came across this years ago but found the libraries to hard to install (great book though)... excited to see the setup.py file, and that it appears to be working well

The book has well written knowledge and resources for this subject. Hard to find so much structured information in one source. Thank you.

The book provides a clear and practical guide to demystifying complex ML models. The book adeptly navigates through interpretability techniques, making them accessible to both beginners and seasoned practitioners. Serg skillfully balances theory with real-world applications, making this a valuable resource for anyone seeking a deeper understanding of model transparency in the ML landscape.Bonus: there's a GitHub repository with all Python exercises covered in each chapter, making it hands-on and practical.

This book can be compared to a new pair of shades. After you read it, you will look at all your pre-built and yet to be trained models in entirely new light! I guarantee it.When this book came out, I actually thought I knew its subject matter well. Alas how naive I was! After reading the first two chapters of “Interpretable Machine Learning by Python” by Serg Masis it was clear to me that my entire knowledge of interpretable ML could be compressed in just those 2 chapters. There were still 12 more chapters and over 500 more pages to go! Thats how little I knew of Interpretable ML. So you can imagine my astonishment when the more I read this book, the more I had to put it down and actually try some of the fantastic code examples that Serg had put together to learn how to look at the models I had built in new ways. It was like have a cool new pair of shades that you wear around not just to impress friends but also to look at old places in new filters.Interpretable ML is the holy grail of all practitioners in this “magic art” we call ML. It’s what every Data Scientist hopes to do after building their best performing machine learning model. But many of them do not know how because they may have built a black box model, while hoping that they would discover tools later to explain how the model actually worked. Luckily for such a data scientist, a book like the one that Serg Masis has created will immensely help.Serg Has painstakingly put together what i believe is a “tour de force” that will find a place in every data scientist’s book shelf. This is a must have book if you want to stand out as a data scientist in your organization or group. Let me tell you why.While most books on interpretable ML focus on techniques, such as shop and lime, they do not help you understand the huge amount of context and learnings needed to apply them effectively to your use case. Serg shows you how by taking real world datasets with 10K or even a million samples and And breaks down each one of them, showing you how to build models, as well as break them apart to reveal what they have learned and how they could be understood by non-technical users. This is a key skill that you have to master as a data scientist. For that alone, this book is worth the money.I learned so much about the wealth of techniques that were available for interrogating models that ranged from the simplest linear model to the most complex transformers we see today. I also found new models such as RuleFit and new techniques like Saliency Maps that I had never heard of. Serg never tires of bringing newer and newer lenses to examining your models!Let me warn however about the size and scope of this book. I thought I would be able to finish the book in a couple of sittings during the Holiday break. I was wrong. It took me two whole weeks to read it to fully understand it. There are so many nuances and code examples that you must sit and try out to really understand it and learn it. This is not for the dilettante in ML. This is for the serious practitioner of ML. But the time you put in will pay you back in spades since more people will listen to you when you explain how your models work which is a critical skill for your success as a data scientist. There you have it! My one line summary of why you should get and read this book!

I just finished reading "Interpretable Machine Learning with Python - Second Edition" Authored by Serg Masís and published by Packt.In the book, readers embark on a comprehensive journey through the intricate world of interpreting machine learning models. Authored with technical precision and practical insights, the book addresses the pressing need for understanding and explaining machine learning algorithms.The initial chapters lay a sturdy foundation, delineating the distinctions between interpretability and explainability while underscoring their significance in real-world applications. Through a compelling business case, readers grasp the imperative of interpretability in decision-making processes.Delving deeper, the book navigates through key concepts and challenges surrounding interpretation methodologies. From traditional model interpretations to the emergence of newer glass-box models, readers gain a nuanced understanding of interpretability paradigms.The narrative unfolds with an exploration of global and local model-agnostic interpretation methods, shedding light on feature importance and interactions. Anchors, counterfactual explanations, and visualization techniques offer multifaceted insights into model behaviors across various domains.The book extends its reach into the realms of convolutional neural networks (CNNs) and natural language processing (NLP) transformers, elucidating complex architectures through visualization and interpretation methods.Further chapters unravel the intricacies of multivariate forecasting, feature selection, bias mitigation, and causal inference methods, empowering readers to navigate through the interpretability landscape with finesse.Finally, discussions on model tuning, adversarial robustness, and future prospects in ML interpretability invite readers to contemplate the evolving role of transparency in machine learning systems."Interpretable Machine Learning with Python" emerges as an indispensable resource for practitioners, researchers, and enthusiasts alike, offering profound insights and actionable strategies to unravel the mysteries of machine learning models.