/**
* Updates the minimum and maximum values for all the attributes based on a new instance.
*
* @param instance the new instance
*/
private void updateMinMax(Instance instance) {
for (int j = 0; j < instance.numAttributes(); j++) {
if (Double.isNaN(m_Min[j])) {
m_Min[j] = instance.value(j);
m_Max[j] = instance.value(j);
} else {
if (instance.value(j) < m_Min[j]) {
m_Min[j] = instance.value(j);
} else {
if (instance.value(j) > m_Max[j]) {
m_Max[j] = instance.value(j);
}
}
}
}
}
/**
* 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;
}
/**
* Gets the index of the branch that an instance applies to. Returns -1 if no branches apply.
*
* @param i the instance
* @return the branch index
*/
public int branchInstanceGoesDown(Instance inst) {
if (inst.isMissing(attIndex)) return -1;
else if (inst.value(attIndex) < splitPoint) return 0;
else return 1;
}
/** if clusterIdx is -1, all instances are used (a single metric for all clusters is used) */
public boolean trainMetric(int clusterIdx) throws Exception {
Init(clusterIdx);
double[] weights = new double[m_numAttributes];
int violatedConstraints = 0;
int numInstances = 0;
for (int instIdx = 0; instIdx < m_instances.numInstances(); instIdx++) {
int assignment = m_clusterAssignments[instIdx];
// only instances assigned to this cluster are of importance
if (assignment == clusterIdx || clusterIdx == -1) {
numInstances++;
if (clusterIdx < 0) {
m_centroid = m_kmeans.getClusterCentroids().instance(assignment);
}
// accumulate variance
Instance instance = m_instances.instance(instIdx);
Instance diffInstance = m_metric.createDiffInstance(instance, m_centroid);
for (int attr = 0; attr < m_numAttributes; attr++) {
weights[attr] += diffInstance.value(attr);
}
// check all constraints for this instance
Object list = m_instanceConstraintMap.get(new Integer(instIdx));
if (list != null) { // there are constraints associated with this instance
ArrayList constraintList = (ArrayList) list;
for (int i = 0; i < constraintList.size(); i++) {
InstancePair pair = (InstancePair) constraintList.get(i);
int linkType = pair.linkType;
int firstIdx = pair.first;
int secondIdx = pair.second;
Instance instance1 = m_instances.instance(firstIdx);
Instance instance2 = m_instances.instance(secondIdx);
int otherIdx =
(firstIdx == instIdx)
? m_clusterAssignments[secondIdx]
: m_clusterAssignments[firstIdx];
if (otherIdx != -1) { // check whether the constraint is violated
if (otherIdx != assignment && linkType == InstancePair.MUST_LINK) {
diffInstance = m_metric.createDiffInstance(instance1, instance2);
for (int attr = 0; attr < m_numAttributes; attr++) {
weights[attr] += 0.5 * m_MLweight * diffInstance.value(attr);
}
} else if (otherIdx == assignment && linkType == InstancePair.CANNOT_LINK) {
diffInstance = m_metric.createDiffInstance(instance1, instance2);
for (int attr = 0; attr < m_numAttributes; attr++) {
// this constraint will be counted twice, hence 0.5
weights[attr] += 0.5 * m_CLweight * m_maxCLDiffInstance.value(attr);
weights[attr] -= 0.5 * m_CLweight * diffInstance.value(attr);
}
}
}
}
}
}
}
// System.out.println("Updating cluster " + clusterIdx
// + " containing " + numInstances);
// check the weights
double[] newWeights = new double[m_numAttributes];
double[] currentWeights = m_metric.getWeights();
boolean needNewtonRaphson = false;
for (int attr = 0; attr < m_numAttributes; attr++) {
if (weights[attr] <= 0) { // check to avoid divide by 0 - TODO!
System.out.println(
"Negative weight "
+ weights[attr]
+ " for clusterIdx="
+ clusterIdx
+ "; using prev value="
+ currentWeights[attr]);
newWeights[attr] = currentWeights[attr];
// needNewtonRaphson = true;
// break;
} else {
if (m_regularize) { // solution of quadratic equation - TODO!
int n = m_instances.numInstances();
double ratio = (m_logTermWeight * n) / (2 * weights[attr]);
newWeights[attr] =
ratio + Math.sqrt(ratio * ratio + (m_regularizerTermWeight * n) / weights[attr]);
} else {
newWeights[attr] = m_logTermWeight * numInstances / weights[attr];
}
}
}
// do NR if needed
if (needNewtonRaphson) {
System.out.println("GOING TO NEWTON-RAPHSON!!!\n");
newWeights = updateWeightsUsingNewtonRaphson(currentWeights, weights);
}
// PRINT routine
// System.out.println("Total constraints violated: " + violatedConstraints/2 + "; weights
// are:");
// for (int attr=0; attr<numAttributes; attr++) {
// System.out.print(newWeights[attr] + "\t");
// }
// System.out.println();
// end PRINT routine
m_metric.setWeights(newWeights);
return true;
}
/**
* 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;
}
/**
* 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;
}