List of usage examples for weka.filters.unsupervised.attribute Remove setAttributeIndices
public void setAttributeIndices(String rangeList)
From source file:ClusteringClass.java
public static void main(String[] args) throws Exception { String filename = "C:\\Users\\Daniele\\Desktop\\Humoradio2.csv"; try {/*from w w w . j a va 2 s . c o m*/ FileWriter fw = new FileWriter(filename); Class.forName("org.apache.derby.jdbc.ClientDriver").newInstance(); Connection conn = DriverManager.getConnection("jdbc:derby://localhost:1527/HumoRadioDB", "dani", "dani"); String query = "SELECT * FROM SONG_RATING2"; Statement stmt = conn.createStatement(); ResultSet rs = stmt.executeQuery(query); for (int i = 1; i < 23; i++) { if (i != 2) { ResultSetMetaData rsmd = rs.getMetaData(); String name = rsmd.getColumnName(i); fw.append(name); if (i != 22) { fw.append(','); } else { fw.append('\n'); } } } String query1 = "SELECT * FROM SONG_DATA"; Statement stmt1 = conn.createStatement(); ResultSet rs1 = stmt1.executeQuery(query1); String[] titles = new String[150]; for (int ii = 0; ii < 150; ii++) { rs1.next(); titles[ii] = rs1.getString("TITLE"); } while (rs.next()) { for (int i = 1; i < 23; i++) { if (i == 22) fw.append('\n'); else if (i != 2) { fw.append(','); } } } fw.flush(); fw.close(); conn.close(); System.out.println("CSV File is created successfully."); /* Clustering part */ DataSource source = new DataSource("C:\\Users\\Daniele\\Desktop\\Humoradio2.csv"); Instances train = source.getDataSet(); /* Applichiamo il filtro Remove fornito da Weka per non considerare un attributo nell'algoritmo di Clustering. */ Remove filter = new Remove(); filter.setAttributeIndices("1"); filter.setInputFormat(train); Instances train2 = Filter.useFilter(train, filter); System.out.println("Nominal attributes removed from computation."); /* Applichiamo il filtro Normalize fornito da Weka per normalizzare il nostro dataset. */ Normalize norm = new Normalize(); norm.setInputFormat(train2); Instances train3 = Filter.useFilter(train2, norm); System.out.println("Dataset normalized."); /* First Clustering Algorithm */ EuclideanDistance df = new EuclideanDistance(); SimpleKMeans clus1 = new SimpleKMeans(); int k = 10; clus1.setNumClusters(k); clus1.setDistanceFunction(df); clus1.setPreserveInstancesOrder(true); clus1.buildClusterer(train3); /* First Evaluation */ ClusterEvaluation eval1 = new ClusterEvaluation(); eval1.setClusterer(clus1); eval1.evaluateClusterer(train3); System.out.println(eval1.clusterResultsToString()); int[] assignments = clus1.getAssignments(); String[][] dati = new String[150][4]; for (int kk = 0; kk < 150; kk++) { dati[kk][0] = String.valueOf(kk); dati[kk][1] = train2.instance(kk).toString(); dati[kk][2] = String.valueOf(assignments[kk]); dati[kk][3] = titles[kk]; } for (int w = 0; w < 10; w++) { System.out.println(); for (int i = 0; i < 150; i++) { if (dati[i][2].equals(String.valueOf(w))) { for (int j = 0; j < 4; j++) { if (j != 3) { System.out.print(dati[i][j] + "-> \t"); } else { System.out.println(dati[i][j]); } } } } } /*first graph PlotData2D predData = ClustererPanel.setUpVisualizableInstances(train, eval1); //String name = (new SimpleDateFormat("HH:mm:ss - ")).format(new Date()); String name = ""; String cname = clus1.getClass().getName(); if (cname.startsWith("weka.clusterers.")) name += cname.substring("weka.clusterers.".length()); else name += cname; VisualizePanel vp = new VisualizePanel(); vp.setName(name + " (" + train.relationName() + ")"); predData.setPlotName(name + " (" + train.relationName() + ")"); vp.addPlot(predData); String plotName = vp.getName(); final javax.swing.JFrame jf = new javax.swing.JFrame("Weka Clusterer Visualize: " + plotName); jf.setSize(500,400); jf.getContentPane().setLayout(new BorderLayout()); jf.getContentPane().add(vp, BorderLayout.CENTER); jf.dispose(); jf.addWindowListener(new java.awt.event.WindowAdapter() { public void windowClosing(java.awt.event.WindowEvent e) { jf.dispose(); } }); jf.setVisible(true); end first graph */ /* Second Clustering Algorithm */ System.out.println(); DBSCAN clus3 = new DBSCAN(); clus3.setEpsilon(0.7); clus3.setMinPoints(2); clus3.buildClusterer(train3); /* Second Evaluation */ ClusterEvaluation eval3 = new ClusterEvaluation(); eval3.setClusterer(clus3); eval3.evaluateClusterer(train3); System.out.println(eval3.clusterResultsToString()); double[] assignments3 = eval3.getClusterAssignments(); String[][] dati3 = new String[150][4]; for (int kk = 0; kk < 150; kk++) { dati3[kk][0] = String.valueOf(kk); dati3[kk][1] = train2.instance(kk).toString(); dati3[kk][2] = String.valueOf(assignments3[kk]); dati3[kk][3] = titles[kk]; } for (int w = 0; w < eval3.getNumClusters(); w++) { System.out.println(); for (int i = 0; i < 150; i++) { if (Double.parseDouble(dati3[i][2]) == w) { for (int j = 0; j < 4; j++) { if (j != 3) { System.out.print(dati3[i][j] + "-> \t"); } else { System.out.println(dati3[i][j]); } } } } } System.out.println(); for (int i = 0; i < 150; i++) { if (Double.parseDouble(dati3[i][2]) == -1.0) { for (int j = 0; j < 4; j++) { if (j != 3) { System.out.print(dati3[i][j] + "-> \t"); } else { System.out.println(dati3[i][j]); } } } } } catch (Exception e) { e.printStackTrace(); } }
From source file:adams.flow.transformer.WekaInstancesMerge.java
License:Open Source License
/** * Excludes attributes from the data./*from w w w.ja v a 2 s. co m*/ * * @param inst the data to process * @return the processed data */ protected Instances excludeAttributes(Instances inst) { Instances result; StringBuilder atts; int i; Remove filter; // determine attribute indices atts = new StringBuilder(); for (i = 0; i < inst.numAttributes(); i++) { if (inst.attribute(i).name().matches(m_ExcludedAttributes)) { if (atts.length() > 0) atts.append(","); atts.append((i + 1)); } } // filter data try { filter = new Remove(); filter.setAttributeIndices(atts.toString()); filter.setInvertSelection(m_InvertMatchingSense); filter.setInputFormat(inst); result = weka.filters.Filter.useFilter(inst, filter); } catch (Exception e) { result = inst; handleException("Error filtering data:", e); } return result; }
From source file:adams.flow.transformer.WekaMultiLabelSplitter.java
License:Open Source License
/** * Returns the generated token./*from ww w .j a v a 2s.c o m*/ * * @return the generated token */ @Override public Token output() { Token result; int index; Remove remove; Reorder reorder; StringBuilder indices; int i; int newIndex; Instances processed; result = null; index = m_AttributesToProcess.remove(0); remove = new Remove(); indices = new StringBuilder(); for (i = 0; i < m_ClassAttributes.size(); i++) { if (m_ClassAttributes.get(i) == index) continue; if (indices.length() > 0) indices.append(","); indices.append("" + (m_ClassAttributes.get(i) + 1)); } remove.setAttributeIndices(indices.toString()); try { remove.setInputFormat(m_Dataset); processed = weka.filters.Filter.useFilter(m_Dataset, remove); if (m_UpdateRelationName) processed.setRelationName(m_Dataset.attribute(index).name()); result = new Token(processed); } catch (Exception e) { processed = null; handleException( "Failed to process dataset with following filter setup:\n" + OptionUtils.getCommandLine(remove), e); } if (m_MakeClassLast && (processed != null)) { newIndex = processed.attribute(m_Dataset.attribute(index).name()).index(); indices = new StringBuilder(); for (i = 0; i < processed.numAttributes(); i++) { if (i == newIndex) continue; if (indices.length() > 0) indices.append(","); indices.append("" + (i + 1)); } if (indices.length() > 0) indices.append(","); indices.append("" + (newIndex + 1)); reorder = new Reorder(); try { reorder.setAttributeIndices(indices.toString()); reorder.setInputFormat(processed); processed = weka.filters.Filter.useFilter(processed, reorder); if (m_UpdateRelationName) processed.setRelationName(m_Dataset.attribute(index).name()); result = new Token(processed); } catch (Exception e) { handleException("Failed to process dataset with following filter setup:\n" + OptionUtils.getCommandLine(reorder), e); } } return result; }
From source file:adams.opt.genetic.DarkLord.java
License:Open Source License
/** * Generates a Properties file that stores information on the setup of * the genetic algorithm. E.g., it backs up the original relation name. * The generated properties file will be used as new relation name for * the data.// ww w . j a v a 2 s . com * * @param data the data to create the setup for * @param job the associated job * @see #PROPS_RELATION * @return the generated setup */ @Override protected Properties storeSetup(Instances data, GeneticAlgorithmJob job) { Properties result; DarkLordJob jobDL; Remove remove; result = super.storeSetup(data, job); jobDL = (DarkLordJob) job; // mask string result.setProperty(PROPS_MASK, jobDL.getMaskAsString()); // remove filter setup remove = new Remove(); remove.setAttributeIndices(jobDL.getRemoveAsString()); remove.setInvertSelection(true); result.setProperty(PROPS_FILTER, OptionUtils.getCommandLine(remove)); return result; }
From source file:adams.opt.optimise.genetic.fitnessfunctions.AttributeSelection.java
License:Open Source License
/** * Callback for best measure so far//from ww w. j ava 2s .c om */ @Override public void newBest(double val, OptData opd) { int cnt = 0; int[] weights = getWeights(opd); Instances newInstances = new Instances(getInstances()); for (int i = 0; i < getInstances().numInstances(); i++) { Instance in = newInstances.instance(i); cnt = 0; for (int a = 0; a < getInstances().numAttributes(); a++) { if (a == getInstances().classIndex()) continue; if (weights[cnt++] == 0) { in.setValue(a, 0); } else { in.setValue(a, in.value(a)); } } } try { File file = new File(getOutputDirectory().getAbsolutePath() + File.separator + Double.toString(getMeasure().adjust(val)) + ".arff"); file.createNewFile(); Writer writer = new BufferedWriter(new FileWriter(file)); Instances header = new Instances(newInstances, 0); // remove filter setup Remove remove = new Remove(); remove.setAttributeIndices(getRemoveAsString(weights)); remove.setInvertSelection(true); header.setRelationName(OptionUtils.getCommandLine(remove)); writer.write(header.toString()); writer.write("\n"); for (int i = 0; i < newInstances.numInstances(); i++) { writer.write(newInstances.instance(i).toString()); writer.write("\n"); } writer.flush(); writer.close(); } catch (Exception e) { e.printStackTrace(); } }
From source file:adams.opt.optimise.GeneticAlgorithm.java
License:Open Source License
public static void main(String[] args) { Environment.setEnvironmentClass(Environment.class); GeneticAlgorithm ga = new GeneticAlgorithm(); ga.setBits(1);//from w w w . j a v a 2 s . com ga.setNumChrom(8); ga.setIterations(10000); ga.setFavorZeroes(true); AttributeSelection as = new AttributeSelection(); //as.setDataset(new PlaceholderFile("/home/dale/blgg/conversion/merged/m_5_.75.arff")); ArrayConsumer.setOptions(as, args); PLSClassifier pls = new PLSClassifier(); PLSFilter pf = (PLSFilter) pls.getFilter(); pf.setNumComponents(11); LinearRegressionJ reg = new LinearRegressionJ(); reg.setEliminateColinearAttributes(false); reg.setAttributeSelectionMethod( new SelectedTag(LinearRegressionJ.SELECTION_NONE, LinearRegressionJ.TAGS_SELECTION)); GPD gp = new GPD(); gp.setNoise(.01); //RBFKernel rbf = new RBFKernel(); //rbf.setChecksTurnedOff(true); //rbf.setGamma(.01); //gp.setKernel(rbf); Remove remove = new Remove(); remove.setAttributeIndices("1"); FilteredClassifier fc = new FilteredClassifier(); MultiFilter mf = new MultiFilter(); Filter[] filters = new Filter[2]; filters[0] = remove; filters[1] = pf; mf.setFilters(filters); fc.setClassifier(gp); fc.setFilter(pf); as.setClassifier(gp); as.setClassIndex("last"); //as.setDataset(new PlaceholderFile("/home/dale/OMD_clean.arff")); //as.setOutputDirectory(new PlaceholderFile("/research/dale")); ga.setLoggingLevel(LoggingLevel.INFO); as.setLoggingLevel(LoggingLevel.INFO); ga.optimise(as.getDataDef(), as); }
From source file:asap.CrossValidation.java
/** * * @param dataInput/*from w w w.ja v a 2 s . c o m*/ * @param classIndex * @param removeIndices * @param cls * @param seed * @param folds * @param modelOutputFile * @return * @throws Exception */ public static String performCrossValidation(String dataInput, String classIndex, String removeIndices, AbstractClassifier cls, int seed, int folds, String modelOutputFile) throws Exception { PerformanceCounters.startTimer("cross-validation ST"); PerformanceCounters.startTimer("cross-validation init ST"); // loads data and set class index Instances data = DataSource.read(dataInput); String clsIndex = classIndex; switch (clsIndex) { case "first": data.setClassIndex(0); break; case "last": data.setClassIndex(data.numAttributes() - 1); break; default: try { data.setClassIndex(Integer.parseInt(clsIndex) - 1); } catch (NumberFormatException e) { data.setClassIndex(data.attribute(clsIndex).index()); } break; } Remove removeFilter = new Remove(); removeFilter.setAttributeIndices(removeIndices); removeFilter.setInputFormat(data); data = Filter.useFilter(data, removeFilter); // randomize data Random rand = new Random(seed); Instances randData = new Instances(data); randData.randomize(rand); if (randData.classAttribute().isNominal()) { randData.stratify(folds); } // perform cross-validation and add predictions Evaluation eval = new Evaluation(randData); Instances trainSets[] = new Instances[folds]; Instances testSets[] = new Instances[folds]; Classifier foldCls[] = new Classifier[folds]; for (int n = 0; n < folds; n++) { trainSets[n] = randData.trainCV(folds, n); testSets[n] = randData.testCV(folds, n); foldCls[n] = AbstractClassifier.makeCopy(cls); } PerformanceCounters.stopTimer("cross-validation init ST"); PerformanceCounters.startTimer("cross-validation folds+train ST"); //paralelize!!:-------------------------------------------------------------- for (int n = 0; n < folds; n++) { Instances train = trainSets[n]; Instances test = testSets[n]; // the above code is used by the StratifiedRemoveFolds filter, the // code below by the Explorer/Experimenter: // Instances train = randData.trainCV(folds, n, rand); // build and evaluate classifier Classifier clsCopy = foldCls[n]; clsCopy.buildClassifier(train); eval.evaluateModel(clsCopy, test); } cls.buildClassifier(data); //until here!----------------------------------------------------------------- PerformanceCounters.stopTimer("cross-validation folds+train ST"); PerformanceCounters.startTimer("cross-validation post ST"); // output evaluation String out = "\n" + "=== Setup ===\n" + "Classifier: " + cls.getClass().getName() + " " + Utils.joinOptions(cls.getOptions()) + "\n" + "Dataset: " + data.relationName() + "\n" + "Folds: " + folds + "\n" + "Seed: " + seed + "\n" + "\n" + eval.toSummaryString("=== " + folds + "-fold Cross-validation ===", false) + "\n"; if (!modelOutputFile.isEmpty()) { SerializationHelper.write(modelOutputFile, cls); } PerformanceCounters.stopTimer("cross-validation post ST"); PerformanceCounters.stopTimer("cross-validation ST"); return out; }
From source file:asap.CrossValidation.java
/** * * @param dataInput//from w w w.j a v a 2 s. c o m * @param classIndex * @param removeIndices * @param cls * @param seed * @param folds * @param modelOutputFile * @return * @throws Exception */ public static String performCrossValidationMT(String dataInput, String classIndex, String removeIndices, AbstractClassifier cls, int seed, int folds, String modelOutputFile) throws Exception { PerformanceCounters.startTimer("cross-validation MT"); PerformanceCounters.startTimer("cross-validation init MT"); // loads data and set class index Instances data = DataSource.read(dataInput); String clsIndex = classIndex; switch (clsIndex) { case "first": data.setClassIndex(0); break; case "last": data.setClassIndex(data.numAttributes() - 1); break; default: try { data.setClassIndex(Integer.parseInt(clsIndex) - 1); } catch (NumberFormatException e) { data.setClassIndex(data.attribute(clsIndex).index()); } break; } Remove removeFilter = new Remove(); removeFilter.setAttributeIndices(removeIndices); removeFilter.setInputFormat(data); data = Filter.useFilter(data, removeFilter); // randomize data Random rand = new Random(seed); Instances randData = new Instances(data); randData.randomize(rand); if (randData.classAttribute().isNominal()) { randData.stratify(folds); } // perform cross-validation and add predictions Evaluation eval = new Evaluation(randData); List<Thread> foldThreads = (List<Thread>) Collections.synchronizedList(new LinkedList<Thread>()); List<FoldSet> foldSets = (List<FoldSet>) Collections.synchronizedList(new LinkedList<FoldSet>()); for (int n = 0; n < folds; n++) { foldSets.add(new FoldSet(randData.trainCV(folds, n), randData.testCV(folds, n), AbstractClassifier.makeCopy(cls))); if (n < Config.getNumThreads() - 1) { Thread foldThread = new Thread(new CrossValidationFoldThread(n, foldSets, eval)); foldThreads.add(foldThread); } } PerformanceCounters.stopTimer("cross-validation init MT"); PerformanceCounters.startTimer("cross-validation folds+train MT"); //paralelize!!:-------------------------------------------------------------- if (Config.getNumThreads() > 1) { for (Thread foldThread : foldThreads) { foldThread.start(); } } else { //use the current thread to run the cross-validation instead of using the Thread instance created here: new CrossValidationFoldThread(0, foldSets, eval).run(); } cls.buildClassifier(data); for (Thread foldThread : foldThreads) { foldThread.join(); } //until here!----------------------------------------------------------------- PerformanceCounters.stopTimer("cross-validation folds+train MT"); PerformanceCounters.startTimer("cross-validation post MT"); // evaluation for output: String out = "\n" + "=== Setup ===\n" + "Classifier: " + cls.getClass().getName() + " " + Utils.joinOptions(cls.getOptions()) + "\n" + "Dataset: " + data.relationName() + "\n" + "Folds: " + folds + "\n" + "Seed: " + seed + "\n" + "\n" + eval.toSummaryString("=== " + folds + "-fold Cross-validation ===", false) + "\n"; if (!modelOutputFile.isEmpty()) { SerializationHelper.write(modelOutputFile, cls); } PerformanceCounters.stopTimer("cross-validation post MT"); PerformanceCounters.stopTimer("cross-validation MT"); return out; }
From source file:br.com.ufu.lsi.rebfnetwork.RBFModel.java
License:Open Source License
/** * Method used to pre-process the data, perform clustering, and * set the initial parameter vector./*from w w w. j a v a 2 s. c o m*/ */ protected Instances initializeClassifier(Instances data) throws Exception { // can classifier handle the data? getCapabilities().testWithFail(data); data = new Instances(data); data.deleteWithMissingClass(); // Make sure data is shuffled Random random = new Random(m_Seed); if (data.numInstances() > 2) { random = data.getRandomNumberGenerator(m_Seed); } data.randomize(random); double y0 = data.instance(0).classValue(); // This stuff is not relevant in classification case int index = 1; while (index < data.numInstances() && data.instance(index).classValue() == y0) { index++; } if (index == data.numInstances()) { // degenerate case, all class values are equal // we don't want to deal with this, too much hassle throw new Exception("All class values are the same. At least two class values should be different"); } double y1 = data.instance(index).classValue(); // Replace missing values m_ReplaceMissingValues = new ReplaceMissingValues(); m_ReplaceMissingValues.setInputFormat(data); data = Filter.useFilter(data, m_ReplaceMissingValues); // Remove useless attributes m_AttFilter = new RemoveUseless(); m_AttFilter.setInputFormat(data); data = Filter.useFilter(data, m_AttFilter); // only class? -> build ZeroR model if (data.numAttributes() == 1) { System.err.println( "Cannot build model (only class attribute present in data after removing useless attributes!), " + "using ZeroR model instead!"); m_ZeroR = new weka.classifiers.rules.ZeroR(); m_ZeroR.buildClassifier(data); return data; } else { m_ZeroR = null; } // Transform attributes m_NominalToBinary = new NominalToBinary(); m_NominalToBinary.setInputFormat(data); data = Filter.useFilter(data, m_NominalToBinary); m_Filter = new Normalize(); ((Normalize) m_Filter).setIgnoreClass(true); m_Filter.setInputFormat(data); data = Filter.useFilter(data, m_Filter); double z0 = data.instance(0).classValue(); // This stuff is not relevant in classification case double z1 = data.instance(index).classValue(); m_x1 = (y0 - y1) / (z0 - z1); // no division by zero, since y0 != y1 guaranteed => z0 != z1 ??? m_x0 = (y0 - m_x1 * z0); // = y1 - m_x1 * z1 m_classIndex = data.classIndex(); m_numClasses = data.numClasses(); m_numAttributes = data.numAttributes(); // Run k-means SimpleKMeans skm = new SimpleKMeans(); skm.setMaxIterations(10000); skm.setNumClusters(m_numUnits); Remove rm = new Remove(); data.setClassIndex(-1); rm.setAttributeIndices((m_classIndex + 1) + ""); rm.setInputFormat(data); Instances dataRemoved = Filter.useFilter(data, rm); data.setClassIndex(m_classIndex); skm.buildClusterer(dataRemoved); Instances centers = skm.getClusterCentroids(); if (centers.numInstances() < m_numUnits) { m_numUnits = centers.numInstances(); } // Set up arrays OFFSET_WEIGHTS = 0; if (m_useAttributeWeights) { OFFSET_ATTRIBUTE_WEIGHTS = (m_numUnits + 1) * m_numClasses; OFFSET_CENTERS = OFFSET_ATTRIBUTE_WEIGHTS + m_numAttributes; } else { OFFSET_ATTRIBUTE_WEIGHTS = -1; OFFSET_CENTERS = (m_numUnits + 1) * m_numClasses; } OFFSET_SCALES = OFFSET_CENTERS + m_numUnits * m_numAttributes; switch (m_scaleOptimizationOption) { case USE_GLOBAL_SCALE: m_RBFParameters = new double[OFFSET_SCALES + 1]; break; case USE_SCALE_PER_UNIT_AND_ATTRIBUTE: m_RBFParameters = new double[OFFSET_SCALES + m_numUnits * m_numAttributes]; break; default: m_RBFParameters = new double[OFFSET_SCALES + m_numUnits]; break; } // Set initial radius based on distance to nearest other basis function double maxMinDist = -1; for (int i = 0; i < centers.numInstances(); i++) { double minDist = Double.MAX_VALUE; for (int j = i + 1; j < centers.numInstances(); j++) { double dist = 0; for (int k = 0; k < centers.numAttributes(); k++) { if (k != centers.classIndex()) { double diff = centers.instance(i).value(k) - centers.instance(j).value(k); dist += diff * diff; } } if (dist < minDist) { minDist = dist; } } if ((minDist != Double.MAX_VALUE) && (minDist > maxMinDist)) { maxMinDist = minDist; } } // Initialize parameters if (m_scaleOptimizationOption == USE_GLOBAL_SCALE) { m_RBFParameters[OFFSET_SCALES] = Math.sqrt(maxMinDist); } for (int i = 0; i < m_numUnits; i++) { if (m_scaleOptimizationOption == USE_SCALE_PER_UNIT) { m_RBFParameters[OFFSET_SCALES + i] = Math.sqrt(maxMinDist); } int k = 0; for (int j = 0; j < m_numAttributes; j++) { if (k == centers.classIndex()) { k++; } if (j != data.classIndex()) { if (m_scaleOptimizationOption == USE_SCALE_PER_UNIT_AND_ATTRIBUTE) { m_RBFParameters[OFFSET_SCALES + (i * m_numAttributes + j)] = Math.sqrt(maxMinDist); } m_RBFParameters[OFFSET_CENTERS + (i * m_numAttributes) + j] = centers.instance(i).value(k); k++; } } } if (m_useAttributeWeights) { for (int j = 0; j < m_numAttributes; j++) { if (j != data.classIndex()) { m_RBFParameters[OFFSET_ATTRIBUTE_WEIGHTS + j] = 1.0; } } } initializeOutputLayer(random); return data; }
From source file:br.fapesp.myutils.MyUtils.java
License:Open Source License
/** * Remove supervision from a data set// w ww .j a va 2s . c om * * @param dataset * an Instances data set * @param classIndex * if -1 use the last attribute * @return a new copy of the data set with supervision removed */ public static Instances removeSupervision(Instances dataset, int classIndex) { Instances unsupervised = new Instances(dataset); String index = classIndex == -1 ? "last" : String.valueOf(classIndex); // Use the Remove filter to delete supervision from the data set: Remove rm = new Remove(); rm.setAttributeIndices(index); try { rm.setInputFormat(unsupervised); unsupervised = Filter.useFilter(unsupervised, rm); return unsupervised; } catch (Exception e) { e.printStackTrace(); } return null; }