book

The Unsupervised Learning Workshop

Name: The Unsupervised Learning Workshop
ISBN: 9781800200708

by Aaron Jones, Christopher Kruger, Benjamin Johnston, Richard Brooker, John Wesley Doyle, Priyanjit Ghosh, Sani Kamal, Ashish Pratik Patil, Philip Solomon, Geetank Raipuria

July 2020

Intermediate to advanced

550 pages

9h 58m

English

Packt Publishing

Read now

Unlock full access

The Unsupervised Learning Workshop
Preface
About the BookAudienceAbout the ChaptersConventionsCode PresentationSetting up Your EnvironmentHardware RequirementsInstalling PythonInstalling Python on WindowsInstalling Python on LinuxInstalling Python on macOSInstalling pipInstalling Anaconda Installing Anaconda on WindowsInstalling Anaconda on LinuxInstalling Anaconda on macOS XSetting up a Virtual EnvironmentInstalling LibrariesSetting up the MachineAccessing the Code Files
1. Introduction to Clustering
IntroductionUnsupervised Learning versus Supervised LearningClusteringIdentifying ClustersTwo-Dimensional DataExercise 1.01: Identifying Clusters in DataIntroduction to k-means ClusteringNo-Math k-means WalkthroughK-means Clustering In-Depth Walkthrough Alternative Distance Metric – Manhattan DistanceDeeper DimensionsExercise 1.02: Calculating Euclidean Distance in PythonExercise 1.03: Forming Clusters with the Notion of DistanceExercise 1.04: K-means from Scratch – Part 1: Data GenerationExercise 1.05: K-means from Scratch – Part 2: Implementing k-meansClustering Performance – Silhouette ScoreExercise 1.06: Calculating the Silhouette ScoreActivity 1.01: Implementing k-means ClusteringSummary
2. Hierarchical Clustering
IntroductionClustering RefresherThe k-means RefresherThe Organization of the HierarchyIntroduction to Hierarchical ClusteringSteps to Perform Hierarchical ClusteringAn Example Walkthrough of Hierarchical ClusteringExercise 2.01: Building a HierarchyLinkageExercise 2.02: Applying Linkage CriteriaAgglomerative versus Divisive ClusteringExercise 2.03: Implementing Agglomerative Clustering with scikit-learnActivity 2.01: Comparing k-means with Hierarchical Clusteringk-means versus Hierarchical ClusteringSummary
3. Neighborhood Approaches and DBSCAN
IntroductionClusters as NeighborhoodsIntroduction to DBSCANDBSCAN in DetailWalkthrough of the DBSCAN AlgorithmExercise 3.01: Evaluating the Impact of Neighborhood Radius SizeDBSCAN Attributes – Neighborhood RadiusActivity 3.01: Implementing DBSCAN from ScratchDBSCAN Attributes – Minimum PointsExercise 3.02: Evaluating the Impact of the Minimum Points ThresholdActivity 3.02: Comparing DBSCAN with k-means and Hierarchical ClusteringDBSCAN versus k-means and Hierarchical ClusteringSummary
4. Dimensionality Reduction Techniques and PCA
IntroductionWhat Is Dimensionality Reduction?Applications of Dimensionality ReductionThe Curse of DimensionalityOverview of Dimensionality Reduction TechniquesDimensionality ReductionPrincipal Component AnalysisMeanStandard DeviationCovarianceCovariance MatrixExercise 4.01: Computing Mean, Standard Deviation, and Variance Using the pandas LibraryEigenvalues and EigenvectorsExercise 4.02: Computing Eigenvalues and EigenvectorsThe Process of PCAExercise 4.03: Manually Executing PCAExercise 4.04: scikit-learn PCAActivity 4.01: Manual PCA versus scikit-learnRestoring the Compressed DatasetExercise 4.05: Visualizing Variance Reduction with Manual PCAExercise 4.06: Visualizing Variance Reduction with scikit-learnExercise 4.07: Plotting 3D Plots in MatplotlibActivity 4.02: PCA Using the Expanded Seeds DatasetSummary
5. Autoencoders
IntroductionFundamentals of Artificial Neural NetworksThe NeuronThe Sigmoid FunctionRectified Linear Unit (ReLU)Exercise 5.01: Modeling the Neurons of an Artificial Neural NetworkExercise 5.02: Modeling Neurons with the ReLU Activation FunctionNeural Networks: Architecture DefinitionExercise 5.03: Defining a Keras ModelNeural Networks: TrainingExercise 5.04: Training a Keras Neural Network ModelActivity 5.01: The MNIST Neural NetworkAutoencodersExercise 5.05: Simple AutoencoderActivity 5.02: Simple MNIST AutoencoderExercise 5.06: Multi-Layer AutoencoderConvolutional Neural NetworksExercise 5.07: Convolutional AutoencoderActivity 5.03: MNIST Convolutional AutoencoderSummary
6. t-Distributed Stochastic Neighbor Embedding
IntroductionThe MNIST DatasetStochastic Neighbor Embedding (SNE)t-Distributed SNEExercise 6.01: t-SNE MNISTActivity 6.01: Wine t-SNEInterpreting t-SNE PlotsPerplexityExercise 6.02: t-SNE MNIST and PerplexityActivity 6.02: t-SNE Wine and PerplexityIterationsExercise 6.03: t-SNE MNIST and IterationsActivity 6.03: t-SNE Wine and IterationsFinal Thoughts on VisualizationsSummary
7. Topic Modeling
IntroductionTopic ModelsExercise 7.01: Setting up the EnvironmentA High-Level Overview of Topic ModelsBusiness ApplicationsExercise 7.02: Data LoadingCleaning Text DataData Cleaning TechniquesExercise 7.03: Cleaning Data Step by StepExercise 7.04: Complete Data CleaningActivity 7.01: Loading and Cleaning Twitter DataLatent Dirichlet AllocationVariational InferenceBag of WordsExercise 7.05: Creating a Bag-of-Words Model Using the Count VectorizerPerplexityExercise 7.06: Selecting the Number of TopicsExercise 7.07: Running LDAVisualizationExercise 7.08: Visualizing LDAExercise 7.09: Trying Four TopicsActivity 7.02: LDA and Health TweetsExercise 7.10: Creating a Bag-of-Words Model Using TF-IDFNon-Negative Matrix FactorizationThe Frobenius NormThe Multiplicative Update AlgorithmExercise 7.11: Non-negative Matrix FactorizationExercise 7.12: Visualizing NMFActivity 7.03: Non-negative Matrix FactorizationSummary
8. Market Basket Analysis
IntroductionMarket Basket AnalysisUse CasesImportant Probabilistic MetricsExercise 8.01: Creating Sample Transaction DataSupportConfidenceLift and LeverageConvictionExercise 8.02: Computing MetricsCharacteristics of Transaction DataExercise 8.03: Loading DataData Cleaning and FormattingExercise 8.04: Data Cleaning and FormattingData EncodingExercise 8.05: Data EncodingActivity 8.01: Loading and Preparing Full Online Retail DataThe Apriori AlgorithmComputational FixesExercise 8.06: Executing the Apriori AlgorithmActivity 8.02: Running the Apriori Algorithm on the Complete Online Retail DatasetAssociation RulesExercise 8.07: Deriving Association RulesActivity 8.03: Finding the Association Rules on the Complete Online Retail DatasetSummary

9. Hotspot Analysis
IntroductionSpatial StatisticsProbability Density FunctionsUsing Hotspot Analysis in BusinessKernel Density EstimationThe Bandwidth ValueExercise 9.01: The Effect of the Bandwidth ValueSelecting the Optimal BandwidthExercise 9.02: Selecting the Optimal Bandwidth Using Grid SearchKernel FunctionsExercise 9.03: The Effect of the Kernel FunctionKernel Density Estimation DerivationExercise 9.04: Simulating the Derivation of Kernel Density EstimationActivity 9.01: Estimating Density in One DimensionHotspot AnalysisExercise 9.05: Loading Data and Modeling with SeabornExercise 9.06: Working with BasemapsActivity 9.02: Analyzing Crime in LondonSummary
Appendix
1. Introduction to ClusteringActivity 1.01: Implementing k-means Clustering2. Hierarchical ClusteringActivity 2.01: Comparing k-means with Hierarchical Clustering3. Neighborhood Approaches and DBSCANActivity 3.01: Implementing DBSCAN from ScratchActivity 3.02: Comparing DBSCAN with k-means and Hierarchical Clustering4. Dimensionality Reduction Techniques and PCAActivity 4.01: Manual PCA versus scikit-learnActivity 4.02: PCA Using the Expanded Seeds Dataset5. AutoencodersActivity 5.01: The MNIST Neural NetworkActivity 5.02: Simple MNIST AutoencoderActivity 5.03: MNIST Convolutional Autoencoder6. t-Distributed Stochastic Neighbor EmbeddingActivity 6.01: Wine t-SNEActivity 6.02: t-SNE Wine and PerplexityActivity 6.03: t-SNE Wine and Iterations7. Topic ModelingActivity 7.01: Loading and Cleaning Twitter DataActivity 7.02: LDA and Health TweetsActivity 7.03: Non-negative Matrix Factorization8. Market Basket AnalysisActivity 8.01: Loading and Preparing Full Online Retail DataActivity 8.02: Running the Apriori Algorithm on the Complete Online Retail DatasetActivity 8.03: Finding the Association Rules on the Complete Online Retail Dataset9. Hotspot AnalysisActivity 9.01: Estimating Density in One DimensionActivity 9.02: Analyzing Crime in London

Overview

'The Unsupervised Learning Workshop' provides a clear and engaging introduction to the concepts and applications of unsupervised machine learning. Through practical examples and explanations, you'll understand how to apply clustering algorithms, leverage dimensionality reduction techniques, and utilize topic modeling to gain insights from unorganized data. This book equips you to handle real-world machine learning challenges.

What this Book will help me do

Understand and differentiate between clustering methods such as k-means and hierarchical clustering.
Learn to reduce the dimensionality of datasets effectively using PCA and t-SNE.
Explore encoding techniques, including the application of autoencoders, for efficient data preparation.
Implement topic modeling for text-based data using natural language processing techniques.
Apply Market Basket Analysis and Hotspot Analysis in real-world contexts to extract actionable insights.

Author(s)

Authors Aaron Jones, Christopher Kruger, and Benjamin Johnston bring their collective expertise in machine learning and data analysis to this comprehensive workshop. With substantial experience in the field and a knack for making technical topics accessible and engaging, they guide readers through complex unsupervised learning concepts with clarity and practical focus.

Who is it for?

This book is designed for data scientists and developers who are new to unsupervised machine learning techniques and want a clear, practical guide. If you have a basic knowledge of Python programming and are eager to gain skills to handle unstructured data, this book is for you. It will be especially beneficial if you're interested in applying data science to practical problems such as pattern recognition or data analysis.

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

The Supervised Learning Workshop - Second Edition

Publisher Resources

ISBN: 9781800200708

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills