List of usage examples for weka.clusterers SimpleKMeans setNumClusters
@Override public void setNumClusters(int n) throws Exception
From source file:org.montp2.m1decol.ter.clustering.KMeansClustering.java
License:Open Source License
public Clusterer computeClustering(String inPath, String outPath, Properties propertiesCluster) throws Exception { Instances inputInstances = WekaUtils.loadARFF(inPath); EuclideanDistance euclideanDistance = new EuclideanDistance(); euclideanDistance.setAttributeIndices("first-last"); euclideanDistance.setDontNormalize(false); euclideanDistance.setInvertSelection(false); SimpleKMeans kmeans = new SimpleKMeans(); kmeans.setPreserveInstancesOrder(/*from w w w. jav a 2 s. c om*/ Boolean.valueOf(propertiesCluster.getProperty(ClusterProperties.Kmeans.PERSERVE_INSTANCE))); kmeans.setDontReplaceMissingValues(Boolean .valueOf(propertiesCluster.getProperty(ClusterProperties.Kmeans.DONT_REPLACE_MISSING_VALUES))); kmeans.setDisplayStdDevs( Boolean.valueOf(propertiesCluster.getProperty(ClusterProperties.Kmeans.DISPLAY_STD_DEVS))); kmeans.setMaxIterations( Integer.valueOf(propertiesCluster.getProperty(ClusterProperties.Kmeans.MAX_ITERATIONS))); kmeans.setNumClusters( Integer.valueOf(propertiesCluster.getProperty(ClusterProperties.Kmeans.NUM_CLUSTERS))); kmeans.setSeed(10); //kmeans.setSeed( // Integer.valueOf(propertiesCluster.getProperty(ClusterProperties.Kmeans.SEED))); kmeans.setDistanceFunction(euclideanDistance); kmeans.buildClusterer(inputInstances); WekaUtils.saveModel(kmeans, outPath); /* * * Pour obtenir les pourcentages de les clusters * ClusterEvaluation eval = new ClusterEvaluation(); * eval.setClusterer(kmeans); * eval.evaluateClusterer(inputInstances); * System.out.println(eval.clusterResultsToString()); * * */ return kmeans; }
From source file:probcog.clustering.multidim.KMeansClusterer.java
License:Open Source License
public KMeansClusterer(SimpleKMeans clusterer, int dimensions, int k) throws Exception { super(clusterer, dimensions); clusterer.setNumClusters(k); }
From source file:qoala.arff.java
public void SimpleKmeans(int numberOfCLuster) throws Exception { Instances train = new Instances(dataSet); SimpleKMeans skm = new SimpleKMeans(); skm.setPreserveInstancesOrder(true); skm.setNumClusters(numberOfCLuster); skm.buildClusterer(train);//from w w w .j a va2s . c o m skm.setSeed(10); int[] ClusterSize = skm.getClusterSizes(); ClusterEvaluation eval = new ClusterEvaluation(); eval.setClusterer(skm); eval.evaluateClusterer(train); System.out.println("Cluster Evaluation:" + eval.clusterResultsToString()); int[] assignments = skm.getAssignments(); System.out.println("# - cluster - distribution"); for (int j = 0; j < skm.getNumClusters(); j++) { int i = 0; for (int clusterNum : assignments) { if (clusterNum == j) System.out.println("Instance " + i + " -> Cluster number: " + clusterNum); i++; } } }
From source file:soccer.core.ASimplePractice.java
public void evaluate() throws IOException, Exception { Instances data = loader.getInstances(); SimpleKMeans cluster = new SimpleKMeans(); cluster.setNumClusters(4); cluster.buildClusterer(data);//from w w w . ja v a2s .c o m ClusterEvaluation eval = new ClusterEvaluation(); eval.setClusterer(cluster); eval.evaluateClusterer(data); System.out.println(eval.clusterResultsToString()); }
From source file:soccer.core.models.PlayerModel.java
public static void main(String[] args) throws Exception { PlayerModel pm = new PlayerModel(); Instances data = pm.buildInstance(); SimpleKMeans cluster = new SimpleKMeans(); cluster.setNumClusters(4); cluster.buildClusterer(data);// ww w.jav a 2 s . co m ClusterEvaluation eval = new ClusterEvaluation(); eval.setClusterer(cluster); eval.evaluateClusterer(data); System.out.println(eval.clusterResultsToString()); }
From source file:swm.project.mappings.UserToUserCluster.java
private void clusterUserHistoryWithKmeans() throws FileNotFoundException, IOException, Exception { Reader reader;//from www. jav a 2 s . c o m userToUserClusterHistory = new HashMap<>(); userClustersToUsersHistory = new HashMap<>(); reader = new FileReader(MappingConstants.USER_MOVIE_CLUSTERS); Instances instanceValues = new Instances(reader); SimpleKMeans kmeans = new SimpleKMeans(); kmeans.setNumClusters(20); kmeans.setPreserveInstancesOrder(true); kmeans.setDistanceFunction(new EuclideanDistance()); kmeans.buildClusterer(instanceValues); int[] assignments = kmeans.getAssignments(); int userid = 0; for (int clusterNo : assignments) { int user = (int) instanceValues.get(userid).value(0); userToUserClusterHistory.put(user, clusterNo); ArrayList<Integer> users = new ArrayList<>(); if (userClustersToUsersHistory.containsKey(clusterNo)) { users = userClustersToUsersHistory.get(clusterNo); users.add(user); } else { users.add(user); userClustersToUsersHistory.put(clusterNo, users); } userid++; } }
From source file:tr.gov.ulakbim.jDenetX.experiments.wrappers.EvalActiveBoostingID.java
License:Open Source License
public Instances clusteredInstances(Instances data) { if (data == null) { throw new NullPointerException("Data is null at clusteredInstances method"); }// w ww . j av a 2 s.c o m Instances sampled_data = data; for (int i = 0; i < sampled_data.numInstances(); i++) { sampled_data.remove(i); } SimpleKMeans sKmeans = new SimpleKMeans(); data.setClassIndex(data.numAttributes() - 1); Remove filter = new Remove(); filter.setAttributeIndices("" + (data.classIndex() + 1)); List assignments = new ArrayList(); try { filter.setInputFormat(data); Instances dataClusterer = Filter.useFilter(data, filter); String[] options = new String[3]; options[0] = "-I"; // max. iterations options[1] = "500"; options[2] = "-O"; sKmeans.setNumClusters(data.numClasses()); sKmeans.setOptions(options); sKmeans.buildClusterer(dataClusterer); System.out.println("Kmeans\n:" + sKmeans); System.out.println(Arrays.toString(sKmeans.getAssignments())); assignments = Arrays.asList(sKmeans.getAssignments()); } catch (Exception e) { e.printStackTrace(); } System.out.println("Assignments\n: " + assignments); ClusterEvaluation eval = new ClusterEvaluation(); eval.setClusterer(sKmeans); try { eval.evaluateClusterer(data); } catch (Exception e) { e.printStackTrace(); } int classesToClustersMap[] = eval.getClassesToClusters(); for (int i = 0; i < classesToClustersMap.length; i++) { if (assignments.get(i).equals(((Integer) classesToClustersMap[(int) data.get(i).classValue()]))) { ((Instances) sampled_data).add(data.get(i)); } } return ((Instances) sampled_data); }
From source file:tubes2.Main.java
/** * @param args the command line arguments *//* w w w . jav a2 s .c om*/ public static void main(String[] args) throws IOException, Exception { // TODO code application logic here String filename = "weather"; //Masih belum mengerti tipe .csv yang dapat dibaca seperti apa //CsvToArff convert = new CsvToArff(filename+".csv"); //LOAD FILE BufferedReader datafile = readDataFile("data/" + filename + ".arff"); Instances data = new Instances(datafile); ArrayList<Integer> numericIdx = new ArrayList<Integer>(); for (int i = 0; i < data.numAttributes(); i++) { if (data.attribute(i).isNumeric()) { numericIdx.add(i); } } System.out.println(); System.out.println("\n----SEBELUM NORMALISASI-----"); System.out.println(data); normalizeData(data, numericIdx); System.out.println("\n----SETELAH NORMALISASI-----"); System.out.println(data); //END OF LOAD FILE SimpleKMeans simpleK = new SimpleKMeans(); simpleK.setNumClusters(4); Clusterer[] clusterers = { simpleK, new myKMeans(4), new myAgnes(4) }; boolean first = true; for (Clusterer clusterer : clusterers) { try { clusterer.buildClusterer(data); System.out.println("\n\n----HASIL CLUSTERING-----"); System.out.println(clusterer); } catch (Exception ex) { Logger.getLogger(Main.class.getName()).log(Level.SEVERE, null, ex); } } }
From source file:wekimini.InputGenerator.java
public void selectKmClusters(int numClusters) throws Exception { buildDataset();/* w ww . jav a 2 s .c om*/ SimpleKMeans km = new SimpleKMeans(); km.setNumClusters(numClusters); km.buildClusterer(dataset); clusters = km.getClusterCentroids(); addKmClustersToTraining(); }