List of usage examples for weka.core Instances variance
publicdouble variance(Attribute att)
From source file:adams.data.instancesanalysis.pls.AbstractMultiClassPLS.java
License:Open Source License
/** * Preprocesses the data.//ww w. ja v a2s . co m * * @param instances the data to process * @return the preprocessed data */ protected Instances preTransform(Instances instances, Map<String, Object> params) throws Exception { Map<Integer, double[]> classValues; int i; int index; switch (m_PredictionType) { case ALL: classValues = null; break; default: classValues = new HashMap<>(); for (i = 0; i < m_ClassAttributeIndices.size(); i++) { index = m_ClassAttributeIndices.get(i); classValues.put(index, instances.attributeToDoubleArray(index)); } } if (classValues != null) params.put(PARAM_CLASSVALUES, classValues); if (!isInitialized()) { if (m_ReplaceMissing) { m_Missing = new ReplaceMissingValues(); m_Missing.setInputFormat(instances); } else { m_Missing = null; } m_ClassMean = new HashMap<>(); m_ClassStdDev = new HashMap<>(); for (i = 0; i < m_ClassAttributeIndices.size(); i++) { index = m_ClassAttributeIndices.get(i); switch (m_PreprocessingType) { case CENTER: m_ClassMean.put(index, instances.meanOrMode(index)); m_ClassStdDev.put(index, 1.0); m_Filter = new Center(); ((Center) m_Filter).setIgnoreClass(true); break; case STANDARDIZE: m_ClassMean.put(index, instances.meanOrMode(index)); m_ClassStdDev.put(index, StrictMath.sqrt(instances.variance(index))); m_Filter = new Standardize(); ((Standardize) m_Filter).setIgnoreClass(true); break; case NONE: m_ClassMean.put(index, 0.0); m_ClassStdDev.put(index, 1.0); m_Filter = null; break; default: throw new IllegalStateException("Unhandled preprocessing type; " + m_PreprocessingType); } } if (m_Filter != null) m_Filter.setInputFormat(instances); } // filter data if (m_Missing != null) instances = Filter.useFilter(instances, m_Missing); if (m_Filter != null) instances = Filter.useFilter(instances, m_Filter); return instances; }
From source file:adams.data.instancesanalysis.pls.AbstractSingleClassPLS.java
License:Open Source License
/** * Preprocesses the data.//from w ww. jav a 2 s .c o m * * @param instances the data to process * @return the preprocessed data */ protected Instances preTransform(Instances instances, Map<String, Object> params) throws Exception { double[] classValues; switch (m_PredictionType) { case ALL: classValues = null; break; default: classValues = instances.attributeToDoubleArray(instances.classIndex()); } if (classValues != null) params.put(PARAM_CLASSVALUES, classValues); if (!isInitialized()) { if (m_ReplaceMissing) { m_Missing = new ReplaceMissingValues(); m_Missing.setInputFormat(instances); } else { m_Missing = null; } switch (m_PreprocessingType) { case CENTER: m_ClassMean = instances.meanOrMode(instances.classIndex()); m_ClassStdDev = 1; m_Filter = new Center(); ((Center) m_Filter).setIgnoreClass(true); break; case STANDARDIZE: m_ClassMean = instances.meanOrMode(instances.classIndex()); m_ClassStdDev = StrictMath.sqrt(instances.variance(instances.classIndex())); m_Filter = new Standardize(); ((Standardize) m_Filter).setIgnoreClass(true); break; case NONE: m_ClassMean = 0; m_ClassStdDev = 1; m_Filter = null; break; default: throw new IllegalStateException("Unhandled preprocessing type; " + m_PreprocessingType); } if (m_Filter != null) m_Filter.setInputFormat(instances); } // filter data if (m_Missing != null) instances = Filter.useFilter(instances, m_Missing); if (m_Filter != null) instances = Filter.useFilter(instances, m_Filter); return instances; }
From source file:adaptedClusteringAlgorithms.MySimpleKMeans.java
License:Open Source License
/** * Generates a clusterer. Has to initialize all fields of the clusterer that * are not being set via options.//from w ww.ja va 2 s .c om * * @param data set of instances serving as training data * @throws Exception if the clusterer has not been generated successfully */ @Override public void buildClusterer(Instances data) throws Exception { if (!SESAME.SESAME_GUI) MyFirstClusterer.weka_gui = true; // can clusterer handle the data? getCapabilities().testWithFail(data); m_Iterations = 0; m_ReplaceMissingFilter = new ReplaceMissingValues(); Instances instances = new Instances(data); instances.setClassIndex(-1); if (!m_dontReplaceMissing) { m_ReplaceMissingFilter.setInputFormat(instances); instances = Filter.useFilter(instances, m_ReplaceMissingFilter); } m_FullMissingCounts = new int[instances.numAttributes()]; if (m_displayStdDevs) { m_FullStdDevs = new double[instances.numAttributes()]; } m_FullNominalCounts = new int[instances.numAttributes()][0]; m_FullMeansOrMediansOrModes = moveCentroid(0, instances, false); for (int i = 0; i < instances.numAttributes(); i++) { m_FullMissingCounts[i] = instances.attributeStats(i).missingCount; if (instances.attribute(i).isNumeric()) { if (m_displayStdDevs) { m_FullStdDevs[i] = Math.sqrt(instances.variance(i)); } if (m_FullMissingCounts[i] == instances.numInstances()) { m_FullMeansOrMediansOrModes[i] = Double.NaN; // mark missing as mean } } else { m_FullNominalCounts[i] = instances.attributeStats(i).nominalCounts; if (m_FullMissingCounts[i] > m_FullNominalCounts[i][Utils.maxIndex(m_FullNominalCounts[i])]) { m_FullMeansOrMediansOrModes[i] = -1; // mark missing as most common // value } } } m_ClusterCentroids = new Instances(instances, m_NumClusters); int[] clusterAssignments = new int[instances.numInstances()]; if (m_PreserveOrder) { m_Assignments = clusterAssignments; } m_DistanceFunction.setInstances(instances); Random RandomO = new Random(getSeed()); int instIndex; HashMap initC = new HashMap(); DecisionTableHashKey hk = null; Instances initInstances = null; if (m_PreserveOrder) { initInstances = new Instances(instances); } else { initInstances = instances; } for (int j = initInstances.numInstances() - 1; j >= 0; j--) { instIndex = RandomO.nextInt(j + 1); hk = new DecisionTableHashKey(initInstances.instance(instIndex), initInstances.numAttributes(), true); if (!initC.containsKey(hk)) { m_ClusterCentroids.add(initInstances.instance(instIndex)); initC.put(hk, null); } initInstances.swap(j, instIndex); if (m_ClusterCentroids.numInstances() == m_NumClusters) { break; } } m_NumClusters = m_ClusterCentroids.numInstances(); // removing reference initInstances = null; int i; boolean converged = false; int emptyClusterCount; Instances[] tempI = new Instances[m_NumClusters]; m_squaredErrors = new double[m_NumClusters]; m_ClusterNominalCounts = new int[m_NumClusters][instances.numAttributes()][0]; m_ClusterMissingCounts = new int[m_NumClusters][instances.numAttributes()]; while (!converged) { emptyClusterCount = 0; m_Iterations++; converged = true; for (i = 0; i < instances.numInstances(); i++) { Instance toCluster = instances.instance(i); int newC = clusterProcessedInstance(toCluster, true); if (newC != clusterAssignments[i]) { converged = false; } clusterAssignments[i] = newC; } // update centroids m_ClusterCentroids = new Instances(instances, m_NumClusters); for (i = 0; i < m_NumClusters; i++) { tempI[i] = new Instances(instances, 0); } for (i = 0; i < instances.numInstances(); i++) { tempI[clusterAssignments[i]].add(instances.instance(i)); } for (i = 0; i < m_NumClusters; i++) { if (tempI[i].numInstances() == 0) { // empty cluster emptyClusterCount++; } else { moveCentroid(i, tempI[i], true); } } if (m_Iterations == m_MaxIterations) { converged = true; } if (emptyClusterCount > 0) { m_NumClusters -= emptyClusterCount; if (converged) { Instances[] t = new Instances[m_NumClusters]; int index = 0; for (int k = 0; k < tempI.length; k++) { if (tempI[k].numInstances() > 0) { t[index] = tempI[k]; for (i = 0; i < tempI[k].numAttributes(); i++) { m_ClusterNominalCounts[index][i] = m_ClusterNominalCounts[k][i]; } index++; } } tempI = t; } else { tempI = new Instances[m_NumClusters]; } } if (!converged) { m_squaredErrors = new double[m_NumClusters]; m_ClusterNominalCounts = new int[m_NumClusters][instances.numAttributes()][0]; } } if (m_displayStdDevs) { m_ClusterStdDevs = new Instances(instances, m_NumClusters); } m_ClusterSizes = new int[m_NumClusters]; for (i = 0; i < m_NumClusters; i++) { if (m_displayStdDevs) { double[] vals2 = new double[instances.numAttributes()]; for (int j = 0; j < instances.numAttributes(); j++) { if (instances.attribute(j).isNumeric()) { vals2[j] = Math.sqrt(tempI[i].variance(j)); } else { vals2[j] = Instance.missingValue(); } } m_ClusterStdDevs.add(new Instance(1.0, vals2)); } m_ClusterSizes[i] = tempI[i].numInstances(); } // Save memory!! m_DistanceFunction.clean(); if (!SESAME.SESAME_GUI) MyFirstClusterer.weka_gui = true; }
From source file:br.ufrn.ia.core.clustering.SimpleKMeansIaProject.java
License:Open Source License
public void buildClusterer(Instances data) throws Exception { // can clusterer handle the data? getCapabilities().testWithFail(data); m_Iterations = 0;//w w w .j a v a 2 s.co m m_ReplaceMissingFilter = new ReplaceMissingValues(); Instances instances = new Instances(data); instances.setClassIndex(-1); if (!m_dontReplaceMissing) { m_ReplaceMissingFilter.setInputFormat(instances); instances = Filter.useFilter(instances, m_ReplaceMissingFilter); } m_FullMissingCounts = new int[instances.numAttributes()]; if (m_displayStdDevs) { m_FullStdDevs = new double[instances.numAttributes()]; } m_FullNominalCounts = new int[instances.numAttributes()][0]; m_FullMeansOrMediansOrModes = moveCentroid(0, instances, false); for (int i = 0; i < instances.numAttributes(); i++) { m_FullMissingCounts[i] = instances.attributeStats(i).missingCount; if (instances.attribute(i).isNumeric()) { if (m_displayStdDevs) { m_FullStdDevs[i] = Math.sqrt(instances.variance(i)); } if (m_FullMissingCounts[i] == instances.numInstances()) { m_FullMeansOrMediansOrModes[i] = Double.NaN; // mark missing // as mean } } else { m_FullNominalCounts[i] = instances.attributeStats(i).nominalCounts; if (m_FullMissingCounts[i] > m_FullNominalCounts[i][Utils.maxIndex(m_FullNominalCounts[i])]) { m_FullMeansOrMediansOrModes[i] = -1; // mark missing as most // common value } } } m_ClusterCentroids = new Instances(instances, m_NumClusters); int[] clusterAssignments = new int[instances.numInstances()]; if (m_PreserveOrder) m_Assignments = clusterAssignments; m_DistanceFunction.setInstances(instances); Random RandomO = new Random(getSeed()); int instIndex; HashMap initC = new HashMap(); DecisionTableHashKey hk = null; Instances initInstances = null; if (m_PreserveOrder) initInstances = new Instances(instances); else initInstances = instances; for (int j = initInstances.numInstances() - 1; j >= 0; j--) { instIndex = RandomO.nextInt(j + 1); hk = new DecisionTableHashKey(initInstances.instance(instIndex), initInstances.numAttributes(), true); if (!initC.containsKey(hk)) { m_ClusterCentroids.add(initInstances.instance(instIndex)); initC.put(hk, null); } initInstances.swap(j, instIndex); if (m_ClusterCentroids.numInstances() == m_NumClusters) { break; } } m_NumClusters = m_ClusterCentroids.numInstances(); // removing reference initInstances = null; int i; boolean converged = false; int emptyClusterCount; Instances[] tempI = new Instances[m_NumClusters]; m_squaredErrors = new double[m_NumClusters]; m_ClusterNominalCounts = new int[m_NumClusters][instances.numAttributes()][0]; m_ClusterMissingCounts = new int[m_NumClusters][instances.numAttributes()]; while (!converged) { emptyClusterCount = 0; m_Iterations++; converged = true; for (i = 0; i < instances.numInstances(); i++) { Instance toCluster = instances.instance(i); int newC = clusterProcessedInstance(toCluster, true); if (newC != clusterAssignments[i]) { converged = false; } clusterAssignments[i] = newC; } // update centroids m_ClusterCentroids = new Instances(instances, m_NumClusters); for (i = 0; i < m_NumClusters; i++) { tempI[i] = new Instances(instances, 0); } for (i = 0; i < instances.numInstances(); i++) { tempI[clusterAssignments[i]].add(instances.instance(i)); } for (i = 0; i < m_NumClusters; i++) { if (tempI[i].numInstances() == 0) { // empty cluster emptyClusterCount++; } else { moveCentroid(i, tempI[i], true); } } if (emptyClusterCount > 0) { m_NumClusters -= emptyClusterCount; if (converged) { Instances[] t = new Instances[m_NumClusters]; int index = 0; for (int k = 0; k < tempI.length; k++) { if (tempI[k].numInstances() > 0) { t[index++] = tempI[k]; } } tempI = t; } else { tempI = new Instances[m_NumClusters]; } } if (m_Iterations == m_MaxIterations) converged = true; if (!converged) { m_squaredErrors = new double[m_NumClusters]; m_ClusterNominalCounts = new int[m_NumClusters][instances.numAttributes()][0]; } } if (m_displayStdDevs) { m_ClusterStdDevs = new Instances(instances, m_NumClusters); } m_ClusterSizes = new int[m_NumClusters]; for (i = 0; i < m_NumClusters; i++) { if (m_displayStdDevs) { double[] vals2 = new double[instances.numAttributes()]; for (int j = 0; j < instances.numAttributes(); j++) { if (instances.attribute(j).isNumeric()) { vals2[j] = Math.sqrt(tempI[i].variance(j)); } else { vals2[j] = Utils.missingValue(); } } m_ClusterStdDevs.add(new DenseInstance(1.0, vals2)); } m_ClusterSizes[i] = tempI[i].numInstances(); } }
From source file:CGLSMethod.LinearRegression.java
License:Open Source License
/** * Builds a regression model for the given data. * * @param data the training data to be used for generating the * linear regression function//from w w w . ja v a2s . c o m * @throws Exception if the classifier could not be built successfully */ public void buildClassifier(Instances data) throws Exception { // Preprocess instances if (!m_checksTurnedOff) { m_TransformFilter = new NominalToBinary(); m_TransformFilter.setInputFormat(data); data = Filter.useFilter(data, m_TransformFilter); m_MissingFilter = new ReplaceMissingValues(); m_MissingFilter.setInputFormat(data); data = Filter.useFilter(data, m_MissingFilter); data.deleteWithMissingClass(); } else { m_TransformFilter = null; m_MissingFilter = null; } m_ClassIndex = data.classIndex(); m_TransformedData = data; // Turn all attributes on for a start m_SelectedAttributes = new boolean[data.numAttributes()]; for (int i = 0; i < data.numAttributes(); i++) { if (i != m_ClassIndex) { m_SelectedAttributes[i] = true; } } m_Coefficients = null; // Compute means and standard deviations m_Means = new double[data.numAttributes()]; m_StdDevs = new double[data.numAttributes()]; for (int j = 0; j < data.numAttributes(); j++) { if (j != data.classIndex()) { m_Means[j] = data.meanOrMode(j); m_StdDevs[j] = Math.sqrt(data.variance(j)); if (m_StdDevs[j] == 0) { m_SelectedAttributes[j] = false; } } } m_ClassStdDev = Math.sqrt(data.variance(m_TransformedData.classIndex())); m_ClassMean = data.meanOrMode(m_TransformedData.classIndex()); // Perform the regression findBestModel(); // Save memory m_TransformedData = new Instances(data, 0); }
From source file:Classifier.supervised.LinearRegression.java
License:Open Source License
/** * Builds a regression model for the given data. * * @param data the training data to be used for generating the * linear regression function/*from w w w. j a va2 s . com*/ * @throws Exception if the classifier could not be built successfully */ public void buildClassifier(Instances data) throws Exception { m_ModelBuilt = false; if (!m_checksTurnedOff) { // can classifier handle the data? getCapabilities().testWithFail(data); // remove instances with missing class data = new Instances(data); data.deleteWithMissingClass(); } // Preprocess instances if (!m_checksTurnedOff) { m_TransformFilter = new NominalToBinary(); m_TransformFilter.setInputFormat(data); data = Filter.useFilter(data, m_TransformFilter); m_MissingFilter = new ReplaceMissingValues(); m_MissingFilter.setInputFormat(data); data = Filter.useFilter(data, m_MissingFilter); data.deleteWithMissingClass(); } else { m_TransformFilter = null; m_MissingFilter = null; } m_ClassIndex = data.classIndex(); m_TransformedData = data; // Turn all attributes on for a start m_SelectedAttributes = new boolean[data.numAttributes()]; for (int i = 0; i < data.numAttributes(); i++) { if (i != m_ClassIndex) { m_SelectedAttributes[i] = true; } } m_Coefficients = null; // Compute means and standard deviations m_Means = new double[data.numAttributes()]; m_StdDevs = new double[data.numAttributes()]; for (int j = 0; j < data.numAttributes(); j++) { if (j != data.classIndex()) { m_Means[j] = data.meanOrMode(j); m_StdDevs[j] = Math.sqrt(data.variance(j)); if (m_StdDevs[j] == 0) { m_SelectedAttributes[j] = false; } } } m_ClassStdDev = Math.sqrt(data.variance(m_TransformedData.classIndex())); m_ClassMean = data.meanOrMode(m_TransformedData.classIndex()); // Perform the regression findBestModel(); // Save memory if (m_Minimal) { m_TransformedData = null; m_Means = null; m_StdDevs = null; } else { m_TransformedData = new Instances(data, 0); } m_ModelBuilt = true; }
From source file:cn.edu.xmu.dm.d3c.clustering.SimpleKMeans.java
License:Open Source License
/** * Generates a clusterer. Has to initialize all fields of the clusterer * that are not being set via options./*from w ww.j av a 2s. c o m*/ * * @param data set of instances serving as training data * @throws Exception if the clusterer has not been * generated successfully */ public void buildClusterer(Instances data) throws Exception { // can clusterer handle the data? getCapabilities().testWithFail(data); m_Iterations = 0; m_ReplaceMissingFilter = new ReplaceMissingValues(); Instances instances = new Instances(data); instances.setClassIndex(-1); if (!m_dontReplaceMissing) { m_ReplaceMissingFilter.setInputFormat(instances); instances = Filter.useFilter(instances, m_ReplaceMissingFilter); } m_FullMissingCounts = new int[instances.numAttributes()]; if (m_displayStdDevs) { m_FullStdDevs = new double[instances.numAttributes()]; } m_FullNominalCounts = new int[instances.numAttributes()][0]; m_FullMeansOrMediansOrModes = moveCentroid(0, instances, false); for (int i = 0; i < instances.numAttributes(); i++) { m_FullMissingCounts[i] = instances.attributeStats(i).missingCount; if (instances.attribute(i).isNumeric()) { if (m_displayStdDevs) { m_FullStdDevs[i] = Math.sqrt(instances.variance(i)); } if (m_FullMissingCounts[i] == instances.numInstances()) { m_FullMeansOrMediansOrModes[i] = Double.NaN; // mark missing as mean } } else { m_FullNominalCounts[i] = instances.attributeStats(i).nominalCounts; if (m_FullMissingCounts[i] > m_FullNominalCounts[i][Utils.maxIndex(m_FullNominalCounts[i])]) { m_FullMeansOrMediansOrModes[i] = -1; // mark missing as most common value } } } m_ClusterCentroids = new Instances(instances, m_NumClusters); int[] clusterAssignments = new int[instances.numInstances()]; if (m_PreserveOrder) m_Assignments = clusterAssignments; m_DistanceFunction.setInstances(instances); Random RandomO = new Random(getSeed()); int instIndex; HashMap initC = new HashMap(); DecisionTableHashKey hk = null; Instances initInstances = null; if (m_PreserveOrder) initInstances = new Instances(instances); else initInstances = instances; if (m_initializeWithKMeansPlusPlus) { kMeansPlusPlusInit(initInstances); } else { for (int j = initInstances.numInstances() - 1; j >= 0; j--) { instIndex = RandomO.nextInt(j + 1); hk = new DecisionTableHashKey(initInstances.instance(instIndex), initInstances.numAttributes(), true); if (!initC.containsKey(hk)) { m_ClusterCentroids.add(initInstances.instance(instIndex)); initC.put(hk, null); } initInstances.swap(j, instIndex); if (m_ClusterCentroids.numInstances() == m_NumClusters) { break; } } } m_NumClusters = m_ClusterCentroids.numInstances(); //removing reference initInstances = null; int i; boolean converged = false; int emptyClusterCount; Instances[] tempI = new Instances[m_NumClusters]; m_squaredErrors = new double[m_NumClusters]; m_ClusterNominalCounts = new int[m_NumClusters][instances.numAttributes()][0]; m_ClusterMissingCounts = new int[m_NumClusters][instances.numAttributes()]; while (!converged) { emptyClusterCount = 0; m_Iterations++; converged = true; for (i = 0; i < instances.numInstances(); i++) { Instance toCluster = instances.instance(i); int newC = clusterProcessedInstance(toCluster, false, true); if (newC != clusterAssignments[i]) { converged = false; } clusterAssignments[i] = newC; } // update centroids m_ClusterCentroids = new Instances(instances, m_NumClusters); for (i = 0; i < m_NumClusters; i++) { tempI[i] = new Instances(instances, 0); } for (i = 0; i < instances.numInstances(); i++) { tempI[clusterAssignments[i]].add(instances.instance(i)); } for (i = 0; i < m_NumClusters; i++) { if (tempI[i].numInstances() == 0) { // empty cluster emptyClusterCount++; } else { moveCentroid(i, tempI[i], true); } } if (emptyClusterCount > 0) { m_NumClusters -= emptyClusterCount; if (converged) { Instances[] t = new Instances[m_NumClusters]; int index = 0; for (int k = 0; k < tempI.length; k++) { if (tempI[k].numInstances() > 0) { t[index++] = tempI[k]; } } tempI = t; } else { tempI = new Instances[m_NumClusters]; } } if (m_Iterations == m_MaxIterations) converged = true; if (!converged) { m_ClusterNominalCounts = new int[m_NumClusters][instances.numAttributes()][0]; } } // calculate errors if (!m_FastDistanceCalc) { for (i = 0; i < instances.numInstances(); i++) { clusterProcessedInstance(instances.instance(i), true, false); } } if (m_displayStdDevs) { m_ClusterStdDevs = new Instances(instances, m_NumClusters); } m_ClusterSizes = new int[m_NumClusters]; for (i = 0; i < m_NumClusters; i++) { if (m_displayStdDevs) { double[] vals2 = new double[instances.numAttributes()]; for (int j = 0; j < instances.numAttributes(); j++) { if (instances.attribute(j).isNumeric()) { vals2[j] = Math.sqrt(tempI[i].variance(j)); } else { vals2[j] = Utils.missingValue(); } } m_ClusterStdDevs.add(new DenseInstance(1.0, vals2)); } m_ClusterSizes[i] = tempI[i].numInstances(); } }
From source file:de.ugoe.cs.cpdp.dataprocessing.NormalizationUtil.java
License:Apache License
/** * <p>//from ww w . j a va 2 s . co m * Z-Score normalization (N2 in Transfer Defect Learning by Nam et al.). * </p> * * @param data * data that is normalized */ public static void zScore(Instances data) { final double[] mean = new double[data.numAttributes()]; final double[] std = new double[data.numAttributes()]; // get means and stddevs of data for (int j = 0; j < data.numAttributes(); j++) { if (data.classIndex() != j) { mean[j] = data.meanOrMode(j); std[j] = Math.sqrt(data.variance(j)); } } applyZScore(data, mean, std); }
From source file:de.ugoe.cs.cpdp.dataprocessing.NormalizationUtil.java
License:Apache License
/** * <p>/*w w w . j a va 2s . c o m*/ * Z-Score normalization using the mean and std of the training data (N3 in Transfer Defect * Learning by Nam et al.). * </p> * * @param testdata * test data of the target product * @param traindata * training data */ public static void zScoreTraining(Instances testdata, Instances traindata) { final double[] mean = new double[testdata.numAttributes()]; final double[] std = new double[testdata.numAttributes()]; // get means of training for (int j = 0; j < traindata.numAttributes(); j++) { if (traindata.classIndex() != j) { mean[j] = traindata.meanOrMode(j); std[j] = Math.sqrt(traindata.variance(j)); } } applyZScore(testdata, mean, std); applyZScore(traindata, mean, std); }
From source file:de.ugoe.cs.cpdp.dataprocessing.NormalizationUtil.java
License:Apache License
/** * <p>//from w w w . j a v a2 s .co m * Z-Score normalization using the mean and std of the test data (N4 in Transfer Defect Learning * by Nam et al.). * </p> * * @param testdata * test data of the target product * @param traindata * training data */ public static void zScoreTarget(Instances testdata, Instances traindata) { final double[] mean = new double[testdata.numAttributes()]; final double[] std = new double[testdata.numAttributes()]; // get means of testdata for (int j = 0; j < testdata.numAttributes(); j++) { if (testdata.classIndex() != j) { mean[j] = testdata.meanOrMode(j); std[j] = Math.sqrt(testdata.variance(j)); } } applyZScore(testdata, mean, std); applyZScore(traindata, mean, std); }