Python Machine Learning: Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow 2, 3rd Edition Paperback – December 12, 2019

I have not finished this book and I just reached chapter 16, but here are my key takeaways for this book:1. Everything before chapter 13, before the book fully gets into deep learning and TensorFlow, are great. With already some background in python for data analysis (I have also taken the Andrew Ng's Coursera course on Machine Learning), this book supplements my knowledge greatly. The biggest highlight I would say is that it introduces you JUST ENOUGH concepts for you to understand how everything works. In addition, the contents are structured really well, too. If I were to rate this section of the book, I would give 10/10 although it would be better to have some exercises, you can always practice using Kaggle datasets.2. Since chapter 13 when the book gets into deep learning, things get worse a little bit... The contents are still good in general, however the connections between contents might not be the case. The connections between contents are important for new learners because that helps them to understand how A leads to B and then leads to C. Here, I found the actual TensorFlow documentation a really good material to review along with the book. After reviewing those documentations, coming back to this book allows me to comprehend much more than reading the first time. In addition, if you are not careful enough, the deep learning sections also seems to have accuracy issues with its contents that could confuse people. Even though I have not finished the book, I would give 9/10 for everything I have read for deep learning.

I really wanted to like this book, but the printed text is unreadable. Smeared, blurry, and faded beyond legibility. Looks like a washed out photocopy of a page printed on a 1980’s ribbon dot-matrix printer.. but a printer that was partially out of ink. There’s no excuse for this. No reputable publisher would ship material this poor.Update: Was contacted by Amazon rep, and new book with corrected print was shipped free of charge. The replacement text looks great. The book itself is great.. well written, easy to follow, and contains a lot of good information.

The book is good but the cover is a little dirty. There may be a defect in the preservation of the book.

I blazed through this book in the runup to a new job involving ML, and it was the perfect text for the job. Not only does it include information on the code side, it also has substantial theoretical fundamentals. I feel like, for the first time, I really understand what SVMs do, or how decision trees are trained. I'd recommend this volume to anyone who, like me, had substantial experience programming in Python and would like to dive into scikit-learn.

I haven't finished reading yet. I am just about halfway through. I like the fact that this book goes into the underlying math and explains concepts very well. The author provides links to his pdf notes where the details are too much of a digression. Rather than using higher-level machine learning libraries like scikit, tensor flow and keras, the author walks through the algorithms in python and numpy. Overall, this book has the right balance between being hands-on with the code and explaining the math. I am happy I got this.

Raschka and Mirjalili's book is required reading for my class in Machine Learning. My students like the clear explanations and illustrations with coding. As a machine learning practitioner, their book is never far away from my computer as reference material. I would recommend that the authors introduce PyTorch and BERT models, among other elements, in their next edition.

I have started to read the first chapter and I have found that the book code just don’t run if you don’t have the correct packages in the Python interpreter. Use the following packages versions for python 3.9.13:NumPy 1.21.2SciPy 1.7.0Scikit-learn 1.0Matplotlib 3.4.3pandas 1.3.2

The book is very comprehensive, up-to-date, and keeps a nice balance of intuition and mathematical rigor.