List of usage examples for weka.estimators DiscreteEstimator DiscreteEstimator
public DiscreteEstimator(int nSymbols, double fPrior)
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;//from w w w . j a va 2 s. co m // 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:br.ufrn.ia.core.clustering.EMIaProject.java
License:Open Source License
private void new_estimators() { for (int i = 0; i < m_num_clusters; i++) { for (int j = 0; j < m_num_attribs; j++) { if (m_theInstances.attribute(j).isNominal()) { m_model[i][j] = new DiscreteEstimator(m_theInstances.attribute(j).numValues(), true); } else { m_modelNormal[i][j][0] = m_modelNormal[i][j][1] = m_modelNormal[i][j][2] = 0.0; }//from w w w . ja v a2 s .c o m } } }
From source file:cn.edu.xjtu.dbmine.source.NaiveBayes.java
License:Open Source License
/** * Generates the classifier.//from w w w . j a v a 2 s .c o m * * @param instances set of instances serving as training data * @exception Exception if the classifier has not been generated * 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(); m_NumClasses = instances.numClasses(); // Copy the instances m_Instances = new Instances(instances); // Discretize instances if required if (m_UseDiscretization) { m_Disc = new weka.filters.supervised.attribute.Discretize(); m_Disc.setInputFormat(m_Instances); m_Instances = weka.filters.Filter.useFilter(m_Instances, m_Disc); } else { m_Disc = null; } // Reserve space for the distributions m_Distributions = new Estimator[m_Instances.numAttributes() - 1][m_Instances.numClasses()]; m_ClassDistribution = new DiscreteEstimator(m_Instances.numClasses(), true); int attIndex = 0; Enumeration enu = m_Instances.enumerateAttributes(); while (enu.hasMoreElements()) { Attribute attribute = (Attribute) enu.nextElement(); // If the attribute is numeric, determine the estimator // numeric precision from differences between adjacent values double numPrecision = DEFAULT_NUM_PRECISION; if (attribute.type() == Attribute.NUMERIC) { m_Instances.sort(attribute); if ((m_Instances.numInstances() > 0) && !m_Instances.instance(0).isMissing(attribute)) { double lastVal = m_Instances.instance(0).value(attribute); double currentVal, deltaSum = 0; int distinct = 0; for (int i = 1; i < m_Instances.numInstances(); i++) { Instance currentInst = m_Instances.instance(i); if (currentInst.isMissing(attribute)) { break; } currentVal = currentInst.value(attribute); if (currentVal != lastVal) { deltaSum += currentVal - lastVal; lastVal = currentVal; distinct++; } } if (distinct > 0) { numPrecision = deltaSum / distinct; } } } for (int j = 0; j < m_Instances.numClasses(); j++) { switch (attribute.type()) { case Attribute.NUMERIC: if (m_UseKernelEstimator) { m_Distributions[attIndex][j] = new KernelEstimator(numPrecision); } else { m_Distributions[attIndex][j] = new NormalEstimator(numPrecision); } break; case Attribute.NOMINAL: m_Distributions[attIndex][j] = new DiscreteEstimator(attribute.numValues(), true); break; default: throw new Exception("Attribute type unknown to NaiveBayes"); } } attIndex++; } // Compute counts Enumeration enumInsts = m_Instances.enumerateInstances(); while (enumInsts.hasMoreElements()) { Instance instance = (Instance) enumInsts.nextElement(); updateClassifier(instance); } // Save space m_Instances = new Instances(m_Instances, 0); }
From source file:main.NaiveBayes.java
License:Open Source License
/** * Generates the classifier./* w ww. j a v a 2 s. c o m*/ * * @param instances set of instances serving as training data * @exception Exception if the classifier has not been generated successfully */ @Override 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(); m_NumClasses = instances.numClasses(); // Copy the instances m_Instances = new Instances(instances); // Discretize instances if required if (m_UseDiscretization) { m_Disc = new weka.filters.supervised.attribute.Discretize(); m_Disc.setInputFormat(m_Instances); m_Instances = weka.filters.Filter.useFilter(m_Instances, m_Disc); } else { m_Disc = null; } // Reserve space for the distributions m_Distributions = new Estimator[m_Instances.numAttributes() - 1][m_Instances.numClasses()]; m_ClassDistribution = new DiscreteEstimator(m_Instances.numClasses(), true); int attIndex = 0; Enumeration<Attribute> enu = m_Instances.enumerateAttributes(); while (enu.hasMoreElements()) { Attribute attribute = enu.nextElement(); // If the attribute is numeric, determine the estimator // numeric precision from differences between adjacent values double numPrecision = DEFAULT_NUM_PRECISION; if (attribute.type() == Attribute.NUMERIC) { m_Instances.sort(attribute); if ((m_Instances.numInstances() > 0) && !m_Instances.instance(0).isMissing(attribute)) { double lastVal = m_Instances.instance(0).value(attribute); double currentVal, deltaSum = 0; int distinct = 0; for (int i = 1; i < m_Instances.numInstances(); i++) { Instance currentInst = m_Instances.instance(i); if (currentInst.isMissing(attribute)) { break; } currentVal = currentInst.value(attribute); if (currentVal != lastVal) { deltaSum += currentVal - lastVal; lastVal = currentVal; distinct++; } } if (distinct > 0) { numPrecision = deltaSum / distinct; } } } for (int j = 0; j < m_Instances.numClasses(); j++) { switch (attribute.type()) { case Attribute.NUMERIC: if (m_UseKernelEstimator) { m_Distributions[attIndex][j] = new KernelEstimator(numPrecision); } else { m_Distributions[attIndex][j] = new NormalEstimator(numPrecision); } break; case Attribute.NOMINAL: m_Distributions[attIndex][j] = new DiscreteEstimator(attribute.numValues(), true); break; default: throw new Exception("Attribute type unknown to NaiveBayes"); } } attIndex++; } // Compute counts Enumeration<Instance> enumInsts = m_Instances.enumerateInstances(); while (enumInsts.hasMoreElements()) { Instance instance = enumInsts.nextElement(); updateClassifier(instance); } // Save space m_Instances = new Instances(m_Instances, 0); }