Book Image

Interpretable Machine Learning with Python

By : Serg Masís
Book Image

Interpretable Machine Learning with Python

By: Serg Masís

Overview of this book

Do you want to gain a deeper understanding of your models and better mitigate poor prediction risks associated with machine learning interpretation? If so, then Interpretable Machine Learning with Python deserves a place on your bookshelf. We’ll be starting off with the fundamentals of interpretability, its relevance in business, and exploring its key aspects and challenges. As you progress through the chapters, you'll then focus on how white-box models work, compare them to black-box and glass-box models, and examine their trade-off. You’ll also get you up to speed with a vast array of interpretation methods, also known as Explainable AI (XAI) methods, and how to apply them to different use cases, be it for classification or regression, for tabular, time-series, image or text. In addition to the step-by-step code, this book will also help you interpret model outcomes using examples. You’ll get hands-on with tuning models and training data for interpretability by reducing complexity, mitigating bias, placing guardrails, and enhancing reliability. The methods you’ll explore here range from state-of-the-art feature selection and dataset debiasing methods to monotonic constraints and adversarial retraining. By the end of this book, you'll be able to understand ML models better and enhance them through interpretability tuning.
Table of Contents (19 chapters)
Section 1: Introduction to Machine Learning Interpretation
Section 2: Mastering Interpretation Methods
Section 3:Tuning for Interpretability

Explaining ICE plots

ICE plots are the answer to the question: What if my PDP plots obscure the variance in my feature-target relationships? Indeed, when you are trying to understand how a feature relates to the prediction of a model, a lot can be lost by averaging it out. If you take a close look at the PDP plots for individual features, many of them have thin lines that are not only distant from the average thick line but don't even follow its general direction. These variations can provide additional insight—and, by the way, the thin lines are essentially what ICE plots are about, except you can do much more with them.

ICE plots can include all of your datasets, but having many lines in your plots can be computationally expensive and—more importantly—difficult to appreciate. This is why it's recommended to either sample your dataset or plot the lines with transparency.

We will use both approaches, but let's first sample the dataset. We...