Applied Unsupervised Learning with R电子书

Preface

About the Book

About the Authors

Elevator Pitch

Key Features

Description

Learning Objectives

Audience

Approach

Hardware Requirements

Software Requirements

Conventions

Installation and Setup

Installing R on Windows

Installing R on macOS X

Installing R on Linux

Chapter 1

Introduction to Clustering Methods

Introduction

Introduction to Clustering

Uses of Clustering

Introduction to the Iris Dataset

Exercise 1: Exploring the Iris Dataset

Types of Clustering

Introduction to k-means Clustering

Euclidean Distance

Manhattan Distance

Cosine Distance

The Hamming Distance

k-means Clustering Algorithm

Steps to Implement k-means Clustering

Exercise 2: Implementing k-means Clustering on the Iris Dataset

Activity 1: k-means Clustering with Three Clusters

Introduction to k-means Clustering with Built-In Functions

k-means Clustering with Three Clusters

Exercise 3: k-means Clustering with R Libraries

Introduction to Market Segmentation

Exercise 4: Exploring the Wholesale Customer Dataset

Activity 2: Customer Segmentation with k-means

Introduction to k-medoids Clustering

The k-medoids Clustering Algorithm

k-medoids Clustering Code

Exercise 5: Implementing k-medoid Clustering

k-means Clustering versus k-medoids Clustering

Activity 3: Performing Customer Segmentation with k-medoids Clustering

Deciding the Optimal Number of Clusters

Types of Clustering Metrics

Silhouette Score

Exercise 6: Calculating the Silhouette Score

Exercise 7: Identifying the Optimum Number of Clusters

WSS/Elbow Method

Exercise 8: Using WSS to Determine the Number of Clusters

The Gap Statistic

Exercise 9: Calculating the Ideal Number of Clusters with the Gap Statistic

Activity 4: Finding the Ideal Number of Market Segments

Summary

Chapter 2

Advanced Clustering Methods

Introduction

Introduction to k-modes Clustering

Steps for k-Modes Clustering

Exercise 10: Implementing k-modes Clustering

Activity 5: Implementing k-modes Clustering on the Mushroom Dataset

Introduction to Density-Based Clustering (DBSCAN)

Steps for DBSCAN

Exercise 11: Implementing DBSCAN

Uses of DBSCAN

Activity 6: Implementing DBSCAN and Visualizing the Results

Introduction to Hierarchical Clustering

Types of Similarity Metrics

Steps to Perform Agglomerative Hierarchical Clustering

Exercise 12: Agglomerative Clustering with Different Similarity Measures

Divisive Clustering

Steps to Perform Divisive Clustering

Exercise 13: Performing DIANA Clustering

Activity 7: Performing Hierarchical Cluster Analysis on the Seeds Dataset

Summary

Chapter 3

Probability Distributions

Introduction

Basic Terminology of Probability Distributions

Uniform Distribution

Exercise 14: Generating and Plotting Uniform Samples in R

Normal Distribution

Exercise 15: Generating and Plotting a Normal Distribution in R

Skew and Kurtosis

Log-Normal Distributions

Exercise 16: Generating a Log-Normal Distribution from a Normal Distribution

The Binomial Distribution

Exercise 17: Generating a Binomial Distribution

The Poisson Distribution

The Pareto Distribution

Introduction to Kernel Density Estimation

KDE Algorithm

Exercise 18: Visualizing and Understanding KDE

Exercise 19: Studying the Effect of Changing Kernels on a Distribution

Activity 8: Finding the Standard Distribution Closest to the Distribution of Variables of the Iris Dataset

Introduction to the Kolmogorov-Smirnov Test

The Kolmogorov-Smirnov Test Algorithm

Exercise 20: Performing the Kolmogorov-Smirnov Test on Two Samples

Activity 9: Calculating the CDF and Performing the Kolmogorov-Smirnov Test with the Normal Distribution

Summary

Chapter 4

Dimension Reduction

Introduction

The Idea of Dimension Reduction

Exercise 21: Examining a Dataset that Contains the Chemical Attributes of Different Wines

Importance of Dimension Reduction

Market Basket Analysis

Exercise 22: Data Preparation for the Apriori Algorithm

Exercise 23: Passing through the Data to Find the Most Common Baskets

Exercise 24: More Passes through the Data

Exercise 25: Generating Associative Rules as the Final Step of the Apriori Algorithm

Principal Component Analysis

Linear Algebra Refresher

Matrices

Variance

Covariance

Exercise 26: Examining Variance and Covariance on the Wine Dataset

Eigenvectors and Eigenvalues

The Idea of PCA

Exercise 27: Performing PCA

Exercise 28: Performing Dimension Reduction with PCA

Activity 10: Performing PCA and Market Basket Analysis on a New Dataset

Summary

Chapter 5

Data Comparison Methods

Introduction

Hash Functions

Exercise 29: Creating and Using a Hash Function

Exercise 30: Verifying Our Hash Function

Analytic Signatures

Exercise 31: Perform the Data Preparation for Creating an Analytic Signature for an Image

Exercise 32: Creating a Brightness Comparison Function

Exercise 33: Creating a Function to Compare Image Sections to All of the Neighboring Sections

Exercise 34: Creating a Function that Generates an Analytic Signature for an Image

Activity 11: Creating an Image Signature for a Photograph of a Person

Comparison of Signatures

Activity 12: Creating an Image Signature for the Watermarked Image

Applying Other Unsupervised Learning Methods to Analytic Signatures

Latent Variable Models – Factor Analysis

Exercise 35: Preparing for Factor Analysis

Linear Algebra behind Factor Analysis

Exercise 36: More Exploration with Factor Analysis

Activity 13: Performing Factor Analysis

Summary

Chapter 6

Anomaly Detection

Introduction

Univariate Outlier Detection

Exercise 37: Performing an Exploratory Visual Check for Outliers Using R's boxplot Function

Exercise 38: Transforming a Fat-Tailed Dataset to Improve Outlier Classification

Exercise 39: Finding Outliers without Using R's Built-In boxplot Function

Exercise 40: Detecting Outliers Using a Parametric Method

Multivariate Outlier Detection

Exercise 41: Calculating Mahalanobis Distance

Detecting Anomalies in Clusters

Other Methods for Multivariate Outlier Detection

Exercise 42: Classifying Outliers based on Comparisons of Mahalanobis Distances

Detecting Outliers in Seasonal Data

Exercise 43: Performing Seasonality Modeling

Exercise 44: Finding Anomalies in Seasonal Data Using a Parametric Method

Contextual and Collective Anomalies

Exercise 45: Detecting Contextual Anomalies

Exercise 46: Detecting Collective Anomalies

Kernel Density

Exercise 47: Finding Anomalies Using Kernel Density Estimation

Continuing in Your Studies of Anomaly Detection

Activity 14: Finding Univariate Anomalies Using a Parametric Method and a Non-parametric Method

Activity 15: Using Mahalanobis Distance to Find Anomalies

Summary

Appendix

Chapter 1: Introduction to Clustering Methods

Activity 1: k-means Clustering with Three Clusters

Activity 2: Customer Segmentation with k-means

Activity 3: Performing Customer Segmentation with k-medoids Clustering

Activity 4: Finding the Ideal Number of Market Segments

Chapter 2: Advanced Clustering Methods

Activity 5: Implementing k-modes Clustering on the Mushroom Dataset

Activity 6: Implementing DBSCAN and Visualizing the Results

Activity 7: Performing a Hierarchical Cluster Analysis on the Seeds Dataset

Chapter 3: Probability Distributions

Activity 8: Finding the Standard Distribution Closest to the Distribution of Variables of the Iris Dataset

Activity 9: Calculating the CDF and Performing the Kolmogorov-Simonov Test with the Normal Distribution

Chapter 4: Dimension Reduction

Activity 10: Performing PCA and Market Basket Analysis on a New Dataset

Chapter 5: Data Comparison Methods

Activity 11: Create an Image Signature for a Photograph of a Person

Activity 12: Create an Image Signature for the Watermarked Image

Activity 13: Performing Factor Analysis

Chapter 6: Anomaly Detection

Activity 14: Finding Univariate Anomalies Using a Parametric Method and a Non-parametric Method

Activity 15: Using Mahalanobis Distance to Find Anomalies