- Paperback: 408 pages
- Publisher: O'Reilly Media; 1 edition (November 3, 2013)
- Language: English
- ISBN-10: 1449358659
- ISBN-13: 978-1449358655
- Product Dimensions: 6 x 0.8 x 9 inches
- Shipping Weight: 1.3 pounds (View shipping rates and policies)
- Average Customer Review: 3.9 out of 5 stars See all reviews (53 customer reviews)
- Amazon Best Sellers Rank: #35,193 in Books (See Top 100 in Books)
Enter your mobile number or email address below and we'll send you a link to download the free Kindle App. Then you can start reading Kindle books on your smartphone, tablet, or computer - no Kindle device required.
To get the free app, enter your mobile phone number.
Doing Data Science: Straight Talk from the Frontline 1st Edition
Use the Amazon App to scan ISBNs and compare prices.
Frequently bought together
Customers who bought this item also bought
From the Publisher
|Data Science for Business||Data Science from Scratch||Doing Data Science||R for Data Science||Data Science at the Command Line||Python Data Science Handbook|
|What You Need to Know about Data Mining and Data-Analytic Thinking||First Principles with Python||Straight Talk from the Frontline||Visualize, Model, Transform, Tidy, and Import Data||Facing the Future with Time-Tested Tools||Tools and Techniques for Developers|
"Every once in a while a single book comes to crystallize a new discipline. If books still have this power in the era of electronic media, "Doing Data Science: Straight Talk from the Frontline" by Rachel Schutt and Cathy O'Neil: O'Reilly, 2013 might just be the book that defines data science."
Professor of statistics and political science, and director of the Applied Statistics Center at Columbia University
"I got a lot out of Doing Data Science, finding the chapter organization on business problem specification, analytics formulation, data access/wrangling, and computer code to be very helpful in understanding DS solutions."
Co-founder, OpenBI, LLC, a Chicago-based business intelligence services firm
About the Author
Cathy O’Neil earned a Ph.D. in math from Harvard, was postdoc at the MIT math department, and a professor at Barnard College where she published a number of research papers in arithmetic algebraic geometry. She then chucked it and switched over to the private sector. She worked as a quant for the hedge fund D.E. Shaw in the middle of the credit crisis, and then for RiskMetrics, a risk software company that assesses risk for the holdings of hedge funds and banks. She is currently a data scientist on the New York start-up scene, writes a blog at mathbabe.org, and is involved with Occupy Wall Street.
Rachel Schutt is the Senior Vice President for Data Science at News Corp. She earned a PhD in Statistics from Columbia University, and was a statistician at Google Research for several years. She is an adjunct professor in Columbia’s Department of Statistics and a founding member of the Education Committee for the Institute for Data Sciences and Engineering at Columbia. She holds several pending patents based on her work at Google, where she helped build user-facing products by prototyping algorithms and building models to understand user behavior. She has a master's degree in mathematics from NYU, and a master's degree in Engineering-Economic Systems and Operations Research from Stanford University. Her undergraduate degree is in Honors Mathematics from the University of Michigan.
If you are a seller for this product, would you like to suggest updates through seller support?
Top customer reviews
More breadth than depth
What is data science? The book Doing Data Science not only explains what data science is but also provides a broad overview of methods and techniques that one must master in order to call one self a data scientist. The book is based on a course about data science given at Columbia University. However it is not to be considered as a text book about data science but more as a broad introduction to a number of topics in data science.
In the spring of 2013 I followed two Coursera courses. One about the statistical programming language R and one on Data Analysis. I had for some time been looking for a book that could be used as a follow-up reading on topics in data science. This was the reason I picked up "Doing Data Science".
The book begins with a chapter about what data science is all about is followed by four chapters on topics like statistical inference, explanatory data analysis, various machine learning algorithms, linear and logistic regression, and Naive Bayes. I have a background in both mathematics and statistics and I was able to understand these chapters but the material is covered in such broad terms that I find it hard to believe that a newcomer to this topics will understand or gain much knowledge from reading these chapters. Basic math is presented about the models but without some kind of detailed explanation one cannot develop any deeper intuition for the approach explained.
The best parts of the book is definitely chapter 6 to 8 and 10. In here we find interesting discussion about coverage of data science applied to financial modeling, extracting information from data, and social networks. I really enjoyed the examination of time stamped data, the Kaggle Model, feature selection, and case-attribute data versus social network data. The math behind these topics was however once again explained quite superficial. Centrality measures is central to social network analysis but it is very hard to develop intuition for there measures without a more detailed explanation about the underlying math. These chapters contains lots of useful resources for finding additional information about the discussed topics.
Data visualization is an integral part of data science for communication results. Beginners in the field of data science needs concrete and easy to follow instruction on how to get started with visualization. Unfortunately the book focuses more on the use of data visualization in modern art projects. The content is simply to abstract for beginners to learn about the usage of visualization in data science.
When I was browsing the book before actual buying it I was kind thrilled to see that it covered topics like causality and epidemiology. Topics that I did not found covered in any other book about data science. However the chapter about epidemiology is not about using data science in epidemiology but 'just' about using data science to evaluate the methods used in epidemiology. Likewise there seems to be no link between data science and causality. I later discovered that the authors used an entire blog post ([...] to explain why causality was part of the university course underlying the book. This material or parts of it should have made it into the book. I am still not convinced that causality is a topic in data science.
There are several examples in which the book assumes the reader to have knowledge of US government structure and organizations. Examples include page 292 when discussing US health care databases and page 298 where FDA is mentioned without further introduction or explanation about what FDA is.
A book than contains programming examples should always make the code accessible to download. Typing in the code yourself is simply waste of time. It is possible to download some of the datasets used in the book through GitHub. But the code does not seem to be available. I also own the electronic version of the book and I tried to copy-paste some of the examples from the e-book but there are several examples of code that hasn't been proof written or tested prior to publication. The sample code misses references to required R libraries or refers to computer folder structures on some local Columbia University computer. The companion datasets that can be downloaded on GitHub consists of a number of Excel files. The R sample code uses the gdata package to load these Excel files into R for further analysis. It took be quite some time to figure out why this process didn't work on a Windows computer. The gdata package requires Perl to be installed on the computer and this is not default software on Windows. In my opinion one should always publish data in a simple format, e.g. csv files and definitely not proprietary formats like xls for Excel files.
Data Science is both science and a lot of practical experience. I guess the title of the book Doing Data Science tries to capture that. You need to do data science in order to learn it. The covered topics are interesting but the material is more breadth than depth. Luckily there are lots of useful links and resources to additional materials. Personally I would prefer more details about the actual data science topics like e.g. extracting meaning from data and social network analysis and less focus on math. The book already requires some knowledge of math, statistics and programming, so why not presume that the reader has the background knowledge and dive straight into the data science discussions.
I really like the idea about having a lot of different people present various topics in data science and the book is well written and contains lots of useful resources for further studies of data science. I will recommend to book to people new to the subject but be aware of the fact that source code is not available and that is a major drawback.
Disclosure: I review for the O'Reilly Reader Review Program and I want to be transparent about my reviews so you should know that I received a free copy of this ebooks in exchange of my review.
From a pedagogical perspective, I think it's a valiant attempt to create a class that's not so "academic." The book is a compendium of individual lectures that were the basis of a data science class at Columbia University, and the corresponding assignments were aimed at giving students a flavor of real-world data science problems (where data is messy, specific questions regarding outcomes are not-well-formed, etc.), which I think is an amazingly valuable experience to give students perspective on what the field is about. But I wonder if the course went a little *too* far into "the real world is not pretty" aspect of things. The students wrote a chapter at the end of the book where they criticize a standard academic problem that comes from a statistical learning textbook and that, in my opinion, is a negative outcome. While elegant mathematical theories do not describe the complexities of the real world, understanding the subtleties of algorithms is an important part of any scientific field, and to discount that is a disservice to the students. Too much depth and not enough breadth is bad in the real world, but so is not having *enough* depth. On the whole, though, I really applaud the approach of the authors at building a "real-world" class.
One of the things that book has left me pondering is whether there is a clear distinction between data *science* and data *engineering*, and whether it is possible to have clear roles for people who are predominately scientists than those who are predominately engineers. A few of the guest lecturers claim that 90% of the work of a data scientist is organizing the data, but I can't help but wonder if that's the bias of the individual speakers---that they *like* this component of the work and, therefore, focus on that more, rather than it being an absolute must to spend 90% of your time working on data structuring. I am sure that if the authors were to read this comment, they would think that I am missing one of their major points (namely, that one can make a lot of mistakes in data leakage and that like from poor data structures, hence making this an integral part of the process). But I think there's a certain personality type that really loves working on the actually processing component who would otherwise be turned off my too much data structuring if it really composed 90% of the work. And harnessing the skills from those types of people is undoubtedly invaluable. So I'm really wondering if many companies are able to break up roles where some people (the scientists) focus more on the processing part, while others (the engineers) focus more on the structuring part.
Most recent customer reviews
I've been doing statistical computing on financial data since about 1997.Read more