I have had a really pragmatic approach about reading them - only focusing first on parts relevant to my projects.
# An Introduction to Statistical Learning (ISL) / The Elements of Statistical Learning (ESL)
I focused on chapter 8-9 of ISL about Tree Based Methods and SVMs, two algorithms I used for my dissertation project. I found ISL to provide very clear explanations of the algorithms with just enough mathematical formalism.
I have a good math background so ESL was interesting to go through. But I am more of a practical person, and I found ISL to be more suited for me when it came down to working on my project and supporting my choices.
# Python Machine Learning
Really great hands-on book ! Sebastian Raschka manages well to guide you through all steps of a ML project data: pre-processing, feature engineering, model selection... - all the steps are defined and covered with practical examples.
I strongly recommend this book if you are just starting out with ML and feel "lost" about how to start your own project.
# Taming Text
I decided to use text data I had available for my dissertation project. However, half-way through the book I realized my dataset was to small to apply any of the techniques described there. I still like the practical approach and in the end the book gave me a good idea of what can be done with text.
# Advanced Analytics with Spark
I picked this book once I started working on the implementation of my project into production - we use Apache Spark (Scala) at work.
It provided me with a good introduction to Spark BUT it's based on the RDD-api and as stated on Spark website: "As of Spark 2.0, the RDD-based APIs in the spark.mllib package have entered maintenance mode. The primary Machine Learning API for Spark is now the DataFrame-based API in the spark.ml package."
I'm now mostly relying on Spark Doc / API, I'm not aware of any up-to-date books yet :)
The ebook is free online, you can buy from Amazon & O'Reilly too.
Could you add your personal reason for keeping these books on your shelf? That would make the page more interesting, and maybe help you out with your job search, as it will give an insight into your thought processes.
I'm also halfway through the Deep Learning Book now. I'm really enjoying it. I got turned on to the book because there were a large number of people and reading groups at work (LinkedIn) that had organized around the book when it first came out in the html format a few months ago.
If you look at the academic lineage of many of these authors, it will also help you understand how they get stuck into little biases.