What do you think?
Rate this book
The Data Science Handbook
Practical, accessible guide to becoming a data scientist, updated to include the latest advances in data science and related fields.
Becoming a data scientist is hard. The job focuses on mathematical tools, but also demands fluency with software engineering, understanding of a business situation, and deep understanding of the data itself. This book provides a crash course in data science, combining all the necessary skills into a unified discipline.
The focus of The Data Science Handbook is on practical applications and the ability to solve real problems, rather than theoretical formalisms that are rarely needed in practice. Among its key points
An emphasis on software engineering and coding skills, which play a significant role in most real data science problems.Extensive sample code, detailed discussions of important libraries, and a solid grounding in core concepts from computer science (computer architecture, runtime complexity, and programming paradigms).A broad overview of important mathematical tools, including classical techniques in statistics, stochastic modeling, regression, numerical optimization, and more.Extensive tips about the practical realities of working as a data scientist, including understanding related jobs functions, project life cycles, and the varying roles of data science in an organization.Exactly the right amount of theory. A solid conceptual foundation is required for fitting the right model to a business problem, understanding a tool’s limitations, and reasoning about discoveries. Data science is a quickly evolving field, and this 2nd edition has been updated to reflect the latest developments, including the revolution in AI that has come from Large Language Models and the growth of ML Engineering as its own discipline. Much of data science has become a skillset that anybody can have, making this book not only for aspiring data scientists, but also for professionals in other fields who want to use analytics as a force multiplier in their organization.
Becoming a data scientist is hard. The job focuses on mathematical tools, but also demands fluency with software engineering, understanding of a business situation, and deep understanding of the data itself. This book provides a crash course in data science, combining all the necessary skills into a unified discipline.
The focus of The Data Science Handbook is on practical applications and the ability to solve real problems, rather than theoretical formalisms that are rarely needed in practice. Among its key points
An emphasis on software engineering and coding skills, which play a significant role in most real data science problems.Extensive sample code, detailed discussions of important libraries, and a solid grounding in core concepts from computer science (computer architecture, runtime complexity, and programming paradigms).A broad overview of important mathematical tools, including classical techniques in statistics, stochastic modeling, regression, numerical optimization, and more.Extensive tips about the practical realities of working as a data scientist, including understanding related jobs functions, project life cycles, and the varying roles of data science in an organization.Exactly the right amount of theory. A solid conceptual foundation is required for fitting the right model to a business problem, understanding a tool’s limitations, and reasoning about discoveries. Data science is a quickly evolving field, and this 2nd edition has been updated to reflect the latest developments, including the revolution in AI that has come from Large Language Models and the growth of ML Engineering as its own discipline. Much of data science has become a skillset that anybody can have, making this book not only for aspiring data scientists, but also for professionals in other fields who want to use analytics as a force multiplier in their organization.
336 pages, Kindle Edition
Published October 31, 2024
32 people are currently reading
146 people want to read
Ratings & Reviews
Friends & Following
Create a free account to discover what your friends think of this book!
Community Reviews
Displaying 1 - 12 of 12 reviews
October 25, 2019
Fun and consise intro.
August 11, 2018
Was looking for an intro text for my academic mates who aren't techie mates: this turned out to be it.
Covers all the important boring stuff (file formats, coding practices) and a bit of the flashy stuff (CNNs, Keras) and was written specifically to drag maths PhDs into basic competence.
Not to be confused with this puffery.
Covers all the important boring stuff (file formats, coding practices) and a bit of the flashy stuff (CNNs, Keras) and was written specifically to drag maths PhDs into basic competence.
Not to be confused with this puffery.
May 1, 2018
Great breadth of topics covered. Good to have the references section at the end of each topic so you can go to more detailed information.
April 8, 2018
Хорошие вводные данные.
May 28, 2018
A great introduction into the field that covers a wide variety of topics, providing an insightful overview to the reader.
July 14, 2024
TL;DR: good to leaf through to appreciate just how diverse the field of data science is. But it is neither reference material, nor an introductory textbook. The blame, however, lies more with Wiley’s poor editorial choices and the failure to clean-up major formatting and layout issues, instead of the author who writes well and covers a lot of ground.
Long Review
A pretty good book, overall, with plenty of example code to build real-life DS skills. The discussion is engaging and the organisation is very modular (with three major sections, in decreasing order of importance for real-life DS). However, the book suffers from three major defects (covered below). Although, of course, a lot of these issues have to do with it not being a Jupyter notebook.
First, the code is pretty darn annoying. The absence of colour coding, dependency mismatches, and deprecations makes the code from 2017 unreadable — if not quite unuseable. The code snippets are also not at a sufficient level of abstraction to allow a user to generalise the learnings. Besides, as it’s not always properly indented, nested loops can be tough to parse.
Second, this handbook is extremely sparing with figures or diagrams. For instance, this book manages to talk about JOINs in SQL without ever using a single Venn diagram or flowchart. Sure, there are (often, very unfinished) images of the output of code, but no conceptual illustrations. Cady is pretty good at explaining concepts in prose and employs good analogies (e.g., his description of typical Git commands in Chp-15 is an excellent introduction), but this approach simply doesn’t lend itself to many areas.
Third, this books cover a lot of ground, and the modular organisation doesn't always help, as many important concepts have in fact been pushed to the end. As a result, the first half often assumes prior knowledge of quite a lot of Python and related libraries; the text comes laced with terms like “scripting languages” and “classes”,and Cady often name-drops a concept just to add, “it’s too difficult so I won’t explain it here, hehe”. (Though, to be fair, classes and OOP do get a discussion, even if only in the final chapters of the book).
Overall, it makes for a good reading, if only to see what all lies out there in the world of DS. And there are nice nuggets of wisdom from a field-practitioner. However, this is not necessarily reference material (you aren’t likely to re-read it), nor is it a textbook (there are no exercises to consolidate learning). And it comes with several poor editorial choices and sometimes unworkable code from 2017. The author also yields to the so-called curse of knowledge, though this may be due to the major concepts getting pushed to the final third of the book.
© Creative Commons CC BY-NC 4.0
Long Review
A pretty good book, overall, with plenty of example code to build real-life DS skills. The discussion is engaging and the organisation is very modular (with three major sections, in decreasing order of importance for real-life DS). However, the book suffers from three major defects (covered below). Although, of course, a lot of these issues have to do with it not being a Jupyter notebook.
First, the code is pretty darn annoying. The absence of colour coding, dependency mismatches, and deprecations makes the code from 2017 unreadable — if not quite unuseable. The code snippets are also not at a sufficient level of abstraction to allow a user to generalise the learnings. Besides, as it’s not always properly indented, nested loops can be tough to parse.
Second, this handbook is extremely sparing with figures or diagrams. For instance, this book manages to talk about JOINs in SQL without ever using a single Venn diagram or flowchart. Sure, there are (often, very unfinished) images of the output of code, but no conceptual illustrations. Cady is pretty good at explaining concepts in prose and employs good analogies (e.g., his description of typical Git commands in Chp-15 is an excellent introduction), but this approach simply doesn’t lend itself to many areas.
Third, this books cover a lot of ground, and the modular organisation doesn't always help, as many important concepts have in fact been pushed to the end. As a result, the first half often assumes prior knowledge of quite a lot of Python and related libraries; the text comes laced with terms like “scripting languages” and “classes”,and Cady often name-drops a concept just to add, “it’s too difficult so I won’t explain it here, hehe”. (Though, to be fair, classes and OOP do get a discussion, even if only in the final chapters of the book).
Overall, it makes for a good reading, if only to see what all lies out there in the world of DS. And there are nice nuggets of wisdom from a field-practitioner. However, this is not necessarily reference material (you aren’t likely to re-read it), nor is it a textbook (there are no exercises to consolidate learning). And it comes with several poor editorial choices and sometimes unworkable code from 2017. The author also yields to the so-called curse of knowledge, though this may be due to the major concepts getting pushed to the final third of the book.
© Creative Commons CC BY-NC 4.0
May 12, 2025
I pretty good overview and a good place to start. There are a lot of typos which could lead you astray if you are not already familiar with material. If there is a second edition fixing this it would be worth seeking out.
The only real complaint I have is from near the end. During the discussion on pointers one of the sections and a occasionally in the text there are references to the stack and heap, but they were never defined or discussed. This would be very confusing to someone not already familiar with the topic.
The only real complaint I have is from near the end. During the discussion on pointers one of the sections and a occasionally in the text there are references to the stack and heap, but they were never defined or discussed. This would be very confusing to someone not already familiar with the topic.
February 2, 2020
Too much generalization. It is good for those who don't know anything about data science and data analytics. The author just added a few pages in each domain (like an introduction section) to cover it up as a handbook.
I have shown this book to a few of my colleagues and they all said one thing "It is just an introduction, not even coverd the full basics."
I have shown this book to a few of my colleagues and they all said one thing "It is just an introduction, not even coverd the full basics."
October 19, 2020
It's a simple intro to Data Science, nothing too fancy.
If you are interested to understand what is data science as a beginner, it's great.
If you're experienced, I don't think you will find much in this book.
Also, it's waaaaay better than the other Data Science Handbook from Carl Shan, seriously, don't even try that one if you want to be a better data scientist.
If you are interested to understand what is data science as a beginner, it's great.
If you're experienced, I don't think you will find much in this book.
Also, it's waaaaay better than the other Data Science Handbook from Carl Shan, seriously, don't even try that one if you want to be a better data scientist.
July 4, 2020
read ch. 9, 12-14
January 2, 2022
Needs to have each chapter prefaced with a Python example. Oscillates too much between theory and applicable.
Want to read
May 25, 2018너무 입문자용이다.
Displaying 1 - 12 of 12 reviews