List of usage examples for weka.core Instance setClassValue
public void setClassValue(String value);
From source file:Helper.ClassifyHelper.java
public static void clasifyInstance(Classifier cls, Instance inst) throws Exception { double result = cls.classifyInstance(inst); inst.setClassValue(result); }
From source file:hsa_jni.hsa_jni.EvaluatePeriodicHeldOutTestBatch.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()); long instancesProcessed = 0; LearningCurve learningCurve = new LearningCurve("evaluation instances"); File dumpFile = this.dumpFileOption.getFile(); PrintStream immediateResultStream = null; if (dumpFile != null) { try {/*from w w w . j a v a2s . 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; InstanceStream testStream = null; int testSize = this.testSizeOption.getValue(); if (this.cacheTestOption.isSet()) { monitor.setCurrentActivity("Caching test examples...", -1.0); Instances testInstances = new Instances(stream.getHeader(), this.testSizeOption.getValue()); while (testInstances.numInstances() < testSize) { testInstances.add(stream.nextInstance()); if (testInstances.numInstances() % INSTANCES_BETWEEN_MONITOR_UPDATES == 0) { if (monitor.taskShouldAbort()) { return null; } monitor.setCurrentActivityFractionComplete( (double) testInstances.numInstances() / (double) (this.testSizeOption.getValue())); } } testStream = new CachedInstancesStream(testInstances); } else { //testStream = (InstanceStream) stream.copy(); testStream = stream; /*monitor.setCurrentActivity("Skipping test examples...", -1.0); for (int i = 0; i < testSize; i++) { stream.nextInstance(); }*/ } instancesProcessed = 0; TimingUtils.enablePreciseTiming(); double totalTrainTime = 0.0; while ((this.trainSizeOption.getValue() < 1 || instancesProcessed < this.trainSizeOption.getValue()) && stream.hasMoreInstances() == true) { monitor.setCurrentActivityDescription("Training..."); long instancesTarget = instancesProcessed + this.sampleFrequencyOption.getValue(); ArrayList<Instance> instanceCache = new ArrayList<Instance>(); long trainStartTime = TimingUtils.getNanoCPUTimeOfCurrentThread(); double lastTrainTime = 0; while (instancesProcessed < instancesTarget && stream.hasMoreInstances() == true) { instanceCache.add(stream.nextInstance()); instancesProcessed++; if (instancesProcessed % INSTANCES_BETWEEN_MONITOR_UPDATES == 0) { if (monitor.taskShouldAbort()) { return null; } monitor.setCurrentActivityFractionComplete( (double) (instancesProcessed) / (double) (this.trainSizeOption.getValue())); } if (instanceCache.size() % 1000 == 0) { trainStartTime = TimingUtils.getNanoCPUTimeOfCurrentThread(); for (Instance inst : instanceCache) { learner.trainOnInstance(inst); } lastTrainTime += TimingUtils .nanoTimeToSeconds(TimingUtils.getNanoCPUTimeOfCurrentThread() - trainStartTime); instanceCache.clear(); } } trainStartTime = TimingUtils.getNanoCPUTimeOfCurrentThread(); for (Instance inst : instanceCache) { learner.trainOnInstance(inst); } if (learner instanceof BatchClassifier) ((BatchClassifier) learner).commit(); lastTrainTime += TimingUtils .nanoTimeToSeconds(TimingUtils.getNanoCPUTimeOfCurrentThread() - trainStartTime); totalTrainTime += lastTrainTime; if (totalTrainTime > this.trainTimeOption.getValue()) { break; } if (this.cacheTestOption.isSet()) { testStream.restart(); } evaluator.reset(); long testInstancesProcessed = 0; monitor.setCurrentActivityDescription("Testing (after " + StringUtils.doubleToString( ((double) (instancesProcessed) / (double) (this.trainSizeOption.getValue()) * 100.0), 2) + "% training)..."); long testStartTime = TimingUtils.getNanoCPUTimeOfCurrentThread(); int instCount = 0; for (instCount = 0; instCount < testSize; instCount++) { if (stream.hasMoreInstances() == false) { break; } Instance testInst = (Instance) testStream.nextInstance().copy(); double trueClass = testInst.classValue(); testInst.setClassMissing(); double[] prediction = learner.getVotesForInstance(testInst); testInst.setClassValue(trueClass); evaluator.addResult(testInst, prediction); testInstancesProcessed++; if (testInstancesProcessed % INSTANCES_BETWEEN_MONITOR_UPDATES == 0) { if (monitor.taskShouldAbort()) { return null; } monitor.setCurrentActivityFractionComplete( (double) testInstancesProcessed / (double) (testSize)); } } if (instCount != testSize) { break; } double testTime = TimingUtils .nanoTimeToSeconds(TimingUtils.getNanoCPUTimeOfCurrentThread() - testStartTime); List<Measurement> measurements = new ArrayList<Measurement>(); measurements.add(new Measurement("evaluation instances", instancesProcessed)); measurements.add(new Measurement("total train time", totalTrainTime)); measurements.add(new Measurement("total train speed", instancesProcessed / totalTrainTime)); measurements.add(new Measurement("last train time", lastTrainTime)); measurements.add( new Measurement("last train speed", this.sampleFrequencyOption.getValue() / lastTrainTime)); measurements.add(new Measurement("test time", testTime)); measurements.add(new Measurement("test speed", this.testSizeOption.getValue() / testTime)); Measurement[] performanceMeasurements = evaluator.getPerformanceMeasurements(); for (Measurement measurement : performanceMeasurements) { measurements.add(measurement); } Measurement[] modelMeasurements = learner.getModelMeasurements(); for (Measurement measurement : modelMeasurements) { measurements.add(measurement); } learningCurve.insertEntry( new LearningEvaluation(measurements.toArray(new Measurement[measurements.size()]))); if (immediateResultStream != null) { if (firstDump) { immediateResultStream.println(learningCurve.headerToString()); firstDump = false; } immediateResultStream.println(learningCurve.entryToString(learningCurve.numEntries() - 1)); immediateResultStream.flush(); } if (monitor.resultPreviewRequested()) { monitor.setLatestResultPreview(learningCurve.copy()); } // if (learner instanceof HoeffdingTree // || learner instanceof HoeffdingOptionTree) { // int numActiveNodes = (int) Measurement.getMeasurementNamed( // "active learning leaves", // modelMeasurements).getValue(); // // exit if tree frozen // if (numActiveNodes < 1) { // break; // } // int numNodes = (int) Measurement.getMeasurementNamed( // "tree size (nodes)", modelMeasurements) // .getValue(); // if (numNodes == lastNumNodes) { // noGrowthCount++; // } else { // noGrowthCount = 0; // } // lastNumNodes = numNodes; // } else if (learner instanceof OzaBoost || learner instanceof // OzaBag) { // double numActiveNodes = Measurement.getMeasurementNamed( // "[avg] active learning leaves", // modelMeasurements).getValue(); // // exit if all trees frozen // if (numActiveNodes == 0.0) { // break; // } // int numNodes = (int) (Measurement.getMeasurementNamed( // "[avg] tree size (nodes)", // learner.getModelMeasurements()).getValue() * Measurement // .getMeasurementNamed("ensemble size", // modelMeasurements).getValue()); // if (numNodes == lastNumNodes) { // noGrowthCount++; // } else { // noGrowthCount = 0; // } // lastNumNodes = numNodes; // } } if (immediateResultStream != null) { immediateResultStream.close(); } return learningCurve; }
From source file:meka.classifiers.multilabel.incremental.RTUpdateable.java
License:Open Source License
@Override public void updateClassifier(Instance x) throws Exception { int L = x.classIndex(); for (int j = 0; j < L; j++) { if (x.value(j) > 0.0) { Instance x_j = convertInstance(x); x_j.setClassValue(j); ((UpdateableClassifier) m_Classifier).updateClassifier(x_j); }//from w w w . j ava 2 s. com } }
From source file:meka.classifiers.multitarget.NSR.java
License:Open Source License
public Instances convertInstances(Instances D, int L) throws Exception { //Gather combinations HashMap<String, Integer> distinctCombinations = MLUtils.classCombinationCounts(D); if (getDebug()) System.out.println("Found " + distinctCombinations.size() + " unique combinations"); //Prune combinations MLUtils.pruneCountHashMap(distinctCombinations, m_P); if (getDebug()) System.out.println("Pruned to " + distinctCombinations.size() + " with P=" + m_P); // Remove all class attributes Instances D_ = MLUtils.deleteAttributesAt(new Instances(D), MLUtils.gen_indices(L)); // Add a new class attribute D_.insertAttributeAt(new Attribute("CLASS", new ArrayList(distinctCombinations.keySet())), 0); // create the class attribute D_.setClassIndex(0);//ww w .j a v a2 s.c o m //Add class values for (int i = 0; i < D.numInstances(); i++) { String y = MLUtils.encodeValue(MLUtils.toIntArray(D.instance(i), L)); // add it if (distinctCombinations.containsKey(y)) //if its class value exists D_.instance(i).setClassValue(y); // decomp else if (m_N > 0) { String d_subsets[] = SuperLabelUtils.getTopNSubsets(y, distinctCombinations, m_N); for (String s : d_subsets) { int w = distinctCombinations.get(s); Instance copy = (Instance) (D_.instance(i)).copy(); copy.setClassValue(s); copy.setWeight(1.0 / d_subsets.length); D_.add(copy); } } } // remove with missing class D_.deleteWithMissingClass(); // keep the header of new dataset for classification m_InstancesTemplate = new Instances(D_, 0); if (getDebug()) System.out.println("" + D_); return D_; }
From source file:meka.core.PSUtils.java
License:Open Source License
/** * Transform instances into a multi-class representation. * @param D original dataset//from w w w . j a va 2 s . c o m * @param L number of labels in the original dataset * @param cname class name for the new dataset (may want to encode the list of indices here for RAkEL-like methods) * @param p pruning value * @param n restoration value * @return transformed dataset */ public static Instances PSTransformation(Instances D, int L, String cname, int p, int n) { D = new Instances(D); // Gather combinations HashMap<LabelSet, Integer> distinctCombinations = PSUtils.countCombinationsSparse(D, L); // Prune combinations if (p > 0) MLUtils.pruneCountHashMap(distinctCombinations, p); // Check there are > 2 if (distinctCombinations.size() <= 1 && p > 0) { // ... or try again if not ... System.err.println("[Warning] You did too much pruning, setting P = P-1"); return PSTransformation(D, L, cname, p - 1, n); } // Create class attribute ArrayList<String> ClassValues = new ArrayList<String>(); for (LabelSet y : distinctCombinations.keySet()) ClassValues.add(y.toString()); Attribute C = new Attribute(cname, ClassValues); // Insert new special attribute (which has all possible combinations of labels) D.insertAttributeAt(C, L); D.setClassIndex(L); //Add class values int N = D.numInstances(); for (int i = 0; i < N; i++) { Instance x = D.instance(i); LabelSet y = new LabelSet(MLUtils.toSparseIntArray(x, L)); String y_string = y.toString(); // add it if (ClassValues.contains(y_string)) //if its class value exists x.setClassValue(y_string); // decomp else if (n > 0) { //String d_subsets[] = getTopNSubsets(comb,distinctCombinations,n); LabelSet d_subsets[] = PSUtils.getTopNSubsets(y, distinctCombinations, n); //LabelSet d_subsets[] = PSUtils.cover(y,distinctCombinations); if (d_subsets.length > 0) { // fast x.setClassValue(d_subsets[0].toString()); // additional if (d_subsets.length > 1) { for (int s_i = 1; s_i < d_subsets.length; s_i++) { Instance x_ = (Instance) (x).copy(); x_.setClassValue(d_subsets[s_i].toString()); D.add(x_); } } } else { x.setClassMissing(); } } } // remove with missing class D.deleteWithMissingClass(); try { D = F.removeLabels(D, L); } catch (Exception e) { // should never happen } D.setClassIndex(0); return D; }
From source file:meka.core.PSUtils.java
License:Open Source License
/** * Transform instances into a multi-class representation. * @param D original dataset//from w w w . j av a 2s.c om * @param L number of labels in that dataset * @param cname class name for the new dataset (may want to encode the list of indices here for RAkEL-like methods) * @param p pruning value * @param n restoration value * @return transformed dataset */ public static Instances SLTransformation(Instances D, int L, String cname, int p, int n) { D = new Instances(D); // Gather combinations HashMap<LabelSet, Integer> distinctCombinations = PSUtils.countCombinationsSparse(D, L); // Prune combinations if (p > 0) MLUtils.pruneCountHashMap(distinctCombinations, p); // Check there are > 2 if (distinctCombinations.size() <= 1 && p > 0) { // ... or try again if not ... System.err.println("[Warning] You did too much pruning, setting P = P-1"); return PSTransformation(D, L, cname, p - 1, n); } // Create class attribute ArrayList<String> ClassValues = new ArrayList<String>(); for (LabelSet y : distinctCombinations.keySet()) ClassValues.add(y.toString()); Attribute C = new Attribute(cname, ClassValues); // Insert new special attribute (which has all possible combinations of labels) D.insertAttributeAt(C, L); D.setClassIndex(L); //Add class values int N = D.numInstances(); for (int i = 0; i < N; i++) { Instance x = D.instance(i); LabelSet y = new LabelSet(MLUtils.toSparseIntArray(x, L)); String y_string = y.toString(); // add it if (ClassValues.contains(y_string)) //if its class value exists x.setClassValue(y_string); // decomp else if (n > 0) { //String d_subsets[] = getTopNSubsets(comb,distinctCombinations,n); LabelSet d_subsets[] = PSUtils.getTopNSubsets(y, distinctCombinations, n); //LabelSet d_subsets[] = PSUtils.cover(y,distinctCombinations); if (d_subsets.length > 0) { // fast x.setClassValue(d_subsets[0].toString()); // additional if (d_subsets.length > 1) { for (int s_i = 1; s_i < d_subsets.length; s_i++) { Instance x_ = (Instance) (x).copy(); x_.setClassValue(d_subsets[s_i].toString()); D.add(x_); } } } else { x.setClassMissing(); } } } // remove with missing class D.deleteWithMissingClass(); try { D = F.removeLabels(D, L); } catch (Exception e) { // should never happen } D.setClassIndex(0); return D; }
From source file:milk.classifiers.SimpleMI.java
License:Open Source License
public Instances transform(Exemplars train) throws Exception { Instances data = new Instances(m_Attributes);// Data to learn a model data.deleteAttributeAt(m_IdIndex);// ID attribute useless Instances dataset = new Instances(data, 0); Instance template = new Instance(dataset.numAttributes()); template.setDataset(dataset);//from w ww . j a v a 2s.c om double N = train.numExemplars(); // Number of exemplars for (int i = 0; i < N; i++) { Exemplar exi = train.exemplar(i); Instances insts = exi.getInstances(); int attIdx = 0; Instance newIns = new Instance(template); newIns.setDataset(dataset); for (int j = 0; j < insts.numAttributes(); j++) { if ((j == m_IdIndex) || (j == m_ClassIndex)) continue; double value; if (m_TransformMethod == 1) { value = insts.meanOrMode(j); } else { double[] minimax = minimax(insts, j); value = (minimax[0] + minimax[1]) / 2.0; } newIns.setValue(attIdx++, value); } newIns.setClassValue(exi.classValue()); data.add(newIns); } return data; }
From source file:moa.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;/* w w w . j a v a 2 s . c o m*/ 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:moa.classifiers.LeveragingBag.java
License:Open Source License
public double[] getVotesForInstanceBinary(Instance inst) { double combinedVote[] = new double[(int) inst.numClasses()]; Instance weightedInst = (Instance) inst.copy(); if (this.initMatrixCodes == false) { for (int i = 0; i < this.ensemble.length; i++) { //Replace class by OC weightedInst.setClassValue((double) this.matrixCodes[i][(int) inst.classValue()]); double vote[]; vote = this.ensemble[i].getVotesForInstance(weightedInst); //Binary Case int voteClass = 0; if (vote.length == 2) { voteClass = (vote[1] > vote[0] ? 1 : 0); }/*from w w w . j a v a 2 s . co m*/ //Update votes for (int j = 0; j < inst.numClasses(); j++) { if (this.matrixCodes[i][j] == voteClass) { combinedVote[j] += 1; } } } } return combinedVote; }
From source file:moa.classifiers.LeveragingBagHalf.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;/* w w w . j a v a 2 s.com*/ 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(); //Train ensemble of classifiers for (int i = 0; i < this.ensemble.length; i++) { int k = this.classifierRandom.nextBoolean() ? 0 : (int) this.weightShrinkOption.getValue(); //half bagging if (k > 0) { if (this.outputCodesOption.isSet()) { weightedInst.setClassValue((double) this.matrixCodes[i][(int) inst.classValue()]); } weightedInst.setWeight(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()); } } }