Confident Data Skills: Master the Fundamentals of Working with Data and Supercharge Your Career (Confident Series)

This book explains Data Science with the lens of a career strategy. The author, Kirill Eremenko, has created many of the most popular and highly rated data science online courses and has a very popular podcast focused on careers in data science. I found in the book a lot of wisdom distilled from the author's own consulting career as well as from hundreds of hours of podcasts interviewing many successful data scientists. The format of this book lends itself for an audiobook even though it provides many details about complex concepts, data analysis methods, and tools. The book presents a very refreshing and optimistic future for those looking into entering the field or using it within their industries.

Part 1: It first introduces data, exposes its commonness, how it is being used by companies in the background, its exponentially growing nature, exposes how data scientists use and present data, and then provides advice on how somebody from outside the industry can approach entering the field.

Part 2: The book introduces “the data science process”, including wisdom on framing the question within context and scope, then strategies and tools for recognizing, preparing, cleaning data, and finally analyzing it to produce relevant answers. It provides an excellent overview of the methods for analyzing data including statistical, machine learning, and artificial intelligence. It also presents examples and guidance providing intuition about how these methods provide answers and apply to different data science problems.

Part 3. Provides closure to the “data science process”, by describing visualization concepts while providing beautiful examples and insight into effective strategies for presenting results. The last chapter then imparts tactical and strategic intelligence in entering the data science field regardless of the industry. As with the podcasts, this book somehow manages to include personal growth wisdom very relevant to data science.

Kirill is always such an amazing storyteller. I found about Kirill by researching courses on Udemy on R, SQL, Python, and basically anything Data Science related. His podcast “Superdatascience” and his LinkedIn profile allowed me to understand more about how Data Science and how it is actively changing industries and the World. I learned what kind of skills that are required and in demand, and how to communicate better with stakeholders on the importance of data science.

This book is a great resource for a beginner, someone who is passionate about data science. This book does not go into details on the high-level coding aspects of data science or elaborate on the different models that data scientist uses to tackle problems in their respective fields. Its intention is to inform and create a solid foundation for the introduction into Data Science. This book feels like a textbook and an autobiography of data scientist, I believe this adds a more personal touch. It is relatable and adds value to the book. Examples include real case studies or problems Kirill and other data scientists faced in their career, how they approached it and the solutions they deployed to solve them.

I had fun reading this book. It made me more passionate about learning more about Data Science and how to be creative in problem-solving. This book will point you in the right direction. Kirill is always such a passionate guy and you can tell that he put a lot of hard work into this book. I highly recommend this book to anyone seeking information or a career in Data Science

Cheers, and happy coding

This book is a simple introduction to what to do to get your career started in data science. The author did a great job of covering the relevant skills needed to be successful in a data science-related career.

Easy to read. Probably suitable for beginner in the data field.

I received an advance copy of this book. Based on my quick read of the book I found that it covers a broad range of data analysis use cases. The author goes beyond a categorical listing of various data analysis techniques suggestions for application. He provides the content in the form of case studies which describe what is being investigated, the data necessary to support the investigation, and suggests an analysis technique and the steps to apply it. Now that I have quickly read the book, I intend to go back and read it a couple more times.

If you have taken Kiril's courses, this book will feel familiar. I use it as a refresher on certain topics.

Great for anyone interested in a data science career

Very easy to follow and considered a great reference for people who wants to know more about the field without getting to the scripting part.

“Confident data skills” provides a bird’s eye view of the data science process, in an easy to understand manner without presuming any mathematics/statistics background. Also, it has a broad approach without assuming any domain specific knowledge.

Real life examples from multiple different fields are presented as stories to illustrate applicability of data science, including data driven programming by a television service; development of algorithms and framework to support voice recognition, even before such a technology could be integrated into smart devices; and using Moore’s law to help understand the astonishing change in pace of human genome mapping.

The author has gone into a little bit more detail in the 2 chapters on data analysis. Many of the common machine learning algorithms including trees and forests, k nearest neighbors, naïve Bayes algorithm, k-means and hierarchical clustering are conceptually and clearly described. Besides providing a good understanding of what these algorithms do, the author is very likely to stimulate the reader to learn more. I think the author must have been torn between the desires to include more detail vs. keeping a reasonable size, since some of the other algorithms like SVM/SVR, GAMs, or resampling methods have been left out. Also, an introductory chapter on programming languages commonly used for data science would have been useful.

The chapter on data visualization is also very useful. Again, author has used real life examples, both historical and contemporary, to showcase different types of graphs. He has also managed to mention the concept of layering as emphasized in the “grammar of graphics” without going into details. The introduction to color theory is particularly interesting. Author has managed to convey the essentials of using a color wheel to help customize your palette, in a nutshell.

Overall, it is a very good book for someone who wants to get an overview of data science process, from formulation of the question, data gathering, organizing/cleaning, visualization, and analysis, all the way to effectively presenting data as well as conclusions from its analysis. It is perfectly suited for people who want to learn “what does data science involve” rather than someone who is looking to learn the nuts and bolts of “how to practice data science”. It will also be helpful for professionals from multiple diverse fields who work with data scientists, to better understand the process.

(Author received a complimentary copy of the book.)

I've read almost every popular book on data science, but this one caught me by surprise. I counted only six simple formulas in over 200 pages of the text. I'm used to seeing that number on each and every page of a typical book on the subject.
So how is it possible to explain "science" part of the data with almost no math? Well, that depends on the target audience. The book is a good introduction to problems people working with large amounts of data face, and some of the approaches taken to solve them. And it's all explained in layman terms. I'd even venture to call this book a popular science on data science. I doubt, however, the book would be compelling for people with engineering background, and aspiring data scientists with intent to do software and algorithm development.