Machine Learning for Hackers [Paperback]

Drew Conway (Author), John Myles White (Author)

Book Description

Publication Date: February 22, 2012 | ISBN-10: 1449303714 | ISBN-13: 978-1449303716 | Edition: 1

If you’re an experienced programmer interested in crunching data, this book will get you started with machine learning—a toolkit of algorithms that enables computers to train themselves to automate useful tasks. Authors Drew Conway and John Myles White help you understand machine learning and statistics tools through a series of hands-on case studies, instead of a traditional math-heavy presentation.

Each chapter focuses on a specific problem in machine learning, such as classification, prediction, optimization, and recommendation. Using the R programming language, you’ll learn how to analyze sample datasets and write simple machine learning algorithms. Machine Learning for Hackers is ideal for programmers from any background, including business, government, and academic research.

• Develop a naïve Bayesian classifier to determine if an email is spam, based only on its text
• Use linear regression to predict the number of page views for the top 1,000 websites
• Learn optimization techniques by attempting to break a simple letter cipher
• Compare and contrast U.S. Senators statistically, based on their voting records
• Build a “whom to follow” recommendation system from Twitter data

Editorial Reviews

About the Author

Drew Conway is a PhD candidate in Politics at NYU. He studies international relations, conflict, and terrorism using the tools of mathematics, statistics, and computer science in an attempt to gain a deeper understanding of these phenomena. His academic curiosity is informed by his years as an analyst in the U.S. intelligence and defense communities.

John Myles White is a PhD candidate in Psychology at Princeton. He studies pattern recognition, decision-making, and economic behavior using behavioral methods and fMRI. He is particularly interested in anomalies of value assessment.

Product Details

• Paperback: 324 pages
• Publisher: O'Reilly Media; 1 edition (February 22, 2012)
• Language: English
• ISBN-10: 1449303714
• ISBN-13: 978-1449303716
• Product Dimensions: 7 x 0.8 x 9.2 inches
• Shipping Weight: 1.2 pounds (View shipping rates and policies)
• Average Customer Review: 3.4 out of 5 stars  See all reviews (20 customer reviews)
• Amazon Best Sellers Rank: #40,479 in Books (See Top 100 in Books)
  • #3 in Books > Computers & Technology > Software > Natural Language Processing
  • #9 in Books > Computers & Technology > Computer Science > Artificial Intelligence > Machine Learning
  • #18 in Books > Computers & Technology > Computer Science > Artificial Intelligence > Human Vision & Language Systems

More About the Author

Discover books, learn about writers, read author blogs, and more.

Most Helpful Customer Reviews

89 of 94 people found the following review helpful

3.0 out of 5 stars Machine Learning for Non-Hackers March 20, 2012

By Voracious Reader

Format:Paperback|Amazon Verified Purchase

By page count, this is primarily a book on R, with some additional time spent on machine learning.

There is way too much time spent on R, dedicated to such things as parsing email messages, and spidering webpages, etc. These are things that no-one with other tools available would do in R. And it's not that it's easier to do it in R, it's actually harder than using an appropriate library, like JavaMail. And yet, while much time is spent in details, like regexes to extract dates (ick!), more interesting R functions are given short shrift.

There's some good material in here, but it's buried under the weight of doing everything in R. If you are a non-programmer, and want to use only one hammer for everything, then R is not a bad choice. But it's not a good choice for developers that are already comfortable with a wider variety of tools.

I'd recommend Programming Collective Intelligence by Segaran, if you would describe yourself as a "Hacker".

30 of 31 people found the following review helpful

3.0 out of 5 stars Not for a hacker, probably for a scientist May 3, 2012

By Sharon Talbot

Format:Paperback

In Machine Learning for Hackers by Drew Conway and John Myles White, the reader is introduced to a number of techniques useful for creating systems that can understand and make use of data. While the book has solid topical material and is written in a fluid and easy to read manner, I don't feel that this book is really for hackers, unless the definition of hacker is vastly different from "programmer".

Much of the text is taken up explaining how to parse strings, change dates, and otherwise munge data into shape to be operated on by statistical functions provided by R. In fact, there is so much of the book in that fashion that I end up skipping through large portions to get back to something that is worth spending time reading about. I can't understand why a programmer would need significant education in string parsing. I was also put off by the vast amount of text explaining basic statistics. Maybe a recent computer science graduate is simply the wrong reader for this book?

I think it is certainly possible to learn the basic principles of machine hacking from this book, and even to put them to good use with R in the same manner displayed in the examples. Indeed, the code and data available for this book would be very useful as prep for an introductory course at an academic institution. To make the best use of the text, you really should be sitting at your computer, reading the text side by side with the code, and operating on the data with R as instructed to do.

Personally, I found that wading through this text wasn't enjoyable it due to the lack of density of material at the depth I was looking for. Other readers may find it is just right for them, but I suspect those readers would not be hackers, contrary to the implication of the title. As best as I can figure, this book would best serve a student scientific researcher who wanted to understand what machine learning was about, and did not have significant prior experience in programming or statistics. Alternatively, if you are significantly distant in years from your time in statistics, or considered learning R one of your goals, this book could work well for you.

I received this book for free as part of the O'Reilly Blogger Review program, which is neat.

I should note that I read this book on the iPhone as an ePub. There were some formatting problems with tables that were distracting, but otherwise it was readable.

18 of 19 people found the following review helpful

2.0 out of 5 stars Erroneous but entertaining July 26, 2012

By Kurt

Format:Paperback

I used this book to teach students about data mining and machine learning with a hands-on approach. I intended it to be used as a book for the students to rely and fall back on. It is not suited well for that purpose.

Pros: The book is affordable and nicely written. The authors take great care in making the book useful and entertaining and one can immediately start putting things into practise. Also, the R examples are interesting and by itself motivating.

Cons: The book has a couple of very grievous errors, that make me wonder the authors understand the subject matter. This is especially striking in the chapters on PCA and Multidimensional Scaling (which I covered in some depth in the class), but also to a lesser degree in other parts of the book that I have read more thoroughly (like optimization and linear and nonlinear regression). Many errors are not typos or simple mistakes but seem to be proof of a profound misunderstanding of concepts by the authors. I am sorry to be so blunt, but one should not write a book about topics that one is not intimate with. Given that the book is probably quite successful, it propagates error into a community whose members may not have the statistical background to spot the errors immediately. Some methods used in the book are quite hard to understand even for graduate students and to be so nonchalant about the underlying theory can be dangerous. I realize that the book is intended to be superficial with regards to mathematical or conceptual depth, but this combined with some of the presented high-level techniques can easily backfire when people are given the tools, but not the understanding. Especially when the explanations on interpretation are plainly wrong (I am talking about using standard deviations instead of variances, substantive interpretation of methodological artifacts, wrong explanation of R output, etc.). Additionally, certain parts of the book became outdated as soon as the book came out, such as the Google example.

Overall, I do not recommend the book. I now only use it as a collection of nice examples and sometimes borrow bits of their R code.