Amazon Customer Nov 16, 2020

I received this book as a sample to review and really enjoyed reading through it. The approach is more practice than theory, which is good if you are the learn-by-doing type. That said, the author does include enough of the theory that the reader will still come away with an understanding of the way the various algorithms work.Things I liked about the book: The book uses python -which is industry standard for implementing machine learning these days. In addition, the author introduces several of standard data science packages (sklearn, matplotlib, pandas) and mostly sticks with these to perform the various analyses, which i think is good in that it doesn't require to reader to install and learn the syntax of a bunch of new packages for every topic covered. Some basic package-management tools (pip, conda) are also described. Another definite plus of the book is that it goes through code to implement the gradient descent algorithm and to build a decision tree from scratch. Seeing the actual implementations will definitely help the reader understand these algorithms far better than a simple summary. Finally, the book contains a number of exercises that the reader can go through to ensure that he/she has a good understanding of the material. The given problems tend to build on the material that was just presented, so that the reader can not only check his/her understanding, but build on it as well.Overall, the book is well written and covers a good array of topics, from data exploration to plotting to model building to performance metrics. The author does a good job of focusing the book to cover most major topics in supervised learning. I would recommend this book to anyone with a basic understanding of Python that wants to get a hands-on overview of supervised learning techniques.

Amazon Verified review

lisa May 27, 2020

I got this book as a sample to review. I was honestly surprised with the way this book was written and put together. Each section was well written and really kept the audience in mind. This book uses Python, which, was a great introduction to using Python over R. I have always wanted to use Python more, so this book really took me through examples, applications, and understanding of using Python for machine learning. What I really loved about this book was the step by step approach and not making the explanations overly detailed and theoretical. Machine learning is a difficult topic to cover, so it was great that this book really took you through each process of understanding machine learning via a step by step process. If you are in the process of learning machine learning and need a supplemental guide or even interested in learning about Python and/or machine learning, get this book. You will walk away after going through the book appreciating the machine learning process and Python more. Happy coding!

Amazon Verified review

jane_thompson Jun 12, 2020

The chapters are rich with sample code for beginners to follow along with the authors. A strong emphasis is placed on business and data understanding before jumping into any model building endeavor. The authors provide an ample number of activities for the users to try on their own, and complete solutions are provided. Experienced readers will benefit from thorough coverage of the math behind least-squares optimization and gradient descent. This is almost certainly the best way to learn new concepts -- by first trying them for yourself and having a resource available for guidance in the event of any questions or confusion. More experienced readers will almost certainly learn new tricks regarding optimizing visualizations, especially with regard to model evaluation. For readers will a lighter background in topics such as regression and classification, this book is a phenomenal way to tap into the mind of an experienced machine learning practitioner and see how they would go about defining, setting up, and analyzing these problems. I would highly recommend this book!

Amazon Verified review

Akhilesh Kumawat Mar 10, 2020

This is one of the best data science books I have come across. It really removes all the noise and helps build a step by step understanding of the subject matter. I wholeheartedly recommend the book for both the amateurs and the experts as the book starts from basics and goes on to cover the complicated topics in an effortless way for the readers.

Amazon Verified review

Marleen Dec 15, 2020

The book can be divided in three logical parts: basics, supervised learning models, model evaluation methods.In the beginning of the book the authors talk about the programming fundamentals necessary for supervised learning. Then, the next chapter is about explanatory analysis - so basically all the analysis you can perform without using any supervised learning, mainly using visualisations and "looking" closer into your dataset. And lastly, what I would still consider "Basics", two chapters about Regression and Autoregression.In the second part "supervised learning model" the authors introduce different types of classification models (approaches like Regression, KNN, Decision Trees, Neural Networks) and in the chapter after some more advanced techniques like one hot encoding, bootstrapping, stacking. The last chapter will teach you everything you need to know about model evaluation.The book takes Windows, Mac OS as well as Linux environments into account, which I like a lot and each chapter is also accompanied by code examples and exercises which is very cool. Other than that, the structure of the book makes a lot of sense to me and I found it easy to follow along and understood all explanations and tasks.Regarding the audience of this book: Even-though there is a part that introduces you to Python programming for supervised learning, I would recommend this book to people that know either a different programming language very well or the basics of python already. Else it might be a bit too hard to follow along. But other than that I think the book manages to give a good introduction as well as advanced techniques for supervised learning. Advanced users could start reading chapter 5 for example. But repeating some old topics like regression might also be a good refreshers for some of the advanced users. Overall I really enjoyed reading the book and especially doing the exercises, they steepened my learning curve tremendously. Thanks and keep up the good work! An unsupervised edition would be more than welcome ;)!

Amazon Verified review

The Supervised Learning Workshop: Predict outcomes from data by building your own powerful predictive models with machine learning in Python , Second Edition

What do you get with eBook?

Key benefits

Description

Who is this book for?

What you will learn

Product Details

What do you get with eBook?

Product Details

Frequently bought together

Recommendations for you

Customer reviews

Filter reviews by

People who bought this also bought

About the 4 authors

FAQs

The Supervised Learning Workshop: Predict outcomes from data by building your own powerful predictive models with machine learning in Python , Second Edition

What do you get with eBook?

Contact Details

Billing Address

Key benefits

Description

Who is this book for?

What you will learn

Product Details

What do you get with eBook?

Contact Details

Billing Address

Product Details

Packt Subscriptions

Frequently bought together

Recommendations for you

Customer reviews

Filter reviews by

People who bought this also bought

About the 4 authors

FAQs