| |
| |
| Foreword | |
| |
| |
| Preface | |
| |
| |
| |
| What's it all about? | |
| |
| |
| |
| Data mining and machine learning | |
| |
| |
| Describing structural patterns | |
| |
| |
| Machine learning | |
| |
| |
| Data mining | |
| |
| |
| |
| Simple examples: The weather problem and others | |
| |
| |
| The weather problem | |
| |
| |
| Contact lenses: An idealized problem | |
| |
| |
| Irises: A classic numeric dataset | |
| |
| |
| CPU performance: Introducing numeric prediction | |
| |
| |
| Labor negotiations: A more realistic example | |
| |
| |
| Soybean classification: A classic machine learning success | |
| |
| |
| |
| Fielded applications | |
| |
| |
| Decisions involving judgment | |
| |
| |
| Screening images | |
| |
| |
| Load forecasting | |
| |
| |
| Diagnosis | |
| |
| |
| Marketing and sales | |
| |
| |
| |
| Machine learning and statistics | |
| |
| |
| |
| Generalization as search | |
| |
| |
| Enumerating the concept space | |
| |
| |
| Bias | |
| |
| |
| |
| Data mining and ethics | |
| |
| |
| |
| Further reading | |
| |
| |
| |
| Input: Concepts, instances, attributes | |
| |
| |
| |
| What's a concept? | |
| |
| |
| |
| What's in an example? | |
| |
| |
| |
| What's in an attribute? | |
| |
| |
| |
| Preparing the input | |
| |
| |
| Gathering the data together | |
| |
| |
| Arff format | |
| |
| |
| Attribute types | |
| |
| |
| Missing values | |
| |
| |
| Inaccurate values | |
| |
| |
| Getting to know your data | |
| |
| |
| |
| Further reading | |
| |
| |
| |
| Output: Knowledge representation | |
| |
| |
| |
| Decision tables | |
| |
| |
| |
| Decision trees | |
| |
| |
| |
| Classification rules | |
| |
| |
| |
| Association rules | |
| |
| |
| |
| Rules with exceptions | |
| |
| |
| |
| Rules involving relations | |
| |
| |
| |
| Trees for numeric prediction | |
| |
| |
| |
| Instance-based representation | |
| |
| |
| |
| Clusters | |
| |
| |
| |
| Further reading | |
| |
| |
| |
| Algorithms: The basic methods | |
| |
| |
| |
| Inferring rudimentary rules | |
| |
| |
| Missing values and numeric attributes | |
| |
| |
| Discussion | |
| |
| |
| |
| Statistical modeling | |
| |
| |
| Missing values and numeric attributes | |
| |
| |
| Discussion | |
| |
| |
| |
| Divide and conquer: Constructing decision trees | |
| |
| |
| Calculating information | |
| |
| |
| Highly branching attributes | |
| |
| |
| Discussion | |
| |
| |
| |
| Covering algorithms: Constructing rules | |
| |
| |
| Rules versus trees | |
| |
| |
| A simple covering algorithm | |
| |
| |
| Rules versus decision lists | |
| |
| |
| |
| Mining association rules | |
| |
| |
| Item sets | |
| |
| |
| Association rules | |
| |
| |
| Generating rules efficiently | |
| |
| |
| Discussion | |
| |
| |
| |
| Linear models | |
| |
| |
| Numeric prediction | |
| |
| |
| Classification | |
| |
| |
| Discussion | |
| |
| |
| |
| Instance-based learning | |
| |
| |
| The distance function | |
| |
| |
| Discussion | |
| |
| |
| |
| Further reading | |
| |
| |
| |
| Credibility: Evaluating what's been learned | |
| |
| |
| |
| Training and testing | |
| |
| |
| |
| Predicting performance | |
| |
| |
| |
| Cross-validation | |
| |
| |
| |
| Other estimates | |
| |
| |
| Leave-one-out | |
| |
| |
| The bootstrap | |
| |
| |
| |
| Comparing data mining schemes | |
| |
| |
| |
| Predicting probabilities | |
| |
| |
| Quadratic loss function | |
| |
| |
| Informational loss function | |
| |
| |
| Discussion | |
| |
| |
| |
| Counting the cost | |
| |
| |
| Lift charts | |
| |
| |
| ROC curves | |
| |
| |
| Cost-sensitive learning | |
| |
| |
| Discussion | |
| |
| |
| |
| Evaluating numeric prediction | |
| |
| |
| |
| The minimum description length principle | |
| |
| |
| |
| Applying MDL to clustering | |
| |
| |
| |
| Further reading | |
| |
| |
| |
| Implementations: Real machine learning schemes | |
| |
| |
| |
| Decision trees | |
| |
| |
| Numeric attributes | |
| |
| |
| Missing values | |
| |
| |
| Pruning | |
| |
| |
| Estimating error rates | |
| |
| |
| Complexity of decision tree induction | |
| |
| |
| From trees to rules | |
| |
| |
| C4.5: Choices and options | |
| |
| |
| Discussion | |
| |
| |
| |
| Classification rules | |
| |
| |
| Criteria for choosing tests | |
| |
| |
| Missing values, numeric attributes | |
| |
| |
| Good rules and bad rules | |
| |
| |
| Generating good rules | |
| |
| |
| Generating good decision lists | |
| |
| |
| Probability measure for rule evaluation | |
| |
| |
| Evaluating rules using a test set | |
| |
| |
| Obtaining rules from partial decision trees | |
| |
| |
| Rules with exceptions | |
| |
| |
| Discussion | |
| |
| |
| |
| Extending linear classification: Support vector machines | |
| |
| |
| The maximum margin hyperplane | |
| |
| |
| Nonlinear class boundaries | |
| |
| |
| Discussion | |
| |
| |
| |
| Instance-based learning | |
| |
| |
| Reducing the number of exemplars | |
| |
| |
| Pruning noisy exemplars | |
| |
| |
| Weighting attributes | |
| |
| |
| Generalizing exemplars | |
| |
| |
| Distance functions for generalized exemplars | |
| |
| |
| Generalized distance functions | |
| |
| |
| Discussion | |
| |
| |
| |
| Numeric prediction | |
| |
| |
| Model trees | |
| |
| |
| Building the tree | |
| |
| |
| Pruning the tree | |
| |
| |
| Nominal attributes | |
| |
| |
| Missing values | |
| |
| |
| Pseudo-code for model tree induction | |
| |
| |
| Locally weighted linear regression | |
| |
| |
| Discussion | |
| |
| |
| |
| Clustering | |
| |
| |
| Iterative distance-based clustering | |
| |
| |
| Incremental clustering | |
| |
| |
| Category utility | |
| |
| |
| Probability-based clustering | |
| |
| |
| The EM algorithm | |
| |
| |
| Extending the mixture model | |
| |
| |
| Bayesian clustering | |
| |
| |
| Discussion | |
| |
| |
| |
| Moving on: Engineering the input and output | |
| |
| |
| |
| Attribute selection | |
| |
| |
| Scheme-independent selection | |
| |
| |
| Searching the attribute space | |
| |
| |
| Scheme-specific selection | |
| |
| |
| |
| Discretizing numeric attributes | |
| |
| |
| Unsupervised discretization | |
| |
| |
| Entropy-based discretization | |
| |
| |
| Other discretization methods | |
| |
| |
| Entropy-based versus error-based discretization | |
| |
| |
| Converting discrete to numeric attributes | |
| |
| |
| |
| Automatic data cleansing | |
| |
| |
| Improving decision trees | |
| |
| |
| Robust regression | |
| |
| |
| Detecting anomalies | |
| |
| |
| |
| Combining multiple models | |
| |
| |
| Bagging | |
| |
| |
| Boosting | |
| |
| |
| Stacking | |
| |
| |
| Error-correcting output codes | |
| |
| |
| |
| Further reading | |
| |
| |
| |
| Nuts and bolts: Machine learning algorithms in Java | |
| |
| |
| |
| Getting started | |
| |
| |
| |
| Javadoc and the class library | |
| |
| |
| Classes, instances, and packages | |
| |
| |
| The weka.core package | |
| |
| |
| The weka.classifiers package | |
| |
| |
| Other packages | |
| |
| |
| Indexes | |
| |
| |
| |
| Processing datasets using the machine learning programs | |
| |
| |
| Using M5' | |
| |
| |
| Generic options | |
| |
| |
| Scheme-specific options | |
| |
| |
| Classifiers | |
| |
| |
| Meta-learning shemes | |
| |
| |
| Filters | |
| |
| |
| Association rules | |
| |
| |
| Clustering | |
| |
| |
| |
| Embedded machine learning | |
| |
| |
| A simple message classifier | |
| |
| |
| |
| Writing new learning schemes | |
| |
| |
| An example classifier | |
| |
| |
| Conventions for implementing classifiers | |
| |
| |
| Writing filters | |
| |
| |
| An example filter | |
| |
| |
| Conventions for writing filters | |
| |
| |
| |
| Looking forward | |
| |
| |
| |
| Learning from massive datasets | |
| |
| |
| |
| Visualizing machine learning | |
| |
| |
| Visualizing the input | |
| |
| |
| Visualizing the output | |
| |
| |
| |
| Incorporating domain knowledge | |
| |
| |
| |
| Text mining | |
| |
| |
| Finding key phrases for documents | |
| |
| |
| Finding information in running text | |
| |
| |
| Soft parsing | |
| |
| |
| |
| Mining the World Wide Web | |
| |
| |
| |
| Further reading | |
| |
| |
| References | |
| |
| |
| Index | |
| |
| |
| About the authors | |