@Override public double[] distributionForInstance(Instance xy) throws Exception { int L = xy.classIndex(); double y[] = new double[L]; double w = 0.0; /* * e.g. K = [3,3,5] * we push y_[] from [0,0,0] to [2,2,4] over all necessary iterations. */ int K[] = getKs(xy.dataset()); if (getDebug()) System.out.println("K[] = " + Arrays.toString(K)); double y_[] = new double[L]; for (int i = 0; i < 1000000; i++) { // limit to 1m // System.out.println(""+i+" "+Arrays.toString(y_)); double w_ = A.product(super.probabilityForInstance(xy, y_)); if (w_ > w) { if (getDebug()) System.out.println("y' = " + Arrays.toString(y_) + ", :" + w_); y = Arrays.copyOf(y_, y_.length); w = w_; } if (push(y_, K, 0)) { // Done ! if (getDebug()) System.out.println("Tried all " + (i + 1) + " combinations."); break; } } return y; }
/** * Generates the classifier. * * @param data set of instances serving as training data * @throws Exception if the classifier has not been generated successfully */ public void buildClassifier(Instances data) throws Exception { // can classifier handle the data? getCapabilities().testWithFail(data); // remove instances with missing class m_theInstances = new Instances(data); m_theInstances.deleteWithMissingClass(); m_rr = new Random(1); if (m_theInstances.classAttribute().isNominal()) { // Set up class priors m_classPriorCounts = new double[data.classAttribute().numValues()]; Arrays.fill(m_classPriorCounts, 1.0); for (int i = 0; i < data.numInstances(); i++) { Instance curr = data.instance(i); m_classPriorCounts[(int) curr.classValue()] += curr.weight(); } m_classPriors = m_classPriorCounts.clone(); Utils.normalize(m_classPriors); } setUpEvaluator(); if (m_theInstances.classAttribute().isNumeric()) { m_disTransform = new weka.filters.unsupervised.attribute.Discretize(); m_classIsNominal = false; // use binned discretisation if the class is numeric ((weka.filters.unsupervised.attribute.Discretize) m_disTransform).setBins(10); ((weka.filters.unsupervised.attribute.Discretize) m_disTransform).setInvertSelection(true); // Discretize all attributes EXCEPT the class String rangeList = ""; rangeList += (m_theInstances.classIndex() + 1); // System.out.println("The class col: "+m_theInstances.classIndex()); ((weka.filters.unsupervised.attribute.Discretize) m_disTransform) .setAttributeIndices(rangeList); } else { m_disTransform = new weka.filters.supervised.attribute.Discretize(); ((weka.filters.supervised.attribute.Discretize) m_disTransform).setUseBetterEncoding(true); m_classIsNominal = true; } m_disTransform.setInputFormat(m_theInstances); m_theInstances = Filter.useFilter(m_theInstances, m_disTransform); m_numAttributes = m_theInstances.numAttributes(); m_numInstances = m_theInstances.numInstances(); m_majority = m_theInstances.meanOrMode(m_theInstances.classAttribute()); // Perform the search int[] selected = m_search.search(m_evaluator, m_theInstances); m_decisionFeatures = new int[selected.length + 1]; System.arraycopy(selected, 0, m_decisionFeatures, 0, selected.length); m_decisionFeatures[m_decisionFeatures.length - 1] = m_theInstances.classIndex(); // reduce instances to selected features m_delTransform = new Remove(); m_delTransform.setInvertSelection(true); // set features to keep m_delTransform.setAttributeIndicesArray(m_decisionFeatures); m_delTransform.setInputFormat(m_theInstances); m_dtInstances = Filter.useFilter(m_theInstances, m_delTransform); // reset the number of attributes m_numAttributes = m_dtInstances.numAttributes(); // create hash table m_entries = new Hashtable((int) (m_dtInstances.numInstances() * 1.5)); // insert instances into the hash table for (int i = 0; i < m_numInstances; i++) { Instance inst = m_dtInstances.instance(i); insertIntoTable(inst, null); } // Replace the global table majority with nearest neighbour? if (m_useIBk) { m_ibk = new IBk(); m_ibk.buildClassifier(m_theInstances); } // Save memory if (m_saveMemory) { m_theInstances = new Instances(m_theInstances, 0); m_dtInstances = new Instances(m_dtInstances, 0); } m_evaluation = null; }