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.

Related Content you might be interested in

Current Title:

Small book image
Interpretable Machine Learning with Python
Serg Masís
Mar, 2021 | 736 pages
Small book image
Applied Machine Learning Explainability Techniques
Aditya Bhattacharya
Jul, 2022 | 306 pages
Small book image
Deep Learning and XAI Techniques for Anomaly Detection
Cher Simon
Jan, 2023 | 218 pages
Small book image
Platform and Model Design for Responsible AI
Sharmistha Chatterjee | Amita Kapoor
Apr, 2023 | 516 pages
Table of Contents (19 chapters)
Preface
Preface
Who this book is for
What this book covers
To get the most out of this book
Download the example code files
Download the color images
Conventions used
Get in touch
Reviews
1
Section 1: Introduction to Machine Learning Interpretation
Section 1: Introduction to Machine Learning Interpretation
Free Chapter
2
Chapter 1: Interpretation, Interpretability, and Explainability; and Why Does It All Matter?
Chapter 1: Interpretation, Interpretability, and Explainability; and Why Does It All Matter?
Technical requirements
What is machine learning interpretation?
Understanding the difference between interpretability and explainability
A business case for interpretability
Summary
Image sources
Further reading
3
Chapter 2: Key Concepts of Interpretability
Chapter 2: Key Concepts of Interpretability
Technical requirements
The mission
The approach
Preparations
Learning about interpretation method types and scopes
Appreciating what hinders machine learning interpretability
Mission accomplished
Summary
Further reading
4
Chapter 3: Interpretation Challenges
Chapter 3: Interpretation Challenges
Technical requirements
The mission
The approach
The preparations
Reviewing traditional model interpretation methods
Understanding limitations of traditional model interpretation methods
Studying intrinsically interpretable (white-box) models
Recognizing the trade-off between performance and interpretability
Discovering newer interpretable (glass-box) models
Mission accomplished
Summary
Dataset sources
Further reading
5
Section 2: Mastering Interpretation Methods
Section 2: Mastering Interpretation Methods
6
Chapter 4: Fundamentals of Feature Importance and Impact
Chapter 4: Fundamentals of Feature Importance and Impact
Technical requirements
The mission
The approach
The preparations
Measuring the impact of a feature on the outcome
Practicing PFI
Interpreting PDPs
Explaining ICE plots
Mission accomplished
Summary
Dataset sources
Further reading
7
Chapter 5: Global Model-Agnostic Interpretation Methods
Chapter 5: Global Model-Agnostic Interpretation Methods
Technical requirements
The mission
The approach
The preparations
Learning about Shapley values
Interpreting SHAP summary and dependence plots
Accumulated Local Effects (ALE) plots
Global surrogates
Mission accomplished
Summary
Further reading
8
Chapter 6: Local Model-Agnostic Interpretation Methods
Chapter 6: Local Model-Agnostic Interpretation Methods
Technical requirements
The mission
The approach
The preparations
Leveraging SHAP's KernelExplainer for local interpretations with SHAP values
Employing LIME
Using LIME for NLP
Trying SHAP for NLP
Comparing SHAP with LIME
Mission accomplished
Summary
Dataset sources
Further reading
9
Chapter 7: Anchor and Counterfactual Explanations
Chapter 7: Anchor and Counterfactual Explanations
Technical requirements
The mission
The approach
The preparations
Understanding anchor explanations
Exploring counterfactual explanations
Comparing with CEM
Mission accomplished
Summary
Dataset sources
Further reading
10
Chapter 8: Visualizing Convolutional Neural Networks
Chapter 8: Visualizing Convolutional Neural Networks
Technical requirements
The mission
The approach
Preparations
Visualizing the learning process with activation-based methods
Evaluating misclassifications with gradient-based attribution methods
Understanding classifications with perturbation-based attribution methods
Mission accomplished
Summary
Dataset and image sources
Further reading
11
Chapter 9: Interpretation Methods for Multivariate Forecasting and Sensitivity Analysis
Chapter 9: Interpretation Methods for Multivariate Forecasting and Sensitivity Analysis
Technical requirements
The mission
The approach
The preparation
Assessing time series models with traditional interpretation methods
Generating LSTM attributions with integrated gradients
Computing global and local attributions with SHAP's KernelExplainer
Identifying influential features with factor prioritization
Quantifying uncertainty and cost sensitivity with factor fixing
Mission accomplished
Summary
Dataset and image sources
References
12
Section 3:Tuning for Interpretability
Section 3:Tuning for Interpretability
13
Chapter 10: Feature Selection and Engineering for Interpretability
Chapter 10: Feature Selection and Engineering for Interpretability
Technical requirements
The mission
The approach
The preparations
Understanding the effect of irrelevant features
Reviewing filter-based feature selection methods
Exploring embedded feature selection methods
Discovering wrapper, hybrid, and advanced feature selection methods
Considering feature engineering
Mission accomplished
Summary
Dataset sources
Further reading
14
Chapter 11: Bias Mitigation and Causal Inference Methods
Chapter 11: Bias Mitigation and Causal Inference Methods
Technical requirements
The mission
The approach
The preparations
Detecting bias
Mitigating bias
Creating a causal model
Understanding heterogeneous treatment effects
Testing estimate robustness
Mission accomplished
Summary
Dataset sources
Further reading
15
Chapter 12: Monotonic Constraints and Model Tuning for Interpretability
Chapter 12: Monotonic Constraints and Model Tuning for Interpretability
Technical requirements
The mission
The approach
The preparations
Placing guardrails with feature engineering
Tuning models for interpretability
Implementing model constraints
Mission accomplished
Summary
Dataset sources
Further reading
16
Chapter 13: Adversarial Robustness
Chapter 13: Adversarial Robustness
Technical requirements
The mission
The approach
The preparations
Learning about evasion attacks
Defending against targeted attacks with preprocessing
Shielding against any evasion attack via adversarial training of a robust classifier
Evaluating and certifying adversarial robustness
Mission accomplished
Summary
Dataset sources
Further reading
17
Chapter 14: What's Next for Machine Learning Interpretability?
Chapter 14: What's Next for Machine Learning Interpretability?
Understanding the current landscape of ML interpretability
Speculating on the future of ML interpretability
Further reading
Why subscribe?
18
Other Books You May Enjoy
Other Books You May Enjoy
Packt is searching for authors like you
Leave a review - let other readers know what you think

To get the most out of this book

You will need a Jupyter environment with Python 3.6+. You can do either of the following:

  • Install one on your machine locally via Anaconda Navigator or from scratch with pip.
  • Use a cloud-based one such as Google Colaboratory, Kaggle Notebooks, Azure Notebooks, or Amazon Sagemaker.

The instructions on how to get started will vary accordingly, so we strongly suggest that you search online for the latest instructions for setting them up.

For instructions on installing the many packages employed throughout the book, please go to the Git repository, which will have the updated instructions in the readme file. We expect these to change from time to time, given how often packages change. We also tested the code with specific versions detailed in the readme, so should anything fail with later versions, please install the specific version instead.

Individual chapters begin with instructions on how to install packages in this form:

!pip install --upgrade nltk lightgbm lime

But depending on the way Jupyter was set up, installing packages might be best done through the command line or using conda, so we suggest you adapt these installation instructions to suit your needs.

If you are using the digital version of this book, we advise you to type the code yourself or access the code via the GitHub repository (link available in the next section). Doing so will help you avoid any potential errors related to the copying and pasting of code.

If you are not a machine learning practitioner or are a beginner, the advice is to read the book sequentially since many concepts are only explained in great detail in earlier chapters. The recommendation for practitioners skilled in machine learning but not acquainted with interpretability is that they can skim the first three chapters to get the ethical context and concept definitions they need to make sense of the rest, but read in the rest in order. As for advanced practitioners that have the foundations of interpretability, reading in any order should be fine.

As for the code, you can read the book without running the code simultaneously or strictly for the theory. But if you plan to run the code, it is best to do it with the book as a guide to assist with the interpretation of outcomes, and to strengthen your understanding of the theory.

While you are reading the book, think of ways in which you could use the tools learned, and by the end of it, hopefully, you will be inspired to put this newly gained knowledge into action!

Previous Section
Next Section