List of usage examples for weka.core Instance weight
public double weight();
From source file:tr.gov.ulakbim.jDenetX.tasks.EvaluateModel.java
License:Open Source License
@Override public Object doMainTask(TaskMonitor monitor, ObjectRepository repository) { Classifier model = (Classifier) getPreparedClassOption(this.modelOption); InstanceStream stream = (InstanceStream) getPreparedClassOption(this.streamOption); ClassificationPerformanceEvaluator evaluator = (ClassificationPerformanceEvaluator) getPreparedClassOption( this.evaluatorOption); int maxInstances = this.maxInstancesOption.getValue(); long instancesProcessed = 0; monitor.setCurrentActivity("Evaluating model...", -1.0); while (stream.hasMoreInstances() && ((maxInstances < 0) || (instancesProcessed < maxInstances))) { Instance testInst = (Instance) stream.nextInstance().copy(); int trueClass = (int) testInst.classValue(); testInst.setClassMissing();// w w w. j a v a 2s. c o m double[] prediction = model.getVotesForInstance(testInst); evaluator.addClassificationAttempt(trueClass, prediction, testInst.weight()); instancesProcessed++; 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(new LearningEvaluation(evaluator.getPerformanceMeasurements())); } } } return new LearningEvaluation(evaluator.getPerformanceMeasurements()); }
From source file:tr.gov.ulakbim.jDenetX.tasks.EvaluatePrequential.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); //New for prequential methods if (evaluator instanceof WindowClassificationPerformanceEvaluator) { ((WindowClassificationPerformanceEvaluator) evaluator).setWindowWidth(widthOption.getValue()); }/*from ww w .ja v a 2s .c om*/ if (evaluator instanceof EWMAClassificationPerformanceEvaluator) { ((EWMAClassificationPerformanceEvaluator) evaluator).setalpha(alphaOption.getValue()); } if (evaluator instanceof FadingFactorClassificationPerformanceEvaluator) { ((FadingFactorClassificationPerformanceEvaluator) evaluator).setalpha(alphaOption.getValue()); } //End New for prequential methods 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 { 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); } } //File for output predictions File outputPredictionFile = this.outputPredictionFileOption.getFile(); PrintStream outputPredictionResultStream = null; if (outputPredictionFile != null) { try { if (outputPredictionFile.exists()) { outputPredictionResultStream = new PrintStream(new FileOutputStream(outputPredictionFile, true), true); } else { outputPredictionResultStream = new PrintStream(new FileOutputStream(outputPredictionFile), true); } } catch (Exception ex) { throw new RuntimeException("Unable to open prediction result file: " + outputPredictionFile, 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); // Output prediction if (outputPredictionFile != null) { outputPredictionResultStream.println(Utils.maxIndex(prediction) + "," + trueClass); } 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(); } if (outputPredictionResultStream != null) { outputPredictionResultStream.close(); } return learningCurve; }
From source file:wekimini.learning.LinearRegressionAttributeTransformer.java
@Override public Instance convertInstance(Instance instance) throws Exception { double[] newVals = new double[numInputs * exponent + 1]; int next = 0; for (int i = 0; i < instance.numAttributes() - 1; i++) { for (int j = 1; j <= exponent; j++) { newVals[next] = Math.pow(instance.value(i), j); next++;/*from w ww. j a v a 2 s.c o m*/ } } //Now add class: newVals[newVals.length - 1] = instance.classValue(); //Convert: return new Instance(instance.weight(), newVals); }
From source file:zhaop.textmining.proj.MyStringToWordVector.java
License:Open Source License
/** * Converts the instance w/o normalization. * /*from w ww .j av a 2 s . co m*/ * @oaram instance the instance to convert * @param v * @return the conerted instance */ private int convertInstancewoDocNorm(Instance instance, FastVector v) { // Convert the instance into a sorted set of indexes TreeMap contained = new TreeMap(); // Copy all non-converted attributes from input to output int firstCopy = 0; for (int i = 0; i < getInputFormat().numAttributes(); i++) { if (!m_SelectedRange.isInRange(i)) { if (getInputFormat().attribute(i).type() != Attribute.STRING) { // Add simple nominal and numeric attributes directly if (instance.value(i) != 0.0) { contained.put(new Integer(firstCopy), new Double(instance.value(i))); } } else { if (instance.isMissing(i)) { contained.put(new Integer(firstCopy), new Double(Instance.missingValue())); } else { // If this is a string attribute, we have to first add // this value to the range of possible values, then add // its new internal index. if (outputFormatPeek().attribute(firstCopy).numValues() == 0) { // Note that the first string value in a // SparseInstance doesn't get printed. outputFormatPeek().attribute(firstCopy) .addStringValue("Hack to defeat SparseInstance bug"); } int newIndex = outputFormatPeek().attribute(firstCopy) .addStringValue(instance.stringValue(i)); contained.put(new Integer(firstCopy), new Double(newIndex)); } } firstCopy++; } } for (int j = 0; j < instance.numAttributes(); j++) { // if ((getInputFormat().attribute(j).type() == Attribute.STRING) if (m_SelectedRange.isInRange(j) && (instance.isMissing(j) == false)) { m_Tokenizer.tokenize(instance.stringValue(j)); while (m_Tokenizer.hasMoreElements()) { String word = (String) m_Tokenizer.nextElement(); if (this.m_lowerCaseTokens == true) word = word.toLowerCase(); word = m_Stemmer.stem(word); Integer index = (Integer) m_Dictionary.get(word); if (index != null) { if (m_OutputCounts) { // Separate if here rather than two lines down // to avoid hashtable lookup Double count = (Double) contained.get(index); if (count != null) { contained.put(index, new Double(count.doubleValue() + 1.0)); } else { contained.put(index, new Double(1)); } } else { contained.put(index, new Double(1)); } } } } } // Doing TFTransform if (m_TFTransform == true) { Iterator it = contained.keySet().iterator(); for (int i = 0; it.hasNext(); i++) { Integer index = (Integer) it.next(); if (index.intValue() >= firstCopy) { double val = ((Double) contained.get(index)).doubleValue(); val = Math.log(val + 1); contained.put(index, new Double(val)); } } } // Doing IDFTransform if (m_IDFTransform == true) { Iterator it = contained.keySet().iterator(); for (int i = 0; it.hasNext(); i++) { Integer index = (Integer) it.next(); if (index.intValue() >= firstCopy) { double val = ((Double) contained.get(index)).doubleValue(); val = val * Math.log(m_NumInstances / (double) m_DocsCounts[index.intValue()]); contained.put(index, new Double(val)); } } } // Convert the set to structures needed to create a sparse instance. double[] values = new double[contained.size()]; int[] indices = new int[contained.size()]; Iterator it = contained.keySet().iterator(); for (int i = 0; it.hasNext(); i++) { Integer index = (Integer) it.next(); Double value = (Double) contained.get(index); values[i] = value.doubleValue(); indices[i] = index.intValue(); } Instance inst = new SparseInstance(instance.weight(), values, indices, outputFormatPeek().numAttributes()); inst.setDataset(outputFormatPeek()); v.addElement(inst); return firstCopy; }