Introduction to Machine Learning with Python: A Guide for Data Scientists

Update: Geron's book is much longer than this one (856 pages vs 400) and almost two-thirds of Geron's is about deep learning. This review is comparing this book to the first third of Geron's book. This book only provides several pages on deep learning (neural nets), similar to the other models. I would suggest this book for a basic foundation and if you want to dig into the minutiae of deep learning read the last 430 pages of Geron. I read the Geron book "Hands-on Machine Learning with Scikit-learn & TensorFlow" before reading this book. This book provides a better start for several reasons. First, it is better organized. Second, the code implementations rely primarily on Python modules, instead of custom programming. Regarding the first, this book is set-up so that a reader can get an understanding of Machine Learning (ML) step-by-step from the bottom-up. For instance, supervised learning, feature engineering, and model evaluation all get separate chapters. The model evaluation chapter provides an entire section, as well as graphics, for understanding the roles of training, validation, and test data, which are probably the most important bedrock concepts in ML. In contrast to this, Geron throws you right into an entire ML pipeline in the second chapter. It's a mix of feature engineering, linear models, stochastic gradient descent, random forest models, cross-validation, grid search, and even object oriented programming for custom transformers! This might be useful for quickly understanding what ML is like in practice. If later sections of Geron then went step-by-step and elaborated on the second chapter, it would be great. Instead, for instance, the second chapter is randomly about binary classification for image data. You only get two paragraphs in the first chapter on cross-validation and validation sets, and a sentence or two later in the book. I had to go to Wikipedia to ensure that I understood it correctly and robustly. I wish I had read this book instead. Regarding the second, this book does not assume a heavy programming background. Most of the ML pipeline is taught through the Python module Scikit-Learn. This is useful because the programming does not distract from learning fundamentals of ML. In contrast, in the second chapter of Geron, there is object oriented programming code involving concepts like constructors and inheritance. For this book, the most sophisticated chapter at the end, which is on pipelines and which expertly explains why feature engineering should be performed during model evaluation, doesn't even go into this. Some reviews mention that the author uses an mglearn Python package that he wrote. It is true that when he uses functions from this package the code is concealed. Arguably, this prevents readers who aren't familiar with Python from getting distracted by code that is unrelated to machine learning (such as creating visualizations). At times I was curious about how some of the code was working in the background (it is all available on GitHub), but the book's job is not to cover all aspects of data analysis with Python (which would be a separate book). In summary Geron teaches more advanced topics interspersed with the basics without an entirely coherent organizational structure. This book has an intuitive structure that elaborates at length on core ML concepts. It doesn't overburden with code, but may leave computer scientists wanting a bit more.

This is a great book, and I'd say it is even great for those that are not familiar with python (you just obviously won't be able to run the code). For anyone with some basic understanding of linear algebra/statistics, the authors are able to present to you all the important (and sometimes subtle but significant) details, without the usage of equations, and more importantly, how they all relate to one another. All the concepts mentioned here are heavily backed with well thought of and well presented figures, in such a way that again I'd suggest you don't even need python to understand. If you do know python, loading the data sets and reproducing the figures is just a few lines of easy to understand code away (with the exception of the mglearn library includes which does some "plotting magic" for you. However, I believe each of them were appropriate. You can ignore them and make the plots in your own way, or just print the variables, it just may not look as publication friendly). Normally, I hesitate purchasing books that claim they may explain algorithms without the need of equations, and I expect them rather to be cook books of lightly and disjointly explained techniques (like an encyclopedia). However, I do not think such is true of this book. The power of scikit-learn is demonstrated and the algorithms behind them explained intuitively, and are referred as to how they fit together and complement each other. As with any introductory read, a supplement is needed from time to time and the authors' reference to Elements of Statistical Learning is a useful one (equation heavy). There are points in the book where the author defers to elements of statistical learning. I found these points suitable since further explanation would be out of scope. I read this book on my free time while on vacation, and much of the time I didn't have access to a computer. The concepts were so well presented that it was just a nice leisurely read. When I finally had time to access a computer, I was able to try the techniques on my data sets with some browsing back and forth through the book again, but otherwise with little effort. Finally, since I myself am a researcher, I would recommend this book to any other researcher willing to start delving into the world of machine learning. Further reading will always be necessary, but this book will give you such a good intuitive understanding and overview of the subject matter that you'll know what to do to proceed next, and how to do it without running in circles. Even better, you'll likely already have applied it to your research!

A really great guide to Machine Learning and the theory behind some key algorithms. This book is not exactly a "cookbook". There are examples to follow and you will build models, of course, but it is more about understanding machine learning than "doing" it.

I bought this book to help me get up and running quick for a project in an "Introduction to Machine Learning" independent study course. Of the books I bought for the same task, this was by far the most helpful for building practical machine learning applications. The book is a great introduction to the scikit-learn framework which, in my opinion, is an extremely elegant machine learning tool kit. Reading this book helped me improve the quality of the code I was developing for the project which dramatically improved the speed I could produce new results for the project. If you are looking for an extremely theoretical text on machine learning, then you might want to look elsewhere. If you are looking for a guided introduction to the "bread-and-butter tools" of a great machine learning framework in Python, buy this.

Informative and well-written

"Introduction to Machine Learning" comes with an exelent overview over standard techniques of machine learning. It focuses on the techniques and implementation in python using mostly the standard samples. The math side is sufficent for people who want to apply the algorithms and not explore the mechanics of the algorithms itself in depth. The lanuage is easy to follow and to the point. All chapter are nicely structured, ending with an excellent summary. I can recommend the book not only to people who want to implement the algorithms in Python but to everybody who want an introduction to machine learning.

Ótimo livro, está me ajudando bastante a responder questões de concursos.

Book is good price is cheap

The book is in greyscale and I can't follow the author's guide into different colors of an image. Really disappointed!

well written, easy to understand for beginners. Highly recommend it.