Think Like a Data Scientist: Tackle the data science process step-by-step

The BEST data science book!! Anyone who is interested to become data Scientist or already working in the field please read this book. I have read so many data science book but none of them explain this well. One of the best investment!!

The content is good enough, dosen't go so deepIs good to get an very hight overall idea of the subject and subjects evolved in it

This book describes exactly what it’s like to look at things from a data scientist perspective.

Thank you for this book!

This book really puts into perspective the stages of projects in data science, how they fit together, how you go from one to the next, and what are the important questions to ask at each phase. Insightful and thorough, beginning of a data science project through to the end.One thing that this book seems to do that others don't is really get to the "why" of doing things in data science. It's doesn't just say "let's apply this machine learning program" but actually discusses the possibilities, with strengths and weaknesses, and essentially let's the reader decide what to do, with lots of guidance. It feels very deliberate and careful, which I thought was good.Other reviewers are right, though, that it doesn't cover much advanced technical stuff, so if you're looking for that, this book isn't for you. I think that wasn't the point of this book, though. It's more about how to think about data and using it to solve problems and achieve goals through a process.I like the writing style. It's a little like stream-of-consciousness thoughts maybe could be organized better, but it really gives the feeling that you know what a data scientist should be thinking. It's actually kind of fun to read, at least compared to other software books. I do disagree with one reviewer's comment that this book doesn't contain much new information. I couldn't find most of the contents elsewhere, which is why I bought the book. Now I feel way more competent talking to my data science colleagues about what they're doing, and I'm probably a better manager, too, since I understand more about it now.Overall, good book about process, goals, concepts, thought process, priorities, and not so much about how to do complex software development. Probably good for beginners, non-technical folks, as well as people who know how to write some code but don't really know where to start with data and data science (like me).

I felt that the book lacked depth and it was just a collection of freely available material if one were to google on how to become data scientist. The book sort of organized the context for someone not to be all over the place and walked the reader starting out in the field of DS, but for someone who already has some experience in DS field this book would be too basic, so feel free to skip it.Many examples that were given in the book (enron dataset, etc) are good examples and the ones that are generally used, but I wanted to see something new. So once again, I feel that this book is a collection of material that can be obtained freely off the web, all it did was to put it in one place for you to read. If you are just starting in the field of DS, then this book would save you time by having everything fundamental for you to read, however if you spent any time with DS already, much of the book would be something that you already saw before.

This is a great intro text to the field. The examples are useful, and the informal writing style makes the subject accessible to anyone with a basic math or engineering background.

It gives a very broad overview instead of deep dive on technologies, I found it's very boring to read this book.

Most Data Science / Machine Learning books are technically demanding – this is not the case.But not technical doesn’t mean not important.The author has a deep knowledge of the topic – with “wisdom” (see below) that you rarely hear from practitioners, let alone academics.Highlights:Page 18: Data Scientists / Machine Learning Engineers (DS/ML) think different that developers.Page 24: How to pose a question that shows you can listen to your customer/boss.Page 71: Pretend you are an algorithm ☺Page 87: Why it is so important to stay “close to the data” – this alone is worth the bookPage 87: Not many experts would admit the following! “Many complicated algorithms might be understood in theory, but each has so many moving parts that we can’t possible comprehend all of the specific pieces and values……”Page 92: Always worth remembering, even though your algorithm might not care: check your assumptions about the data / distributionPage 96: Brute force for DS/ML: look through your data manually ☺Page 103: Why you should start with a simple algorithm.Page 164: Finally an expert who understands the link between DL and feature engineering.Page 167: When you should use Excel …we often neglect it or don’t want to admit it that the world’s number one data analysis tool is Excel.Page 202: I enjoyed reading relational vs. document oriented databases.Page 206: when to use databases and when not – rarely covered by experts.Page 211: finally an author who dares to state the misconception of big data – and what it really is.I would recommend it for any DS/ML/DL for a technically light reading – e.g. as a break when you think your head explodes on something complicated.