/**
* Gets the search specification string, which contains the class name of the search method and
* any options to it
*
* @return the search string.
*/
protected String getSearchSpec() {
ASSearch s = getSearch();
if (s instanceof OptionHandler) {
return s.getClass().getName() + " " + Utils.joinOptions(((OptionHandler) s).getOptions());
}
return s.getClass().getName();
}
/**
* 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();
}
/**
* Parses the options for this object.
*
* <p>
* <!-- options-start -->
* Valid options are:
*
* <p>
*
* <pre> -S <search method specification>
* Full class name of search method, followed
* by its options.
* eg: "weka.attributeSelection.BestFirst -D 1"
* (default weka.attributeSelection.BestFirst)</pre>
*
* <pre> -X <number of folds>
* Use cross validation to evaluate features.
* Use number of folds = 1 for leave one out CV.
* (Default = leave one out CV)</pre>
*
* <pre> -E <acc | rmse | mae | auc>
* Performance evaluation measure to use for selecting attributes.
* (Default = accuracy for discrete class and rmse for numeric class)</pre>
*
* <pre> -I
* Use nearest neighbour instead of global table majority.</pre>
*
* <pre> -R
* Display decision table rules.
* </pre>
*
* <pre>
* Options specific to search method weka.attributeSelection.BestFirst:
* </pre>
*
* <pre> -P <start set>
* Specify a starting set of attributes.
* Eg. 1,3,5-7.</pre>
*
* <pre> -D <0 = backward | 1 = forward | 2 = bi-directional>
* Direction of search. (default = 1).</pre>
*
* <pre> -N <num>
* Number of non-improving nodes to
* consider before terminating search.</pre>
*
* <pre> -S <num>
* Size of lookup cache for evaluated subsets.
* Expressed as a multiple of the number of
* attributes in the data set. (default = 1)</pre>
*
* <!-- options-end -->
*
* @param options the list of options as an array of strings
* @throws Exception if an option is not supported
*/
public void setOptions(String[] options) throws Exception {
String optionString;
resetOptions();
optionString = Utils.getOption('X', options);
if (optionString.length() != 0) {
m_CVFolds = Integer.parseInt(optionString);
}
m_useIBk = Utils.getFlag('I', options);
m_displayRules = Utils.getFlag('R', options);
optionString = Utils.getOption('E', options);
if (optionString.length() != 0) {
if (optionString.equals("acc")) {
setEvaluationMeasure(new SelectedTag(EVAL_ACCURACY, TAGS_EVALUATION));
} else if (optionString.equals("rmse")) {
setEvaluationMeasure(new SelectedTag(EVAL_RMSE, TAGS_EVALUATION));
} else if (optionString.equals("mae")) {
setEvaluationMeasure(new SelectedTag(EVAL_MAE, TAGS_EVALUATION));
} else if (optionString.equals("auc")) {
setEvaluationMeasure(new SelectedTag(EVAL_AUC, TAGS_EVALUATION));
} else {
throw new IllegalArgumentException("Invalid evaluation measure");
}
}
String searchString = Utils.getOption('S', options);
if (searchString.length() == 0)
searchString = weka.attributeSelection.BestFirst.class.getName();
String[] searchSpec = Utils.splitOptions(searchString);
if (searchSpec.length == 0) {
throw new IllegalArgumentException("Invalid search specification string");
}
String searchName = searchSpec[0];
searchSpec[0] = "";
setSearch(ASSearch.forName(searchName, searchSpec));
}
/**
* 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();
}
}
/**
* Generates the classifier.
*
* @param data set of instances serving as training data
* @throws Exception if the classifier has not been generated successfully
*/
public void buildClassifier(Instances data) throws Exception {
// can classifier handle the data?
getCapabilities().testWithFail(data);
// remove instances with missing class
m_theInstances = new Instances(data);
m_theInstances.deleteWithMissingClass();
m_rr = new Random(1);
if (m_theInstances.classAttribute().isNominal()) { // Set up class priors
m_classPriorCounts = new double[data.classAttribute().numValues()];
Arrays.fill(m_classPriorCounts, 1.0);
for (int i = 0; i < data.numInstances(); i++) {
Instance curr = data.instance(i);
m_classPriorCounts[(int) curr.classValue()] += curr.weight();
}
m_classPriors = m_classPriorCounts.clone();
Utils.normalize(m_classPriors);
}
setUpEvaluator();
if (m_theInstances.classAttribute().isNumeric()) {
m_disTransform = new weka.filters.unsupervised.attribute.Discretize();
m_classIsNominal = false;
// use binned discretisation if the class is numeric
((weka.filters.unsupervised.attribute.Discretize) m_disTransform).setBins(10);
((weka.filters.unsupervised.attribute.Discretize) m_disTransform).setInvertSelection(true);
// Discretize all attributes EXCEPT the class
String rangeList = "";
rangeList += (m_theInstances.classIndex() + 1);
// System.out.println("The class col: "+m_theInstances.classIndex());
((weka.filters.unsupervised.attribute.Discretize) m_disTransform)
.setAttributeIndices(rangeList);
} else {
m_disTransform = new weka.filters.supervised.attribute.Discretize();
((weka.filters.supervised.attribute.Discretize) m_disTransform).setUseBetterEncoding(true);
m_classIsNominal = true;
}
m_disTransform.setInputFormat(m_theInstances);
m_theInstances = Filter.useFilter(m_theInstances, m_disTransform);
m_numAttributes = m_theInstances.numAttributes();
m_numInstances = m_theInstances.numInstances();
m_majority = m_theInstances.meanOrMode(m_theInstances.classAttribute());
// Perform the search
int[] selected = m_search.search(m_evaluator, m_theInstances);
m_decisionFeatures = new int[selected.length + 1];
System.arraycopy(selected, 0, m_decisionFeatures, 0, selected.length);
m_decisionFeatures[m_decisionFeatures.length - 1] = m_theInstances.classIndex();
// reduce instances to selected features
m_delTransform = new Remove();
m_delTransform.setInvertSelection(true);
// set features to keep
m_delTransform.setAttributeIndicesArray(m_decisionFeatures);
m_delTransform.setInputFormat(m_theInstances);
m_dtInstances = Filter.useFilter(m_theInstances, m_delTransform);
// reset the number of attributes
m_numAttributes = m_dtInstances.numAttributes();
// create hash table
m_entries = new Hashtable((int) (m_dtInstances.numInstances() * 1.5));
// insert instances into the hash table
for (int i = 0; i < m_numInstances; i++) {
Instance inst = m_dtInstances.instance(i);
insertIntoTable(inst, null);
}
// Replace the global table majority with nearest neighbour?
if (m_useIBk) {
m_ibk = new IBk();
m_ibk.buildClassifier(m_theInstances);
}
// Save memory
if (m_saveMemory) {
m_theInstances = new Instances(m_theInstances, 0);
m_dtInstances = new Instances(m_dtInstances, 0);
}
m_evaluation = null;
}