List of usage examples for weka.clusterers Clusterer clusterInstance
int clusterInstance(Instance instance) throws Exception;
From source file:core.ClusterEvaluationEX.java
License:Open Source License
/** * Print the cluster statistics for either the training * or the testing data./*from www . j a v a 2 s. c o m*/ * * @param clusterer the clusterer to use for generating statistics. * @param fileName the file to load * @return a string containing cluster statistics. * @throws Exception if statistics can't be generated. */ private static String printClusterStats(Clusterer clusterer, String fileName) throws Exception { StringBuffer text = new StringBuffer(); int i = 0; int cnum; double loglk = 0.0; int cc = clusterer.numberOfClusters(); double[] instanceStats = new double[cc]; int unclusteredInstances = 0; if (fileName.length() != 0) { DataSource source = new DataSource(fileName); Instances structure = source.getStructure(); Instance inst; while (source.hasMoreElements(structure)) { inst = source.nextElement(structure); try { cnum = clusterer.clusterInstance(inst); if (clusterer instanceof DensityBasedClusterer) { loglk += ((DensityBasedClusterer) clusterer).logDensityForInstance(inst); // temp = Utils.sum(dist); } instanceStats[cnum]++; } catch (Exception e) { unclusteredInstances++; } i++; } /* // count the actual number of used clusters int count = 0; for (i = 0; i < cc; i++) { if (instanceStats[i] > 0) { count++; } } if (count > 0) { double[] tempStats = new double [count]; count=0; for (i=0;i<cc;i++) { if (instanceStats[i] > 0) { tempStats[count++] = instanceStats[i]; } } instanceStats = tempStats; cc = instanceStats.length; } */ int clustFieldWidth = (int) ((Math.log(cc) / Math.log(10)) + 1); int numInstFieldWidth = (int) ((Math.log(i) / Math.log(10)) + 1); double sum = Utils.sum(instanceStats); loglk /= sum; text.append("Clustered Instances\n"); for (i = 0; i < cc; i++) { if (instanceStats[i] > 0) { text.append(Utils.doubleToString((double) i, clustFieldWidth, 0) + " " + Utils.doubleToString(instanceStats[i], numInstFieldWidth, 0) + " (" + Utils.doubleToString((instanceStats[i] / sum * 100.0), 3, 0) + "%)\n"); } } if (unclusteredInstances > 0) { text.append("\nUnclustered Instances : " + unclusteredInstances); } if (clusterer instanceof DensityBasedClusterer) { text.append("\n\nLog likelihood: " + Utils.doubleToString(loglk, 1, 5) + "\n"); } } return text.toString(); }
From source file:core.ClusterEvaluationEX.java
License:Open Source License
/** * Print the cluster assignments for either the training * or the testing data.//from w w w . ja va 2s . co m * * @param clusterer the clusterer to use for cluster assignments * @param trainFileName the train file * @param testFileName an optional test file * @param attributesToOutput the attributes to print * @return a string containing the instance indexes and cluster assigns. * @throws Exception if cluster assignments can't be printed */ private static String printClusterings(Clusterer clusterer, String trainFileName, String testFileName, Range attributesToOutput) throws Exception { StringBuffer text = new StringBuffer(); int i = 0; int cnum; DataSource source = null; Instance inst; Instances structure; if (testFileName.length() != 0) source = new DataSource(testFileName); else source = new DataSource(trainFileName); structure = source.getStructure(); while (source.hasMoreElements(structure)) { inst = source.nextElement(structure); try { cnum = clusterer.clusterInstance(inst); text.append(i + " " + cnum + " " + attributeValuesString(inst, attributesToOutput) + "\n"); } catch (Exception e) { /* throw new Exception('\n' + "Unable to cluster instance\n" + e.getMessage()); */ text.append(i + " Unclustered " + attributeValuesString(inst, attributesToOutput) + "\n"); } i++; } return text.toString(); }
From source file:guineu.modules.dataanalysis.clustering.em.EMClusterer.java
License:Open Source License
public List<Integer> getClusterGroups(Instances dataset) { List<Integer> clusters = new ArrayList<Integer>(); String[] options = new String[2]; Clusterer clusterer = new EM(); int numberOfIterations = parameters.getParameter(EMClustererParameters.numberOfIterations).getValue(); options[0] = "-I"; options[1] = String.valueOf(numberOfIterations); try {/* w ww . j a v a 2 s. c o m*/ ((EM) clusterer).setOptions(options); clusterer.buildClusterer(dataset); Enumeration e = dataset.enumerateInstances(); while (e.hasMoreElements()) { clusters.add(clusterer.clusterInstance((Instance) e.nextElement())); } this.numberOfGroups = clusterer.numberOfClusters(); } catch (Exception ex) { Logger.getLogger(EMClusterer.class.getName()).log(Level.SEVERE, null, ex); } return clusters; }
From source file:guineu.modules.dataanalysis.clustering.farthestfirst.FarthestFirstClusterer.java
License:Open Source License
public List<Integer> getClusterGroups(Instances dataset) { List<Integer> clusters = new ArrayList<Integer>(); String[] options = new String[2]; Clusterer clusterer = new FarthestFirst(); int numberOfGroups = parameters.getParameter(FarthestFirstClustererParameters.numberOfGroups).getValue(); options[0] = "-N"; options[1] = String.valueOf(numberOfGroups); try {/*w ww.ja v a2s . c o m*/ ((FarthestFirst) clusterer).setOptions(options); clusterer.buildClusterer(dataset); Enumeration e = dataset.enumerateInstances(); while (e.hasMoreElements()) { clusters.add(clusterer.clusterInstance((Instance) e.nextElement())); } this.numberOfGroups = clusterer.numberOfClusters(); } catch (Exception ex) { Logger.getLogger(FarthestFirstClusterer.class.getName()).log(Level.SEVERE, null, ex); } return clusters; }
From source file:guineu.modules.dataanalysis.clustering.simplekmeans.SimpleKMeansClusterer.java
License:Open Source License
public List<Integer> getClusterGroups(Instances dataset) { List<Integer> clusters = new ArrayList<Integer>(); String[] options = new String[2]; Clusterer clusterer = new SimpleKMeans(); int numberOfGroups = parameters.getParameter(SimpleKMeansClustererParameters.numberOfGroups).getValue(); options[0] = "-N"; options[1] = String.valueOf(numberOfGroups); try {/*from w w w. jav a 2s .c o m*/ ((SimpleKMeans) clusterer).setOptions(options); clusterer.buildClusterer(dataset); Enumeration e = dataset.enumerateInstances(); while (e.hasMoreElements()) { clusters.add(clusterer.clusterInstance((Instance) e.nextElement())); } this.numberOfGroups = clusterer.numberOfClusters(); } catch (Exception ex) { Logger.getLogger(SimpleKMeansClusterer.class.getName()).log(Level.SEVERE, null, ex); } return clusters; }
From source file:intensityclustering.IntensityClustering.java
/** * Draws the 2D Histogram Plot in the IntensityClustering. X-Axsis is * intensity value of chanel 2 image (where the stained nuclei are). Y-axis * are relative frequencies of present nuclei. * * @param tss The TMAspots whose nuclei are considered (both gold-standard * and estimated nuclei).//ww w .j ava 2 s . c o m * @param doAlsoClustering If true, the TMApoints are also clustered * according to the histogram. */ void drawNucleiIntensities2D(List<TMAspot> tss, boolean doAlsoClustering) { // draw the plot Plot2DPanel plot; if (((java.awt.BorderLayout) (jPanel9.getLayout())) .getLayoutComponent(java.awt.BorderLayout.CENTER) != null) { plot = (Plot2DPanel) ((java.awt.BorderLayout) (jPanel9.getLayout())) .getLayoutComponent(java.awt.BorderLayout.CENTER); plot.removeAllPlots(); plot.removeAllPlotables(); } else { plot = new Plot2DPanel(PlotPanel.SOUTH); plot.setAxisLabels("Intensity", "Frequency"); plot.plotCanvas.setBackground(jPanel9.getBackground()); plot.plotLegend.setBackground(jPanel9.getBackground()); plot.plotToolBar.setBackground(plot.plotCanvas.getBackground()); } if (((java.awt.BorderLayout) (jPanel9.getLayout())) .getLayoutComponent(java.awt.BorderLayout.CENTER) == null) { jPanel9.add(plot, java.awt.BorderLayout.CENTER); jPanel15.setBackground(plot.plotCanvas.getBackground()); jPanel15.setVisible(true); validate(); pack(); } if (tss.size() > 0) { try { this.setCursor(Cursor.getPredefinedCursor(Cursor.WAIT_CURSOR)); List<Integer> intensities = new ArrayList<>(); int intensity; int min = Integer.parseInt(jTextField1.getText()); int max = Integer.parseInt(jTextField16.getText()); for (TMAspot ts : tss) { //TODO: GET THE CHANNEL 2 Image //BufferedImage img = ts.getBufferedImage(TMAspot.SHOW_CHANNEL2_IMAGE, false); BufferedImage img = ts.getBufferedImage(false); // img can be null if color deconvolution has not been performed, yet. if (img != null) { List<TMApoint> tps = ts.getPoints(); for (TMALabel tp : tps) { intensity = TMAspot.getAverageColorAtPoint(img, tp.x, tp.y, ts.getParam_r(), false) .getRed(); if (intensity >= min && intensity <= max) { intensities.add(intensity); } } } } double[] intensities_array = new double[intensities.size()]; for (int i = 0; i < intensities.size(); i++) { intensities_array[i] = intensities.get(i); } int nbins = jSlider7.getValue(); if (intensities_array.length > 0) { plot.addHistogramPlot("TMA points", intensities_array, 0, 256, nbins); } //else { // JOptionPane.showMessageDialog(this, "No TMA points have been found.", "No TMA points found.", JOptionPane.WARNING_MESSAGE); //} //// Cluster Points according to histograms if (doAlsoClustering) { // Find Clusters int n = getParam_nClusters(); // Create ARFF Data FastVector atts; Instances data; int i; // 1. create arff data format atts = new FastVector(1); for (i = 0; i < 1; i++) { atts.addElement(new Attribute(Integer.toString(i))); } // 2. create Instances object data = new Instances("TMA points", atts, tmarker.getNumberNuclei(tss)); // 3. fill with data for (i = 0; i < intensities_array.length; i++) { // add the instance Instance inst = new Instance(1.0, new double[] { intensities_array[i] }); inst.setDataset(data); data.add(inst); } // 4. set data class index (last attribute is the class) //data.setClassIndex(data.numAttributes() - 1); // not for weka 3.5.X if (tmarker.DEBUG > 4) { java.util.logging.Logger.getLogger(getClass().getName()).log(java.util.logging.Level.INFO, data.toString()); } Clusterer clusterer = getClusterer(); String[] options = getClustererOptions(); if (tmarker.DEBUG > 3) { if (options.length > 0) { String info = "Clusterer should have options:\n"; for (String o : options) { info += o + " "; } info += "\n"; java.util.logging.Logger.getLogger(getClass().getName()) .log(java.util.logging.Level.INFO, info); } } clusterer.setOptions(options); // set the clusterer options clusterer.buildClusterer(data); // build the clusterer // order the clusters according to the brightness // The most bright cluster should be 0, then 1, then 2,... ArrayList<ArrayList<Double>> values = new ArrayList<>(); for (i = 0; i < n; i++) { values.add(new ArrayList<Double>()); } int z; double value; for (i = 0; i < data.numInstances(); i++) { z = clusterer.clusterInstance(data.instance(i)); value = data.instance(i).value(0); values.get(z).add(value); } double[] means = new double[n]; double[] stds = new double[n]; for (i = 0; i < n; i++) { means[i] = Misc.mean(values.get(i).toArray(new Double[values.get(i).size()])); stds[i] = Misc.std(values.get(i).toArray(new Double[values.get(i).size()])); } int[] ordering = Misc.orderArray(means, true); for (i = 0; i < n; i++) { int ind = Misc.IndexOf(ordering, i); plot.addPlotable(new Line(getParam_ColorOfClassK(i), new double[] { means[ind], plot.plotCanvas.base.roundXmin[1] }, new double[] { means[ind], plot.plotCanvas.base.roundXmax[1] }, 2 * stds[ind])); plot.addPlot(Plot2DPanel.LINE, "Staining " + i, getParam_ColorOfClassK(i), new double[][] { new double[] { means[ind], plot.plotCanvas.base.roundXmin[1] }, new double[] { means[ind], plot.plotCanvas.base.roundXmax[1] } }); } String clusterInfo = ""; for (String o : clusterer.getOptions()) { clusterInfo += o + " "; } clusterInfo += "\n\n"; clusterInfo += clusterer.toString().trim(); if (getParam_AutomaticClustererString().equalsIgnoreCase("Hierarchical")) { try { clusterInfo += ((HierarchicalClusterer) clusterer).graph(); HierarchyVisualizer a = new HierarchyVisualizer( ((HierarchicalClusterer) clusterer).graph()); a.setSize(800, 600); if (clusterVisualizer == null) { clusterVisualizer = new JFrame("Hierarchical Clusterer Dendrogram"); clusterVisualizer.setIconImage(getIconImage()); clusterVisualizer.setDefaultCloseOperation(JFrame.DISPOSE_ON_CLOSE); clusterVisualizer.setSize(800, 600); } Container contentPane = clusterVisualizer.getContentPane(); contentPane.removeAll(); contentPane.add(a); } catch (Exception e) { clusterVisualizer = null; } } jTextArea1.setText(clusterInfo); if (tmarker.DEBUG > 3) { String info = "Clusterer has options\n"; for (String o : clusterer.getOptions()) { info += o + " "; } info += "\n"; info += clusterer.toString() + "\n"; // info += (clusterer).globalInfo() + "\n"; info += "\n"; info += clusterInfo + "\n"; java.util.logging.Logger.getLogger(getClass().getName()).log(java.util.logging.Level.INFO, info); } // cluster all TMAspots and assign the corresponding class to them // Cluster the points List<List<Integer>> clustered_points = new ArrayList<>(); for (i = 0; i < n; i++) { clustered_points.add(new ArrayList<Integer>()); } int k; for (TMAspot ts : tss) { //TODO: GET THE CHANNEL 2 IMAGE //BufferedImage img = ts.getBufferedImage(TMAspot.SHOW_CHANNEL2_IMAGE, false); BufferedImage img = ts.getBufferedImage(false); List<TMApoint> tps = ts.getPoints(); for (TMApoint tp : tps) { intensity = TMAspot.getAverageColorAtPoint(img, tp.x, tp.y, ts.getParam_r(), false) .getRed(); // add the instance Instance inst = new Instance(1.0, new double[] { intensity }); inst.setDataset(data); k = ordering[clusterer.clusterInstance(inst)]; // store the color for later visualization clustered_points.get(k).add(intensity); // set the staining of the TMApoint switch (k) { case 0: tp.setStaining(TMALabel.STAINING_0); break; case 1: tp.setStaining(TMALabel.STAINING_1); break; case 2: tp.setStaining(TMALabel.STAINING_2); break; default: tp.setStaining(TMALabel.STAINING_3); break; } } ts.dispStainingInfo(); if (manager.getVisibleTMAspot() == ts) { manager.repaintVisibleTMAspot(); } } // Write the description String description = "Nuclei clustered with " + getParam_AutomaticClustererString(); if (getParam_AutomaticClustererString().equalsIgnoreCase("Hierarchical")) { description += " (" + getParam_HierarchicalClusteringMethod() + ")"; } description += ", n=" + getParam_nClusters() + ", channel 2 intensity."; jLabel42.setText(description); jLabel41.setText(" "); } } catch (Exception e) { e.printStackTrace(); } finally { this.setCursor(Cursor.getPredefinedCursor(Cursor.DEFAULT_CURSOR)); } } }
From source file:intensityclustering.IntensityClustering.java
/** * Clusters the TMApoints on given TMAspots according to their staining * intensity (color). All parameters (e.g. clusterer and parameters) are * selected by the user. Features are simple color features. * * @param tss The TMAspots of which all nuclei (gold-standard and estimated) * are clustered according to color./*w w w. j av a 2 s. com*/ */ private void clusterPointsAutomaticallyColorSpace(List<TMAspot> tss) { if (tss.size() > 0) { try { this.setCursor(Cursor.getPredefinedCursor(Cursor.WAIT_CURSOR)); int n = getParam_nClusters(); // Create ARFF Data FastVector atts; Instances data; int i; // 1. create arff data format atts = new FastVector(3); for (i = 0; i < 3; i++) { atts.addElement(new Attribute(Integer.toString(i))); } // 2. create Instances object data = new Instances("TMA points", atts, tmarker.getNumberNuclei(tss)); // 3. fill with data BufferedImage img; Color c; float[] features = new float[3]; String colorSpace = getParam_ColorSpace(); for (TMAspot ts : tss) { img = ts.getBufferedImage(); List<TMApoint> tps = ts.getPoints(); for (TMApoint tp : tps) { Color2Feature(TMAspot.getAverageColorAtPoint(img, tp.x, tp.y, ts.getParam_r(), false), colorSpace, features); // add the instance Instance inst = new Instance(1.0, new double[] { features[0], features[1], features[2] }); inst.setDataset(data); data.add(inst); } } // 4. set data class index (last attribute is the class) //data.setClassIndex(data.numAttributes() - 1); // not for weka 3.5.X if (tmarker.DEBUG > 4) { java.util.logging.Logger.getLogger(getClass().getName()).log(java.util.logging.Level.INFO, data.toString()); } Clusterer clusterer = getClusterer(); String[] options = getClustererOptions(); if (false && colorSpace.equalsIgnoreCase("hsb")) { String[] newoptions = new String[options.length + 2]; System.arraycopy(options, 0, newoptions, 0, options.length); newoptions[options.length] = "-A"; newoptions[options.length + 1] = "weka.core.MyHSBDistance"; options = newoptions; } if (tmarker.DEBUG > 3) { if (options.length > 0) { String info = "Clusterer should have options\n"; for (String o : options) { info += o + " "; } info += "\n"; java.util.logging.Logger.getLogger(getClass().getName()).log(java.util.logging.Level.INFO, info); } } clusterer.setOptions(options); // set the clusterer options clusterer.buildClusterer(data); // build the clusterer // order the clusters according to the brightness // The most bright cluster should be 0, then 1, then 2,... ArrayList<ArrayList<Double>> values = new ArrayList<>(); for (i = 0; i < clusterer.numberOfClusters(); i++) { values.add(new ArrayList<Double>()); } int z; double value; for (i = 0; i < data.numInstances(); i++) { z = clusterer.clusterInstance(data.instance(i)); value = getParam_ColorSpace().equalsIgnoreCase("hsb") ? data.instance(i).value(2) : Misc.RGBToGray(data.instance(i).value(0), data.instance(i).value(1), data.instance(i).value(2)); values.get(z).add(value); } double[] means = new double[clusterer.numberOfClusters()]; for (i = 0; i < clusterer.numberOfClusters(); i++) { means[i] = Misc.mean(values.get(i).toArray(new Double[values.get(i).size()])); } int[] ordering = Misc.orderArray(means, !getParam_ColorSpace().equalsIgnoreCase("rtp")); String clusterInfo = ""; for (String o : clusterer.getOptions()) { clusterInfo += o + " "; } clusterInfo += "\n\n"; clusterInfo += clusterer.toString().trim(); if (getParam_AutomaticClustererString().equalsIgnoreCase("Hierarchical")) { try { clusterInfo += ((HierarchicalClusterer) clusterer).graph(); HierarchyVisualizer a = new HierarchyVisualizer( ((HierarchicalClusterer) clusterer).graph()); a.setSize(800, 600); if (clusterVisualizer == null) { clusterVisualizer = new JFrame("Hierarchical Clusterer Dendrogram"); clusterVisualizer.setIconImage(getIconImage()); clusterVisualizer.setDefaultCloseOperation(JFrame.DISPOSE_ON_CLOSE); clusterVisualizer.setSize(800, 600); } Container contentPane = clusterVisualizer.getContentPane(); contentPane.removeAll(); contentPane.add(a); } catch (Exception e) { clusterVisualizer = null; } } jTextArea1.setText(clusterInfo); if (tmarker.DEBUG > 3) { String info = "Clusterer has options\n"; for (String o : clusterer.getOptions()) { info += o + " "; } info += "\n"; info += clusterer.toString() + "\n"; // info += (clusterer).globalInfo() + "\n"; info += "\n"; info += clusterInfo + "\n"; java.util.logging.Logger.getLogger(getClass().getName()).log(java.util.logging.Level.INFO, info); } // cluster all TMAspots and assign the corresponding class to them // Cluster the points List<List<Color>> clustered_points = new ArrayList<>(); for (i = 0; i < clusterer.numberOfClusters(); i++) { clustered_points.add(new ArrayList<Color>()); } int k; for (TMAspot ts : tss) { img = ts.getBufferedImage(); List<TMApoint> tps = ts.getPoints(); for (TMApoint tp : tps) { c = TMAspot.getAverageColorAtPoint(img, tp.x, tp.y, ts.getParam_r(), false); Color2Feature(c, colorSpace, features); // add the instance Instance inst = new Instance(1.0, new double[] { features[0], features[1], features[2] }); inst.setDataset(data); k = ordering[clusterer.clusterInstance(inst)]; // store the color for later visualization clustered_points.get(k).add(c); // set the staining of the TMApoint switch (k) { case 0: tp.setStaining(TMALabel.STAINING_0); break; case 1: tp.setStaining(TMALabel.STAINING_1); break; case 2: tp.setStaining(TMALabel.STAINING_2); break; default: tp.setStaining(TMALabel.STAINING_3); break; } } ts.dispStainingInfo(); if (manager.getVisibleTMAspot() == ts) { manager.repaintVisibleTMAspot(); } } // draw the points Plot3DPanel plot; if (((java.awt.BorderLayout) (jPanel2.getLayout())) .getLayoutComponent(java.awt.BorderLayout.CENTER) != null) { plot = (Plot3DPanel) ((java.awt.BorderLayout) (jPanel2.getLayout())) .getLayoutComponent(java.awt.BorderLayout.CENTER); plot.removeAllPlots(); } else { plot = new Plot3DPanel(); plot.plotCanvas.setBackground(jPanel2.getBackground()); plot.addLegend(PlotPanel.SOUTH); plot.plotLegend.setBackground(jPanel2.getBackground()); } if (colorSpace.equalsIgnoreCase("hsb")) { plot.setAxisLabels("Hue", "Saturation", "Brightness"); } else if (colorSpace.equalsIgnoreCase("rtp")) { plot.setAxisLabels("R", "Theta", "Phi"); } else { plot.setAxisLabels("Red", "Green", "Blue"); } for (i = 0; i < clusterer.numberOfClusters(); i++) { double[] xs = new double[clustered_points.get(i).size()]; double[] ys = new double[clustered_points.get(i).size()]; double[] zs = new double[clustered_points.get(i).size()]; for (int j = 0; j < clustered_points.get(i).size(); j++) { Color2Feature(clustered_points.get(i).get(j), colorSpace, features); xs[j] = features[0]; ys[j] = features[1]; zs[j] = features[2]; } if (xs.length > 0) { c = getParam_ColorOfClassK(i); plot.addScatterPlot("Staining " + i, c, xs, ys, zs); } } // Write the description String description = "Nuclei clustered with " + getParam_AutomaticClustererString(); if (getParam_AutomaticClustererString().equalsIgnoreCase("Hierarchical")) { description += " (" + getParam_HierarchicalClusteringMethod() + ")"; } description += ", n=" + getParam_nClusters() + ", color space " + getParam_ColorSpace() + "."; jLabel41.setText(description); jLabel42.setText(" "); if (((java.awt.BorderLayout) (jPanel2.getLayout())) .getLayoutComponent(java.awt.BorderLayout.CENTER) == null) { jPanel2.add(plot, java.awt.BorderLayout.CENTER); validate(); pack(); } } catch (Exception | OutOfMemoryError e) { java.util.logging.Logger.getLogger(getClass().getName()).log(java.util.logging.Level.SEVERE, null, e); JOptionPane.showMessageDialog(this, "The clustering could not be performed.\n\n" + "A possible reasons is:\n" + "- Not enough memory (too many points), \n\n" + "You might want to try a different clustering method or less TMAspots.\n\n" + "The error message is: \n" + e.getMessage(), "Error at Nucleus clustering", JOptionPane.WARNING_MESSAGE); } finally { this.setCursor(Cursor.getPredefinedCursor(Cursor.DEFAULT_CURSOR)); } } }
From source file:myclusterer.WekaCode.java
public static Instances classifyUnseenData(Clusterer clusterer, Instances dataSet) throws Exception { Instances labeledData = new Instances(dataSet); // labeling data for (int i = 0; i < labeledData.numInstances(); i++) { double clsLabel = clusterer.clusterInstance(dataSet.instance(i)); labeledData.instance(i).setClassValue(clsLabel); }// w ww . ja va2 s . c o m return labeledData; }
From source file:myclusterer.WekaCode.java
public static void classifyUnseenData(String[] attributes, Clusterer clusterer, Instances data) throws Exception { Instance newInstance = new Instance(data.numAttributes()); newInstance.setDataset(data);//from w w w. ja v a 2 s .c o m for (int i = 0; i < data.numAttributes() - 1; i++) { if (Attribute.NUMERIC == data.attribute(i).type()) { Double value = Double.valueOf(attributes[i]); newInstance.setValue(i, value); } else { newInstance.setValue(i, attributes[i]); } } double clsLabel = clusterer.clusterInstance(newInstance); newInstance.setClassValue(clsLabel); String result = data.classAttribute().value((int) clsLabel); System.out.println("Hasil Classify Unseen Data Adalah: " + result); }
From source file:org.mcennis.graphrat.algorithm.clustering.WekaClassifierClusterer.java
License:Open Source License
@Override public void execute(Graph g) { ActorByMode mode = (ActorByMode) ActorQueryFactory.newInstance().create("ActorByMode"); mode.buildQuery((String) parameter.get("GroundMode").get(), ".*", false); try {//ww w . ja v a2s . co m Clusterer clusterer = (Clusterer) ((Class) parameter.get("Clusterer").get()).newInstance(); String[] options = ((String) parameter.get("Options").get()).split("\\s+"); ((OptionHandler) clusterer).setOptions(options); Iterator<Actor> actor = AlgorithmMacros.filterActor(parameter, g, mode, null, null); Instances dataSet = null; while (actor.hasNext()) { Actor a = actor.next(); Property property = a.getProperty( AlgorithmMacros.getSourceID(parameter, g, (String) parameter.get("SourceProperty").get())); if (!property.getValue().isEmpty()) { Instance value = (Instance) property.getValue().get(0); if ((dataSet == null) && (value.dataset() != null)) { FastVector attributes = new FastVector(); for (int i = 0; i < value.dataset().numAttributes(); ++i) { attributes.addElement(value.dataset().attribute(i)); } dataSet = new Instances("Clustering", attributes, 1000); } else if ((dataSet == null)) { FastVector attributes = new FastVector(); for (int i = 0; i < value.numAttributes(); ++i) { Attribute element = new Attribute(Integer.toString(i)); attributes.addElement(element); } dataSet = new Instances("Clustering", attributes, 1000); } dataSet.add(value); } } clusterer.buildClusterer(dataSet); actor = AlgorithmMacros.filterActor(parameter, g, mode, null, null); HashMap<Integer, Graph> clusters = new HashMap<Integer, Graph>(); while (actor.hasNext()) { Actor a = actor.next(); Property property = a.getProperty( AlgorithmMacros.getSourceID(parameter, g, (String) parameter.get("SourceProperty").get())); if (!property.getValue().isEmpty()) { Instance instance = (Instance) property.getValue().get(0); int cluster = -1; try { cluster = clusterer.clusterInstance(instance); if (!clusters.containsKey(cluster)) { Graph graph = GraphFactory.newInstance().create(AlgorithmMacros.getDestID(parameter, g, (String) parameter.get("GraphID").get() + cluster), parameter); clusters.put(cluster, graph); } clusters.get(cluster).add(a); } catch (Exception ex) { Logger.getLogger(WekaClassifierClusterer.class.getName()).log(Level.SEVERE, "ClusterInstance on clusterer failed", ex); } Property clusterProperty = PropertyFactory.newInstance().create("BasicProperty", AlgorithmMacros .getDestID(parameter, g, (String) parameter.get("DestinationProperty").get()), Integer.class); clusterProperty.add(new Integer(cluster)); a.add(clusterProperty); } } Iterator<Graph> graphIt = clusters.values().iterator(); while (graphIt.hasNext()) { LinkQuery query = (LinkQuery) parameter.get("LinkQuery").get(); Graph graph = graphIt.next(); Iterator<Link> link = query.executeIterator(g, graph.getActor(), graph.getActor(), null); while (link.hasNext()) { graph.add(link.next()); } if ((Boolean) parameter.get("AddContext").get()) { TreeSet<Actor> actorSet = new TreeSet<Actor>(); actorSet.addAll(graph.getActor()); link = query.executeIterator(g, actorSet, null, null); while (link.hasNext()) { Link l = link.next(); Actor d = l.getDestination(); if (graph.getActor(d.getMode(), d.getID()) == null) { graph.add(d); } if (graph.getLink(l.getRelation(), l.getSource(), l.getDestination()) == null) { graph.add(l); } } link = query.executeIterator(g, null, actorSet, null); while (link.hasNext()) { Link l = link.next(); Actor d = l.getSource(); if (graph.getActor(d.getMode(), d.getID()) == null) { graph.add(d); } if (graph.getLink(l.getRelation(), l.getSource(), l.getDestination()) == null) { graph.add(l); } } } } } catch (InstantiationException ex) { Logger.getLogger(WekaClassifierClusterer.class.getName()).log(Level.SEVERE, null, ex); } catch (IllegalAccessException ex) { Logger.getLogger(WekaClassifierClusterer.class.getName()).log(Level.SEVERE, null, ex); } catch (Exception ex) { Logger.getLogger(WekaClassifierClusterer.class.getName()).log(Level.SEVERE, null, ex); } }