Causal Inference and Discovery in Python: Unlock the secrets of modern causal machine learning with DoWhy, EconML, PyTorch and more

by Aleksander Molak

Demystify causal inference and casual discovery by uncovering causal principles and merging them with powerful machine learning algorithms for observational and experimental data Purchase of the print or Kindle book includes a free PDF eBook Causal methods present unique challenges compared to traditional machine learning and statistics. Learning causality can be challenging, but it offers distinct advantages that elude a purely statistical mindset. Causal Inference and Discovery in Python helps you unlock the potential of causality. You’ll start with basic motivations behind causal thinking and a comprehensive introduction to Pearlian causal concepts, such as structural causal models, interventions, counterfactuals, and more. Each concept is accompanied by a theoretical explanation and a set of practical exercises with Python code. Next, you’ll dive into the world of causal effect estimation, consistently progressing towards modern machine learning methods. Step-by-step, you’ll discover Python causal ecosystem and harness the power of cutting-edge algorithms. You’ll further explore the mechanics of how “causes leave traces” and compare the main families of causal discovery algorithms. The final chapter gives you a broad outlook into the future of causal AI where we examine challenges and opportunities and provide you with a comprehensive list of resources to learn more. This book is for machine learning engineers, data scientists, and machine learning researchers looking to extend their data science toolkit and explore causal machine learning. It will also help developers familiar with causality who have worked in another technology and want to switch to Python, and data scientists with a history of working with traditional causality who want to learn causal machine learning. It’s also a must-read for tech-savvy entrepreneurs looking to build a competitive edge for their products and go beyond the limitations of traditional machine learning.

Genres: Programming, Artificial Intelligence, Computers, Textbooks, Mathematics, Science, Technology

456 pages, Paperback

Published May 31, 2023

Reviews

[Natalia Bielczyk · Rating 5 out of 5]

This book was so necessary! Currently, the IT world is obsessed with prediction models based on correlations while correlation is not causation! No wonder that LLMs and other models built into AI create biases and produce false statements about the world. Causal inference is the key to build more reliable representations of the real-world systems and unlock the next level of (artificial) intelligence.

I wish I had this book in my hands before I started my PhD in causal inference in cognitive neuroimaging many years ago. Aleksander Molak is a great educator and he made this material comprehensible to a wide audience. Practical examples make this material directly applicable to R&D research. If you would like to supercharge your skills in Data Science with causal inference from the comfort of your home, this is currently the best choice in the market. Highly recommended!

[Emre Sevinç · Rating 5 out of 5]

I read this book a few months after Causal Inference in Python: Applying Causal Inference in the Tech Industry, and I tend to think of them as a pair. Together, they probably constitute the most practical introduction to dealing with causal inference for practitioners working in all sorts of companies. But make no mistake, this book, like the other one mentioned, no matter how practical and full of useful examples in Python, using many state-of-the-art libraries, demands serious attention and deep thinking. I plan to go back to this book again and again for causal inference related problems. We're lucky to have such practical introductions, full of code examples and explanations, because establishing causal relationships will only get more important as time passes and gathering more and more data will become easier and cheaper, as exemplified by Elias Bareinboim in his excellent commentary on whether worrying causality makes any for "purely" predictive tasks.

Conclusion: if you're curious what it means to "calculate" and then interpret causality for various data sets using popular Python libraries, you can't go wrong with this practical introduction. Strongly recommended.

[Nouroz Amon · Rating 5 out of 5]

The book on causal discovery was a game-changer for me during my master's thesis. It made understanding causal discovery a breeze with its clear explanations, practical examples, and easy-to-follow code snippets. Unlike other complex reads, this book simplified concepts and offered relatable use cases that made learning a lot easier.

What I loved most was its straightforward approach. It didn't try to sound fancy or dramatic. Instead, it focused on delivering practical knowledge. The book's simplicity made it stand out among other resources I used for my thesis.

I'd highly recommend this book to anyone interested in causal discovery. Whether you're a student or a researcher, its accessible language, helpful examples, and practical insights make it a valuable read. It certainly made a significant impact on how I approached and understood my thesis topic.

[Josua Naiborhu · Rating 5 out of 5]

i can't thank enough for the resources given in this book. The author clearly walks through every single concept of causal inference. The formula and some metaphors that explain the concepts makes me able to grasp and apply them into my ongoing and future project i am building. One thing that makes this book standout is the hands-on approach of every chapter along with the code available is a plus point of this book.

[Matthew Mechtly · Rating 5 out of 5]

A great, practical guide to transition from the theory in books like "The Book of Why" to writing implementable Python and making real-world tradeoffs.

Molak's code runs well almost without exception (an unfortunately uncommon quality when writing books using relatively immature libraries).

[Wamuyu Wanjohi · Rating 3 out of 5]

If a beginner to causal thinking, consider a different book first .
The examples remained sufficiently vague for this to be termed a collection of words on paper. Might just revisit

[Sebastian Waisbrot · Rating 5 out of 5]

This book is a must read for anyone interested in science and machine learning. The text is very clear for anyone with some basic understanding in the subject and it provides good examples.

[Serhii Kushchenko · Rating 3 out of 5]

I found this book disappointing. I spent about a month trying to extract some useful knowledge from it, only to realize that reading the Python DoWhy package documentation was a far better use of my time and effort.

Strengths of the book

1. From this book I learned about the existence of a wonderful Python DoWhy package.
2. Most of the code examples run successfully.
3. It provides many useful references to other solid books and papers.
4. The author warns readers that propensity score models are misleading and should be avoided when the goal is to uncover the truth.

Weaknesses of the book

1. The author wrote it in a rushed and careless way.
2. The explanations are weak, particularly in the context of machine learning.
3. Without strong prior knowledge of regression and machine learning, readers will gain little from it.