book

Data Without Labels

Name: Data Without Labels
Author: Vaibhav Verdhan
ISBN: 9781617298721

by Vaibhav Verdhan

May 2025

Intermediate to advanced

352 pages

10h 44m

English

Manning Publications

Audiobook available

Read now

Unlock full access

Data Without Labels
copyright
contents
Praise for Data Without Labels
dedication
foreword
preface
acknowledgments
about this book
about the author

about the cover illustration
Part 1 Basics
1 Introduction to machine learning
1.1 Technical toolkit1.2 Data, data types, data management, and quality1.2.1 What is data?1.2.2 Various types of data1.2.3 Data quality1.2.4 Data engineering and management1.3 Data analysis, ML, AI, and business intelligence1.4 Nuts and bolts of ML1.5 Types of ML algorithms1.5.1 Supervised learning1.5.2 Unsupervised algorithms1.5.3 Semisupervised algorithms1.5.4 Reinforcement learning1.6 Concluding thoughts
2 Clustering techniques
2.1 Technical toolkit2.2 Clustering2.3 Centroid-based clustering2.3.1 K-means clustering2.3.2 Measuring the accuracy of clustering2.3.3 Finding the optimum value of k2.3.4 Pros and cons of k-means clustering2.3.5 K-means clustering implementation using Python2.4 Connectivity-based clustering2.4.1 Types of hierarchical clustering2.4.2 Linkage criterion for distance measurement2.4.3 Optimal number of clusters2.4.4 Pros and cons of hierarchical clustering2.4.5 Hierarchical clustering case study using Python2.5 Density-based clustering2.5.1 Neighborhood and density2.5.2 DBSCAN clustering2.6 Case study using clustering2.6.1 Business context2.6.2 Dataset for the analysis2.6.3 Suggested solutions2.6.4 Solution for the problem2.7 Common challenges faced in clustering2.8 Concluding thoughts2.9 Practical next steps and suggested readings
3 Dimensionality reduction
3.1 Technical toolkit3.2 The curse of dimensionality3.3 Dimension reduction methods3.3.1 Mathematical foundation3.4 Manual methods of dimensionality reduction3.4.1 Manual feature selection3.4.2 Correlation coefficient3.4.3 Algorithm-based methods for reducing dimensions3.5 Principal component analysis3.5.1 Eigenvalue decomposition3.5.2 Python solution using PCA3.6 Singular value decomposition3.6.1 Python solution using SVD3.7 Pros and cons of dimensionality reduction3.8 Case study for dimension reduction3.9 Concluding thoughts3.10 Practical next steps and suggested readings
Part 2 Intermediate level
4 Association rules
4.1 Technical toolkit4.2 Association rule overview4.3 The building blocks of association rules4.3.1 Support, confidence, lift, and conviction4.4 Apriori algorithm4.4.1 Python implementation4.4.2 Challenges with the Apriori algorithm4.5 Equivalence class clustering and bottom-up lattice traversal4.5.1 Python implementation4.6 F-P algorithm4.7 Sequence rule mining4.7.1 Sequential Pattern Discovery Using Equivalence4.8 Case study for association rules4.9 Concluding thoughts4.10 Practical next steps and suggested readings
5 Clustering
5.1 Technical toolkit5.2 Clustering: A brief recap5.3 Spectral clustering5.3.1 Building blocks of spectral clustering5.3.2 The process of spectral clustering5.4 Python implementation of spectral clustering5.5 Fuzzy clustering5.5.1 Types of fuzzy clustering5.5.2 Python implementation of FCM5.6 Gaussian mixture model5.6.1 EM technique5.6.2 Python implementation of GMM5.7 Concluding thoughts5.8 Practical next steps and suggested readings
6 Dimensionality reduction
6.1 Technical toolkit6.2 Multidimensional scaling6.2.1 Classic MDS6.2.2 Nonmetric MDS6.3 Python implementation of MDS6.4 t-distributed stochastic neighbor embedding6.4.1 Cauchy distribution6.4.2 Python implementation of t-SNE6.5 Uniform manifold approximation projection6.5.1 Working with UMAP6.5.2 Using UMAP6.5.3 Key points of UMAP6.6 Case study6.7 Concluding thoughts6.8 Practical next steps and suggested readings
7 Unsupervised learning for text data
7.1 Technical toolkit7.2 Text data is everywhere7.3 Use cases of text data7.4 Challenges with text data7.5 Preprocessing the text data7.6 Data cleaning7.7 Extracting features from the text dataset7.8 Tokenization7.9 BOW approach7.10 Term frequency and inverse document frequency7.11 Language models7.12 Text cleaning using Python7.13 Word embeddings7.14 Word2Vec and GloVe7.15 Sentiment analysis case study with Python implementation7.16 Text clustering using Python7.17 GenAI for text data7.18 Concluding thoughts7.19 Practical next steps and suggested readings
Part 3 Advanced concepts
8 Deep learning: The foundational concepts
8.1 Technical toolkit8.1.1 Deep learning: What is it? What does it do?8.2 Building blocks of a neural network8.2.1 Neural networks for solutions8.2.2 Artificial neurons and perceptrons8.2.3 Different layers in a network8.2.4 Activation functions8.2.5 Hyperparameters8.2.6 Optimization functions8.3 How does deep learning work in a supervised manner?8.3.1 Supervised learning algorithms8.3.2 Step 1: Feed-forward propagation8.3.3 Step 2: Adding the loss function8.3.4 Step 3: Calculating the error8.4 Backpropagation8.4.1 The mathematics behind backpropagation8.4.2 Step 4: Optimization8.5 How deep learning works in an unsupervised manner8.6 Convolutional neural networks8.6.1 Key concepts of CNN8.6.2 Use of CNN8.7 Recurrent neural networks8.7.1 Key concepts of RNN8.8 Boltzmann learning rule8.8.1 Concepts of the Boltzmann learning rule8.8.2 Key points8.9 Deep belief networks8.9.1 Key points of DBN8.10 Popular deep learning libraries8.10.1 Python code for Keras and TF8.11 Concluding thoughts8.12 Practical next steps and suggested readings
9 Autoencoders
9.1 Technical toolkit9.2 Feature learning9.3 Introducing autoencoders9.4 Components of autoencoders9.5 Training of autoencoders9.6 Application of autoencoders9.7 Types of autoencoders9.8 Python implementation of autoencoders9.9 Concluding thoughts9.10 Practical next steps and suggested readings
10 Generative adversarial networks, generative AI, and ChatGPT
10.1 AI: A transformation10.2 GenAI and its significance10.3 Discriminative models and GenAI10.4 Generative adversarial networks10.4.1 The generator network10.4.2 The discriminator network10.4.3 Adversarial training10.4.4 Variants and applications of GANs10.4.5 BERT, GPT-3, and others10.5 ChatGPT and its details10.5.1 Key features of ChatGPT10.5.2 Applications of ChatGPT10.6 Integration of GenAI10.7 Concluding thoughts10.8 Practical next steps and suggested readings
11 End-to-end model deployment
11.1 The machine learning modeling process11.2 Business problem definition11.3 Data discovery and feasibility analysis11.4 Data cleaning and prepreparation11.5 Duplicate values in the data11.6 Categorical variables11.7 Missing values in dataset11.8 Outliers present in the data11.9 Exploratory data analysis11.10 Model development and business approval11.11 Model deployment11.12 Purpose of model deployment11.13 Types of model deployment11.14 Considerations while deploying the model11.15 Documentation11.16 Model maintenance and refresh11.17 Concluding thoughts11.18 Practical next steps and suggested readings
appendix A Mathematical foundations
A.1 List of clustering algorithmsA.1.1 Partitioning-based algorithmsA.1.2 Hierarchical clusteringA.1.3 Density-based algorithmsA.1.4 Grid-based algorithmsA.1.5 Model-based algorithmsA.1.6 Spectral clusteringA.1.7 Graph-based clusteringA.1.8 Subspace and high-dimensional clusteringA.1.9 Fuzzy and soft clusteringA.1.10 Constraint-based clusteringA.1.11 Evolutionary and genetic clusteringA.1.12 Neural network-based clusteringA.1.13 Other algorithmsA.2 What is a centroid?A.3 L1 vs. L2 normA.4 Different scaling techniques used in the industryA.5 Time complexity O(n)A.6 How to install packages in PythonA.7 CorrelationA.7.1 Correlation coefficientA.7.2 Uses of correlationA.7.3 Important considerationsA.8 Time-series analysisA.9 Mathematical foundation for data representationA.9.1 Scalar and vectorA.9.2 Standard deviation and varianceA.9.3 Covariance and correlationA.9.4 Matrix decomposition, eigenvectors, and eigenvaluesA.9.5 Special matricesA.10 Hyperparameters vs. parameters

Content preview from Data Without Labels

Part 1 Basics

Welcome to part 1.

Machine learning and AI are not magic. Neither are they a secret art that can be understood only by a select few. At their core, they are simply a way for us to help the algorithms assimilate historical datasets and generate insights for us. These insights help us to initiate better, faster, and more influential business effects We give clear, logical instructions that guide the algorithms to do what we want.

But, like any art, learning machine learning and AI take practice. It’s not about memorizing Python or R or a programming language syntax or learning some commands to run the code or cut-paste the code. It’s about solving pragmatic business problems, thinking about the business objectives critically, ...

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

Publisher Resources

ISBN: 9781617298721Publisher Support Publisher Website

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

Data Without Labels

by Vaibhav Verdhan

Part 1 Basics

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.