List of usage examples for weka.core Instance weight
public double weight();
From source file:tr.gov.ulakbim.jDenetX.classifiers.CoOzaBagASHT.java
License:Open Source License
@Override public void trainOnInstanceImpl(Instance inst) { int trueClass = (int) inst.classValue(); for (int i = 0; i < this.ensemble.length; i++) { int k = MiscUtils.poisson(1.0, this.classifierRandom); if (k > 0) { Instance weightedInst = (Instance) inst.copy(); weightedInst.setWeight(inst.weight() * k); if (Utils.maxIndex(this.ensemble[i].getVotesForInstance(inst)) == trueClass) { // Here we used the getVotesForInstanceFunction of HoeffdingTree this.error[i] += alpha * (0.0 - this.error[i]); // EWMA } else { this.error[i] += alpha * (1.0 - this.error[i]); // EWMA }/*from w w w . j a v a 2 s . com*/ this.ensemble[i].trainOnInstance(weightedInst); } } }
From source file:tr.gov.ulakbim.jDenetX.classifiers.LeveragingBag.java
License:Open Source License
@Override public void trainOnInstanceImpl(Instance inst) { int numClasses = inst.numClasses(); //Output Codes if (this.initMatrixCodes == true) { this.matrixCodes = new int[this.ensemble.length][inst.numClasses()]; for (int i = 0; i < this.ensemble.length; i++) { int numberOnes; int numberZeros; do { // until we have the same number of zeros and ones numberOnes = 0;/*from w ww. j a va 2s. c om*/ numberZeros = 0; for (int j = 0; j < numClasses; j++) { int result = 0; if (j == 1 && numClasses == 2) { result = 1 - this.matrixCodes[i][0]; } else { result = (this.classifierRandom.nextBoolean() ? 1 : 0); } this.matrixCodes[i][j] = result; if (result == 1) numberOnes++; else numberZeros++; } } while ((numberOnes - numberZeros) * (numberOnes - numberZeros) > (this.ensemble.length % 2)); } this.initMatrixCodes = false; } boolean Change = false; double w = 1.0; double mt = 0.0; Instance weightedInst = (Instance) inst.copy(); /*for (int i = 0; i < this.ensemble.length; i++) { if (this.outputCodesOption.isSet()) { weightedInst.setClassValue((double) this.matrixCodes[i][(int) inst.classValue()] ); } if(!this.ensemble[i].correctlyClassifies(weightedInst)) { mt++; } }*/ //update w w = this.weightShrinkOption.getValue(); //1.0 +mt/2.0; //Train ensemble of classifiers for (int i = 0; i < this.ensemble.length; i++) { int k = MiscUtils.poisson(w, this.classifierRandom); if (k > 0) { if (this.outputCodesOption.isSet()) { weightedInst.setClassValue((double) this.matrixCodes[i][(int) inst.classValue()]); } weightedInst.setWeight(inst.weight() * k); this.ensemble[i].trainOnInstance(weightedInst); } boolean correctlyClassifies = this.ensemble[i].correctlyClassifies(weightedInst); double ErrEstim = this.ADError[i].getEstimation(); if (this.ADError[i].setInput(correctlyClassifies ? 0 : 1)) if (this.ADError[i].getEstimation() > ErrEstim) Change = true; } if (Change) { numberOfChangesDetected++; double max = 0.0; int imax = -1; for (int i = 0; i < this.ensemble.length; i++) { if (max < this.ADError[i].getEstimation()) { max = this.ADError[i].getEstimation(); imax = i; } } if (imax != -1) { this.ensemble[imax].resetLearning(); //this.ensemble[imax].trainOnInstance(inst); this.ADError[imax] = new ADWIN((double) this.deltaAdwinOption.getValue()); } } }
From source file:tr.gov.ulakbim.jDenetX.classifiers.LeveragingBagWT.java
License:Open Source License
@Override public void trainOnInstanceImpl(Instance inst) { int numClasses = inst.numClasses(); //Output Codes if (this.initMatrixCodes == true) { this.matrixCodes = new int[this.ensemble.length][inst.numClasses()]; for (int i = 0; i < this.ensemble.length; i++) { int numberOnes; int numberZeros; do { // until we have the same number of zeros and ones numberOnes = 0;//from w w w . j a va 2 s . c om numberZeros = 0; for (int j = 0; j < numClasses; j++) { int result = 0; if (j == 1 && numClasses == 2) { result = 1 - this.matrixCodes[i][0]; } else { result = (this.classifierRandom.nextBoolean() ? 1 : 0); } this.matrixCodes[i][j] = result; if (result == 1) numberOnes++; else numberZeros++; } } while ((numberOnes - numberZeros) * (numberOnes - numberZeros) > (this.ensemble.length % 2)); } this.initMatrixCodes = false; } boolean Change = false; double w = 1.0; double mt = 0.0; Instance weightedInst = (Instance) inst.copy(); //update w w = this.weightShrinkOption.getValue(); //Train ensemble of classifiers for (int i = 0; i < this.ensemble.length; i++) { int k = 1 + MiscUtils.poisson(w, this.classifierRandom); if (k > 0) { if (this.outputCodesOption.isSet()) { weightedInst.setClassValue((double) this.matrixCodes[i][(int) inst.classValue()]); } weightedInst.setWeight(inst.weight() * k); this.ensemble[i].trainOnInstance(weightedInst); } boolean correctlyClassifies = this.ensemble[i].correctlyClassifies(weightedInst); double ErrEstim = this.ADError[i].getEstimation(); if (this.ADError[i].setInput(correctlyClassifies ? 0 : 1)) if (this.ADError[i].getEstimation() > ErrEstim) Change = true; } if (Change) { numberOfChangesDetected++; double max = 0.0; int imax = -1; for (int i = 0; i < this.ensemble.length; i++) { if (max < this.ADError[i].getEstimation()) { max = this.ADError[i].getEstimation(); imax = i; } } if (imax != -1) { this.ensemble[imax].resetLearning(); //this.ensemble[imax].trainOnInstance(inst); this.ADError[imax] = new ADWIN((double) this.deltaAdwinOption.getValue()); } } }
From source file:tr.gov.ulakbim.jDenetX.classifiers.OCBoost.java
License:Open Source License
@Override public void trainOnInstanceImpl(Instance inst) { double d = 1.0; int[] m = new int[this.ensemble.length]; for (int j = 0; j < this.ensemble.length; j++) { int j0 = 0; //max(0,j-K) pipos[j] = 1.0;/*from w w w . j a v a 2 s .c om*/ pineg[j] = 1.0; m[j] = -1; if (this.ensemble[j].correctlyClassifies(inst)) { m[j] = 1; } for (int k = j0; k <= j - 1; k++) { pipos[j] *= wpos[j][k] / wpos[j][j] * Math.exp(-alphainc[k]) + (1.0 - wpos[j][k] / wpos[j][j]) * Math.exp(alphainc[k]); pineg[j] *= wneg[j][k] / wneg[j][j] * Math.exp(-alphainc[k]) + (1.0 - wneg[j][k] / wneg[j][j]) * Math.exp(alphainc[k]); } for (int k = 0; k <= j; k++) { wpos[j][k] = wpos[j][k] * pipos[j] + d * (m[k] == 1 ? 1 : 0) * (m[j] == 1 ? 1 : 0); wneg[j][k] = wneg[j][k] * pineg[j] + d * (m[k] == -1 ? 1 : 0) * (m[j] == -1 ? 1 : 0); } alphainc[j] = -alpha[j]; alpha[j] = 0.5 * Math.log(wpos[j][j] / wneg[j][j]); alphainc[j] += alpha[j]; d = d * Math.exp(-alpha[j] * m[j]); if (d > 0.0) { Instance weightedInst = (Instance) inst.copy(); weightedInst.setWeight(inst.weight() * d); this.ensemble[j].trainOnInstance(weightedInst); } } }
From source file:tr.gov.ulakbim.jDenetX.classifiers.OzaBagASHOT.java
License:Open Source License
@Override public void trainOnInstanceImpl(Instance inst) { final int trueClass = (int) inst.classValue(); //System.out.println("Ensemble Length " + this.ensemble.length); for (int i = 0; i < this.ensemble.length; i++) { final int k = MiscUtils.poisson(1.0, this.classifierRandom); if (k > 0) { final Instance weightedInst = (Instance) inst.copy(); weightedInst.setWeight(inst.weight() * k); if (Utils.maxIndex(this.ensemble[i].getVotesForInstance(inst)) == trueClass) { this.error[i] += alpha * (0.0 - this.error[i]); //EWMA } else { this.error[i] += alpha * (1.0 - this.error[i]); //EWMA }/* w ww. ja va 2 s. com*/ this.ensemble[i].trainOnInstance(weightedInst); } // System.out.println("ClassifierRandom: " + k); //System.out.println("EWMA Error Ensemble "+i+" "+ this.error[i]); if (this.error[i] > 0.6) { System.out.println("Error is " + this.error[i]); System.out.println("Ensemble " + i); System.err.println("Warning!!!!!"); } } }
From source file:tr.gov.ulakbim.jDenetX.classifiers.OzaBoostAdwin.java
License:Open Source License
@Override public void trainOnInstanceImpl(Instance inst) { int numClasses = inst.numClasses(); // Set log (k-1) and (k-1) for SAMME Method if (this.sammeOption.isSet()) { this.Km1 = numClasses - 1; this.logKm1 = Math.log(this.Km1); this.initKm1 = false; }/*from w w w. j a v a2 s . co m*/ //Output Codes if (this.initMatrixCodes) { this.matrixCodes = new int[this.ensemble.length][inst.numClasses()]; for (int i = 0; i < this.ensemble.length; i++) { int numberOnes; int numberZeros; do { // until we have the same number of zeros and ones numberOnes = 0; numberZeros = 0; for (int j = 0; j < numClasses; j++) { int result = 0; if (j == 1 && numClasses == 2) { result = 1 - this.matrixCodes[i][0]; } else { result = (this.classifierRandom.nextBoolean() ? 1 : 0); } this.matrixCodes[i][j] = result; if (result == 1) numberOnes++; else numberZeros++; } } while ((numberOnes - numberZeros) * (numberOnes - numberZeros) > (this.ensemble.length % 2)); } this.initMatrixCodes = false; } boolean Change = false; double lambda_d = 1.0; Instance weightedInst = (Instance) inst.copy(); for (int i = 0; i < this.ensemble.length; i++) { double k = this.pureBoostOption.isSet() ? lambda_d : MiscUtils.poisson(lambda_d * this.Km1, this.classifierRandom); if (k > 0.0) { if (this.outputCodesOption.isSet()) { weightedInst.setClassValue((double) this.matrixCodes[i][(int) inst.classValue()]); } weightedInst.setWeight(inst.weight() * k); this.ensemble[i].trainOnInstance(weightedInst); } boolean correctlyClassifies = this.ensemble[i].correctlyClassifies(weightedInst); if (correctlyClassifies) { this.scms[i] += lambda_d; lambda_d *= this.trainingWeightSeenByModel / (2 * this.scms[i]); } else { this.swms[i] += lambda_d; lambda_d *= this.trainingWeightSeenByModel / (2 * this.swms[i]); } double ErrEstim = this.ADError[i].getEstimation(); if (this.ADError[i].setInput(correctlyClassifies ? 0 : 1)) if (this.ADError[i].getEstimation() > ErrEstim) Change = true; } if (Change) { numberOfChangesDetected++; double max = 0.0; int imax = -1; for (int i = 0; i < this.ensemble.length; i++) { if (max < this.ADError[i].getEstimation()) { max = this.ADError[i].getEstimation(); imax = i; } } if (imax != -1) { this.ensemble[imax].resetLearning(); //this.ensemble[imax].trainOnInstance(inst); this.ADError[imax] = new ADWIN((double) this.deltaAdwinOption.getValue()); this.scms[imax] = 0; this.swms[imax] = 0; } } }
From source file:tr.gov.ulakbim.jDenetX.experiments.wrappers.EvalActiveBoostingID.java
License:Open Source License
protected int selfTest(InstanceStream testStream) { int returnStatus = 1; Instance testInst = null; int maxInstances = this.maxInstancesOption.getValue(); long instancesProcessed = 0; //InstanceStream testStream = (InstanceStream) getPreparedClassOption(this.testStreamOption); ClassificationPerformanceEvaluator evaluator = new BasicClassificationPerformanceEvaluator(); evaluator.reset();//from w w w. ja v a 2s. c o m while (testStream.hasMoreInstances() && ((maxInstances < 0) || (instancesProcessed < maxInstances))) { testInst = (Instance) testStream.nextInstance().copy(); int trueClass = (int) testInst.classValue(); testInst.setClassMissing(); double[] prediction = model.getVotesForInstance(testInst); evaluator.addClassificationAttempt(trueClass, prediction, testInst.weight()); instancesProcessed++; if (instancesProcessed % INSTANCES_BETWEEN_MONITOR_UPDATES == 0) { long estimatedRemainingInstances = testStream.estimatedRemainingInstances(); if (maxInstances > 0) { long maxRemaining = maxInstances - instancesProcessed; if ((estimatedRemainingInstances < 0) || (maxRemaining < estimatedRemainingInstances)) { estimatedRemainingInstances = maxRemaining; } } System.out.println(estimatedRemainingInstances < 0 ? -1.0 : (double) instancesProcessed / (double) (instancesProcessed + estimatedRemainingInstances)); } } return returnStatus; }
From source file:tr.gov.ulakbim.jDenetX.experiments.wrappers.EvalActiveBoostingID.java
License:Open Source License
public LearningEvaluation evalModel(InstanceStream trainStream, InstanceStream testStream, AbstractClassifier model) {// w ww.jav a 2 s . co m model = new SelfOzaBoostID(); InstanceStream stream = (InstanceStream) trainStream.copy(); ClassificationPerformanceEvaluator evaluator = new BasicClassificationPerformanceEvaluator(); Instance testInst = null; int maxInstances = this.maxInstancesOption.getValue(); long instancesProcessed = 0; System.out.println("Evaluating model..."); while (stream.hasMoreInstances() && ((maxInstances < 0) || (instancesProcessed < maxInstances))) { testInst = (Instance) stream.nextInstance().copy(); int trueClass = (int) testInst.classValue(); testInst.setClassMissing(); double[] prediction = model.getVotesForInstance(testInst); evaluator.addClassificationAttempt(trueClass, prediction, testInst.weight()); instancesProcessed++; if (instancesProcessed % INSTANCES_BETWEEN_MONITOR_UPDATES == 0) { long estimatedRemainingInstances = stream.estimatedRemainingInstances(); if (maxInstances > 0) { long maxRemaining = maxInstances - instancesProcessed; if ((estimatedRemainingInstances < 0) || (maxRemaining < estimatedRemainingInstances)) { estimatedRemainingInstances = maxRemaining; } } System.out.println(estimatedRemainingInstances < 0 ? -1.0 : (double) instancesProcessed / (double) (instancesProcessed + estimatedRemainingInstances)); } } System.out.println("Accuracy result before self-train: " + evaluator.getPerformanceMeasurements()[1]); selfTrain(testInst); int returnStatus = selfTest(testStream); EvalActiveBoostingID.model.resetLearningImpl(); //Learning is completed so we can reset return new LearningEvaluation(evaluator.getPerformanceMeasurements()); }
From source file:tr.gov.ulakbim.jDenetX.streams.filters.AddNoiseFilter.java
License:Open Source License
public Instance nextInstance() { Instance inst = (Instance) this.inputStream.nextInstance().copy(); for (int i = 0; i < inst.numAttributes(); i++) { double noiseFrac = i == inst.classIndex() ? this.classNoiseFractionOption.getValue() : this.attNoiseFractionOption.getValue(); if (inst.attribute(i).isNominal()) { DoubleVector obs = (DoubleVector) this.attValObservers.get(i); if (obs == null) { obs = new DoubleVector(); this.attValObservers.set(i, obs); }// w w w .j a v a 2 s . co m int originalVal = (int) inst.value(i); if (!inst.isMissing(i)) { obs.addToValue(originalVal, inst.weight()); } if ((this.random.nextDouble() < noiseFrac) && (obs.numNonZeroEntries() > 1)) { do { inst.setValue(i, this.random.nextInt(obs.numValues())); } while (((int) inst.value(i) == originalVal) || (obs.getValue((int) inst.value(i)) == 0.0)); } } else { GaussianEstimator obs = (GaussianEstimator) this.attValObservers.get(i); if (obs == null) { obs = new GaussianEstimator(); this.attValObservers.set(i, obs); } obs.addObservation(inst.value(i), inst.weight()); inst.setValue(i, inst.value(i) + this.random.nextGaussian() * obs.getStdDev() * noiseFrac); } } return inst; }
From source file:tr.gov.ulakbim.jDenetX.tasks.EvaluateInterleavedTestThenTrain.java
License:Open Source License
@Override protected Object doMainTask(TaskMonitor monitor, ObjectRepository repository) { Classifier learner = (Classifier) getPreparedClassOption(this.learnerOption); InstanceStream stream = (InstanceStream) getPreparedClassOption(this.streamOption); ClassificationPerformanceEvaluator evaluator = (ClassificationPerformanceEvaluator) getPreparedClassOption( this.evaluatorOption); learner.setModelContext(stream.getHeader()); int maxInstances = this.instanceLimitOption.getValue(); long instancesProcessed = 0; int maxSeconds = this.timeLimitOption.getValue(); int secondsElapsed = 0; monitor.setCurrentActivity("Evaluating learner...", -1.0); LearningCurve learningCurve = new LearningCurve("learning evaluation instances"); File dumpFile = this.dumpFileOption.getFile(); PrintStream immediateResultStream = null; if (dumpFile != null) { try {/*from ww w . ja v a 2 s . c o m*/ if (dumpFile.exists()) { immediateResultStream = new PrintStream(new FileOutputStream(dumpFile, true), true); } else { immediateResultStream = new PrintStream(new FileOutputStream(dumpFile), true); } } catch (Exception ex) { throw new RuntimeException("Unable to open immediate result file: " + dumpFile, ex); } } boolean firstDump = true; boolean preciseCPUTiming = TimingUtils.enablePreciseTiming(); long evaluateStartTime = TimingUtils.getNanoCPUTimeOfCurrentThread(); long lastEvaluateStartTime = evaluateStartTime; double RAMHours = 0.0; while (stream.hasMoreInstances() && ((maxInstances < 0) || (instancesProcessed < maxInstances)) && ((maxSeconds < 0) || (secondsElapsed < maxSeconds))) { Instance trainInst = stream.nextInstance(); Instance testInst = (Instance) trainInst.copy(); int trueClass = (int) trainInst.classValue(); testInst.setClassMissing(); double[] prediction = learner.getVotesForInstance(testInst); evaluator.addClassificationAttempt(trueClass, prediction, testInst.weight()); learner.trainOnInstance(trainInst); instancesProcessed++; if (instancesProcessed % this.sampleFrequencyOption.getValue() == 0) { long evaluateTime = TimingUtils.getNanoCPUTimeOfCurrentThread(); double time = TimingUtils.nanoTimeToSeconds(evaluateTime - evaluateStartTime); double timeIncrement = TimingUtils.nanoTimeToSeconds(evaluateTime - lastEvaluateStartTime); double RAMHoursIncrement = learner.measureByteSize() / (1024.0 * 1024.0 * 1024.0); //GBs RAMHoursIncrement *= (timeIncrement / 3600.0); //Hours RAMHours += RAMHoursIncrement; lastEvaluateStartTime = evaluateTime; learningCurve.insertEntry(new LearningEvaluation( new Measurement[] { new Measurement("learning evaluation instances", instancesProcessed), new Measurement("evaluation time (" + (preciseCPUTiming ? "cpu " : "") + "seconds)", time), new Measurement("model cost (RAM-Hours)", RAMHours) }, evaluator, learner)); if (immediateResultStream != null) { if (firstDump) { immediateResultStream.println(learningCurve.headerToString()); firstDump = false; } immediateResultStream.println(learningCurve.entryToString(learningCurve.numEntries() - 1)); immediateResultStream.flush(); } } if (instancesProcessed % INSTANCES_BETWEEN_MONITOR_UPDATES == 0) { if (monitor.taskShouldAbort()) { return null; } long estimatedRemainingInstances = stream.estimatedRemainingInstances(); if (maxInstances > 0) { long maxRemaining = maxInstances - instancesProcessed; if ((estimatedRemainingInstances < 0) || (maxRemaining < estimatedRemainingInstances)) { estimatedRemainingInstances = maxRemaining; } } monitor.setCurrentActivityFractionComplete(estimatedRemainingInstances < 0 ? -1.0 : (double) instancesProcessed / (double) (instancesProcessed + estimatedRemainingInstances)); if (monitor.resultPreviewRequested()) { monitor.setLatestResultPreview(learningCurve.copy()); } secondsElapsed = (int) TimingUtils .nanoTimeToSeconds(TimingUtils.getNanoCPUTimeOfCurrentThread() - evaluateStartTime); } } if (immediateResultStream != null) { immediateResultStream.close(); } return learningCurve; }