Contents
Foreword
v
Preface
xxiii
Updated and revised content
xxvii
Acknowledgments
xxix
Part I Machine learning tools and techniques
1
1
What’s it all about?
3
1.1
Data mining and machine learning
4
Describing structural patterns
6
Machine learning
7
Data mining
9
1.2
Simple examples: The weather problem and others
9
The weather problem
10
Contact lenses: An idealized problem
13
Irises: A classic numeric dataset
15
CPU performance: Introducing numeric prediction
16
Labor negotiations: A more realistic example
17
Soybean classification: A classic machine learning success
18
1.3
Fielded applications
22
Decisions involving judgment
22
Screening images
23
Load forecasting
24
Diagnosis
25
Marketing and sales
26
Other applications
28
v i i
P088407-FM.qxd 4/30/05 10:55 AM Page vii
1.4
Machine learning and statistics
29
1.5
Generalization as search
30
Enumerating the concept space
31
Bias
32
1.6
Data mining and ethics
35
1.7
Further reading
37
2
Input: Concepts, instances, and attributes
41
2.1
What’s a concept?
42
2.2
What’s in an example?
45
2.3
What’s in an attribute?
49
2.4
Preparing the input
52
Gathering the data together
52
ARFF format
53
Sparse data
55
Attribute types
56
Missing values
58
Inaccurate values
59
Getting to know your data
60
2.5
Further reading
60
3
Output: Knowledge representation
61
3.1
Decision tables
62
3.2
Decision trees
62
3.3
Classification rules
65
3.4
Association rules
69
3.5
Rules with exceptions
70
3.6
Rules involving relations
73
3.7
Trees for numeric prediction
76
3.8
Instance-based representation
76
3.9
Clusters
81
3.10
Further reading
82
v i i i
C O N T E N TS
P088407-FM.qxd 4/30/05 10:55 AM Page viii
4
Algorithms: The basic methods
83
4.1
Inferring rudimentary rules
84
Missing values and numeric attributes
86
Discussion
88
4.2
Statistical modeling
88
Missing values and numeric attributes
92
Bayesian models for document classification
94
Discussion
96
4.3
Divide-and-conquer: Constructing decision trees
97
Calculating information
100
Highly branching attributes
102
Discussion
105
4.4
Covering algorithms: Constructing rules
105
Rules versus trees
107
A simple covering algorithm
107
Rules versus decision lists
111
4.5
Mining association rules
112
Item sets
113
Association rules
113
Generating rules efficiently
117
Discussion
118
4.6
Linear models
119
Numeric prediction: Linear regression
119
Linear classification: Logistic regression
121
Linear classification using the perceptron
124
Linear classification using Winnow
126
4.7
Instance-based learning
128
The distance function
128
Finding nearest neighbors efficiently
129
Discussion
135
4.8
Clustering
136
Iterative distance-based clustering
137
Faster distance calculations
138
Discussion
139
4.9
Further reading
139
C O N T E N TS
i x
P088407-FM.qxd 4/30/05 10:55 AM Page ix