What do you think?
Rate this book
처음 배우는 데이터 과학: 통계, 수학, 머신러닝, 프로그래밍까지
데이터 과학자가 알아야 하는 거의 모든 것
프로그래밍 경험은 많지만 통계나 데이터 분석을 잘 모르거나, 반대로 이론은 잘 알지만 실제로 데이터를 다루는 프로그래밍 경험이 없다면 데이터 과학을 어떻게 공부해야 할지 막막하기 마련입니다. 이 책은 데이터 과학자의 실무에 필요한 컴퓨터 공학 및 프로그래밍을 자세히 소개합니다. 또 널리 사용하는 머신러닝 알고리즘에 대한 직관적 설명, 수학적 배경, 실제 사례를 다룹니다. 데이터 과학에서 필수인 시각화 방법과 도구, 데이터를 해석하는 데 필요한 확률과 통계도 다룹니다. 마지막으로 데이터 과학 업무 결과를 정리하고 소통하는 노하우를 소개합니다. 이 책은 데이터 과학자가 알아야 하는 내용을 빠르고 체계적으로 전달하는 최고의 안내서입니다.
프로그래밍 경험은 많지만 통계나 데이터 분석을 잘 모르거나, 반대로 이론은 잘 알지만 실제로 데이터를 다루는 프로그래밍 경험이 없다면 데이터 과학을 어떻게 공부해야 할지 막막하기 마련입니다. 이 책은 데이터 과학자의 실무에 필요한 컴퓨터 공학 및 프로그래밍을 자세히 소개합니다. 또 널리 사용하는 머신러닝 알고리즘에 대한 직관적 설명, 수학적 배경, 실제 사례를 다룹니다. 데이터 과학에서 필수인 시각화 방법과 도구, 데이터를 해석하는 데 필요한 확률과 통계도 다룹니다. 마지막으로 데이터 과학 업무 결과를 정리하고 소통하는 노하우를 소개합니다. 이 책은 데이터 과학자가 알아야 하는 내용을 빠르고 체계적으로 전달하는 최고의 안내서입니다.
420 pages, Paperback
Published February 20, 2018
32 people are currently reading
148 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