Data Science Foundations Tools and Techniques: Core Skills for Quantitative Analysis with R and Git (Addison-Wesley Data & Analytics Series)

If you want nice and tidy package of all the things you need to know to get ready to do great Data Science, then this is the book for you!Programming Skills for Data Science starts at the beginning of the DS journey. It takes you through the basics, careful to ensure that no tricky acronym or software 'gotcha' is left unexplained. Folks will appreciate the book's guiding hand which provides a consistent and carefully thought out introduction to all the tools and technologies you need to know. It starts with command line tools and git, making sure the reader is prepared for the more advanced stuff later in the book. I liked the inclusion on a chapter about using Markdown for documentation purposes. If you already are familiar with this markup language, its an easy thing to skim. But if you haven't used Markdown before, it is great to have it here, right in-line with the other prerequisites.The next section of the book provides a great introduction to R - a powerful and wildly popular tool for 'doing' data science. The way Mike Freeman and Joel Ross build up from simple programming concepts to advanced R features really showcase that they've been teaching this stuff for a long time - and have a system that works! I love the walkthrough of basic data types in R (which are kinda weird even if you are familiar with data types from other languages). I also appreciate the section on where one can find help. Thats one of the biggest lessons to learn when doing any programming work - its completely ok to search out answers when you get stuck. Mike and Joel provide a comprehensive list for doing just that.The main section of the book gets people comfortable with the primary tasks of a Data Scientist - wrangling and visualizing data using code. And here, Joel and Mike again show their expertise by picking the best-in-class packages for working with data in R today. Their showcasing of the 'tidyverse' of packages gets you parsing and working with data in the most direct and powerful way possible. They show you how to get started with ggplot2 for visualizing data quickly. I thought it was nice they include a quick description of the 'grammar of graphics' which is the conceptual framework ggplot2 is built from. There is even a section on making maps in R - using the same tools!The final section of the book on building and publishing data-driven reports and analyses really ties everything together. Their suggestions for building and publishing static and interactive analyses are really some of the best ways to get your work out there. I learned a lot of how to build out these interactive tools using Shiny - and make them look good too!Throughout the book I loved the writing style and the attention to detail. There are innumerable call-outs, tips, and warnings as you read. I love that they provide both Windows and Mac examples of setup and screenshots. And I love that the book comes in full color! So those graphics are easy to read and understand. I think a critique that could be leveled against this book is "well can't you find this all on the Internet?". But really, what book couldn't you say that about, these days? But it is true - there are resources out there that cover chunks of this material. You could probably amass a body of work that hit roughly the same topics. But a benefit of this book is having a single resource where all of this material is packaged for you in one handy-dandy guide, so you don't have to be constantly googling mystery words and trying to piece disparate narratives together while learning something new.This book is a great guide and a great resource for starting down the Data Science path. I have a copy and will be getting one for my friends and associates that are interested in getting started with working and analyzing data!!

While Freeman and Ross's Programming Skills for Data Science is a standout compilation of a variety of introductory data science topics, the value of the text is diminished by the authors' inability to fully articulate many of the nuances of data science.What is really great:1. An excellent spread of important topics that are often omitted from a data science text, but are skills that every data scientist should know, including git (for collaboration), markdown and bash.2. Elegant coding and plots. Being an effective communicator cannot be understated and the care the authors take in providing beautiful code demonstrates their pedagogic expertise.3. A nice set of complementary exercises and code available on GitHub to practice your data science skill set.What isn't so great:1. Part of the challenge of data science is it encompasses so many topics and while the authors do try to include many references, when I finished the book, I felt that a number of noteworthy topics were not given any treatment whatsoever. There was no mention of object oriented programming or computational complexity. The data wrangling section seems a bit short and does not really get into how ugly a data set can be and what functions you need to clean it (e.g. drop duplicate records). And perhaps worst of all, the authors bemoan the challenge of resolving package conflicts, but do not mention any potential solutions to help address these difficulties (like Docker).2. The examples at time tend to be very dry or misaligned with a data science textbook. Seeing multiple toy references to data sets about people's height is painful. Part of an introductory data science text is to inspire the reader regarding the versatility of the field and the lack of attention given to providing interesting data sets causes the text to lose some of its persuasive message. (The constant focus on geospatial visualization is a bit too much at times as such plotting techniques are probably better for a more specialized text on geospatial data science.).3. Finally, the prose in Designing Visualizations and Understanding Data is a bit too dry or contradictory at times. The Understanding Data section would be much better motivated by relating stories where not understanding the story behind the data led to disastrous consequences as opposed to just reiterating trite talking points (e.g. know your data). Similarly, while most of the visualizations are absolutely stunning and the code to write them is very short and readable, they are sometimes cluttered with large or awkward font- a point the authors admit should be avoided when possible.Overall, I would certainly recommend this text to a colleague and I look forward to seeing future revisions of the text that hopefully will address some of the shortcomings listed above.

This is the best data science + intro to Programming (R) book I’ve read thus far. I can recommend this to people when teaching different data focused gatherings. They really put their best forward in simplifying and explaining so many details, even though there is so much more to learn (that’s the fun part!). I look forward to future books and would be bummed if I didn’t get to own and read 50+ different future writings of michael freeman and Joel Ross.

This is an incredibly well-written book. The language is accessible and straightforward. Concepts are easy to grasp.The authors provide step by step explanation about how to download the necessary programs and operate them.I highly recommend this book. You won't regret.

Amazing!

I've recommended other R books in the past but this relatively new one is the best of the bunch. A pedagogical masterpiece, it leads you gently through the basics of R (importantly, including elements of the "Tidyverse") with short chapters of just the right length and exercises that aren't too difficult (experienced programmers may of course find them a tad easy). What is outstanding about this book is that all the important areas of basic R are covered (e.g. apply functions, dplyr and tidyr libraries) in what is a very short book (about 340 pages) that can easily be read in a week or two. You won't be an expert after this, of course, but it will provide a solid foundation.

Excellent book for beginners. It covers a broad range of topics that are relevant for data science, including working with terminal, git and R. It doesn't cover these topics in depth, but there are other resources for that. For me this book does serve as a reference quite frequently.

The example Codes are in black and White and this does not seem to be a Original Copy.

Buena introducción.