clustering US senators on the basis of similarity in voting records on legislation .It showcases matrix multiplication using %*% and also the dist function to compute distance matrix.

Chapter 10 has the subject of K Nearest Neighbors for recommendation systems. Packages used include class ,reshape and and functions used include cor, function and log. It also demonstrates creating a custom kNN function for calculating Euclidean distance between center of centroids and data. The case study used is the R package recommendation contest on Kaggle. Overall a simplistic introduction to creating a recommendation system using K nearest neighbors, without getting into any of the prepackaged packages within R that deal with association analysis , clustering or recommendation systems.

Chapter 11 introduces the reader to social network analysis (and elements of graph theory) using the example of Erdos Number as an interesting example of social networks of mathematicians. The example of Social Graph API by Google for hacking are quite new and intriguing (though a bit obsolete by changes, and should be rectified in either the errata or next edition) . However there exists packages within R that should be atleast referenced or used within this chapter (like TwitteR package that use the Twitter API and ROauth package for other social networks). Packages used within this chapter include Rcurl, RJSONIO, and igraph packages of R and functions used include rbind and ifelse. It also introduces the reader to the advanced software Gephi. The last example is to build a recommendation engine for whom to follow in Twitter using R.

Chapter 12 is about model comparison and introduces the concept of Support Vector Machines. It uses the package e1071 and shows the svm function. It also introduces the concept of tuning hyper parameters within default algorithms . A small problem in understanding the concepts is the misalignment of diagram pages with the relevant code. It lastly concludes with using mean square error as a method for comparing models built with different algorithms.


Overall the book is a welcome addition in the library of books based on R programming language, and the refreshing nature of the flow of material and the practicality of it’s case studies make this a recommended addition to both academic and corporate business analysts trying to derive insights by hacking lots of heterogeneous data.

Have a look for yourself at-

Timo Elliott on 2012

Continuing the DecisionStats series on  trends for 2012, Timo Elliott , Technology Evangelist  at SAP Business Objects, looks at the predictions he made in the beginning of  2011 and follows up with the things that surprised him in 2011, and what he foresees in 2012.

You can read last year’s predictions by Mr Elliott at

Timo- Here are my comments on the “top three analytics trends” predictions I made last year:

(1) Analytics, reinvented. New DW techniques make it possible to do sub-second, interactive analytics directly against row-level operational data. Now BI processes and interfaces need to be rethought and redesigned to make best use of this — notably by blurring the distinctions between the “design” and “consumption” phases of BI.

I spent most of 2011 talking about this theme at various conferences: how existing BI technology israpidly becoming obsolete and how the changes are akin to the move from film to digital photography. Technology that has been around for many years (in-memory, column stores, datawarehouse appliances, etc.) came together to create exciting new opportunities and even generally-skeptical industry analysts put out press releases such as “Gartner Says Data Warehousing Reaching Its Most Significant Inflection Point Since Its Inception.” Some of the smaller BI vendors had been pushing in-memory analytics for years, but the general market started paying more attention when megavendors like SAP started painting a long-term vision of in-memory becoming a core platform for applications, not just analytics. Database leader Oracle was forced to upgrade their in-memory messaging from “It’s a complete fantasy” to “we have that too”.

(2) Corporate and personal BI come together. The ability to mix corporate and personal data for quick, pragmatic analysis is a common business need. The typical solution to the problem — extracting and combining the data into a local data store (either Excel or a departmental data mart) — pleases users, but introduces duplication and extra costs and makes a mockery of information governance. 2011 will see the rise of systems that let individuals and departments load their data into personal spaces in the corporate environment, allowing pragmatic analytic flexibility without compromising security and governance.

The number of departmental “data discovery” initiatives continued to rise through 2011, but new tools do make it easier for business people to upload and manipulate their own information while using the corporate standards. 2012 will see more development of “enterprise data discovery” interfaces for casual users.

(3) The next generation of business applications. Where are the business applications designed to support what people really do all day, such as implementing this year’s strategy, launching new products, or acquiring another company? 2011 will see the first prototypes of people-focused, flexible, information-centric, and collaborative applications, bringing together the best of business intelligence, “enterprise 2.0”, and existing operational applications.

2011 saw the rise of sophisticated, user-centric mobile applications that combine data from corporate systems with GPS mapping and the ability to “take action”, such as mobile medical analytics for doctors or mobile beauty advisor applications, and collaborative BI started becoming a standard part of enterprise platforms.

And one that should happen, but probably won’t: (4) Intelligence = Information + PEOPLE. Successful analytics isn’t about technology — it’s about people, process, and culture. The biggest trend in 2011 should be organizations spending the majority of their efforts on user adoption rather than technical implementation.

Unsurprisingly, there was still high demand for presentations on why BI projects fail and how to implement BI competency centers.  The new architectures probably resulted in even more emphasis on technology than ever, while business peoples’ expectations skyrocketed, fueled by advances in the consumer world. The result was probably even more dissatisfaction in the past, but the benefits of the new architectures should start becoming clearer during 2012.

What surprised me the most:

The rapid rise of Hadoop / NoSQL. The potentials of the technology have always been impressive, but I was surprised just how quickly these technology has been used to address real-life business problems (beyond the “big web” vendors where it originated), and how quickly it is becoming part of mainstream enterprise analytic architectures (e.g. Sybase IQ 15.4 includes native MapReduce APIs, Hadoop integration and federation, etc.)

Prediction for 2012:

As I sat down to gather my thoughts about BI in 2012, I quickly came up with the same long laundry list of BI topics as everybody else: in-memory, mobile, predictive, social, collaborative decision-making, data discovery, real-time, etc. etc.  All of these things are clearly important, and where going to continue to see great improvements this year. But I think that the real “next big thing” in BI is what I’m seeing when I talk to customers: they’re using these new opportunities not only to “improve analytics” but also fundamentally rethink some of their key business processes.

Instead of analytics being something that is used to monitor and eventually improve a business process, analytics is becoming a more fundamental part of the business process itself. One example is a large telco company that has transformed the way they attract customers. Instead of laboriously creating a range of rate plans, promoting them, and analyzing the results, they now use analytics to automatically create hundreds of more complex, personalized rate plans. They then throw them out into the market, monitor in real time, and quickly cull any that aren’t successful. It’s a way of doing business that would have been inconceivable in the past, and a lot more common in the future.




Timo Elliott

Timo Elliott is a 20-year veteran of SAP BusinessObjects, and has spent the last quarter-century working with customers around the world on information strategy.

He works closely with SAP research and innovation centers around the world to evangelize new technology prototypes.

His popular Business Analytics blog tracks innovation in analytics and social media, including topics such as augmented corporate reality, collaborative decision-making, and social network analysis.

His PowerPoint Twitter Tools lets presenters see and react to tweets in real time, embedded directly within their slides.

A popular and engaging speaker, Elliott presents regularly to IT and business audiences at international conferences, on subjects such as why BI projects fail and what to do about it, and the intersection of BI and enterprise 2.0.

Prior to Business Objects, Elliott was a computer consultant in Hong Kong and led analytics projects for Shell in New Zealand. He holds a first-class honors degree in Economics with Statistics from Bristol University, England

Timo can be contacted via Twitter at

 Part 1 of this series was from James Kobielus, Forrestor at

Oracle Public Cloud

The slick website of Oracle Public Cloud- coming soon to an office near your location.


and including the oracle social network 😉

Oracle Social Network

A secure collaboration tool for everyone you work with.

Public Cloud


Research on Social Games

Social Gaming is slightly different from arcade gaming, and the heavy duty PSP3, XBox, Wii world of gaming.  Some observations on my research ( 😉 ) on social gaming across internet is as follows-

There are mostly 3 types of social games-

1) Quest- Build a town/area/farm to earn in game money or points

2) Fight- fight other people /players /pigs earn in game money or points

3) Puzzle- Stack up, make three of a kind, etc

Most successful social games are a crossover between the above three kinds of social games (so build and fight, or fight and puzzle etc)

In addition most social games have some in game incentives that are peculiar to social networks only. In game incentives are mostly in game cash to build, energy to fight others, or shortcuts in puzzle games. These social gaming incentives are-

1) Some incentive to log in daily/regularly/visit game site more often

2) Some incentive to invite other players on the social network

A characteristic of this domain is blatant me-too, copying and ripping creative ideas (but not the creative itself)  from other social games. In general the successful game which is the early leader gets most of the players but other game studios can and do build up substantial long tail network of players by copying games. Thus there are a huge variety of games.

However there are massive hits like Farmville and Angry Birds, that prove that a single social game well executed can be very valuable and profitable to both itself as well as the primary social network hosting it.

Accordingly the leading game studios are Zynga, Electronic Arts and (yes) Microsoft while Google has been mostly a investor in these.

A good website for studying data about social games is while a sister website for studying developments is

As you can see below Appdata is a formidable data gatherer here (though I find the top App – Static HTML as both puzzling and a sign of un corrected automated data gathering),

but I expect more competition in this very lucrative segment.