List of usage examples for weka.filters.supervised.instance Resample setInputFormat
@Override public boolean setInputFormat(Instances instanceInfo) throws Exception
From source file:de.ugoe.cs.cpdp.dataprocessing.Oversampling.java
License:Apache License
@Override public void apply(Instances testdata, Instances traindata) { final int[] counts = traindata.attributeStats(traindata.classIndex()).nominalCounts; if (counts[1] < counts[0]) { Instances negatives = new Instances(traindata); Instances positives = new Instances(traindata); for (int i = traindata.size() - 1; i >= 0; i--) { if (Double.compare(1.0, negatives.get(i).classValue()) == 0) { negatives.remove(i);/*w w w . ja v a 2s .c o m*/ } if (Double.compare(0.0, positives.get(i).classValue()) == 0) { positives.remove(i); } } Resample resample = new Resample(); resample.setSampleSizePercent((100.0 * counts[0]) / counts[1]); try { resample.setInputFormat(traindata); positives = Filter.useFilter(positives, resample); } catch (Exception e) { throw new RuntimeException(e); } traindata.clear(); for (int i = 0; i < negatives.size(); i++) { traindata.add(negatives.get(i)); } for (int i = 0; i < positives.size(); i++) { traindata.add(positives.get(i)); } } }
From source file:de.ugoe.cs.cpdp.dataprocessing.Resampling.java
License:Apache License
@Override public void apply(Instances testdata, Instances traindata) { Resample resample = new Resample(); resample.setSampleSizePercent(100);//w w w. j a v a2 s.c om resample.setBiasToUniformClass(1.0); Instances traindataSample; try { resample.setInputFormat(traindata); traindataSample = Filter.useFilter(traindata, resample); } catch (Exception e) { throw new RuntimeException(e); } traindata.clear(); for (int i = 0; i < traindataSample.size(); i++) { traindata.add(traindataSample.get(i)); } }
From source file:de.ugoe.cs.cpdp.dataselection.LACE2.java
License:Apache License
@Override public void apply(Instances testdata, SetUniqueList<Instances> traindataSet) { Instances selectedData = new Instances(testdata); selectedData.clear();/*from w w w.ja va 2s .c om*/ LinkedList<Instances> traindataCopy = new LinkedList<>(traindataSet); Collections.shuffle(traindataCopy); CLIFF cliff = new CLIFF(); cliff.setParameter(Double.toString(percentage)); MORPH morph = new MORPH(); Median median = new Median(); double minDist = Double.MIN_VALUE; for (Instances traindata : traindataCopy) { Instances cliffedData = cliff.applyCLIFF(traindata); if (minDist == Double.MIN_VALUE) { // determine distance for leader-follower algorithm Instances sample; if (traindata.size() > 100) { Resample resample = new Resample(); resample.setSampleSizePercent(100.0 / traindata.size() * 100.0); resample.setBiasToUniformClass(0.0); resample.setNoReplacement(true); try { resample.setInputFormat(traindata); sample = Filter.useFilter(traindata, resample); } catch (Exception e) { throw new RuntimeException(e); } } else { sample = new Instances(traindata); } double[] distances = new double[sample.size()]; for (int i = 0; i < sample.size(); i++) { Instance unlikeNeighbor = morph.getNearestUnlikeNeighbor(sample.get(i), sample); distances[i] = MathArrays.distance(WekaUtils.instanceValues(sample.get(i)), WekaUtils.instanceValues(unlikeNeighbor)); } minDist = median.evaluate(distances); } for (int i = 0; i < cliffedData.size(); i++) { Instance unlikeNeighbor = morph.getNearestUnlikeNeighbor(cliffedData.get(i), selectedData); if (unlikeNeighbor == null) { selectedData.add(cliffedData.get(i)); } else { double distance = MathArrays.distance(WekaUtils.instanceValues(cliffedData.get(i)), WekaUtils.instanceValues(unlikeNeighbor)); if (distance > minDist) { morph.morphInstance(cliffedData.get(i), cliffedData); selectedData.add(cliffedData.get(i)); } } } } }
From source file:function.FilterResample.java
public static Instances filterResample(Instances inst) { Resample filter = new Resample(); Instances instResample = null;//from w w w. j ava2 s .c o m filter.setBiasToUniformClass(1.0); try { filter.setInputFormat(inst); filter.setNoReplacement(false); filter.setSampleSizePercent(100); instResample = Filter.useFilter(inst, filter); } catch (Exception e) { System.out.println("Error when resampling input data!"); e.printStackTrace(); } return instResample; }
From source file:gyc.SMOTEBagging.java
License:Open Source License
/** * //from w w w .j av a2s . c o m * 100%majminSMOTE (k, a). * @param data * @param i * @return */ protected Instances randomSampling(Instances copia, int majC, int minC, int a, Random simplingRandom) { int[] majExamples = new int[copia.numInstances()]; int[] minExamples = new int[copia.numInstances()]; int majCount = 0, minCount = 0; // First, we copy the examples from the minority class and save the indexes of the majority // resample min at rate (Nmaj/Nmin)*a% int size = copia.attributeStats(copia.classIndex()).nominalCounts[majC] * a / 100; // class name String majClassName = copia.attribute(copia.classIndex()).value(majC); for (int i = 0; i < copia.numInstances(); i++) { if (copia.instance(i).stringValue(copia.classIndex()).equalsIgnoreCase(majClassName)) { // save index majExamples[majCount] = i; majCount++; } else { minExamples[minCount] = i; minCount++; } } /* random undersampling of the majority */ Instances myDataset = new Instances(copia, 0); int r; //100%majC for (int i = 0; i < majCount; i++) { myDataset.add(copia.instance(majExamples[i])); } if (minCount == 0) return myDataset; //(Nmaj/Nmin)*a% minC for (int i = 0; i < size; i++) { r = simplingRandom.nextInt(minCount); myDataset.add(copia.instance(minExamples[r])); } myDataset.randomize(simplingRandom); if (size == 1) { try { //neighbor Resample filter = new Resample(); filter.setInputFormat(myDataset); filter.setBiasToUniformClass(1.0); filter.setRandomSeed(simplingRandom.nextInt()); myDataset = Filter.useFilter(myDataset, filter); } catch (Exception e) { // TODO Auto-generated catch block e.printStackTrace(); } } if (size > 1) { try { SMOTE filter = new SMOTE(); filter.setInputFormat(myDataset); // filter capabilities are checked here //data. double value = 100.0 * majCount / size - 100; //Percentage filter.setPercentage(value); //if (nMin<5) filter.setNearestNeighbors(nMin); filter.setRandomSeed(simplingRandom.nextInt()); //filterSMOTESMOTE myDataset = Filter.useFilter(myDataset, filter); //t.stop(); } catch (Exception e) { // TODO Auto-generated catch block e.printStackTrace(); } } return myDataset; }
From source file:Helper.CustomFilter.java
public Instances resampling(Instances structure) { Resample filter = new Resample(); Instances filteredIns = null;//from www . ja v a 2 s.co m filter.setBiasToUniformClass(1.0); try { filter.setInputFormat(structure); filter.setNoReplacement(false); filter.setSampleSizePercent(100); filteredIns = Filter.useFilter(structure, filter); } catch (Exception e) { e.printStackTrace(); } return filteredIns; }
From source file:id3j48.WekaAccess.java
public static Instances resampleData(Instances data) throws Exception { Resample resample = new Resample(); String filterOptions = "-B 0.0 -S 1 -Z 100.0"; resample.setOptions(Utils.splitOptions(filterOptions)); resample.setRandomSeed(1);/*from w w w .ja v a 2 s. co m*/ resample.setInputFormat(data); Instances newDataSet = Filter.useFilter(data, resample); return newDataSet; }
From source file:meansagnes.MeansAgnes.java
public void resample(double b, double z, int seed) { try {//w w w . j ava 2 s .c om System.out.println(data.toString() + "\n"); Resample resampleFilter = new Resample(); resampleFilter.setInputFormat(data); resampleFilter.setNoReplacement(false); resampleFilter.setBiasToUniformClass(b); // Uniform distribution of class resampleFilter.setSampleSizePercent(z); resampleFilter.setRandomSeed(seed); data = Filter.useFilter(data, resampleFilter); /*Random R = new Random(); data.resample(R);*/ System.out.println("HASIL RESAMPLE\n\n"); System.out.println(data.toString() + "\n"); } catch (Exception ex) { Logger.getLogger(MeansAgnes.class.getName()).log(Level.SEVERE, null, ex); } }
From source file:myclassifier.wekaCode.java
public static Instances resampleData(Instances data) throws Exception { Resample resample = new Resample(); resample.setInputFormat(data); Instances filterData = Filter.useFilter(data, resample); return filterData; }
From source file:org.openml.webapplication.generatefolds.GenerateFolds.java
License:Open Source License
private Instances sample_splits_bootstrap(String name) throws Exception { Instances splits = new Instances(name, am.getArffHeader(), splits_size); for (int r = 0; r < evaluationMethod.getRepeats(); ++r) { Resample resample = new Resample(); String[] resampleOptions = { "-B", "0.0", "-Z", "100.0", "-S", r + "" }; resample.setOptions(resampleOptions); resample.setInputFormat(dataset); Instances trainingsset = Filter.useFilter(dataset, resample); // create training set, consisting of instances from for (int i = 0; i < trainingsset.numInstances(); ++i) { int rowid = (int) trainingsset.instance(i).value(0); splits.add(am.createInstance(true, rowid, r, 0)); }//from w w w.ja va 2s. c om for (int i = 0; i < dataset.numInstances(); ++i) { int rowid = (int) dataset.instance(i).value(0); splits.add(am.createInstance(false, rowid, r, 0)); } } return splits; }