book

Principles of Data Science - Third Edition

Name: Principles of Data Science - Third Edition
Author: Sinan Ozdemir
ISBN: 9781837636303

by Sinan Ozdemir

January 2024

Beginner to intermediate

326 pages

8h 36m

English

Packt Publishing

Read now

Unlock full access

Principles of Data Science
ContributorAbout the authorAbout the reviewer
Preface
Who is this book for?What this book coversTo get the most out of this bookDownload the example code filesConventions usedGet in touchShare Your ThoughtsDownload a free PDF copy of this book
Chapter 1: Data Science Terminology
What is data science?Understanding basic data science terminologyWhy data science?Example – predicting COVID-19 with machine learningThe data science Venn diagramThe mathComputer programmingExample – parsing a single tweetDomain knowledgeSome more terminologyData science case studiesCase study – automating government paper pushingCase study – what’s in a job description?Summary
Chapter 2: Types of Data
Structured versus unstructured dataQuantitative versus qualitative dataDigging deeperThe four levels of dataThe nominal levelMeasures of centerThe ordinal levelThe interval levelThe ratio levelData is in the eye of the beholderSummaryQuestions and answers
Chapter 3: The Five Steps of Data Science
Introduction to data scienceOverview of the five stepsExploring the dataGuiding questions for data explorationDataFramesSeriesExploration tips for qualitative dataSummary
Chapter 4: Basic Mathematics
Basic symbols and terminologyVectors and matricesArithmetic symbolsSummationLogarithms/exponentsSet theoryLinear algebraMatrix multiplicationHow to multiply matrices togetherSummary
Chapter 5: Impossible or Improbable – A Gentle Introduction to Probability
Basic definitionsWhat do we mean by “probability”?Bayesian versus frequentistFrequentist approachThe law of large numbersCompound eventsConditional probabilityHow to utilize the rules of probabilityThe addition ruleMutual exclusivityThe multiplication ruleIndependenceComplementary eventsIntroduction to binary classifiersSummary
Chapter 6: Advanced Probability
Bayesian ideas revisitedBayes’ theoremMore applications of Bayes’ theoremRandom variablesDiscrete random variablesContinuous random variablesSummary
Chapter 7: What Are the Chances? An Introduction to Statistics
What are statistics?How do we obtain and sample data?Obtaining dataObservationalExperimentalSampling dataHow do we measure statistics?Measures of centerMeasures of variationThe coefficient of variationMeasures of relative standingThe insightful part – correlations in dataThe empirical ruleExample – exam scoresSummary
Chapter 8: Advanced Statistics
Understanding point estimatesSampling distributionsConfidence intervalsHypothesis testsConducting a hypothesis testOne-sample t-testsType I and Type II errorsHypothesis testing for categorical variablesChi-square goodness of fit testChi-square test for association/independenceSummary

Chapter 9: Communicating Data
Why does communication matter?Identifying effective visualizationsScatter plotsLine graphsBar chartsHistogramsBox plotsWhen graphs and statistics lieCorrelation versus causationSimpson’s paradoxIf correlation doesn’t imply causation, then what does?Verbal communicationIt’s about telling a storyOn the more formal side of thingsThe why/how/what strategy for presentingSummary
Chapter 10: How to Tell if Your Toaster is Learning – Machine Learning Essentials
Introducing MLExample – facial recognitionML isn’t perfectHow does ML work?Types of MLSLULRLOverview of the types of MLML paradigms – pros and consPredicting continuous variables with linear regressionCorrelation versus causationCausationAdding more predictorsRegression metricsSummary
Chapter 11: Predictions Don’t Grow on Trees, or Do They?
Performing naïve Bayes classificationClassification metricsUnderstanding decision treesMeasuring purityExploring the Titanic datasetDummy variablesDiving deep into ULWhen to use ULk-means clusteringThe Silhouette CoefficientFeature extraction and PCASummary
Chapter 12: Introduction to Transfer Learning and Pre-Trained Models
Understanding pre-trained modelsBenefits of using pre-trained modelsCommonly used pre-trained modelsDecoding BERT’s pre-trainingTLDifferent types of TLInductive TLTransductive TLUnsupervised TL – feature extractionTL with BERT and GPTExamples of TLExample – Fine-tuning a pre-trained model for text classificationSummary
Chapter 13: Mitigating Algorithmic Bias and Tackling Model and Data Drift
Understanding algorithmic biasTypes of biasSources of algorithmic biasMeasuring biasConsequences of unaddressed bias and the importance of fairnessMitigating algorithmic biasMitigation during data preprocessingMitigation during model in-processingMitigation during model postprocessingBias in LLMsUncovering bias in GPT-2Emerging techniques in bias and fairness in MLUnderstanding model drift and decayModel driftData driftMitigating driftUnderstanding the contextContinuous monitoringRegular model retrainingImplementing feedback systemsModel adaptation techniquesSummary
Chapter 14: AI Governance
Mastering data governanceCurrent hurdles in data governanceData management: crafting the bedrockData ingestion – the gateway to informationData integration – from collection to deliveryData warehouses and entity resolutionThe quest for data qualityDocumentation and cataloging – the unsung heroes of governanceUnderstanding the path of dataRegulatory compliance and audit preparednessChange management and impact analysisUpholding data qualityTroubleshooting and analysisNavigating the intricacy and the anatomy of ML governanceML governance pillarsModel interpretabilityThe many facets of ML developmentBeyond training – model deployment and monitoringA guide to architectural governanceThe five pillars of architectural governanceTransformative architectural principlesZooming in on architectural dimensionsSummary
Chapter 15: Navigating Real-World Data Science Case Studies in Action
Introduction to the COMPAS dataset case studyUnderstanding the task/outlining successPreliminary data explorationPreparing the data for modelingFinal thoughtsText embeddings using pretrainedmodels and OpenAISetting up and importing necessary librariesData collection – fetching the textbook dataConverting text to embeddingsQuerying – searching for relevant informationConcluding thoughts – the power of modern pre-trained modelsSummary
Index
Why subscribe?
Other Books You May EnjoyPackt is searching for authors like youShare Your ThoughtsDownload a free PDF copy of this book

Content preview from Principles of Data Science - Third Edition

13 Mitigating Algorithmic Bias and Tackling Model and Data Drift

If you’re playing in the arena of machine learning (ML) and data science, you’re going to run into some hurdles. You can count on meeting two challenges: algorithmic bias and model and data drift. They’re like the tricky questions in a pop quiz – you might not see them coming, but you’d better be prepared to handle them.

Algorithmic bias can creep into our models, and when it does, it’s not a good look. It can lead to unfair results, and, quite frankly, it’s just not cool. But don’t worry – we’re going to tackle it head on and talk about ways to mitigate it.

Even if we consider bias, over time, changes can happen that make our models less accurate. It’s like when your favorite ...

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.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Practical Statistics for Data Scientists, 2nd Edition

Publisher Resources

ISBN: 9781837636303

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

Principles of Data Science - Third Edition

by Sinan Ozdemir

13

Mitigating Algorithmic Bias and Tackling Model and Data Drift

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.