book

Interpretable Machine Learning with Python

by Serg Masís

March 2021

Beginner to intermediate

736 pages

16h 54m

English

Packt Publishing

Read now

Unlock full access

ContributorsAbout the authorAbout the reviewersPackt is searching for authors like you
Who this book is forWhat this book coversTo get the most out of this bookDownload the example code filesDownload the color imagesConventions usedGet in touchReviews
Technical requirementsWhat is machine learning interpretation?Understanding a simple weight prediction modelUnderstanding the difference between interpretability and explainabilityWhat is interpretability?Beware of complexityWhen does interpretability matter?What are black-box models?What are white-box models?What is explainability?Why and when does explainability matter?A business case for interpretabilityBetter decisionsMore trusted brandsMore ethicalMore profitableSummaryImage sourcesFurther reading
Technical requirementsThe missionDetails about CVDThe approachPreparationsLoading the librariesUnderstanding and preparing the dataThe data dictionaryData preparationLearning about interpretation method types and scopesModel interpretability method typesModel interpretability scopesInterpreting individual predictions with logistic regressionAppreciating what hinders machine learning interpretabilityNon-linearityInteractivityNon-monotonicityMission accomplishedSummaryFurther reading
Technical requirementsThe missionThe approachThe preparationsLoading the librariesUnderstanding and preparing the dataThe data dictionaryData preparationReviewing traditional model interpretation methodsPredicting minutes delayed with various regression methodsClassifying flights as delayed or not delayed with various classification methodsTraining and evaluating the classification modelsVisualizing delayed flights with dimensionality reduction methodsUnderstanding limitations of traditional model interpretation methodsStudying intrinsically interpretable (white-box) models Generalized Linear Models (GLMs)Linear regressionRidge regressionPolynomial regressionLogistic regressionDecision treesCART decision treesRuleFitNearest neighborsk-Nearest NeighborsNaïve BayesGaussian Naïve BayesRecognizing the trade-off between performance and interpretabilitySpecial model propertiesThe key property: explainabilityThe remedial property: regularizationAssessing performanceDiscovering newer interpretable (glass-box) modelsExplainable Boosting Machine (EBM)Global interpretationLocal interpretationPerformanceSkoped RulesGlobal interpretationLocal interpretationPerformanceMission accomplishedSummaryDataset sourcesFurther reading
Technical requirementsThe missionPersonality and birth orderThe approachThe preparationsLoading the librariesUnderstanding and preparing the dataThe data dictionaryData preparationMeasuring the impact of a feature on the outcomeFeature importance for tree-based modelsFeature importance for Logistic RegressionFeature importance for LDAFeature importance for the Multi-layer PerceptronPracticing PFIDisadvantages of PFIInterpreting PDPsInteraction PDPsDisadvantages of PDPExplaining ICE plotsDisadvantages of ICEMission accomplishedSummaryDataset sourcesFurther reading
Technical requirementsThe missionThe approachThe preparationsLoading the librariesUnderstanding and preparing the dataThe data dictionaryData preparationModeling and performance evaluation for deep neural networksModeling and performance evaluation for XGBoostLearning about Shapley valuesInterpreting SHAP summary and dependence plotsGenerating SHAP summary plotsUnderstanding interactionsSHAP dependence plotsSHAP force plotsAccumulated Local Effects (ALE) plotsGlobal surrogatesFitting surrogatesEvaluating surrogatesInterpreting surrogatesMission accomplishedSummaryFurther reading
Technical requirementsThe missionThe approachThe preparationsLoading the librariesUnderstanding and preparing the dataThe data dictionaryData preparationLeveraging SHAP's KernelExplainer for local interpretations with SHAP values Training a C-SVC modelComputing SHAP values using KernelExplainerLocal interpretation for a group of predictions using decision plotsLocal interpretation for a single prediction at a time using a force plotEmploying LIMEWhat is LIME?Local interpretation for a single prediction at a time using LimeTabularExplainerUsing LIME for NLPTraining a LightGBM modelLocal interpretation for a single prediction at a time using LimeTextExplainerTrying SHAP for NLPComparing SHAP with LIMEMission accomplishedSummaryDataset sourcesFurther reading

Technical requirementsThe missionUnfair bias in recidivisim risk assessmentsThe approachThe preparationsLoading the librariesUnderstanding and preparing the dataThe data dictionaryExamining predictive bias with confusion matricesData preparationModelingGetting acquainted with our "instance of interest"Understanding anchor explanationsPreparations for anchor and counterfactual explanations with alibiLocal interpretations for anchor explanationsExploring counterfactual explanationsCounterfactual explanations guided by prototypesCounterfactual instances and much more with the What-If Tool (WIT)Configuring WITDatapoint editorPerformance & FairnessComparing with CEMMission accomplishedSummaryDataset sourcesFurther reading
Technical requirementsThe missionThe approachPreparationsLoading the librariesUnderstanding and preparing the dataLoading the CNN modelAssessing the CNN classifier with traditional interpretation methodsDetermining what misclassifications to focus onVisualizing the learning process with activation-based methodsIntermediate activationsActivation maximizationEvaluating misclassifications with gradient-based attribution methodsSaliency mapsGrad-CAMCreating GradCam++ mapsIntegrated gradientsUsing the explainerTying it all togetherUnderstanding classifications with perturbation-based attribution methodsOcclusion sensitivityLIME's ImageExplainer1) Initializing and creating explanations2) Extracting an image and mask from the explanation 3) Plotting explanationsCEMTying it all togetherBonus method: SHAP's DeepExplainerMission accomplishedSummaryDataset and image sourcesFurther reading
Technical requirementsThe missionThe approachThe preparationLoading the librariesUnderstanding and preparing the dataThe data dictionaryUnderstanding the dataData preparationLoading the LSTM modelsAssessing time series models with traditional interpretation methodsUsing standard regression metricsGenerating LSTM attributions with integrated gradientsComputing global and local attributions with SHAP's KernelExplainerIdentifying influential features with factor prioritizationComputing Morris sensitivity indicesAnalyzing the elementary effectsQuantifying uncertainty and cost sensitivity with factor fixingGenerating and predicting on Salteli samplesPerforming Sobol sensitivity analysisIncorporating a realistic cost functionMission accomplishedSummaryDataset and image sourcesReferences
Technical requirementsThe missionThe approachThe preparationsLoading the librariesUnderstanding and preparing the dataUnderstanding the effect of irrelevant featuresCreating a base modelEvaluating the modelTraining the base model at different max depthsReviewing filter-based feature selection methodsBasic filter-based methodsConstant features with a variance thresholdQuasi-constant features with Value-CountsDuplicating featuresRemoving unnecessary featuresCorrelation filter-based methodsRanking filter-based methodsComparing filter-based methodsExploring embedded feature selection methodsDiscovering wrapper, hybrid, and advanced feature selection methodsWrapper methodsSequential forward selection (SFS)Sequential Backward Selection (SBS)Hybrid methodsRecursive feature eliminationAdvanced methodsDimensionality reductionModel-agnostic feature importanceGenetic algorithmsEvaluating all feature-selected modelsConsidering feature engineeringMission accomplishedSummaryDataset sourcesFurther reading
Technical requirementsThe missionThe approachThe preparationsLoading the librariesUnderstanding and preparing the dataThe data dictionaryData preparationDetecting biasVisualizing dataset biasQuantifying dataset biasQuantifying model biasMitigating biasPre-processing bias mitigation methodsReweighing methodDisparate impact remover methodIn-processing bias mitigation methodsPrejudice remover methodGerry fair classifier methodPost-processing bias mitigation methodsEqualized odds post-processing methodCalibrated equalized odds postprocessing methodTying it all together!Creating a causal modelUnderstanding the results of the experimentUnderstanding causal modelsInitializing the linear doubly robust learnerFitting the causal modelUnderstanding heterogeneous treatment effectsChoosing policiesTesting estimate robustnessAdding random common causeReplacing treatment with a random variableMission accomplishedSummaryDataset sourcesFurther reading
Technical requirementsThe missionThe approachThe preparationsLoading the librariesUnderstanding and preparing the dataVerifying the sampling balancePlacing guardrails with feature engineeringOrdinalizationDiscretizationInteraction terms and non-linear transformationsCategorical encodingOther preparationsTuning models for interpretabilityTuning a Keras neural networkDefining the model and parameters to tuneRunning the hyperparameter tuningExamining the resultsEvaluating the best modelTuning other popular model classesA quick introduction to relevant model parametersBatch hyperparameter tuning modelsEvaluating models by precisionAssessing fairness for the highest-performing modelOptimizing for fairness with Bayesian hyperparameter tuning and custom metricsDesigning a custom metricRunning Bayesian hyperparameter tuningFitting and evaluating a model with the best parametersExamining racial bias through feature importanceImplementing model constraintsConstraints for XGBoostConstraints for TensorFlow LatticeMission accomplishedSummaryDataset sourcesFurther reading
Technical requirementsThe missionThe approachThe preparationsLoading the librariesUnderstanding and preparing the dataLoading the CNN base modelAssessing the CNN base classifierLearning about evasion attacksFast Gradient Sign Method attackC&W infinity-norm attackTargeted AP attackDefending against targeted attacks with preprocessingShielding against any evasion attack via adversarial training of a robust classifierEvaluating and certifying adversarial robustnessComparing model robustness with attack strengthCertifying robustness with randomized smoothingMission accomplishedSummaryDataset sourcesFurther reading
Understanding the current landscape of ML interpretabilityTying everything together!Current trendsSpeculating on the future of ML interpretabilityA new vision for MLA multidisciplinary approachAdequate standardization Enforcing regulationSeamless machine learning automation with built-in interpretationTighter integration with MLOps engineersFurther reading
Other Books You May EnjoyPackt is searching for authors like youLeave a review - let other readers know what you think

Content preview from Interpretable Machine Learning with Python

Chapter 13: Adversarial Robustness

Machine learning interpretation has many concerns, ranging from knowledge discovery to high-stakes ones with tangible ethical implications, such as the fairness issues examined in the last two chapters. In this chapter, we will direct our attention to concerns involving reliability, safety, and security.

As we realized using the contrastive explanation method (CEM) in Chapter 8, Visualizing Convolutional Neural Networks, we can easily trick an image classifier into making embarrassingly false predictions. This ability can have serious ramifications. For instance, a perpetrator can place a black sticker on a yield sign, and while most drivers would still recognize this as a yield sign, a self-driving car would ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Start your free trial

Interpretable Machine Learning with Python - Second Edition

Publisher Resources

ISBN: 9781800203907Supplemental Content

Interpretable Machine Learning with Python

by Serg Masís

Chapter 13: Adversarial Robustness

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

You might also like