List of usage examples for weka.clusterers SimpleKMeans setSeed
@Override public void setSeed(int value)
From source file:br.com.ufu.lsi.rebfnetwork.RBFNetwork.java
License:Open Source License
/** * Builds the classifier/* ww w. java2 s .c om*/ * * @param instances the training data * @throws Exception if the classifier could not be built successfully */ public void buildClassifier(Instances instances) throws Exception { // can classifier handle the data? getCapabilities().testWithFail(instances); // remove instances with missing class instances = new Instances(instances); instances.deleteWithMissingClass(); // only class? -> build ZeroR model if (instances.numAttributes() == 1) { System.err.println( "Cannot build model (only class attribute present in data!), " + "using ZeroR model instead!"); m_ZeroR = new weka.classifiers.rules.ZeroR(); m_ZeroR.buildClassifier(instances); return; } else { m_ZeroR = null; } m_standardize = new Standardize(); m_standardize.setInputFormat(instances); instances = Filter.useFilter(instances, m_standardize); SimpleKMeans sk = new SimpleKMeans(); sk.setNumClusters(m_numClusters); sk.setSeed(m_clusteringSeed); MakeDensityBasedClusterer dc = new MakeDensityBasedClusterer(); dc.setClusterer(sk); dc.setMinStdDev(m_minStdDev); m_basisFilter = new ClusterMembership(); m_basisFilter.setDensityBasedClusterer(dc); m_basisFilter.setInputFormat(instances); Instances transformed = Filter.useFilter(instances, m_basisFilter); if (instances.classAttribute().isNominal()) { m_linear = null; m_logistic = new Logistic(); m_logistic.setRidge(m_ridge); m_logistic.setMaxIts(m_maxIts); m_logistic.buildClassifier(transformed); } else { m_logistic = null; m_linear = new LinearRegression(); m_linear.setAttributeSelectionMethod( new SelectedTag(LinearRegression.SELECTION_NONE, LinearRegression.TAGS_SELECTION)); m_linear.setRidge(m_ridge); m_linear.buildClassifier(transformed); } }
From source file:br.ufrn.ia.core.clustering.EMIaProject.java
License:Open Source License
private void EM_Init(Instances inst) throws Exception { int i, j, k;/* w w w .j a v a 2 s . com*/ // run k means 10 times and choose best solution SimpleKMeans bestK = null; double bestSqE = Double.MAX_VALUE; for (i = 0; i < 10; i++) { SimpleKMeans sk = new SimpleKMeans(); sk.setSeed(m_rr.nextInt()); sk.setNumClusters(m_num_clusters); sk.setDisplayStdDevs(true); sk.buildClusterer(inst); if (sk.getSquaredError() < bestSqE) { bestSqE = sk.getSquaredError(); bestK = sk; } } // initialize with best k-means solution m_num_clusters = bestK.numberOfClusters(); m_weights = new double[inst.numInstances()][m_num_clusters]; m_model = new DiscreteEstimator[m_num_clusters][m_num_attribs]; m_modelNormal = new double[m_num_clusters][m_num_attribs][3]; m_priors = new double[m_num_clusters]; Instances centers = bestK.getClusterCentroids(); Instances stdD = bestK.getClusterStandardDevs(); double[][][] nominalCounts = bestK.getClusterNominalCounts(); double[] clusterSizes = bestK.getClusterSizes(); for (i = 0; i < m_num_clusters; i++) { Instance center = centers.instance(i); for (j = 0; j < m_num_attribs; j++) { if (inst.attribute(j).isNominal()) { m_model[i][j] = new DiscreteEstimator(m_theInstances.attribute(j).numValues(), true); for (k = 0; k < inst.attribute(j).numValues(); k++) { m_model[i][j].addValue(k, nominalCounts[i][j][k]); } } else { double minStdD = (m_minStdDevPerAtt != null) ? m_minStdDevPerAtt[j] : m_minStdDev; double mean = (center.isMissing(j)) ? inst.meanOrMode(j) : center.value(j); m_modelNormal[i][j][0] = mean; double stdv = (stdD.instance(i).isMissing(j)) ? ((m_maxValues[j] - m_minValues[j]) / (2 * m_num_clusters)) : stdD.instance(i).value(j); if (stdv < minStdD) { stdv = inst.attributeStats(j).numericStats.stdDev; if (Double.isInfinite(stdv)) { stdv = minStdD; } if (stdv < minStdD) { stdv = minStdD; } } if (stdv <= 0) { stdv = m_minStdDev; } m_modelNormal[i][j][1] = stdv; m_modelNormal[i][j][2] = 1.0; } } } for (j = 0; j < m_num_clusters; j++) { // m_priors[j] += 1.0; m_priors[j] = clusterSizes[j]; } Utils.normalize(m_priors); }
From source file:controller.MineroControler.java
public String clasificarSimpleKmeans(int numClusters) { BufferedReader breader = null; Instances datos = null;/*from w ww .j a va 2 s . c om*/ breader = new BufferedReader(fuente_arff); try { datos = new Instances(breader); } catch (IOException ex) { System.err.println("Problemas al intentar cargar los datos"); } SimpleKMeans skmeans = new SimpleKMeans(); try { skmeans.setSeed(10); skmeans.setPreserveInstancesOrder(true); skmeans.setNumClusters(numClusters); skmeans.buildClusterer(datos); } catch (Exception ex) { System.err.println("Problemas al ejecutar algorimo de clasificacion"); } return skmeans.toString(); }
From source file:entities.ArffFile.java
/** * Dada una lista de parametros, se ejecuta el filtro de microagregacion. * Todos estos parametros son entrada del usuario. * @param df Puede ser Euclidian o Manhattan distance, se especifica en la entrada. * @param numCluster/*from ww w.j a v a 2s . c o m*/ * @param seed * @param maxIterations * @param replaceMissingValues * @param preserveInstancesOrder * @param attributes lista de los atributos que se desean generalizar con cluster */ public void microAgregacion(DistanceFunction df, int numCluster, int seed, int maxIterations, boolean replaceMissingValues, boolean preserveInstancesOrder, List<Integer> attributes) throws Exception { //instancesFilter = new Instances(instances); SimpleKMeans kMeans; kMeans = new SimpleKMeans(); Instances uniqueAttributes; uniqueAttributes = new Instances(instancesFilter); List<String> names = new ArrayList<>(); int i = 0; for (Integer attribute : attributes) { String name = new String(instancesFilter.attribute(attribute).name()); if (instancesFilter.attribute(attribute).isDate() || instancesFilter.attribute(attribute).isString()) throw new Exception("No se puede hacer cluster con atributos de tipo DATE o STRING"); names.add(name); } while (uniqueAttributes.numAttributes() != attributes.size()) { if (!names.contains(uniqueAttributes.attribute(i).name())) uniqueAttributes.deleteAttributeAt(i); else i++; } try { kMeans.setNumClusters(numCluster); kMeans.setMaxIterations(maxIterations); kMeans.setSeed(seed); kMeans.setDisplayStdDevs(false); kMeans.setDistanceFunction(df); kMeans.setDontReplaceMissingValues(replaceMissingValues); kMeans.setPreserveInstancesOrder(preserveInstancesOrder); kMeans.buildClusterer(uniqueAttributes); //System.out.println(kMeans); for (int j = 0; j < uniqueAttributes.numInstances(); j++) { int cluster = kMeans.clusterInstance(uniqueAttributes.instance(j)); for (int k = 0; k < uniqueAttributes.numAttributes(); k++) { if (uniqueAttributes.attribute(k).isNumeric()) uniqueAttributes.instance(j).setValue(k, Double.parseDouble(kMeans.getClusterCentroids().instance(cluster).toString(k))); else uniqueAttributes.instance(j).setValue(k, kMeans.getClusterCentroids().instance(cluster).toString(k)); } } replaceValues(uniqueAttributes, attributes); } catch (Exception ex) { Logger.getLogger(ArffFile.class.getName()).log(Level.SEVERE, null, ex); } //saveToFile("4"); }
From source file:eu.cassandra.appliance.IsolatedApplianceExtractor.java
License:Apache License
/** * This is an auxiliary function that prepares the clustering data set. The * events must be translated to instances of the data set that can be used for * clustering./*from w w w . j av a 2s . com*/ * * @param isolated * The list of the events containing an isolated appliance. * @return The instances of the data * @throws Exception */ private Instances createInstances(ArrayList<Event> isolated) throws Exception { // Initializing auxiliary variables namely the attributes of the data set Attribute id = new Attribute("id"); Attribute pDiffRise = new Attribute("pDiffRise"); Attribute qDiffRise = new Attribute("qDiffRise"); Attribute pDiffReduce = new Attribute("pDiffReduce"); Attribute qDiffReduce = new Attribute("qDiffReduce"); ArrayList<Attribute> attr = new ArrayList<Attribute>(); attr.add(id); attr.add(pDiffRise); attr.add(qDiffRise); attr.add(pDiffReduce); attr.add(qDiffReduce); Instances instances = new Instances("Isolated", attr, 0); // Each event is translated to an instance with the above attributes for (Event event : isolated) { Instance inst = new DenseInstance(5); inst.setValue(id, event.getId()); inst.setValue(pDiffRise, event.getRisingPoints().get(0).getPDiff()); inst.setValue(qDiffRise, event.getRisingPoints().get(0).getQDiff()); inst.setValue(pDiffReduce, event.getReductionPoints().get(0).getPDiff()); inst.setValue(qDiffReduce, event.getReductionPoints().get(0).getQDiff()); instances.add(inst); } int n = Constants.MAX_CLUSTERS_NUMBER; Instances newInst = null; System.out.println("Instances: " + instances.toSummaryString()); System.out.println("Max Clusters: " + n); // Create the addcluster filter of Weka and the set up the hierarchical // clusterer. AddCluster addcluster = new AddCluster(); if (instances.size() > Constants.KMEANS_LIMIT_NUMBER || instances.size() == 0) { HierarchicalClusterer clusterer = new HierarchicalClusterer(); String[] opt = { "-N", "" + n + "", "-P", "-D", "-L", "AVERAGE" }; clusterer.setDistanceFunction(new EuclideanDistance()); clusterer.setNumClusters(n); clusterer.setOptions(opt); clusterer.setPrintNewick(true); clusterer.setDebug(true); // clusterer.getOptions(); addcluster.setClusterer(clusterer); addcluster.setInputFormat(instances); addcluster.setIgnoredAttributeIndices("1"); // Cluster data set newInst = Filter.useFilter(instances, addcluster); } else { SimpleKMeans kmeans = new SimpleKMeans(); kmeans.setSeed(10); // This is the important parameter to set kmeans.setPreserveInstancesOrder(true); kmeans.setNumClusters(n); kmeans.buildClusterer(instances); addcluster.setClusterer(kmeans); addcluster.setInputFormat(instances); addcluster.setIgnoredAttributeIndices("1"); // Cluster data set newInst = Filter.useFilter(instances, addcluster); } return newInst; }
From source file:eu.cassandra.appliance.IsolatedEventsExtractor.java
License:Apache License
/** * This is an auxiliary function that prepares the clustering data set. The * events must be translated to instances of the data set that can be used for * clustering./*from w ww .j a v a2 s. c o m*/ * * @param isolated * The list of the events containing an isolated appliance. * @return The instances of the data * @throws Exception */ private Instances createInstances(ArrayList<Event> isolated) throws Exception { // Initializing auxiliary variables namely the attributes of the data set Attribute id = new Attribute("id"); Attribute pDiffRise = new Attribute("pDiffRise"); Attribute qDiffRise = new Attribute("qDiffRise"); Attribute pDiffReduce = new Attribute("pDiffReduce"); Attribute qDiffReduce = new Attribute("qDiffReduce"); Attribute duration = new Attribute("duration"); ArrayList<Attribute> attr = new ArrayList<Attribute>(); attr.add(id); attr.add(pDiffRise); attr.add(qDiffRise); attr.add(pDiffReduce); attr.add(qDiffReduce); attr.add(duration); Instances instances = new Instances("Isolated", attr, 0); // Each event is translated to an instance with the above attributes for (Event event : isolated) { Instance inst = new DenseInstance(6); inst.setValue(id, event.getId()); inst.setValue(pDiffRise, event.getRisingPoints().get(0).getPDiff()); inst.setValue(qDiffRise, event.getRisingPoints().get(0).getQDiff()); inst.setValue(pDiffReduce, event.getReductionPoints().get(0).getPDiff()); inst.setValue(qDiffReduce, event.getReductionPoints().get(0).getQDiff()); inst.setValue(duration, event.getEndMinute() - event.getStartMinute()); instances.add(inst); } int n = Constants.MAX_CLUSTERS_NUMBER; Instances newInst = null; log.info("Instances: " + instances.toSummaryString()); log.info("Max Clusters: " + n); // Create the addcluster filter of Weka and the set up the hierarchical // clusterer. AddCluster addcluster = new AddCluster(); if (instances.size() > Constants.KMEANS_LIMIT_NUMBER || instances.size() == 0) { HierarchicalClusterer clusterer = new HierarchicalClusterer(); String[] opt = { "-N", "" + n + "", "-P", "-D", "-L", "AVERAGE" }; clusterer.setDistanceFunction(new EuclideanDistance()); clusterer.setNumClusters(n); clusterer.setOptions(opt); clusterer.setPrintNewick(true); clusterer.setDebug(true); // clusterer.getOptions(); addcluster.setClusterer(clusterer); addcluster.setInputFormat(instances); addcluster.setIgnoredAttributeIndices("1"); // Cluster data set newInst = Filter.useFilter(instances, addcluster); } else { SimpleKMeans kmeans = new SimpleKMeans(); kmeans.setSeed(10); // This is the important parameter to set kmeans.setPreserveInstancesOrder(true); kmeans.setNumClusters(n); kmeans.buildClusterer(instances); addcluster.setClusterer(kmeans); addcluster.setInputFormat(instances); addcluster.setIgnoredAttributeIndices("1"); // Cluster data set newInst = Filter.useFilter(instances, addcluster); } return newInst; }
From source file:eu.cassandra.server.mongo.csn.MongoCluster.java
License:Apache License
/** * //from w ww .j a va 2s . c om * @param message * @param graph_id * @param clusterBasedOn * @param numberOfClusters * @param httpHeaders * @return */ private DBObject clusterKmeans(String message, String graph_id, String run_id, String clusterBasedOn, int numberOfClusters, String name, String clusterbasedon) { try { Instances instances = getInstances(clusterBasedOn, graph_id); if (instances.numInstances() < 2) { return new JSONtoReturn().createJSONError(message, new Exception("Number of CSN Nodes is < 2")); } SimpleKMeans kmeans = new SimpleKMeans(); kmeans.setSeed((int) Calendar.getInstance().getTimeInMillis()); // This is the important parameter to set kmeans.setPreserveInstancesOrder(true); kmeans.setNumClusters(numberOfClusters); kmeans.buildClusterer(instances); // This array returns the cluster number (starting with 0) for each instance // The array has as many elements as the number of instances int[] assignments = kmeans.getAssignments(); int i = 0; HashMap<Integer, Vector<String>> clusters = new HashMap<Integer, Vector<String>>(); for (int clusterNum : assignments) { if (clusters.containsKey(clusterNum)) { Vector<String> cluster = clusters.get(clusterNum); cluster.add(nodeIDs.get(i)); clusters.put(clusterNum, cluster); } else { Vector<String> cluster = new Vector<String>(); cluster.add(nodeIDs.get(i)); clusters.put(clusterNum, cluster); } i++; } nodeIDs.clear(); return saveClusters(graph_id, run_id, "kmeans", clusters, null, name, clusterbasedon); } catch (Exception e) { e.printStackTrace(); return new JSONtoReturn().createJSONError(message, e); } }
From source file:eu.cassandra.utils.Utils.java
License:Apache License
/** * This function is used in order to create clusters of points of interest * based on the active power difference they have. * /* w w w . ja va 2s . com*/ * @param pois * The list of points of interest that will be clustered. * @return The newly created clusters with the points that are comprising * them. * @throws Exception */ public static ArrayList<ArrayList<PointOfInterest>> clusterPoints(ArrayList<PointOfInterest> pois, int bias) throws Exception { // Initialize the auxiliary variables ArrayList<ArrayList<PointOfInterest>> result = new ArrayList<ArrayList<PointOfInterest>>(); // Estimating the number of clusters that will be created int numberOfClusters = (int) (Math.ceil((double) pois.size() / (double) Constants.MAX_POINTS_OF_INTEREST)) + bias; log.info("Clusters: " + pois.size() + " / " + Constants.MAX_POINTS_OF_INTEREST + " + " + bias + " = " + numberOfClusters); // Create a new empty list of points for each cluster for (int i = 0; i < numberOfClusters; i++) result.add(new ArrayList<PointOfInterest>()); // Initializing auxiliary variables namely the attributes of the data set Attribute id = new Attribute("id"); Attribute pDiffRise = new Attribute("pDiff"); ArrayList<Attribute> attr = new ArrayList<Attribute>(); attr.add(id); attr.add(pDiffRise); Instances instances = new Instances("Points of Interest", attr, 0); // Each event is translated to an instance with the above attributes for (int i = 0; i < pois.size(); i++) { Instance inst = new DenseInstance(2); inst.setValue(id, i); inst.setValue(pDiffRise, Math.abs(pois.get(i).getPDiff())); instances.add(inst); } // System.out.println(instances.toString()); Instances newInst = null; log.debug("Instances: " + instances.toSummaryString()); // Create the addcluster filter of Weka and the set up the hierarchical // clusterer. AddCluster addcluster = new AddCluster(); SimpleKMeans kmeans = new SimpleKMeans(); kmeans.setSeed(numberOfClusters); // This is the important parameter to set kmeans.setPreserveInstancesOrder(true); kmeans.setNumClusters(numberOfClusters); kmeans.buildClusterer(instances); addcluster.setClusterer(kmeans); addcluster.setInputFormat(instances); addcluster.setIgnoredAttributeIndices("1"); // Cluster data set newInst = Filter.useFilter(instances, addcluster); // System.out.println(newInst.toString()); // Parse through the dataset to see where each point is placed in the // clusters. for (int i = 0; i < newInst.size(); i++) { String cluster = newInst.get(i).stringValue(newInst.attribute(2)); cluster = cluster.replace("cluster", ""); log.debug("Point of Interest: " + i + " Cluster: " + cluster); result.get(Integer.parseInt(cluster) - 1).add(pois.get(i)); } // Sorting the each cluster points by their minutes. for (int i = result.size() - 1; i >= 0; i--) { if (result.get(i).size() == 0) result.remove(i); else Collections.sort(result.get(i), Constants.comp); } // Sorting the all clusters by their active power. Collections.sort(result, Constants.comp5); return result; }
From source file:gr.auth.ee.lcs.AbstractLearningClassifierSystem.java
License:Open Source License
/** * Initialize the rule population by clustering the train set and producing rules based upon the clusters. * The train set is initially divided in as many partitions as are the distinct label combinations. * @throws Exception //from www . j a v a2 s .c om * * @param file * the .arff file * */ public ClassifierSet initializePopulation(final String file) throws Exception { final double gamma = SettingsLoader.getNumericSetting("CLUSTER_GAMMA", .2); int numberOfLabels = (int) SettingsLoader.getNumericSetting("numberOfLabels", 1); final Instances set = InstancesUtility.openInstance(file); SimpleKMeans kmeans = new SimpleKMeans(); kmeans.setSeed(10); kmeans.setPreserveInstancesOrder(true); /* * Table partitions will hold instances only with attributes. * On the contrary, table partitionsWithCLasses will hold only the labels */ Instances[] partitions = InstancesUtility.partitionInstances(this, file); Instances[] partitionsWithCLasses = InstancesUtility.partitionInstances(this, file); /* * Instead of having multiple positions for the same label combination, use only one. * This is the one that will be used to "cover" the centroids. */ for (int i = 0; i < partitionsWithCLasses.length; i++) { Instance temp = partitionsWithCLasses[i].instance(0); partitionsWithCLasses[i].delete(); partitionsWithCLasses[i].add(temp); } /* * Delete the labels from the partitions. */ String attributesIndicesForDeletion = ""; for (int k = set.numAttributes() - numberOfLabels + 1; k <= set.numAttributes(); k++) { if (k != set.numAttributes()) attributesIndicesForDeletion += k + ","; else attributesIndicesForDeletion += k; } /* attributesIncicesForDeletion = 8,9,10,11,12,13,14 e.g. for 7 attributes and 7 labels. * It does not start from 7 because it assumes that the user inputs the number. See the api. */ for (int i = 0; i < partitions.length; i++) { Remove remove = new Remove(); remove.setAttributeIndices(attributesIndicesForDeletion); remove.setInvertSelection(false); remove.setInputFormat(partitions[i]); partitions[i] = Filter.useFilter(partitions[i], remove); //System.out.println(partitions[i]); } // partitions now contains only attributes /* * delete the attributes from partitionsWithCLasses */ String labelsIndicesForDeletion = ""; for (int k = 1; k <= set.numAttributes() - numberOfLabels; k++) { if (k != set.numAttributes() - numberOfLabels) labelsIndicesForDeletion += k + ","; else labelsIndicesForDeletion += k; } /* attributesIncicesForDeletion = 8,9,10,11,12,13,14 e.g. for 7 attributes and 7 labels. * It does not start from 7 because it assumes that the user inputs the number. See the api. */ for (int i = 0; i < partitionsWithCLasses.length; i++) { Remove remove = new Remove(); remove.setAttributeIndices(labelsIndicesForDeletion); remove.setInvertSelection(false); remove.setInputFormat(partitionsWithCLasses[i]); partitionsWithCLasses[i] = Filter.useFilter(partitionsWithCLasses[i], remove); //System.out.println(partitionsWithCLasses[i]); } // partitionsWithCLasses now contains only labels int populationSize = (int) SettingsLoader.getNumericSetting("populationSize", 1500); // the set used to store the rules from all the clusters ClassifierSet initialClassifiers = new ClassifierSet(new FixedSizeSetWorstFitnessDeletion(this, populationSize, new RouletteWheelSelector(AbstractUpdateStrategy.COMPARISON_MODE_DELETION, true))); for (int i = 0; i < partitions.length; i++) { try { kmeans.setNumClusters((int) Math.ceil(gamma * partitions[i].numInstances())); kmeans.buildClusterer(partitions[i]); int[] assignments = kmeans.getAssignments(); /* int k=0; for (int j = 0; j < assignments.length; j++) { System.out.printf("Instance %d => Cluster %d ", k, assignments[j]); k++; System.out.println(); } System.out.println();*/ Instances centroids = kmeans.getClusterCentroids(); int numOfCentroidAttributes = centroids.numAttributes(); /* * The centroids in this stage hold only attributes. To continue, we need to provide them the labels. * These are the ones we removed earlier. * But first, open up positions for attributes. * */ for (int j = 0; j < numberOfLabels; j++) { Attribute label = new Attribute("label" + j); centroids.insertAttributeAt(label, numOfCentroidAttributes + j); } for (int centroidInstances = 0; centroidInstances < centroids.numInstances(); centroidInstances++) { for (int labels = 0; labels < numberOfLabels; labels++) { centroids.instance(centroidInstances).setValue(numOfCentroidAttributes + labels, partitionsWithCLasses[i].instance(0).value(labels)); } } double[][] centroidsArray = InstancesUtility.convertIntancesToDouble(centroids); for (int j = 0; j < centroidsArray.length; j++) { //System.out.printf("Instance %d => Cluster %d ", k, assignments[j]); final Classifier coveringClassifier = this.getClassifierTransformBridge() .createRandomClusteringClassifier(centroidsArray[j]); coveringClassifier.setClassifierOrigin(Classifier.CLASSIFIER_ORIGIN_INIT); initialClassifiers.addClassifier(new Macroclassifier(coveringClassifier, 1), false); } } catch (Exception e) { e.printStackTrace(); } } System.out.println(initialClassifiers); return initialClassifiers; }
From source file:gr.auth.ee.lcs.AbstractLearningClassifierSystem.java
License:Open Source License
/** * Initialize the rule population by clustering the train set and producing rules based upon the clusters. * The train set is initially divided in as many partitions as are the distinct label combinations. * @throws Exception //from www .j a va2s. c o m * * @param trainSet * the type of Instances train set * */ public ClassifierSet initializePopulation(final Instances trainset) throws Exception { final double gamma = SettingsLoader.getNumericSetting("CLUSTER_GAMMA", .2); int numberOfLabels = (int) SettingsLoader.getNumericSetting("numberOfLabels", 1); final Instances set = trainset; SimpleKMeans kmeans = new SimpleKMeans(); kmeans.setSeed(10); kmeans.setPreserveInstancesOrder(true); /* * Table partitions will hold instances only with attributes. * On the contrary, table partitionsWithCLasses will hold only the labels */ Instances[] partitions = InstancesUtility.partitionInstances(this, trainset); Instances[] partitionsWithCLasses = InstancesUtility.partitionInstances(this, trainset); /* * Instead of having multiple positions for the same label combination, use only one. * This is the one that will be used to "cover" the centroids. */ for (int i = 0; i < partitionsWithCLasses.length; i++) { Instance temp = partitionsWithCLasses[i].instance(0); partitionsWithCLasses[i].delete(); partitionsWithCLasses[i].add(temp); } /* * Delete the labels from the partitions. */ String attributesIndicesForDeletion = ""; for (int k = set.numAttributes() - numberOfLabels + 1; k <= set.numAttributes(); k++) { if (k != set.numAttributes()) attributesIndicesForDeletion += k + ","; else attributesIndicesForDeletion += k; } /* attributesIncicesForDeletion = 8,9,10,11,12,13,14 e.g. for 7 attributes and 7 labels. * It does not start from 7 because it assumes that the user inputs the number. See the api. */ for (int i = 0; i < partitions.length; i++) { Remove remove = new Remove(); remove.setAttributeIndices(attributesIndicesForDeletion); remove.setInvertSelection(false); remove.setInputFormat(partitions[i]); partitions[i] = Filter.useFilter(partitions[i], remove); } // partitions now contains only attributes /* * delete the attributes from partitionsWithCLasses */ String labelsIndicesForDeletion = ""; for (int k = 1; k <= set.numAttributes() - numberOfLabels; k++) { if (k != set.numAttributes() - numberOfLabels) labelsIndicesForDeletion += k + ","; else labelsIndicesForDeletion += k; } /* attributesIncicesForDeletion = 8,9,10,11,12,13,14 e.g. for 7 attributes and 7 labels. * It does not start from 7 because it assumes that the user inputs the number. See the api. */ for (int i = 0; i < partitionsWithCLasses.length; i++) { Remove remove = new Remove(); remove.setAttributeIndices(labelsIndicesForDeletion); remove.setInvertSelection(false); remove.setInputFormat(partitionsWithCLasses[i]); partitionsWithCLasses[i] = Filter.useFilter(partitionsWithCLasses[i], remove); //System.out.println(partitionsWithCLasses[i]); } // partitionsWithCLasses now contains only labels int populationSize = (int) SettingsLoader.getNumericSetting("populationSize", 1500); // the set used to store the rules from all the clusters ClassifierSet initialClassifiers = new ClassifierSet(new FixedSizeSetWorstFitnessDeletion(this, populationSize, new RouletteWheelSelector(AbstractUpdateStrategy.COMPARISON_MODE_DELETION, true))); for (int i = 0; i < partitions.length; i++) { try { kmeans.setNumClusters((int) Math.ceil(gamma * partitions[i].numInstances())); kmeans.buildClusterer(partitions[i]); int[] assignments = kmeans.getAssignments(); /* int k=0; for (int j = 0; j < assignments.length; j++) { System.out.printf("Instance %d => Cluster %d ", k, assignments[j]); k++; System.out.println(); } System.out.println();*/ Instances centroids = kmeans.getClusterCentroids(); int numOfCentroidAttributes = centroids.numAttributes(); /* * The centroids in this stage hold only attributes. To continue, we need to provide them the labels. * These are the ones we removed earlier. * But first, open up positions for attributes. * */ for (int j = 0; j < numberOfLabels; j++) { Attribute label = new Attribute("label" + j); centroids.insertAttributeAt(label, numOfCentroidAttributes + j); } for (int centroidInstances = 0; centroidInstances < centroids.numInstances(); centroidInstances++) { for (int labels = 0; labels < numberOfLabels; labels++) { centroids.instance(centroidInstances).setValue(numOfCentroidAttributes + labels, partitionsWithCLasses[i].instance(0).value(labels)); } } //System.out.println(centroids); double[][] centroidsArray = InstancesUtility.convertIntancesToDouble(centroids); for (int j = 0; j < centroidsArray.length; j++) { //System.out.printf("Instance %d => Cluster %d ", k, assignments[j]); final Classifier coveringClassifier = this.getClassifierTransformBridge() .createRandomCoveringClassifier(centroidsArray[j]); coveringClassifier.setClassifierOrigin(Classifier.CLASSIFIER_ORIGIN_INIT); initialClassifiers.addClassifier(new Macroclassifier(coveringClassifier, 1), false); } } catch (Exception e) { e.printStackTrace(); } } //System.out.println(initialClassifiers); return initialClassifiers; }