Python Machine Learning - Second Edition: Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow

This book is excellent for the following demographic: People who already have a decent level of skill and experience in statistics who want to: - 1) Elevate their understanding of ML techniques without absolutely breaking their skull on dense theory - 2) Learn how to implement the algorithms in Python and gain moderate proficiency in sci-kit learn I would say it's not a beginner's book, but more for intermediates. I am half-way through and find it a little challenging, but definitely attainable. This balance I consider to be putting me right in the sweet spot for learning. To judge whether you're a good candidate for this book, you can compare your experience and skill to me : I started this book after earning a PhD in the social sciences, which basically gave me good coverage in inferential and applied statistics (T, F distributions, p-values, confidence intervals, linear regression, one-way and factorial ANOVA, PCA, etc.). I also took a machine learning graduate course at my university and a few online courses in introductory ML for R. All of this background gave me solid grounding in statistics. With all this I still find this book somewhat challenging, but definitely not too hard. I'd say without my background I would find this book hard to get through. There is linear algebra, concepts like minimizing cost functions, bias/variance tradeoff, learning from errors, etc. So, if you are just starting out or reading the previous sentence and don't know what I'm talking about, I would recommend learning more stats fundamentals before starting this. After you gain some proficiency in stats, come learn this book and elevate your understanding of the algorithms, add nuance to them, integrate them into your mental conceptual structures more fully (e.g. you'll know more nuances of ML, e.g. which subsets of algorithms are preferred for controlling more of the bias, variance, how random forest is basically bagging with a twist, how adaboost's treatment of classification errors has kind of an element of perceptron implementation, and many more).

This book will stay on your reference shelf for years to come! The authors clearly have taught these materials many times before, and their significant mathematical and technical prowess is delivered using a very approachable style. This book seems best suited for someone who wants to sit down and begin to apply Python Machine Learning to a problem that they already know they have. It's not particularly an "intro course to M.L.", but it contains enough details that you could easily follow along and learn how to use the various tools and techniques of the field if you've never seen or heard of them before. The copious notes scattered throughout this book are pure gold, mined from the obvious experiences of the authors while working in the field. If there ever is a Machine Learning equivalent to the venerable "Forrest M. Mims Engineering Notebook" for electronics, I feel these two authors could write it! Once you use this book to work on your current M.L. problem in Python, you will find yourself returning to it as a reference for other problems in the M.L. space. Its lucid explanations will help reinforce the topics presented, and cement your understanding of the materials. This book will get you writing Python Machine Learning code to work your current M.L. problem in no time flat!

Book gives a good overview of how to tackle a learning problem. Preparing learning data and evaluation of learning model. Witch python libraries to use and a lot of examples. Was very useful l for me Thanks guys

(I own the 1st edition, and was given early access to a pre-release PDF of the 2nd ed. My paperback copy just arrived.) This is the best book I've seen for professional software engineers to bootstrap themselves into Data Science, Machine Learning and (with the 2nd ed) Deep Learning. It makes heavy use of the scikit-learn library; and the latter chapters give an excellent high-level overview of TensorFlow. Books in this space can often feel either too basic or too academic. Not this one -- for me it hits the sweet spot of explaining and doing. What I love about Raschka's writing is how he builds up from theory to practical code. It lays out the concepts, math, and code together which helps comprehension. So, if you happen to be rusty in math, like me, you can look to the code to help explain what the equations actually do. The chapters of the book build up from each other; so many of the examples feel like they can be used as recipes for building your own custom models.

I found this book to be very clearly written and also very informative since in addition to providing code examples it tried to illustrate the basics of theory behind what makes machine learning work. The explanations were mainly done by showing examples of data on a x-y plot and how the different techniques separate the data to make a decision. This is a nice way to reduce the complexity of explanation and getting lost in the details of the mathematics and programming syntax etc and to get at the heart of where different algorithms have strengths. This is review is from the perspective of someone who knows a little python and had little knowledge of machine learning, but has kind of seen neural nets and regressions used in different applications over the years. Part of its usefulness to me is that it gives me a nice way to explain machine learning to non-scientists.

Very steep learning curve. I almost gave up in chapter two at perceptron but since that algorithm is the foundation of all I spent a whole week to understand it. The code the author uses is pretty much optimized and it was not in sync with the mathematical introduction. But the first 30 pages are absolutely neccessary to read and understand deeply in order to move on. After page 30 it became a little faster to proceed with the book since topics from page 30 - 107 are mostly the extension of the perceptron. At page 107- 160 I am already accustomedto the authors style and to the books logic so it is now quite effective to read and digest the models. And that is where I am at the moment. I gave this book 5 stars since I wanted a high quality ML and python book which leads me through the models in a step-by-step way no matter how hard it is mathematically or programmtechnically. And I got this. negative: The pdf version has color pictures which is nice especially for multiline charts ( like page 212) where the b&w book just visually flat and some chart elements cannot be identified.

It is helping me learn TensorFlow (with Keras too). Although there are web pages that can do this it is nice to have it al together. Like all Packet books down loading the errata and sample code was not as easy as they make it sound.

I am a relatively new at python, and have never been associated with some of the libraries in the book. The coding was almost immediatly over my head but was realatively easy to figure out. Just going throught the coding and analyzing what was going on has taught me a great deal (much more than I every thought that I could) about python and the machine learning/math libraries. If you truly want to learn, and are not afraid to put in some extra homework, I highly recommend this book.

It is a great book. Read it and enjoy the ideas.

Le livre trouve un bon équilibre entre l'application du machine learning en python et les raisonnements mathématiques derrière les algorithmes. Il est très complet et je le conseille pour ceux qui souhaitent explorer le sujet en profondeur. Le code est mis a disposition pour téléchargement ce qui permet de tester directement ce qui est expliqué.

This is one of the best beginner's books out there. If anyone wants to start ML they have to go through this book, although the DL part of the book uses TF version 1 which is not used anymore. You will also learn a lot of numpy, pandas and matplotlib features

内容が近く、おすすめです。早く購入すればよかった。

Nice book that constructs a bridge between theory and implementation. It doesnt include detailed theory. But it mentions many methods that can help one know the knowledge framework that can facilitate future study.