The Data Science Handbook

The author did an incredible job writing “The Data Science Handbook”. I like how he organized the book so that readers could easily browse through the chapters that they want to read without losing the content. Besides, each chapter has its own audiences. For example, if the reader is an experienced data scientist, he/she could start from “Advanced Topics”. If the reader is a business analyst or a manager, he/she could start reading about “Big Data”, “Databases”, “Machine Learning Overview”, etc. Every chapter has its own level of complexity, real life examples and Python Codes. This is exactly how a great engineering mind would organize the book.I usually feel that textbooks and handbooks are boring in general. However, “The Data Science Handbook” is not at all. The author utilized a conversation style language – it almost feels like he is talking to you and sharing his extensive real life data science experiences.So, what about improvements for next edition:There was a comment on changing examples from Python version 2.7 to Python version 3.0. I think this is not an immediate need. Programming languages evolve but the fundamentals stay the same. The author explains the fundamentals very well, and this book does not have an intention to teach programming languages as well.Mr. Cady provided real life examples in each chapter. I believe he could add a capstone data science project at the end of the book. He can define a problem or problems and data sets and let the readers of his book design a solution around the problem and let them publish it in his website.I think “The Data Science Handbook” will be an invaluable reference book for data scientists, students, business analysts and managers for a long time.

I am 100 pages in and I love this book. It is important to note, however, that you should not expect a ton of exercises with in depth explanations. The real value in this book is not the exercises but the author's thoughts and advice he shares throughout the book. It is super useful to hear from somebody who works in the data science field and who explains how you should think about the job, what steps to take from beginning to end in the data science process(broadly speaking), what questions you should ask about the data, what techniques you will rarely use, what you will often use, the limitations of certain statistical methods and much more. I basically look at this book as a way to complete the circle after you have learned much of the deep concepts of python and the syntax. This book will serve me well when I begin looking for employment in this field as he gives you a clear understanding what you need to do to be a good data scientist.

If there is one data science book you need or wish to buy consider this one. In just a couple of hundred pages the author distills theory, practice and plenty of actual examples and real code! The theory is succinct and erudite whetting the appetite of readers that need to understand it. The practical examples go into adequate detail. As a bonus the author covers related topics like programming tips, hints for improving performance of code, his personal preferences and idioms etc. The breadth of topics covered is impressive. Almost all machine learning and data science algorithms and software packages are explored. The book can be skimmed in a few days, can be used along with the copious references to probe deeper into any particular topic and will prove an invaluable reference guide as well.

I think is a great intuitive complement to the famous Introduction to Statistical Learning by Witten, James and Hastie

I am reading the book and I find it well written. Field, you should take up teaching. you have explianed all the details very well. The only thing missing is the sample data so your scripts can be tried on immediately.I did a 10 course - data science certification recently and this book is helping me, brush up on my newly learnt skills.Well done Field

The clear writing style with code examples makes this a great way for me to learn data science on my own. It is also a super reference book to have on my shelf. This is very readable and explains some tricky concepts in an accessible manner. Thank you for this great book!

One of the best all around data science books I have found. It covers lots of real-life applications rather than the typical pie in the sky theory examples. I think it would make a good desk top tool for the number cruncher or database jockey of any skill level.

Half the pages are stuck together and is generally just not an easy book to read compared to other Data Science books in this area.

This is supposed to be a Data Science Handbook, a resource for people who delve into data analysis and problem-solving. If a significant portion of their time is spent, not learning a particular implementation, and instead figuring out what to change in the Python code to make it compatible with version 3.x misses the whole point of having a resource at hand... It is requested that the author reconsiders this decision and migrate the code to Python 3.x in an updated edition of the book.

Algunos critican a este libro por utilizar un lenguaje demasiado coloquial, pero es lo que a veces alguien realmente necesita para evitar el tedio de un libro "elevado"y "académico. Los temas son abordados con mucho conocimiento y las gráficas son explícitas y coloridas. El único gran problema es que el autor utilizó Python 2 para su código, por lo que es posible que aún cuando los conceptos son explicados brillantemente, el código ilustrativo pronto caiga en la obsolescencia.

This particular book would be useful to non technical managers in helping them understand applications of data science. I wouldn't say this book is useful to anybody who wants to be serious in the field, unless you are just now starting out. The writing is friendly and fun to read, the cool just isn't technical enough to be called a handbook.

Provides a good overview of key areas of data science. Great for understanding the field at a high level. Some of the more detailed descriptions (e.g. on ML, big data etc.) feel a bit out of place, as they are neither long enough to provide a detailed clear understanding, nor short/non-technical enough to just give the bigger picture. For these topics I'd recommend more specialist text books. But for a general overview of the field, this is a good.

The book is full of coding mistakes that make it confusing.I cannot believe that the author has not reviewed the code and that:100000 * 1.05 = 110250Even the explanation of indexing is wrong.Definitely the worst coding examples ever seen.I understand that data scientists are not developers and know very little about coding but this book makes it even worse.