Today, there are more than a million ways to learn any new skill you want. You can head to youtube and look for videos, you can go to Medium and read some useful articles, or you can listen to a podcast and learn while doing something else.
But, one of the learning methods that existed since the beginning of written languages is Books. Books – in my opinion – are a gem of information, no matter what you want to learn, chances are, a book or books is talking about it. Books have been one of my favorite and trusty sources of information, old or new.
They might not be everyone’s preferred method of learning, but we can all admit that, at some point, we all went back for a book to check for information. Books are not going to teach you a skill magically; just like any other form of learning, you need to put in the effort and have the willingness to learn so you can make the best of any book or learning resource.
Data Science Lingo 101: 10 Terms You Need to Know as a Data Scientist
Data science has – arguably – what feels like an infinite number of learning resources online and off. And you can only predict that the number of resources will grow larger as the field grows bigger. Over the past years, there were so many data science books published in almost any language you’re comfortable reading.
In this article, I will propose to you 5 new data science books published in 2020 and 2021 that I feel are very promising for you to read whether you’re new to data science or you’ve already been part of the field for a while.
№1: Data Science: The Complete Guide To Data Science For Beginners By Sabra Deal
It’s undeniable that data science continues to attract new and intelligent people to join every day. And honestly, I don’t see that slowing down anytime soon. The first book on this list is targeted towards beginners in the field.
My favorite thing about this book is how light it is when the main information you need to learn is explained over only 62 pages. This book is not meant to give you all the details you need to become a data science master. Rather you can think of this book as a detailed, high-level data science roadmap for anyone confused about what data science is and what it takes to become a data scientist.
The book covers the main language and terminology used in data science, from maths, statistics to Machine Learning and artificial intelligence. Basically, this book is a great first step if you’re completely new to data science.
№2: Measurement and Data Science By Gábor Péceli
Data science is a vast field, with applications in almost all aspects of life, from the simplest one of recommending a book or a movie to life-critical applications in medicine and healthcare. The data used in any data science project is collected differently based on the application.
Some are collected from sensors; others are collected from the web. Because of this variety of sources, there are different ways of performing measurements on the data. Measurement and Data Science covers all the basics and more about the topic of data and measurement.
The different chapters of this book go through the research conducted by the department of measurement and information systems in Hungary and summarize the results of combing classical and theoretical measurement with data processing. This 371-page book will get you familiar with all you need to know about measurement in data science.
№3: A Tour of Data Science: Learn R and Python in Parallel By Nailong Zhang
Two of the most used programming languages in data science are Python and R. They are both useful languages with a lot to offer to the field. However, in the flow of a data science project, some tasks are more efficient if you use R to perform them and vice-versa.
Writing and understanding code written in both languages is a useful skill for any data scientist to obtain. The next book on this list allows you to learn and use both R and Python in parallel, saving you a lot of time and effort if you decided to learn them independently.
This 216-page book will take you through learning both programming languages, focusing on data science rather than abstract and general syntax. You will learn how to perform statistics, optimize, build predictive models, and more in both languages simultaneously.
№4: Data Analytics Guide For Beginners By Hosea Droski
As I always say, data science is all about the data, and one of the essential steps in any data science project is data collection and analytics. Data Analytics Guide For Beginners focuses on teaching you how to take raw data collected from different sources and extract useful information from it.
Data analytics is a critical process for your project to make the correct prediction and help your client or business make correct decisions. This book will teach all the basics of data analytics, from data mining to dealing with big data and visualizing the results.
Moreover, the books cover an important aspect of data collections, such as web scraping and using machine learning to collect data and form alternative datasets. Finally, the book goes a bit in-depth about data management and business intelligence, all in 124 pages.
№5: Linear Algebra and Optimization for Machine Learning By Charu C. Aggarwal
One of the things that may drive people away from data science is the fact that it’s built on fundamental algebra and probability concepts. The fear of maths is real, and it was why many people would tell me that they don’t want to become a data scientist because maths is too hard.
But, math is the core engine of almost all technological fields, not just data science. One of the main usages of maths, more precisely linear algebra, is during the optimization of machine learning models. Linear Algebra and Optimization for Machine Learning covers all the linear algebra you need to optimize your machine learning models efficiently.
This book goes in-depth about the application of linear algebra in machine learning optimization. It covers how to perform many important applications such as singular value decomposition (SVD), graph analysis, matrix factorization, and more. It also covers why machine learning models need optimization and when and how to do so. This book is the longest one on our list, with nearly 500 pages.
Takeaways
When I first started my postgrad studies, my supervisor had the largest collection of books I had ever seen in one room. The books were not only on the shelves, but everywhere. In fact, he found a way to use books to keep the privacy of his desk. The books formed somewhat of a maze from the door to his chair.
I remember asking him once, why do you not donate old books or just use digital ones. He said, for me, books are not just a way of learning a topic; it’s about learning a new personality. It’s like you’re seeking a peek into the author’s mind.
Growing up, books – both prints and ebooks – have been one of the main constants in my life. I still trust the information I gain from reading a book more than the ones I obtain any other way. Today, I listed 5 books that I believe are very promising, new data science books that I believe everyone should give a read.