/**
* initializes the algorithm
*
* @param data the data to work with
* @throws Exception if m_SVM is null
*/
protected void init(Instances data) throws Exception {
if (m_SVM == null) {
throw new Exception("SVM not initialized in optimizer. Use RegOptimizer.setSVMReg()");
}
m_C = m_SVM.getC();
m_data = data;
m_classIndex = data.classIndex();
m_nInstances = data.numInstances();
// Initialize kernel
m_kernel = Kernel.makeCopy(m_SVM.getKernel());
m_kernel.buildKernel(data);
// init m_target
m_target = new double[m_nInstances];
for (int i = 0; i < m_nInstances; i++) {
m_target[i] = data.instance(i).classValue();
}
m_random = new Random(m_nSeed);
// initialize alpha and alpha* array to all zero
m_alpha = new double[m_target.length];
m_alphaStar = new double[m_target.length];
m_supportVectors = new SMOset(m_nInstances);
m_b = 0.0;
m_nEvals = 0;
m_nCacheHits = -1;
}
/**
* GetKs - return [K_1,K_2,...,K_L] where each Y_j \in {1,...,K_j}. In the multi-label case, K[j]
* = 2 for all j = 1,...,L.
*
* @param D a dataset
* @return an array of the number of values that each label can take
*/
private static int[] getKs(Instances D) {
int L = D.classIndex();
int K[] = new int[L];
for (int k = 0; k < L; k++) {
K[k] = D.attribute(k).numValues();
}
return K;
}
/**
* loads the given dataset and prints the Capabilities necessary to process it.
*
* <p>Valid parameters:
*
* <p>-file filename <br>
* the file to load
*
* <p>-c index the explicit index of the class attribute (default: none)
*
* @param args the commandline arguments
* @throws Exception if something goes wrong
*/
public static void main(String[] args) throws Exception {
String tmpStr;
String filename;
DataSource source;
Instances data;
int classIndex;
Capabilities cap;
Iterator iter;
if (args.length == 0) {
System.out.println(
"\nUsage: " + Capabilities.class.getName() + " -file <dataset> [-c <class index>]\n");
return;
}
// get parameters
tmpStr = Utils.getOption("file", args);
if (tmpStr.length() == 0) throw new Exception("No file provided with option '-file'!");
else filename = tmpStr;
tmpStr = Utils.getOption("c", args);
if (tmpStr.length() != 0) {
if (tmpStr.equals("first")) classIndex = 0;
else if (tmpStr.equals("last")) classIndex = -2; // last
else classIndex = Integer.parseInt(tmpStr) - 1;
} else {
classIndex = -3; // not set
}
// load data
source = new DataSource(filename);
if (classIndex == -3) data = source.getDataSet();
else if (classIndex == -2) data = source.getDataSet(source.getStructure().numAttributes() - 1);
else data = source.getDataSet(classIndex);
// determine and print capabilities
cap = forInstances(data);
System.out.println("File: " + filename);
System.out.println(
"Class index: " + ((data.classIndex() == -1) ? "not set" : "" + (data.classIndex() + 1)));
System.out.println("Capabilities:");
iter = cap.capabilities();
while (iter.hasNext()) System.out.println("- " + iter.next());
}
/**
* Determines the output format based on the input format and returns this. In case the output
* format cannot be returned immediately, i.e., immediateOutputFormat() returns false, then this
* method will be called from batchFinished().
*
* @param inputFormat the input format to base the output format on
* @return the output format
* @throws Exception in case the determination goes wrong
* @see #hasImmediateOutputFormat()
* @see #batchFinished()
*/
protected Instances determineOutputFormat(Instances inputFormat) throws Exception {
Instances data;
Instances result;
FastVector atts;
FastVector values;
HashSet hash;
int i;
int n;
boolean isDate;
Instance inst;
Vector sorted;
m_Cols.setUpper(inputFormat.numAttributes() - 1);
data = new Instances(inputFormat);
atts = new FastVector();
for (i = 0; i < data.numAttributes(); i++) {
if (!m_Cols.isInRange(i) || !data.attribute(i).isNumeric()) {
atts.addElement(data.attribute(i));
continue;
}
// date attribute?
isDate = (data.attribute(i).type() == Attribute.DATE);
// determine all available attribtues in dataset
hash = new HashSet();
for (n = 0; n < data.numInstances(); n++) {
inst = data.instance(n);
if (inst.isMissing(i)) continue;
if (isDate) hash.add(inst.stringValue(i));
else hash.add(new Double(inst.value(i)));
}
// sort values
sorted = new Vector();
for (Object o : hash) sorted.add(o);
Collections.sort(sorted);
// create attribute from sorted values
values = new FastVector();
for (Object o : sorted) {
if (isDate) values.addElement(o.toString());
else values.addElement(Utils.doubleToString(((Double) o).doubleValue(), MAX_DECIMALS));
}
atts.addElement(new Attribute(data.attribute(i).name(), values));
}
result = new Instances(inputFormat.relationName(), atts, 0);
result.setClassIndex(inputFormat.classIndex());
return result;
}
/**
* Calculates the distance between two instances
*
* @param test the first instance
* @param train the second instance
* @return the distance between the two given instances, between 0 and 1
*/
protected double distance(Instance first, Instance second) {
double distance = 0;
int firstI, secondI;
for (int p1 = 0, p2 = 0; p1 < first.numValues() || p2 < second.numValues(); ) {
if (p1 >= first.numValues()) {
firstI = m_instances.numAttributes();
} else {
firstI = first.index(p1);
}
if (p2 >= second.numValues()) {
secondI = m_instances.numAttributes();
} else {
secondI = second.index(p2);
}
if (firstI == m_instances.classIndex()) {
p1++;
continue;
}
if (secondI == m_instances.classIndex()) {
p2++;
continue;
}
double diff;
if (firstI == secondI) {
diff = difference(firstI, first.valueSparse(p1), second.valueSparse(p2));
p1++;
p2++;
} else if (firstI > secondI) {
diff = difference(secondI, 0, second.valueSparse(p2));
p2++;
} else {
diff = difference(firstI, first.valueSparse(p1), 0);
p1++;
}
distance += diff * diff;
}
return Math.sqrt(distance / m_instances.numAttributes());
}
/**
* Initializes a gain ratio attribute evaluator. Discretizes all attributes that are numeric.
*
* @param data set of instances serving as training data
* @throws Exception if the evaluator has not been generated successfully
*/
public void buildEvaluator(Instances data) throws Exception {
// can evaluator handle data?
getCapabilities().testWithFail(data);
m_trainInstances = data;
m_classIndex = m_trainInstances.classIndex();
m_numAttribs = m_trainInstances.numAttributes();
m_numInstances = m_trainInstances.numInstances();
Discretize disTransform = new Discretize();
disTransform.setUseBetterEncoding(true);
disTransform.setInputFormat(m_trainInstances);
m_trainInstances = Filter.useFilter(m_trainInstances, disTransform);
m_numClasses = m_trainInstances.attribute(m_classIndex).numValues();
}
/**
* Generates an attribute evaluator. Has to initialise all fields of the evaluator that are not
* being set via options.
*
* @param data set of instances serving as training data
* @throws Exception if the evaluator has not been generated successfully
*/
public void buildEvaluator(Instances data) throws Exception {
// can evaluator handle data?
getCapabilities().testWithFail(data);
m_trainInstances = new Instances(data);
m_trainInstances.deleteWithMissingClass();
m_numAttribs = m_trainInstances.numAttributes();
m_numInstances = m_trainInstances.numInstances();
// if the data has no decision feature, m_classIndex is negative
m_classIndex = m_trainInstances.classIndex();
// supervised
if (m_classIndex >= 0) {
m_isNumeric = m_trainInstances.attribute(m_classIndex).isNumeric();
if (m_isNumeric) {
m_DecisionSimilarity = m_Similarity;
} else m_DecisionSimilarity = m_SimilarityEq;
}
m_Similarity.setInstances(m_trainInstances);
m_DecisionSimilarity.setInstances(m_trainInstances);
m_SimilarityEq.setInstances(m_trainInstances);
m_composition = m_Similarity.getTNorm();
m_FuzzyMeasure.set(
m_Similarity,
m_DecisionSimilarity,
m_TNorm,
m_composition,
m_Implicator,
m_SNorm,
m_numInstances,
m_numAttribs,
m_classIndex,
m_trainInstances);
}
/**
* Writes a Batch of instances
*
* @throws IOException throws IOException if saving in batch mode is not possible
*/
public void writeBatch() throws IOException {
Instances instances = getInstances();
if (instances == null) throw new IOException("No instances to save");
if (instances.classIndex() == -1) {
instances.setClassIndex(instances.numAttributes() - 1);
System.err.println("No class specified. Last attribute is used as class attribute.");
}
if (instances.attribute(instances.classIndex()).isNumeric())
throw new IOException("To save in C4.5 format the class attribute cannot be numeric.");
if (getRetrieval() == INCREMENTAL)
throw new IOException("Batch and incremental saving cannot be mixed.");
setRetrieval(BATCH);
if (retrieveFile() == null || getWriter() == null) {
throw new IOException(
"C4.5 format requires two files. Therefore no output to standard out can be generated.\nPlease specifiy output files using the -o option.");
}
setWriteMode(WRITE);
// print names file
setFileExtension(".names");
PrintWriter outW = new PrintWriter(getWriter());
for (int i = 0; i < instances.attribute(instances.classIndex()).numValues(); i++) {
outW.write(instances.attribute(instances.classIndex()).value(i));
if (i < instances.attribute(instances.classIndex()).numValues() - 1) {
outW.write(",");
} else {
outW.write(".\n");
}
}
for (int i = 0; i < instances.numAttributes(); i++) {
if (i != instances.classIndex()) {
outW.write(instances.attribute(i).name() + ": ");
if (instances.attribute(i).isNumeric() || instances.attribute(i).isDate()) {
outW.write("continuous.\n");
} else {
Attribute temp = instances.attribute(i);
for (int j = 0; j < temp.numValues(); j++) {
outW.write(temp.value(j));
if (j < temp.numValues() - 1) {
outW.write(",");
} else {
outW.write(".\n");
}
}
}
}
}
outW.flush();
outW.close();
// print data file
String out = retrieveFile().getAbsolutePath();
setFileExtension(".data");
out = out.substring(0, out.lastIndexOf('.')) + getFileExtension();
File namesFile = new File(out);
try {
setFile(namesFile);
} catch (Exception ex) {
throw new IOException(
"Cannot create data file, only names file created (Reason: " + ex.toString() + ").");
}
if (retrieveFile() == null || getWriter() == null) {
throw new IOException("Cannot create data file, only names file created.");
}
outW = new PrintWriter(getWriter());
// print data file
for (int i = 0; i < instances.numInstances(); i++) {
Instance temp = instances.instance(i);
for (int j = 0; j < temp.numAttributes(); j++) {
if (j != instances.classIndex()) {
if (temp.isMissing(j)) {
outW.write("?,");
} else if (instances.attribute(j).isNominal() || instances.attribute(j).isString()) {
outW.write(instances.attribute(j).value((int) temp.value(j)) + ",");
} else {
outW.write("" + temp.value(j) + ",");
}
}
}
// write the class value
if (temp.isMissing(instances.classIndex())) {
outW.write("?");
} else {
outW.write(
instances
.attribute(instances.classIndex())
.value((int) temp.value(instances.classIndex())));
}
outW.write("\n");
}
outW.flush();
outW.close();
setFileExtension(".names");
setWriteMode(WAIT);
outW = null;
resetWriter();
setWriteMode(CANCEL);
}
/**
* Saves an instances incrementally. Structure has to be set by using the setStructure() method or
* setInstances() method.
*
* @param inst the instance to save
* @throws IOException throws IOEXception if an instance cannot be saved incrementally.
*/
public void writeIncremental(Instance inst) throws IOException {
int writeMode = getWriteMode();
Instances structure = getInstances();
PrintWriter outW = null;
if (structure != null) {
if (structure.classIndex() == -1) {
structure.setClassIndex(structure.numAttributes() - 1);
System.err.println("No class specified. Last attribute is used as class attribute.");
}
if (structure.attribute(structure.classIndex()).isNumeric())
throw new IOException("To save in C4.5 format the class attribute cannot be numeric.");
}
if (getRetrieval() == BATCH || getRetrieval() == NONE)
throw new IOException("Batch and incremental saving cannot be mixed.");
if (retrieveFile() == null || getWriter() == null) {
throw new IOException(
"C4.5 format requires two files. Therefore no output to standard out can be generated.\nPlease specifiy output files using the -o option.");
}
outW = new PrintWriter(getWriter());
if (writeMode == WAIT) {
if (structure == null) {
setWriteMode(CANCEL);
if (inst != null)
System.err.println("Structure(Header Information) has to be set in advance");
} else setWriteMode(STRUCTURE_READY);
writeMode = getWriteMode();
}
if (writeMode == CANCEL) {
if (outW != null) outW.close();
cancel();
}
if (writeMode == STRUCTURE_READY) {
setWriteMode(WRITE);
// write header: here names file
for (int i = 0; i < structure.attribute(structure.classIndex()).numValues(); i++) {
outW.write(structure.attribute(structure.classIndex()).value(i));
if (i < structure.attribute(structure.classIndex()).numValues() - 1) {
outW.write(",");
} else {
outW.write(".\n");
}
}
for (int i = 0; i < structure.numAttributes(); i++) {
if (i != structure.classIndex()) {
outW.write(structure.attribute(i).name() + ": ");
if (structure.attribute(i).isNumeric() || structure.attribute(i).isDate()) {
outW.write("continuous.\n");
} else {
Attribute temp = structure.attribute(i);
for (int j = 0; j < temp.numValues(); j++) {
outW.write(temp.value(j));
if (j < temp.numValues() - 1) {
outW.write(",");
} else {
outW.write(".\n");
}
}
}
}
}
outW.flush();
outW.close();
writeMode = getWriteMode();
String out = retrieveFile().getAbsolutePath();
setFileExtension(".data");
out = out.substring(0, out.lastIndexOf('.')) + getFileExtension();
File namesFile = new File(out);
try {
setFile(namesFile);
} catch (Exception ex) {
throw new IOException("Cannot create data file, only names file created.");
}
if (retrieveFile() == null || getWriter() == null) {
throw new IOException("Cannot create data file, only names file created.");
}
outW = new PrintWriter(getWriter());
}
if (writeMode == WRITE) {
if (structure == null) throw new IOException("No instances information available.");
if (inst != null) {
// write instance: here data file
for (int j = 0; j < inst.numAttributes(); j++) {
if (j != structure.classIndex()) {
if (inst.isMissing(j)) {
outW.write("?,");
} else if (structure.attribute(j).isNominal() || structure.attribute(j).isString()) {
outW.write(structure.attribute(j).value((int) inst.value(j)) + ",");
} else {
outW.write("" + inst.value(j) + ",");
}
}
}
// write the class value
if (inst.isMissing(structure.classIndex())) {
outW.write("?");
} else {
outW.write(
structure
.attribute(structure.classIndex())
.value((int) inst.value(structure.classIndex())));
}
outW.write("\n");
// flushes every 100 instances
m_incrementalCounter++;
if (m_incrementalCounter > 100) {
m_incrementalCounter = 0;
outW.flush();
}
} else {
// close
if (outW != null) {
outW.flush();
outW.close();
}
setFileExtension(".names");
m_incrementalCounter = 0;
resetStructure();
outW = null;
resetWriter();
}
}
}
/**
* Tests a certain range of attributes of the given data, whether it can be processed by the
* handler, given its capabilities. Classifiers implementing the <code>
* MultiInstanceCapabilitiesHandler</code> interface are checked automatically for their
* multi-instance Capabilities (if no bags, then only the bag-structure, otherwise only the first
* bag).
*
* @param data the data to test
* @param fromIndex the range of attributes - start (incl.)
* @param toIndex the range of attributes - end (incl.)
* @return true if all the tests succeeded
* @see MultiInstanceCapabilitiesHandler
* @see #m_InstancesTest
* @see #m_MissingValuesTest
* @see #m_MissingClassValuesTest
* @see #m_MinimumNumberInstancesTest
*/
public boolean test(Instances data, int fromIndex, int toIndex) {
int i;
int n;
int m;
Attribute att;
Instance inst;
boolean testClass;
Capabilities cap;
boolean missing;
Iterator iter;
// shall we test the data?
if (!m_InstancesTest) return true;
// no Capabilities? -> warning
if ((m_Capabilities.size() == 0)
|| ((m_Capabilities.size() == 1) && handles(Capability.NO_CLASS)))
System.err.println(createMessage("No capabilities set!"));
// any attributes?
if (toIndex - fromIndex < 0) {
m_FailReason = new WekaException(createMessage("No attributes!"));
return false;
}
// do wee need to test the class attribute, i.e., is the class attribute
// within the range of attributes?
testClass =
(data.classIndex() > -1)
&& (data.classIndex() >= fromIndex)
&& (data.classIndex() <= toIndex);
// attributes
for (i = fromIndex; i <= toIndex; i++) {
att = data.attribute(i);
// class is handled separately
if (i == data.classIndex()) continue;
// check attribute types
if (!test(att)) return false;
}
// class
if (!handles(Capability.NO_CLASS) && (data.classIndex() == -1)) {
m_FailReason = new UnassignedClassException(createMessage("Class attribute not set!"));
return false;
}
// special case: no class attribute can be handled
if (handles(Capability.NO_CLASS) && (data.classIndex() > -1)) {
cap = getClassCapabilities();
cap.disable(Capability.NO_CLASS);
iter = cap.capabilities();
if (!iter.hasNext()) {
m_FailReason = new WekaException(createMessage("Cannot handle any class attribute!"));
return false;
}
}
if (testClass && !handles(Capability.NO_CLASS)) {
att = data.classAttribute();
if (!test(att, true)) return false;
// special handling of RELATIONAL class
// TODO: store additional Capabilities for this case
// missing class labels
if (m_MissingClassValuesTest) {
if (!handles(Capability.MISSING_CLASS_VALUES)) {
for (i = 0; i < data.numInstances(); i++) {
if (data.instance(i).classIsMissing()) {
m_FailReason =
new WekaException(createMessage("Cannot handle missing class values!"));
return false;
}
}
} else {
if (m_MinimumNumberInstancesTest) {
int hasClass = 0;
for (i = 0; i < data.numInstances(); i++) {
if (!data.instance(i).classIsMissing()) hasClass++;
}
// not enough instances with class labels?
if (hasClass < getMinimumNumberInstances()) {
m_FailReason =
new WekaException(
createMessage(
"Not enough training instances with class labels (required: "
+ getMinimumNumberInstances()
+ ", provided: "
+ hasClass
+ ")!"));
return false;
}
}
}
}
}
// missing values
if (m_MissingValuesTest) {
if (!handles(Capability.MISSING_VALUES)) {
missing = false;
for (i = 0; i < data.numInstances(); i++) {
inst = data.instance(i);
if (inst instanceof SparseInstance) {
for (m = 0; m < inst.numValues(); m++) {
n = inst.index(m);
// out of scope?
if (n < fromIndex) continue;
if (n > toIndex) break;
// skip class
if (n == inst.classIndex()) continue;
if (inst.isMissing(n)) {
missing = true;
break;
}
}
} else {
for (n = fromIndex; n <= toIndex; n++) {
// skip class
if (n == inst.classIndex()) continue;
if (inst.isMissing(n)) {
missing = true;
break;
}
}
}
if (missing) {
m_FailReason =
new NoSupportForMissingValuesException(
createMessage("Cannot handle missing values!"));
return false;
}
}
}
}
// instances
if (m_MinimumNumberInstancesTest) {
if (data.numInstances() < getMinimumNumberInstances()) {
m_FailReason =
new WekaException(
createMessage(
"Not enough training instances (required: "
+ getMinimumNumberInstances()
+ ", provided: "
+ data.numInstances()
+ ")!"));
return false;
}
}
// Multi-Instance? -> check structure (regardless of attribute range!)
if (handles(Capability.ONLY_MULTIINSTANCE)) {
// number of attributes?
if (data.numAttributes() != 3) {
m_FailReason =
new WekaException(
createMessage("Incorrect Multi-Instance format, must be 'bag-id, bag, class'!"));
return false;
}
// type of attributes and position of class?
if (!data.attribute(0).isNominal()
|| !data.attribute(1).isRelationValued()
|| (data.classIndex() != data.numAttributes() - 1)) {
m_FailReason =
new WekaException(
createMessage(
"Incorrect Multi-Instance format, must be 'NOMINAL att, RELATIONAL att, CLASS att'!"));
return false;
}
// check data immediately
if (getOwner() instanceof MultiInstanceCapabilitiesHandler) {
MultiInstanceCapabilitiesHandler handler = (MultiInstanceCapabilitiesHandler) getOwner();
cap = handler.getMultiInstanceCapabilities();
boolean result;
if (data.numInstances() > 0) result = cap.test(data.attribute(1).relation(0));
else result = cap.test(data.attribute(1).relation());
if (!result) {
m_FailReason = cap.m_FailReason;
return false;
}
}
}
// passed all tests!
return true;
}
/**
* Calculates the accuracy on a test fold for internal cross validation of feature sets
*
* @param fold set of instances to be "left out" and classified
* @param fs currently selected feature set
* @return the accuracy for the fold
* @throws Exception if something goes wrong
*/
double evaluateFoldCV(Instances fold, int[] fs) throws Exception {
int i;
int ruleCount = 0;
int numFold = fold.numInstances();
int numCl = m_theInstances.classAttribute().numValues();
double[][] class_distribs = new double[numFold][numCl];
double[] instA = new double[fs.length];
double[] normDist;
DecisionTableHashKey thekey;
double acc = 0.0;
int classI = m_theInstances.classIndex();
Instance inst;
if (m_classIsNominal) {
normDist = new double[numCl];
} else {
normDist = new double[2];
}
// first *remove* instances
for (i = 0; i < numFold; i++) {
inst = fold.instance(i);
for (int j = 0; j < fs.length; j++) {
if (fs[j] == classI) {
instA[j] = Double.MAX_VALUE; // missing for the class
} else if (inst.isMissing(fs[j])) {
instA[j] = Double.MAX_VALUE;
} else {
instA[j] = inst.value(fs[j]);
}
}
thekey = new DecisionTableHashKey(instA);
if ((class_distribs[i] = (double[]) m_entries.get(thekey)) == null) {
throw new Error("This should never happen!");
} else {
if (m_classIsNominal) {
class_distribs[i][(int) inst.classValue()] -= inst.weight();
} else {
class_distribs[i][0] -= (inst.classValue() * inst.weight());
class_distribs[i][1] -= inst.weight();
}
ruleCount++;
}
m_classPriorCounts[(int) inst.classValue()] -= inst.weight();
}
double[] classPriors = m_classPriorCounts.clone();
Utils.normalize(classPriors);
// now classify instances
for (i = 0; i < numFold; i++) {
inst = fold.instance(i);
System.arraycopy(class_distribs[i], 0, normDist, 0, normDist.length);
if (m_classIsNominal) {
boolean ok = false;
for (int j = 0; j < normDist.length; j++) {
if (Utils.gr(normDist[j], 1.0)) {
ok = true;
break;
}
}
if (!ok) { // majority class
normDist = classPriors.clone();
}
// if (ok) {
Utils.normalize(normDist);
if (m_evaluationMeasure == EVAL_AUC) {
m_evaluation.evaluateModelOnceAndRecordPrediction(normDist, inst);
} else {
m_evaluation.evaluateModelOnce(normDist, inst);
}
/* } else {
normDist[(int)m_majority] = 1.0;
if (m_evaluationMeasure == EVAL_AUC) {
m_evaluation.evaluateModelOnceAndRecordPrediction(normDist, inst);
} else {
m_evaluation.evaluateModelOnce(normDist, inst);
}
} */
} else {
if (Utils.eq(normDist[1], 0.0)) {
double[] temp = new double[1];
temp[0] = m_majority;
m_evaluation.evaluateModelOnce(temp, inst);
} else {
double[] temp = new double[1];
temp[0] = normDist[0] / normDist[1];
m_evaluation.evaluateModelOnce(temp, inst);
}
}
}
// now re-insert instances
for (i = 0; i < numFold; i++) {
inst = fold.instance(i);
m_classPriorCounts[(int) inst.classValue()] += inst.weight();
if (m_classIsNominal) {
class_distribs[i][(int) inst.classValue()] += inst.weight();
} else {
class_distribs[i][0] += (inst.classValue() * inst.weight());
class_distribs[i][1] += inst.weight();
}
}
return acc;
}
/**
* returns a Capabilities object specific for this data. The minimum number of instances is not
* set, the check for multi-instance data is optional.
*
* @param data the data to base the capabilities on
* @param multi if true then the structure is checked, too
* @return a data-specific capabilities object
* @throws Exception in case an error occurrs, e.g., an unknown attribute type
*/
public static Capabilities forInstances(Instances data, boolean multi) throws Exception {
Capabilities result;
Capabilities multiInstance;
int i;
int n;
int m;
Instance inst;
boolean missing;
result = new Capabilities(null);
// class
if (data.classIndex() == -1) {
result.enable(Capability.NO_CLASS);
} else {
switch (data.classAttribute().type()) {
case Attribute.NOMINAL:
if (data.classAttribute().numValues() == 1) result.enable(Capability.UNARY_CLASS);
else if (data.classAttribute().numValues() == 2) result.enable(Capability.BINARY_CLASS);
else result.enable(Capability.NOMINAL_CLASS);
break;
case Attribute.NUMERIC:
result.enable(Capability.NUMERIC_CLASS);
break;
case Attribute.STRING:
result.enable(Capability.STRING_CLASS);
break;
case Attribute.DATE:
result.enable(Capability.DATE_CLASS);
break;
case Attribute.RELATIONAL:
result.enable(Capability.RELATIONAL_CLASS);
break;
default:
throw new UnsupportedAttributeTypeException(
"Unknown class attribute type '" + data.classAttribute() + "'!");
}
// missing class values
for (i = 0; i < data.numInstances(); i++) {
if (data.instance(i).classIsMissing()) {
result.enable(Capability.MISSING_CLASS_VALUES);
break;
}
}
}
// attributes
for (i = 0; i < data.numAttributes(); i++) {
// skip class
if (i == data.classIndex()) continue;
switch (data.attribute(i).type()) {
case Attribute.NOMINAL:
result.enable(Capability.UNARY_ATTRIBUTES);
if (data.attribute(i).numValues() == 2) result.enable(Capability.BINARY_ATTRIBUTES);
else if (data.attribute(i).numValues() > 2) result.enable(Capability.NOMINAL_ATTRIBUTES);
break;
case Attribute.NUMERIC:
result.enable(Capability.NUMERIC_ATTRIBUTES);
break;
case Attribute.DATE:
result.enable(Capability.DATE_ATTRIBUTES);
break;
case Attribute.STRING:
result.enable(Capability.STRING_ATTRIBUTES);
break;
case Attribute.RELATIONAL:
result.enable(Capability.RELATIONAL_ATTRIBUTES);
break;
default:
throw new UnsupportedAttributeTypeException(
"Unknown attribute type '" + data.attribute(i).type() + "'!");
}
}
// missing values
missing = false;
for (i = 0; i < data.numInstances(); i++) {
inst = data.instance(i);
if (inst instanceof SparseInstance) {
for (m = 0; m < inst.numValues(); m++) {
n = inst.index(m);
// skip class
if (n == inst.classIndex()) continue;
if (inst.isMissing(n)) {
missing = true;
break;
}
}
} else {
for (n = 0; n < data.numAttributes(); n++) {
// skip class
if (n == inst.classIndex()) continue;
if (inst.isMissing(n)) {
missing = true;
break;
}
}
}
if (missing) {
result.enable(Capability.MISSING_VALUES);
break;
}
}
// multi-instance data?
if (multi) {
if ((data.numAttributes() == 3)
&& (data.attribute(0).isNominal()) // bag-id
&& (data.attribute(1).isRelationValued()) // bag
&& (data.classIndex() == data.numAttributes() - 1)) {
multiInstance = new Capabilities(null);
multiInstance.or(result.getClassCapabilities());
multiInstance.enable(Capability.NOMINAL_ATTRIBUTES);
multiInstance.enable(Capability.RELATIONAL_ATTRIBUTES);
multiInstance.enable(Capability.ONLY_MULTIINSTANCE);
result.assign(multiInstance);
}
}
return result;
}
/**
* Evaluates a feature subset by cross validation
*
* @param feature_set the subset to be evaluated
* @param num_atts the number of attributes in the subset
* @return the estimated accuracy
* @throws Exception if subset can't be evaluated
*/
protected double estimatePerformance(BitSet feature_set, int num_atts) throws Exception {
m_evaluation = new Evaluation(m_theInstances);
int i;
int[] fs = new int[num_atts];
double[] instA = new double[num_atts];
int classI = m_theInstances.classIndex();
int index = 0;
for (i = 0; i < m_numAttributes; i++) {
if (feature_set.get(i)) {
fs[index++] = i;
}
}
// create new hash table
m_entries = new Hashtable((int) (m_theInstances.numInstances() * 1.5));
// insert instances into the hash table
for (i = 0; i < m_numInstances; i++) {
Instance inst = m_theInstances.instance(i);
for (int j = 0; j < fs.length; j++) {
if (fs[j] == classI) {
instA[j] = Double.MAX_VALUE; // missing for the class
} else if (inst.isMissing(fs[j])) {
instA[j] = Double.MAX_VALUE;
} else {
instA[j] = inst.value(fs[j]);
}
}
insertIntoTable(inst, instA);
}
if (m_CVFolds == 1) {
// calculate leave one out error
for (i = 0; i < m_numInstances; i++) {
Instance inst = m_theInstances.instance(i);
for (int j = 0; j < fs.length; j++) {
if (fs[j] == classI) {
instA[j] = Double.MAX_VALUE; // missing for the class
} else if (inst.isMissing(fs[j])) {
instA[j] = Double.MAX_VALUE;
} else {
instA[j] = inst.value(fs[j]);
}
}
evaluateInstanceLeaveOneOut(inst, instA);
}
} else {
m_theInstances.randomize(m_rr);
m_theInstances.stratify(m_CVFolds);
// calculate 10 fold cross validation error
for (i = 0; i < m_CVFolds; i++) {
Instances insts = m_theInstances.testCV(m_CVFolds, i);
evaluateFoldCV(insts, fs);
}
}
switch (m_evaluationMeasure) {
case EVAL_DEFAULT:
if (m_classIsNominal) {
return m_evaluation.pctCorrect();
}
return -m_evaluation.rootMeanSquaredError();
case EVAL_ACCURACY:
return m_evaluation.pctCorrect();
case EVAL_RMSE:
return -m_evaluation.rootMeanSquaredError();
case EVAL_MAE:
return -m_evaluation.meanAbsoluteError();
case EVAL_AUC:
double[] classPriors = m_evaluation.getClassPriors();
Utils.normalize(classPriors);
double weightedAUC = 0;
for (i = 0; i < m_theInstances.classAttribute().numValues(); i++) {
double tempAUC = m_evaluation.areaUnderROC(i);
if (!Utils.isMissingValue(tempAUC)) {
weightedAUC += (classPriors[i] * tempAUC);
} else {
System.err.println("Undefined AUC!!");
}
}
return weightedAUC;
}
// shouldn't get here
return 0.0;
}
public void runFilter() throws Exception {
System.out.println("filtering attributes...");
System.out.println("running weka filters and weka-libsvm");
File svmfile = new File(sentiAnalysis.DIR.concat(sentiAnalysis.outout.concat(".libsvm")));
LibSVMLoader libl = new LibSVMLoader();
libl.setFile(svmfile);
Instances data = libl.getDataSet();
NumericToNominal nm = new NumericToNominal(); // Converting last index
// attribute to type
// nominal from numeric
nm.setAttributeIndices("last"); // as the last index would be class
// label for the data
nm.setInputFormat(data);
filteredData = Filter.useFilter(data, nm); // filtered data stored in
// new Instances object
AttrNo = filteredData.numAttributes(); // number of attributes in given
// file
RecordNo = filteredData.numInstances(); // Number of records in given
// file
lowerBound = 0;
upperBound = AttrNo - 1;
AttributeSelection atsl = new AttributeSelection();
Ranker search = new Ranker();
InfoGainAttributeEval infog = new InfoGainAttributeEval(); // Applying
// Attribute
// Selection
// using
// InfoGain
// evaluator
// with
// Ranker
// search
atsl.setEvaluator(infog);
atsl.setSearch(search);
atsl.SelectAttributes(filteredData);
InfoGain = atsl.rankedAttributes();
SelectedAttributes = atsl.selectedAttributes();
// count non zero infoGain
int count = 0;
for (int i = 0; i < InfoGain.length; i++) {
count = (InfoGain[i][1] > 0) ? count + 1 : count;
}
System.out.println("writing attributes with non-zero InfoGain...");
FileWriter svmout =
new FileWriter(sentiAnalysis.DIR.concat(sentiAnalysis.outout.concat("_new.libsvm")));
for (int i = 0; i < RecordNo; i++) {
int index = 1;
svmout.write((int) filteredData.instance(i).value(filteredData.classIndex()) + " ");
for (int j = 0; j < count; j++) {
svmout.write(
index + ":" + (int) filteredData.instance(i).value((int) InfoGain[j][0]) + " ");
index++;
}
svmout.write("\n");
}
svmout.close();
// filtered
File newsvm = new File(sentiAnalysis.DIR.concat(sentiAnalysis.outout.concat("_new.libsvm")));
LibSVMLoader liblnew = new LibSVMLoader();
liblnew.setFile(newsvm);
Instances newdata = liblnew.getDataSet();
nm = new NumericToNominal(); // Converting last index attribute to type
// nominal from numeric
nm.setAttributeIndices("last"); // as the last index would be class
// label for the data
nm.setInputFormat(newdata);
Instances filteredDataNew = Filter.useFilter(newdata, nm); // filtered
// data
// stored in
// new
// Instances
// object
// test file
File newsvmtest =
new File(sentiAnalysis.DIR.concat(sentiAnalysis.outout.concat("_test.libsvm")));
LibSVMLoader libltest = new LibSVMLoader();
libltest.setFile(newsvmtest);
Instances newdatatest = libltest.getDataSet();
nm = new NumericToNominal(); // Converting last index attribute to type
// nominal from numeric
nm.setAttributeIndices("last"); // as the last index would be class
// label for the data
nm.setInputFormat(newdatatest);
Instances filteredDataTest = Filter.useFilter(newdatatest, nm); // filtered
// data
// stored
// in
// new
// Instances
// object
// weka.classifiers.functions.LibSVM -S 0 -K 2 -D 3 -G 0.0 -R 0.0 -N 0.5
// -M 40.0 -C 1.0 -E 0.001 -P 0.1 -seed 1
String[] options = new String[1];
options[0] = "-S 0 -K 2 -D 3 -G 0.1 -R 0.0 -N 0.5 -M 40.0 -C 1.0 -E 0.001 -P 0.1 -seed 1 -h 0";
System.out.println("building classifier...");
LibSVM svm_model = new LibSVM();
svm_model.setOptions(options); // set the options
svm_model.buildClassifier(filteredData); // build classifier
DecimalFormat df = new DecimalFormat("0.00");
System.out.println("running cross validation...");
Evaluation eval = new Evaluation(filteredData);
// eval.crossValidateModel(svm_model, filteredDataNew, 10, new
// Random(1));
eval.evaluateModel(svm_model, filteredDataTest);
FileWriter results =
new FileWriter(sentiAnalysis.DIR.concat(sentiAnalysis.outout.concat("_results.txt")));
results.write("Classifier 1: Support Vector Machines\n");
results.write("Positive class precision: " + df.format(eval.precision(0)) + "\n");
results.write("Positive class recall: " + df.format(eval.recall(0)) + "\n");
results.write("Positive class f-score: " + df.format(eval.fMeasure(0)) + "\n");
results.write("Negative class precision: " + df.format(eval.precision(0)) + "\n");
results.write("Negative class recall: " + df.format(eval.precision(0)) + "\n");
results.write("Negative class f-score: " + df.format(eval.fMeasure(0)) + "\n");
System.out.println("generating results...");
System.out.println("*" + sentiAnalysis.outout + "*\t" + "\tPositive\tNegative\tNeutral");
System.out.println(
"Precision\t"
+ df.format(eval.precision(0))
+ "\t"
+ df.format(eval.precision(2))
+ "\t"
+ df.format(eval.precision(1)));
System.out.println(
"Recall\t"
+ df.format(eval.recall(0))
+ "\t"
+ df.format(eval.recall(2))
+ "\t"
+ df.format(eval.recall(1)));
System.out.println(
"F-score\t"
+ df.format(eval.fMeasure(0))
+ "\t"
+ df.format(eval.fMeasure(2))
+ "\t"
+ df.format(eval.fMeasure(1)));
results.close();
}
/**
* 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();
}
}
public void buildClassifier(Instances insts) throws Exception {
// Compute mean of target value
double yMean = insts.meanOrMode(insts.classIndex());
// Choose best attribute
double minMsq = Double.MAX_VALUE;
m_attribute = null;
int chosen = -1;
double chosenSlope = Double.NaN;
double chosenIntercept = Double.NaN;
for (int i = 0; i < insts.numAttributes(); i++) {
if (i != insts.classIndex()) {
if (!insts.attribute(i).isNumeric()) {
throw new Exception("UnivariateLinearRegression: Only numeric attributes!");
}
m_attribute = insts.attribute(i);
// Compute slope and intercept
double xMean = insts.meanOrMode(i);
double sumWeightedXDiffSquared = 0;
double sumWeightedYDiffSquared = 0;
m_slope = 0;
for (int j = 0; j < insts.numInstances(); j++) {
Instance inst = insts.instance(j);
if (!inst.isMissing(i) && !inst.classIsMissing()) {
double xDiff = inst.value(i) - xMean;
double yDiff = inst.classValue() - yMean;
double weightedXDiff = inst.weight() * xDiff;
double weightedYDiff = inst.weight() * yDiff;
m_slope += weightedXDiff * yDiff;
sumWeightedXDiffSquared += weightedXDiff * xDiff;
sumWeightedYDiffSquared += weightedYDiff * yDiff;
}
}
// Skip attribute if not useful
if (sumWeightedXDiffSquared == 0) {
continue;
}
double numerator = m_slope;
m_slope /= sumWeightedXDiffSquared;
m_intercept = yMean - m_slope * xMean;
// Compute sum of squared errors
double msq = sumWeightedYDiffSquared - m_slope * numerator;
// Check whether this is the best attribute
if (msq < minMsq) {
minMsq = msq;
chosen = i;
chosenSlope = m_slope;
chosenIntercept = m_intercept;
}
}
}
// Set parameters
if (chosen == -1) {
System.err.println("----- no useful attribute found");
m_attribute = null;
m_slope = 0;
m_intercept = yMean;
} else {
m_attribute = insts.attribute(chosen);
m_slope = chosenSlope;
m_intercept = chosenIntercept;
}
}
/**
* Calculates the distance between two instances. Offers speed up (if the distance function class
* in use supports it) in nearest neighbour search by taking into account the cutOff or maximum
* distance. Depending on the distance function class, post processing of the distances by
* postProcessDistances(double []) may be required if this function is used.
*
* @param first the first instance
* @param second the second instance
* @param cutOffValue If the distance being calculated becomes larger than cutOffValue then the
* rest of the calculation is discarded.
* @param stats the performance stats object
* @return the distance between the two given instances or Double.POSITIVE_INFINITY if the
* distance being calculated becomes larger than cutOffValue.
*/
@Override
public double distance(
Instance first, Instance second, double cutOffValue, PerformanceStats stats) {
double distance = 0;
int firstI, secondI;
int firstNumValues = first.numValues();
int secondNumValues = second.numValues();
int numAttributes = m_Data.numAttributes();
int classIndex = m_Data.classIndex();
validate();
for (int p1 = 0, p2 = 0; p1 < firstNumValues || p2 < secondNumValues; ) {
if (p1 >= firstNumValues) {
firstI = numAttributes;
} else {
firstI = first.index(p1);
}
if (p2 >= secondNumValues) {
secondI = numAttributes;
} else {
secondI = second.index(p2);
}
if (firstI == classIndex) {
p1++;
continue;
}
if ((firstI < numAttributes) && !m_ActiveIndices[firstI]) {
p1++;
continue;
}
if (secondI == classIndex) {
p2++;
continue;
}
if ((secondI < numAttributes) && !m_ActiveIndices[secondI]) {
p2++;
continue;
}
double diff;
if (firstI == secondI) {
diff = difference(firstI, first.valueSparse(p1), second.valueSparse(p2));
p1++;
p2++;
} else if (firstI > secondI) {
diff = difference(secondI, 0, second.valueSparse(p2));
p2++;
} else {
diff = difference(firstI, first.valueSparse(p1), 0);
p1++;
}
if (stats != null) {
stats.incrCoordCount();
}
distance = updateDistance(distance, diff);
if (distance > cutOffValue) {
return Double.POSITIVE_INFINITY;
}
}
return distance;
}
/**
* Ranks attributes using the specified attribute evaluator and then searches the ranking using
* the supplied subset evaluator.
*
* @param ASEval the subset evaluator to guide the search
* @param data the training instances.
* @return an array (not necessarily ordered) of selected attribute indexes
* @throws Exception if the search can't be completed
*/
public int[] search(ASEvaluation ASEval, Instances data) throws Exception {
double best_merit = -Double.MAX_VALUE;
double temp_merit;
BitSet temp_group, best_group = null;
if (!(ASEval instanceof SubsetEvaluator)) {
throw new Exception(ASEval.getClass().getName() + " is not a " + "Subset evaluator!");
}
m_SubsetEval = ASEval;
m_Instances = data;
m_numAttribs = m_Instances.numAttributes();
/* if (m_ASEval instanceof AttributeTransformer) {
throw new Exception("Can't use an attribute transformer "
+"with RankSearch");
} */
if (m_ASEval instanceof UnsupervisedAttributeEvaluator
|| m_ASEval instanceof UnsupervisedSubsetEvaluator) {
m_hasClass = false;
/* if (!(m_SubsetEval instanceof UnsupervisedSubsetEvaluator)) {
throw new Exception("Must use an unsupervised subset evaluator.");
} */
} else {
m_hasClass = true;
m_classIndex = m_Instances.classIndex();
}
if (m_ASEval instanceof AttributeEvaluator) {
// generate the attribute ranking first
Ranker ranker = new Ranker();
m_ASEval.buildEvaluator(m_Instances);
if (m_ASEval instanceof AttributeTransformer) {
// get the transformed data a rebuild the subset evaluator
m_Instances = ((AttributeTransformer) m_ASEval).transformedData(m_Instances);
((ASEvaluation) m_SubsetEval).buildEvaluator(m_Instances);
}
m_Ranking = ranker.search(m_ASEval, m_Instances);
} else {
GreedyStepwise fs = new GreedyStepwise();
double[][] rankres;
fs.setGenerateRanking(true);
((ASEvaluation) m_ASEval).buildEvaluator(m_Instances);
fs.search(m_ASEval, m_Instances);
rankres = fs.rankedAttributes();
m_Ranking = new int[rankres.length];
for (int i = 0; i < rankres.length; i++) {
m_Ranking[i] = (int) rankres[i][0];
}
}
// now evaluate the attribute ranking
for (int i = m_startPoint; i < m_Ranking.length; i += m_add) {
temp_group = new BitSet(m_numAttribs);
for (int j = 0; j <= i; j++) {
temp_group.set(m_Ranking[j]);
}
temp_merit = ((SubsetEvaluator) m_SubsetEval).evaluateSubset(temp_group);
if (temp_merit > best_merit) {
best_merit = temp_merit;
;
best_group = temp_group;
}
}
m_bestMerit = best_merit;
return attributeList(best_group);
}
/**
* 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;
}
