weka的ID3 source code

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
/*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/

/*
* Id3.java
* Copyright (C) 1999 University of Waikato, Hamilton, New Zealand
*
*/

package weka.classifiers.trees;

import java.util.Enumeration;

import weka.classifiers.AbstractClassifier;
import weka.classifiers.Sourcable;
import weka.core.Attribute;
import weka.core.Capabilities;
import weka.core.Capabilities.Capability;
import weka.core.Instance;
import weka.core.Instances;
import weka.core.NoSupportForMissingValuesException;
import weka.core.RevisionUtils;
import weka.core.TechnicalInformation;
import weka.core.TechnicalInformation.Field;
import weka.core.TechnicalInformation.Type;
import weka.core.TechnicalInformationHandler;
import weka.core.Utils;

/**
* <!-- globalinfo-start --> Class for constructing an unpruned decision tree
* based on the ID3 algorithm. Can only deal with nominal attributes. No missing
* values allowed. Empty leaves may result in unclassified instances. For more
* information see: <br/>
* <br/>
* R. Quinlan (1986). Induction of decision trees. Machine Learning.
* 1(1):81-106.
* <p/>
* <!-- globalinfo-end -->
*
* <!-- technical-bibtex-start --> BibTeX:
*
* <pre>
* &#64;article{Quinlan1986,
* author = {R. Quinlan},
* journal = {Machine Learning},
* number = {1},
* pages = {81-106},
* title = {Induction of decision trees},
* volume = {1},
* year = {1986}
* }
* </pre>
* <p/>
* <!-- technical-bibtex-end -->
*
* <!-- options-start --> Valid options are:
* <p/>
*
* <pre>
* -D
* If set, classifier is run in debug mode and
* may output additional info to the console
* </pre>
*
* <!-- options-end -->
*
* @author Eibe Frank ([email protected])
* @version $Revision$
*/
public class Id3 extends AbstractClassifier implements
TechnicalInformationHandler, Sourcable {

/** for serialization */
static final long serialVersionUID = -2693678647096322561L;

/** The node's successors. */
private Id3[] m_Successors;

/** Attribute used for splitting. */
private Attribute m_Attribute;

/** Class value if node is leaf. */
private double m_ClassValue;

/** Class distribution if node is leaf. */
private double[] m_Distribution;

/** Class attribute of dataset. */
private Attribute m_ClassAttribute;

/**
* Returns a string describing the classifier.
*
* @return a description suitable for the GUI.
*/
public String globalInfo() {

return "Class for constructing an unpruned decision tree based on the ID3 "
+ "algorithm. Can only deal with nominal attributes. No missing values "
+ "allowed. Empty leaves may result in unclassified instances. For more "
+ "information see: \n\n" + getTechnicalInformation().toString();
}

/**
* Returns an instance of a TechnicalInformation object, containing detailed
* information about the technical background of this class, e.g., paper
* reference or book this class is based on.
*
* @return the technical information about this class
*/
@Override
public TechnicalInformation getTechnicalInformation() {
TechnicalInformation result;

result = new TechnicalInformation(Type.ARTICLE);
result.setValue(Field.AUTHOR, "R. Quinlan");
result.setValue(Field.YEAR, "1986");
result.setValue(Field.TITLE, "Induction of decision trees");
result.setValue(Field.JOURNAL, "Machine Learning");
result.setValue(Field.VOLUME, "1");
result.setValue(Field.NUMBER, "1");
result.setValue(Field.PAGES, "81-106");

return result;
}

/**
* Returns default capabilities of the classifier.
*
* @return the capabilities of this classifier
*/
@Override
public Capabilities getCapabilities() {
Capabilities result = super.getCapabilities();
result.disableAll();

// attributes
result.enable(Capability.NOMINAL_ATTRIBUTES);

// class
result.enable(Capability.NOMINAL_CLASS);
result.enable(Capability.MISSING_CLASS_VALUES);

// instances
result.setMinimumNumberInstances(0);

return result;
}

/**
* Builds Id3 decision tree classifier.
*
* @param data the training data
* @exception Exception if classifier can't be built successfully
*/
@Override
public void buildClassifier(Instances data) throws Exception {

// can classifier handle the data?
getCapabilities().testWithFail(data);

// remove instances with missing class
data = new Instances(data);
data.deleteWithMissingClass();

makeTree(data);
}

/**
* Method for building an Id3 tree.
*
* @param data the training data
* @exception Exception if decision tree can't be built successfully
*/
private void makeTree(Instances data) throws Exception {

// Check if no instances have reached this node.
if (data.numInstances() == 0) {
m_Attribute = null;
m_ClassValue = Utils.missingValue();
m_Distribution = new double[data.numClasses()];
return;
}

// Compute attribute with maximum information gain.
double[] infoGains = new double[data.numAttributes()];
Enumeration<Attribute> attEnum = data.enumerateAttributes();
while (attEnum.hasMoreElements()) {
Attribute att = attEnum.nextElement();
infoGains[att.index()] = computeInfoGain(data, att);
}
m_Attribute = data.attribute(Utils.maxIndex(infoGains));

// Make leaf if information gain is zero.
// Otherwise create successors.
if (Utils.eq(infoGains[m_Attribute.index()], 0)) {
m_Attribute = null;
m_Distribution = new double[data.numClasses()];
Enumeration<Instance> instEnum = data.enumerateInstances();
while (instEnum.hasMoreElements()) {
Instance inst = instEnum.nextElement();
m_Distribution[(int) inst.classValue()]++;
}
Utils.normalize(m_Distribution);
m_ClassValue = Utils.maxIndex(m_Distribution);
m_ClassAttribute = data.classAttribute();
} else {
Instances[] splitData = splitData(data, m_Attribute);
m_Successors = new Id3[m_Attribute.numValues()];
for (int j = 0; j < m_Attribute.numValues(); j++) {
m_Successors[j] = new Id3();
m_Successors[j].makeTree(splitData[j]);
}
}
}

/**
* Classifies a given test instance using the decision tree.
*
* @param instance the instance to be classified
* @return the classification
* @throws NoSupportForMissingValuesException if instance has missing values
*/
@Override
public double classifyInstance(Instance instance)
throws NoSupportForMissingValuesException {

if (instance.hasMissingValue()) {
throw new NoSupportForMissingValuesException("Id3: no missing values, "
+ "please.");
}
if (m_Attribute == null) {
return m_ClassValue;
} else {
return m_Successors[(int) instance.value(m_Attribute)]
.classifyInstance(instance);
}
}

/**
* Computes class distribution for instance using decision tree.
*
* @param instance the instance for which distribution is to be computed
* @return the class distribution for the given instance
* @throws NoSupportForMissingValuesException if instance has missing values
*/
@Override
public double[] distributionForInstance(Instance instance)
throws NoSupportForMissingValuesException {

if (instance.hasMissingValue()) {
throw new NoSupportForMissingValuesException("Id3: no missing values, "
+ "please.");
}
if (m_Attribute == null) {
return m_Distribution;
} else {
return m_Successors[(int) instance.value(m_Attribute)]
.distributionForInstance(instance);
}
}

/**
* Prints the decision tree using the private toString method from below.
*
* @return a textual description of the classifier
*/
@Override
public String toString() {

if ((m_Distribution == null) && (m_Successors == null)) {
return "Id3: No model built yet.";
}
return "Id3\n\n" + toString(0);
}

/**
* Computes information gain for an attribute.
*
* @param data the data for which info gain is to be computed
* @param att the attribute
* @return the information gain for the given attribute and data
* @throws Exception if computation fails
*/
private double computeInfoGain(Instances data, Attribute att)
throws Exception {

double infoGain = computeEntropy(data);
Instances[] splitData = splitData(data, att);
for (int j = 0; j < att.numValues(); j++) {
if (splitData[j].numInstances() > 0) {
infoGain -= ((double) splitData[j].numInstances() / (double) data
.numInstances()) * computeEntropy(splitData[j]);
}
}
return infoGain;
}

/**
* Computes the entropy of a dataset.
*
* @param data the data for which entropy is to be computed
* @return the entropy of the data's class distribution
* @throws Exception if computation fails
*/
private double computeEntropy(Instances data) throws Exception {

double[] classCounts = new double[data.numClasses()];
Enumeration<Instance> instEnum = data.enumerateInstances();
while (instEnum.hasMoreElements()) {
Instance inst = instEnum.nextElement();
classCounts[(int) inst.classValue()]++;
}
double entropy = 0;
for (int j = 0; j < data.numClasses(); j++) {
if (classCounts[j] > 0) {
entropy -= classCounts[j] * Utils.log2(classCounts[j]);
}
}
entropy /= data.numInstances();
return entropy + Utils.log2(data.numInstances());
}

/**
* Splits a dataset according to the values of a nominal attribute.
*
* @param data the data which is to be split
* @param att the attribute to be used for splitting
* @return the sets of instances produced by the split
*/
private Instances[] splitData(Instances data, Attribute att) {

Instances[] splitData = new Instances[att.numValues()];
for (int j = 0; j < att.numValues(); j++) {
splitData[j] = new Instances(data, data.numInstances());
}
Enumeration<Instance> instEnum = data.enumerateInstances();
while (instEnum.hasMoreElements()) {
Instance inst = instEnum.nextElement();
splitData[(int) inst.value(att)].add(inst);
}
for (Instances element : splitData) {
element.compactify();
}
return splitData;
}

/**
* Outputs a tree at a certain level.
*
* @param level the level at which the tree is to be printed
* @return the tree as string at the given level
*/
private String toString(int level) {

StringBuffer text = new StringBuffer();

if (m_Attribute == null) {
if (Utils.isMissingValue(m_ClassValue)) {
text.append(": null");
} else {
text.append(": " + m_ClassAttribute.value((int) m_ClassValue));
}
} else {
for (int j = 0; j < m_Attribute.numValues(); j++) {
text.append("\n");
for (int i = 0; i < level; i++) {
text.append("| ");
}
text.append(m_Attribute.name() + " = " + m_Attribute.value(j));
text.append(m_Successors[j].toString(level + 1));
}
}
return text.toString();
}

/**
* Adds this tree recursively to the buffer.
*
* @param id the unqiue id for the method
* @param buffer the buffer to add the source code to
* @return the last ID being used
* @throws Exception if something goes wrong
*/
protected int toSource(int id, StringBuffer buffer) throws Exception {
int result;
int i;
int newID;
StringBuffer[] subBuffers;

buffer.append("\n");
buffer.append(" protected static double node" + id + "(Object[] i) {\n");

// leaf?
if (m_Attribute == null) {
result = id;
if (Double.isNaN(m_ClassValue)) {
buffer.append(" return Double.NaN;");
} else {
buffer.append(" return " + m_ClassValue + ";");
}
if (m_ClassAttribute != null) {
buffer.append(" // " + m_ClassAttribute.value((int) m_ClassValue));
}
buffer.append("\n");
buffer.append(" }\n");
} else {
buffer.append(" checkMissing(i, " + m_Attribute.index() + ");\n\n");
buffer.append(" // " + m_Attribute.name() + "\n");

// subtree calls
subBuffers = new StringBuffer[m_Attribute.numValues()];
newID = id;
for (i = 0; i < m_Attribute.numValues(); i++) {
newID++;

buffer.append(" ");
if (i > 0) {
buffer.append("else ");
}
buffer.append("if (((String) i[" + m_Attribute.index() + "]).equals(\""
+ m_Attribute.value(i) + "\"))\n");
buffer.append(" return node" + newID + "(i);\n");

subBuffers[i] = new StringBuffer();
newID = m_Successors[i].toSource(newID, subBuffers[i]);
}
buffer.append(" else\n");
buffer.append(" throw new IllegalArgumentException(\"Value '\" + i["
+ m_Attribute.index() + "] + \"' is not allowed!\");\n");
buffer.append(" }\n");

// output subtree code
for (i = 0; i < m_Attribute.numValues(); i++) {
buffer.append(subBuffers[i].toString());
}
subBuffers = null;

result = newID;
}

return result;
}

/**
* Returns a string that describes the classifier as source. The classifier
* will be contained in a class with the given name (there may be auxiliary
* classes), and will contain a method with the signature:
*
* <pre>
* <code>
* public static double classify(Object[] i);
* </code>
* </pre>
*
* where the array <code>i</code> contains elements that are either Double,
* String, with missing values represented as null. The generated code is
* public domain and comes with no warranty. <br/>
* Note: works only if class attribute is the last attribute in the dataset.
*
* @param className the name that should be given to the source class.
* @return the object source described by a string
* @throws Exception if the source can't be computed
*/
@Override
public String toSource(String className) throws Exception {
StringBuffer result;
int id;

result = new StringBuffer();

result.append("class " + className + " {\n");
result
.append(" private static void checkMissing(Object[] i, int index) {\n");
result.append(" if (i[index] == null)\n");
result.append(" throw new IllegalArgumentException(\"Null values "
+ "are not allowed!\");\n");
result.append(" }\n\n");
result.append(" public static double classify(Object[] i) {\n");
id = 0;
result.append(" return node" + id + "(i);\n");
result.append(" }\n");
toSource(id, result);
result.append("}\n");

return result.toString();
}

/**
* Returns the revision string.
*
* @return the revision
*/
@Override
public String getRevision() {
return RevisionUtils.extract("$Revision$");
}

/**
* Main method.
*
* @param args the options for the classifier
*/
public static void main(String[] args) {
runClassifier(new Id3(), args);
}
}