Hands-On Unsupervised Learning Using Python: How to Build Applied Machine Learning Solutions from Unlabeled Data 1st Edition, Kindle Edition

So currently I work as a data scientist, but my main focus is supervised learning and time-series analysis. I got this book to help me brush up on some skills and learn some new ones. This book runs with the suggestion that you already have a good understanding of python, both in terms of general use and data cleansing. Not only does it walk you threw some projects, but if you take time to break down the code and attempt to understand the “why am I using this” instead of “what do I have to replace for my own job” you will learn a lot more.Personally, I love these kind of books because it shows you multiple ways to test a model, recommends you run multiple models, and even use some underrated features of python. If you have a decent foundation, in python and stats (optional), i highly recommend this book.

I've been looking to add more machine learning to my developer toolbox and this book was the absolute best thing I could find on the web. The author is NOT some professor who makes his living writing books, but a man at the edge of the space who has fought for the knowledge and experience in the real world.I love how the book takes you from ground up implementing real systems in python. Not just unfinished snippets to show you how the m/l packages work (you can read their docs for that!) but he fills in the rest of the bigger picture which is "how do i make something that actually accomplishes a task in the world" your college prof probably has never had to ask that.At $50 it's a steal, pickup a copy and don't look back.

I focus on supervised classification in a domain specific area at work.. and would love to find an unsupervised labeling scheme that gets me at least partly to a properly tagged dataset. We don't get the IRIS dataset in the real world. This book had several helpful examples which I tossed in the development hopper as preliminary ideas for better feature engineering. I look forward to future versions with Pytorch and / or Snorkel examples.

A very nicely written book. I really enjoyed going with some of the extended examples. I haven't finished it yet, but it's very enjoyable so far!

As several mentioned before me, this book is a terrible disappointment and I would say a kind of scientific fraud. The technical explanations are poor, several severe mistakes are included, the code is poor. More problematic is the way that the author works : on each data-sciences challenge introduced in the book's chapters, he is accumulating methods that DO NOT WORK and he knows it, as he indicates the poor metrics obtained by his models. In a sense, this book is a succession of modeling failures. So it is a terrible conclusion : writing a good book about Unsupervised Machine Learning needs a lot of ... Supervision from the publisher in order to avoid such catastrophic result.

I really wanted to write a higher star for this book. There just isn't enough meat regarding the topics I was looking for, specifically metric evaluation in a completely unsupervised situation. It's kind of cheating if you throw in a target variable and compare the predicted cluster to the real cluster. Where's the metric evaluation when you don't have a target variable? I haven't seen the section or it's missing. Plus nearly the first hundred pages of the book is going over supervised learning for some reason.

As an analyst trying to get more into the world of machine learning and python, I thought this was a great resource. I've been briefly exposed to a lot of the content in this book before, but this book does a great job of breaking concepts down with clear code examples and visualizations. I'd recommend this to any individuals or analytics teams trying to expand their knowledge of machine learning.

This is a must-read for anyone interested in building AI applications. The introduction and conclusion are clear and informative, and the main content and code examples are forward thinking. All industry professionals, from data scientists to executives should read this book.

Concepts had been well explained

This book is exceptionally well written and very complete. It’s definitely in my top ten picks on data science.

Muito bom!

It is good on the unsupervised learning but the issue is the book is printed black and white. There are many plots and there is no point understanding them where all look the same. The colored codes are difficult to read in many places. I returned the book and bought the electronic version.

Compared to hands-on machine learning with scikit learn & tensorflow this is relatively poor.A lot of explanations don't have graphics to help explain things - I already know the basics of some unsupervised learning but the RBM description was not helpful in chapter 1.Not sure how much proof reading went on as in chapter two the recall and precision formulas both equate to the same things.Finally I found the important bit of code snippets not explained and continually had to look at the respective packages API to see what it did. Also loads of unnecessary imports were given that were not necessary eg time series chapter and all the tf and keras ones - this really obscured understanding.