/**
* Gets the subset of instances that apply to a particluar branch of the split. If the branch
* index is -1, the subset will consist of those instances that don't apply to any branch.
*
* @param branch the index of the branch
* @param sourceInstances the instances from which to find the subset
* @return the set of instances that apply
*/
public ReferenceInstances instancesDownBranch(int branch, Instances instances) {
ReferenceInstances filteredInstances = new ReferenceInstances(instances, 1);
if (branch == -1) {
for (Enumeration e = instances.enumerateInstances(); e.hasMoreElements(); ) {
Instance inst = (Instance) e.nextElement();
if (inst.isMissing(attIndex)) filteredInstances.addReference(inst);
}
} else if (branch == 0) {
for (Enumeration e = instances.enumerateInstances(); e.hasMoreElements(); ) {
Instance inst = (Instance) e.nextElement();
if (!inst.isMissing(attIndex) && inst.value(attIndex) < splitPoint)
filteredInstances.addReference(inst);
}
} else {
for (Enumeration e = instances.enumerateInstances(); e.hasMoreElements(); ) {
Instance inst = (Instance) e.nextElement();
if (!inst.isMissing(attIndex) && inst.value(attIndex) >= splitPoint)
filteredInstances.addReference(inst);
}
}
return filteredInstances;
}
/**
* Returns an enumeration describing the available options.
*
* @return an enumeration of all the available options.
*/
public Enumeration listOptions() {
Vector newVector = new Vector(7);
newVector.addElement(
new Option(
"\tFull class name of search method, followed\n"
+ "\tby its options.\n"
+ "\teg: \"weka.attributeSelection.BestFirst -D 1\"\n"
+ "\t(default weka.attributeSelection.BestFirst)",
"S",
1,
"-S <search method specification>"));
newVector.addElement(
new Option(
"\tUse cross validation to evaluate features.\n"
+ "\tUse number of folds = 1 for leave one out CV.\n"
+ "\t(Default = leave one out CV)",
"X",
1,
"-X <number of folds>"));
newVector.addElement(
new Option(
"\tPerformance evaluation measure to use for selecting attributes.\n"
+ "\t(Default = accuracy for discrete class and rmse for numeric class)",
"E",
1,
"-E <acc | rmse | mae | auc>"));
newVector.addElement(
new Option("\tUse nearest neighbour instead of global table majority.", "I", 0, "-I"));
newVector.addElement(new Option("\tDisplay decision table rules.\n", "R", 0, "-R"));
newVector.addElement(
new Option(
"",
"",
0,
"\nOptions specific to search method " + m_search.getClass().getName() + ":"));
Enumeration enu = ((OptionHandler) m_search).listOptions();
while (enu.hasMoreElements()) {
newVector.addElement(enu.nextElement());
}
return newVector.elements();
}
/**
* Returns an enumeration describing the available options
*
* @return an enumeration of all the available options
*/
public Enumeration listOptions() {
Vector newVector = new Vector(8);
newVector.addElement(
new Option("\tDesired size of ensemble.\n" + "\t(default 10)", "E", 1, "-E"));
newVector.addElement(
new Option(
"\tFactor that determines number of artificial examples to generate.\n"
+ "\tSpecified proportional to training set size.\n"
+ "\t(default 1.0)",
"R",
1,
"-R"));
Enumeration enu = super.listOptions();
while (enu.hasMoreElements()) {
newVector.addElement(enu.nextElement());
}
return newVector.elements();
}
/**
* Returns a description of the classifier.
*
* @return a description of the classifier as a string.
*/
public String toString() {
if (m_entries == null) {
return "Decision Table: No model built yet.";
} else {
StringBuffer text = new StringBuffer();
text.append(
"Decision Table:"
+ "\n\nNumber of training instances: "
+ m_numInstances
+ "\nNumber of Rules : "
+ m_entries.size()
+ "\n");
if (m_useIBk) {
text.append("Non matches covered by IB1.\n");
} else {
text.append("Non matches covered by Majority class.\n");
}
text.append(m_search.toString());
/*text.append("Best first search for feature set,\nterminated after "+
m_maxStale+" non improving subsets.\n"); */
text.append("Evaluation (for feature selection): CV ");
if (m_CVFolds > 1) {
text.append("(" + m_CVFolds + " fold) ");
} else {
text.append("(leave one out) ");
}
text.append("\nFeature set: " + printFeatures());
if (m_displayRules) {
// find out the max column width
int maxColWidth = 0;
for (int i = 0; i < m_dtInstances.numAttributes(); i++) {
if (m_dtInstances.attribute(i).name().length() > maxColWidth) {
maxColWidth = m_dtInstances.attribute(i).name().length();
}
if (m_classIsNominal || (i != m_dtInstances.classIndex())) {
Enumeration e = m_dtInstances.attribute(i).enumerateValues();
while (e.hasMoreElements()) {
String ss = (String) e.nextElement();
if (ss.length() > maxColWidth) {
maxColWidth = ss.length();
}
}
}
}
text.append("\n\nRules:\n");
StringBuffer tm = new StringBuffer();
for (int i = 0; i < m_dtInstances.numAttributes(); i++) {
if (m_dtInstances.classIndex() != i) {
int d = maxColWidth - m_dtInstances.attribute(i).name().length();
tm.append(m_dtInstances.attribute(i).name());
for (int j = 0; j < d + 1; j++) {
tm.append(" ");
}
}
}
tm.append(m_dtInstances.attribute(m_dtInstances.classIndex()).name() + " ");
for (int i = 0; i < tm.length() + 10; i++) {
text.append("=");
}
text.append("\n");
text.append(tm);
text.append("\n");
for (int i = 0; i < tm.length() + 10; i++) {
text.append("=");
}
text.append("\n");
Enumeration e = m_entries.keys();
while (e.hasMoreElements()) {
DecisionTableHashKey tt = (DecisionTableHashKey) e.nextElement();
text.append(tt.toString(m_dtInstances, maxColWidth));
double[] ClassDist = (double[]) m_entries.get(tt);
if (m_classIsNominal) {
int m = Utils.maxIndex(ClassDist);
try {
text.append(m_dtInstances.classAttribute().value(m) + "\n");
} catch (Exception ee) {
System.out.println(ee.getMessage());
}
} else {
text.append((ClassDist[0] / ClassDist[1]) + "\n");
}
}
for (int i = 0; i < tm.length() + 10; i++) {
text.append("=");
}
text.append("\n");
text.append("\n");
}
return text.toString();
}
}