List of usage examples for weka.core Instances deleteWithMissingClass
public void deleteWithMissingClass()
From source file:ann.SingleLayerPerceptron.java
@Override public void buildClassifier(Instances data) throws Exception { // can classifier handle the data? getCapabilities().testWithFail(data); annOptions = new ANNOptions(); annOptions = annOptions.loadConfiguration(); output = new ArrayList<Neuron>(); normalize = new Normalize(); ntb = new NominalToBinary(); output = annOptions.output;/* w w w .j a v a 2 s .c o m*/ // remove instances with missing class data = new Instances(data); data.deleteWithMissingClass(); //nominal to binary filter ntb.setInputFormat(data); data = new Instances(Filter.useFilter(data, ntb)); //normalize filter normalize.setInputFormat(data); data = new Instances(Filter.useFilter(data, normalize)); // do main function doPerceptron(data); }
From source file:ann.SingleLayerPerceptron.java
public int[] classifyInstances(Instances data) throws Exception { int[] classValue = new int[data.numInstances()]; // remove instances with missing class data = new Instances(data); data.deleteWithMissingClass(); //nominal to binary filter ntb.setInputFormat(data);/* w w w . j av a2 s. c o m*/ data = new Instances(Filter.useFilter(data, ntb)); int right = 0; for (int i = 0; i < data.numInstances(); i++) { int outputSize = output.size(); double[] result = new double[outputSize]; for (int j = 0; j < outputSize; j++) { result[j] = 0.0; for (int k = 0; k < data.numAttributes(); k++) { double input = 1; if (k < data.numAttributes() - 1) { input = data.instance(i).value(k); } result[j] += output.get(j).weights.get(k) * input; } result[j] = Util.activationFunction(result[j], annOptions); } if (outputSize >= 2) { for (int j = 0; j < outputSize; j++) { if (result[j] > result[classValue[i]]) { classValue[i] = j; } } } else { classValue[i] = (int) result[0]; } double target = data.instance(i).classValue(); double output = classValue[i]; System.out.println("Intance-" + i + " target: " + target + " output: " + output); if (target == output) { right = right + 1; } } System.out.println("Percentage: " + ((double) right / (double) data.numInstances())); return classValue; }
From source file:boosting.classifiers.DecisionStumpWritable.java
License:Open Source License
/** * Generates the classifier.// w w w .j a v a 2s .co m * * @param instances set of instances serving as training data * @throws Exception if the classifier has not been generated successfully */ public void buildClassifier(Instances instances) throws Exception { double bestVal = Double.MAX_VALUE, currVal; double bestPoint = -Double.MAX_VALUE; int bestAtt = -1, numClasses; // can classifier handle the data? getCapabilities().testWithFail(instances); // remove instances with missing class instances = new Instances(instances); instances.deleteWithMissingClass(); // only class? -> build ZeroR model if (instances.numAttributes() == 1) { System.err.println( "Cannot build model (only class attribute present in data!), " + "using ZeroR model instead!"); m_ZeroR = new weka.classifiers.rules.ZeroR(); m_ZeroR.buildClassifier(instances); return; } else { m_ZeroR = null; } double[][] bestDist = new double[3][instances.numClasses()]; m_Instances = new Instances(instances); if (m_Instances.classAttribute().isNominal()) { numClasses = m_Instances.numClasses(); } else { numClasses = 1; } // For each attribute boolean first = true; for (int i = 0; i < m_Instances.numAttributes(); i++) { if (i != m_Instances.classIndex()) { // Reserve space for distribution. m_Distribution = new double[3][numClasses]; // Compute value of criterion for best split on attribute if (m_Instances.attribute(i).isNominal()) { currVal = findSplitNominal(i); } else { currVal = findSplitNumeric(i); } if ((first) || (currVal < bestVal)) { bestVal = currVal; bestAtt = i; bestPoint = m_SplitPoint; for (int j = 0; j < 3; j++) { System.arraycopy(m_Distribution[j], 0, bestDist[j], 0, numClasses); } } // First attribute has been investigated first = false; } } // Set attribute, split point and distribution. m_AttIndex = bestAtt; m_SplitPoint = bestPoint; m_Distribution = bestDist; if (m_Instances.classAttribute().isNominal()) { for (int i = 0; i < m_Distribution.length; i++) { double sumCounts = Utils.sum(m_Distribution[i]); if (sumCounts == 0) { // This means there were only missing attribute values System.arraycopy(m_Distribution[2], 0, m_Distribution[i], 0, m_Distribution[2].length); Utils.normalize(m_Distribution[i]); } else { Utils.normalize(m_Distribution[i], sumCounts); } } } // Save memory m_Instances = new Instances(m_Instances, 0); }
From source file:br.com.ufu.lsi.rebfnetwork.RBFModel.java
License:Open Source License
/** * Method used to pre-process the data, perform clustering, and * set the initial parameter vector.//from ww w .j ava2 s.c o m */ protected Instances initializeClassifier(Instances data) throws Exception { // can classifier handle the data? getCapabilities().testWithFail(data); data = new Instances(data); data.deleteWithMissingClass(); // Make sure data is shuffled Random random = new Random(m_Seed); if (data.numInstances() > 2) { random = data.getRandomNumberGenerator(m_Seed); } data.randomize(random); double y0 = data.instance(0).classValue(); // This stuff is not relevant in classification case int index = 1; while (index < data.numInstances() && data.instance(index).classValue() == y0) { index++; } if (index == data.numInstances()) { // degenerate case, all class values are equal // we don't want to deal with this, too much hassle throw new Exception("All class values are the same. At least two class values should be different"); } double y1 = data.instance(index).classValue(); // Replace missing values m_ReplaceMissingValues = new ReplaceMissingValues(); m_ReplaceMissingValues.setInputFormat(data); data = Filter.useFilter(data, m_ReplaceMissingValues); // Remove useless attributes m_AttFilter = new RemoveUseless(); m_AttFilter.setInputFormat(data); data = Filter.useFilter(data, m_AttFilter); // only class? -> build ZeroR model if (data.numAttributes() == 1) { System.err.println( "Cannot build model (only class attribute present in data after removing useless attributes!), " + "using ZeroR model instead!"); m_ZeroR = new weka.classifiers.rules.ZeroR(); m_ZeroR.buildClassifier(data); return data; } else { m_ZeroR = null; } // Transform attributes m_NominalToBinary = new NominalToBinary(); m_NominalToBinary.setInputFormat(data); data = Filter.useFilter(data, m_NominalToBinary); m_Filter = new Normalize(); ((Normalize) m_Filter).setIgnoreClass(true); m_Filter.setInputFormat(data); data = Filter.useFilter(data, m_Filter); double z0 = data.instance(0).classValue(); // This stuff is not relevant in classification case double z1 = data.instance(index).classValue(); m_x1 = (y0 - y1) / (z0 - z1); // no division by zero, since y0 != y1 guaranteed => z0 != z1 ??? m_x0 = (y0 - m_x1 * z0); // = y1 - m_x1 * z1 m_classIndex = data.classIndex(); m_numClasses = data.numClasses(); m_numAttributes = data.numAttributes(); // Run k-means SimpleKMeans skm = new SimpleKMeans(); skm.setMaxIterations(10000); skm.setNumClusters(m_numUnits); Remove rm = new Remove(); data.setClassIndex(-1); rm.setAttributeIndices((m_classIndex + 1) + ""); rm.setInputFormat(data); Instances dataRemoved = Filter.useFilter(data, rm); data.setClassIndex(m_classIndex); skm.buildClusterer(dataRemoved); Instances centers = skm.getClusterCentroids(); if (centers.numInstances() < m_numUnits) { m_numUnits = centers.numInstances(); } // Set up arrays OFFSET_WEIGHTS = 0; if (m_useAttributeWeights) { OFFSET_ATTRIBUTE_WEIGHTS = (m_numUnits + 1) * m_numClasses; OFFSET_CENTERS = OFFSET_ATTRIBUTE_WEIGHTS + m_numAttributes; } else { OFFSET_ATTRIBUTE_WEIGHTS = -1; OFFSET_CENTERS = (m_numUnits + 1) * m_numClasses; } OFFSET_SCALES = OFFSET_CENTERS + m_numUnits * m_numAttributes; switch (m_scaleOptimizationOption) { case USE_GLOBAL_SCALE: m_RBFParameters = new double[OFFSET_SCALES + 1]; break; case USE_SCALE_PER_UNIT_AND_ATTRIBUTE: m_RBFParameters = new double[OFFSET_SCALES + m_numUnits * m_numAttributes]; break; default: m_RBFParameters = new double[OFFSET_SCALES + m_numUnits]; break; } // Set initial radius based on distance to nearest other basis function double maxMinDist = -1; for (int i = 0; i < centers.numInstances(); i++) { double minDist = Double.MAX_VALUE; for (int j = i + 1; j < centers.numInstances(); j++) { double dist = 0; for (int k = 0; k < centers.numAttributes(); k++) { if (k != centers.classIndex()) { double diff = centers.instance(i).value(k) - centers.instance(j).value(k); dist += diff * diff; } } if (dist < minDist) { minDist = dist; } } if ((minDist != Double.MAX_VALUE) && (minDist > maxMinDist)) { maxMinDist = minDist; } } // Initialize parameters if (m_scaleOptimizationOption == USE_GLOBAL_SCALE) { m_RBFParameters[OFFSET_SCALES] = Math.sqrt(maxMinDist); } for (int i = 0; i < m_numUnits; i++) { if (m_scaleOptimizationOption == USE_SCALE_PER_UNIT) { m_RBFParameters[OFFSET_SCALES + i] = Math.sqrt(maxMinDist); } int k = 0; for (int j = 0; j < m_numAttributes; j++) { if (k == centers.classIndex()) { k++; } if (j != data.classIndex()) { if (m_scaleOptimizationOption == USE_SCALE_PER_UNIT_AND_ATTRIBUTE) { m_RBFParameters[OFFSET_SCALES + (i * m_numAttributes + j)] = Math.sqrt(maxMinDist); } m_RBFParameters[OFFSET_CENTERS + (i * m_numAttributes) + j] = centers.instance(i).value(k); k++; } } } if (m_useAttributeWeights) { for (int j = 0; j < m_numAttributes; j++) { if (j != data.classIndex()) { m_RBFParameters[OFFSET_ATTRIBUTE_WEIGHTS + j] = 1.0; } } } initializeOutputLayer(random); return data; }
From source file:br.com.ufu.lsi.rebfnetwork.RBFNetwork.java
License:Open Source License
/** * Builds the classifier/*from w w w . ja va 2 s . co m*/ * * @param instances the training data * @throws Exception if the classifier could not be built 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(); // only class? -> build ZeroR model if (instances.numAttributes() == 1) { System.err.println( "Cannot build model (only class attribute present in data!), " + "using ZeroR model instead!"); m_ZeroR = new weka.classifiers.rules.ZeroR(); m_ZeroR.buildClassifier(instances); return; } else { m_ZeroR = null; } m_standardize = new Standardize(); m_standardize.setInputFormat(instances); instances = Filter.useFilter(instances, m_standardize); SimpleKMeans sk = new SimpleKMeans(); sk.setNumClusters(m_numClusters); sk.setSeed(m_clusteringSeed); MakeDensityBasedClusterer dc = new MakeDensityBasedClusterer(); dc.setClusterer(sk); dc.setMinStdDev(m_minStdDev); m_basisFilter = new ClusterMembership(); m_basisFilter.setDensityBasedClusterer(dc); m_basisFilter.setInputFormat(instances); Instances transformed = Filter.useFilter(instances, m_basisFilter); if (instances.classAttribute().isNominal()) { m_linear = null; m_logistic = new Logistic(); m_logistic.setRidge(m_ridge); m_logistic.setMaxIts(m_maxIts); m_logistic.buildClassifier(transformed); } else { m_logistic = null; m_linear = new LinearRegression(); m_linear.setAttributeSelectionMethod( new SelectedTag(LinearRegression.SELECTION_NONE, LinearRegression.TAGS_SELECTION)); m_linear.setRidge(m_ridge); m_linear.buildClassifier(transformed); } }
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/*w w w. j a v a2 s .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 . ja 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:classifiers.mlp.MultilayerPerceptronCustom.java
License:Open Source License
/** * Call this function to build and train a neural network for the training * data provided./* w ww . j a va2 s . c o m*/ * @param i The training data. * @throws Exception if can't build classification properly. */ public void buildClassifier(Instances i) throws Exception { // can classifier handle the data? getCapabilities().testWithFail(i); // remove instances with missing class i = new Instances(i); i.deleteWithMissingClass(); m_ZeroR = new weka.classifiers.rules.ZeroR(); m_ZeroR.buildClassifier(i); // only class? -> use ZeroR model if (i.numAttributes() == 1) { System.err.println( "Cannot build model (only class attribute present in data!), " + "using ZeroR model instead!"); m_useDefaultModel = true; return; } else { m_useDefaultModel = false; } m_epoch = 0; m_error = 0; m_instances = null; m_currentInstance = null; m_controlPanel = null; m_nodePanel = null; m_outputs = new NeuralEnd[0]; m_inputs = new NeuralEnd[0]; m_numAttributes = 0; m_numClasses = 0; m_neuralNodes = new NeuralConnection[0]; m_selected = new FastVector(4); m_graphers = new FastVector(2); m_nextId = 0; m_stopIt = true; m_stopped = true; m_accepted = false; m_instances = new Instances(i); m_random = new Random(m_randomSeed); m_instances.randomize(m_random); if (m_useNomToBin) { m_nominalToBinaryFilter = new NominalToBinary(); m_nominalToBinaryFilter.setInputFormat(m_instances); m_instances = Filter.useFilter(m_instances, m_nominalToBinaryFilter); } m_numAttributes = m_instances.numAttributes() - 1; m_numClasses = m_instances.numClasses(); setClassType(m_instances); //this sets up the validation set. Instances valSet = null; //numinval is needed later int numInVal = (int) (m_valSize / 100.0 * m_instances.numInstances()); if (m_valSize > 0) { if (numInVal == 0) { numInVal = 1; } valSet = new Instances(m_instances, 0, numInVal); } /////////// setupInputs(); setupOutputs(); if (m_autoBuild) { setupHiddenLayer(); } ///////////////////////////// //this sets up the gui for usage if (m_gui) { m_win = new JFrame(); m_win.addWindowListener(new WindowAdapter() { public void windowClosing(WindowEvent e) { boolean k = m_stopIt; m_stopIt = true; int well = JOptionPane .showConfirmDialog(m_win, "Are You Sure...\n" + "Click Yes To Accept" + " The Neural Network" + "\n Click No To Return", "Accept Neural Network", JOptionPane.YES_NO_OPTION); if (well == 0) { m_win.setDefaultCloseOperation(JFrame.DISPOSE_ON_CLOSE); m_accepted = true; blocker(false); } else { m_win.setDefaultCloseOperation(JFrame.DO_NOTHING_ON_CLOSE); } m_stopIt = k; } }); m_win.getContentPane().setLayout(new BorderLayout()); m_win.setTitle("Neural Network"); m_nodePanel = new NodePanel(); // without the following two lines, the NodePanel.paintComponents(Graphics) // method will go berserk if the network doesn't fit completely: it will // get called on a constant basis, using 100% of the CPU // see the following forum thread: // http://forum.java.sun.com/thread.jspa?threadID=580929&messageID=2945011 m_nodePanel.setPreferredSize(new Dimension(640, 480)); m_nodePanel.revalidate(); JScrollPane sp = new JScrollPane(m_nodePanel, JScrollPane.VERTICAL_SCROLLBAR_ALWAYS, JScrollPane.HORIZONTAL_SCROLLBAR_NEVER); m_controlPanel = new ControlPanel(); m_win.getContentPane().add(sp, BorderLayout.CENTER); m_win.getContentPane().add(m_controlPanel, BorderLayout.SOUTH); m_win.setSize(640, 480); m_win.setVisible(true); } //This sets up the initial state of the gui if (m_gui) { blocker(true); m_controlPanel.m_changeEpochs.setEnabled(false); m_controlPanel.m_changeLearning.setEnabled(false); m_controlPanel.m_changeMomentum.setEnabled(false); } //For silly situations in which the network gets accepted before training //commenses if (m_numeric) { setEndsToLinear(); } if (m_accepted) { m_win.dispose(); m_controlPanel = null; m_nodePanel = null; m_instances = new Instances(m_instances, 0); m_currentInstance = null; return; } //connections done. double right = 0; double driftOff = 0; double lastRight = Double.POSITIVE_INFINITY; double bestError = Double.POSITIVE_INFINITY; double tempRate; double totalWeight = 0; double totalValWeight = 0; double origRate = m_learningRate; //only used for when reset //ensure that at least 1 instance is trained through. if (numInVal == m_instances.numInstances()) { numInVal--; } if (numInVal < 0) { numInVal = 0; } for (int noa = numInVal; noa < m_instances.numInstances(); noa++) { if (!m_instances.instance(noa).classIsMissing()) { totalWeight += m_instances.instance(noa).weight(); } } if (m_valSize != 0) { for (int noa = 0; noa < valSet.numInstances(); noa++) { if (!valSet.instance(noa).classIsMissing()) { totalValWeight += valSet.instance(noa).weight(); } } } m_stopped = false; for (int noa = 1; noa < m_numEpochs + 1; noa++) { right = 0; for (int nob = numInVal; nob < m_instances.numInstances(); nob++) { m_currentInstance = m_instances.instance(nob); if (!m_currentInstance.classIsMissing()) { //this is where the network updating (and training occurs, for the //training set resetNetwork(); calculateOutputs(); tempRate = m_learningRate * m_currentInstance.weight(); if (m_decay) { tempRate /= noa; } right += (calculateErrors() / m_instances.numClasses()) * m_currentInstance.weight(); updateNetworkWeights(tempRate, m_momentum); } } right /= totalWeight; if (Double.isInfinite(right) || Double.isNaN(right)) { if (!m_reset) { m_instances = null; throw new Exception("Network cannot train. Try restarting with a" + " smaller learning rate."); } else { //reset the network if possible if (m_learningRate <= Utils.SMALL) throw new IllegalStateException( "Learning rate got too small (" + m_learningRate + " <= " + Utils.SMALL + ")!"); m_learningRate /= 2; buildClassifier(i); m_learningRate = origRate; m_instances = new Instances(m_instances, 0); m_currentInstance = null; return; } } ////////////////////////do validation testing if applicable if (m_valSize != 0) { right = 0; for (int nob = 0; nob < valSet.numInstances(); nob++) { m_currentInstance = valSet.instance(nob); if (!m_currentInstance.classIsMissing()) { //this is where the network updating occurs, for the validation set resetNetwork(); calculateOutputs(); right += (calculateErrors() / valSet.numClasses()) * m_currentInstance.weight(); //note 'right' could be calculated here just using //the calculate output values. This would be faster. //be less modular } } if (right < lastRight) { if (right < bestError) { bestError = right; // save the network weights at this point for (int noc = 0; noc < m_numClasses; noc++) { m_outputs[noc].saveWeights(); } driftOff = 0; } } else { driftOff++; } lastRight = right; if (driftOff > m_driftThreshold || noa + 1 >= m_numEpochs) { for (int noc = 0; noc < m_numClasses; noc++) { m_outputs[noc].restoreWeights(); } m_accepted = true; } right /= totalValWeight; } m_epoch = noa; m_error = right; //shows what the neuralnet is upto if a gui exists. updateDisplay(); //This junction controls what state the gui is in at the end of each //epoch, Such as if it is paused, if it is resumable etc... if (m_gui) { while ((m_stopIt || (m_epoch >= m_numEpochs && m_valSize == 0)) && !m_accepted) { m_stopIt = true; m_stopped = true; if (m_epoch >= m_numEpochs && m_valSize == 0) { m_controlPanel.m_startStop.setEnabled(false); } else { m_controlPanel.m_startStop.setEnabled(true); } m_controlPanel.m_startStop.setText("Start"); m_controlPanel.m_startStop.setActionCommand("Start"); m_controlPanel.m_changeEpochs.setEnabled(true); m_controlPanel.m_changeLearning.setEnabled(true); m_controlPanel.m_changeMomentum.setEnabled(true); blocker(true); if (m_numeric) { setEndsToLinear(); } } m_controlPanel.m_changeEpochs.setEnabled(false); m_controlPanel.m_changeLearning.setEnabled(false); m_controlPanel.m_changeMomentum.setEnabled(false); m_stopped = false; //if the network has been accepted stop the training loop if (m_accepted) { m_win.dispose(); m_controlPanel = null; m_nodePanel = null; m_instances = new Instances(m_instances, 0); m_currentInstance = null; return; } } if (m_accepted) { m_instances = new Instances(m_instances, 0); m_currentInstance = null; return; } //TODO: // Customization: store the model created after this epoch ObjectOutputStream oos = new ObjectOutputStream(new FileOutputStream("mlp/temp/" + noa + ".model")); oos.writeObject(this); oos.flush(); oos.close(); } if (m_gui) { m_win.dispose(); m_controlPanel = null; m_nodePanel = null; } m_instances = new Instances(m_instances, 0); m_currentInstance = null; }
From source file:cn.edu.xjtu.dbmine.source.NaiveBayes.java
License:Open Source License
/** * Generates the classifier.// www. ja v a2 s .c om * * @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:com.ifmo.recommendersystem.metafeatures.classifierbased.internal.extractors.MultilayerPerceptron.java
License:Open Source License
/** * Call this function to build and train a neural network for the training * data provided.//w w w . j a v a 2 s. c o m * * @param i The training data. * @throws Exception if can't build classification properly. */ @Override public void buildClassifier(Instances i) throws Exception { // can classifier handle the data? getCapabilities().testWithFail(i); // remove instances with missing class i = new Instances(i); i.deleteWithMissingClass(); m_ZeroR = new weka.classifiers.rules.ZeroR(); m_ZeroR.buildClassifier(i); // only class? -> use ZeroR model if (i.numAttributes() == 1) { System.err.println( "Cannot build model (only class attribute present in data!), " + "using ZeroR model instead!"); m_useDefaultModel = true; return; } else { m_useDefaultModel = false; } m_epoch = 0; m_error = 0; m_instances = null; m_currentInstance = null; m_controlPanel = null; m_nodePanel = null; m_outputs = new NeuralEnd[0]; m_inputs = new NeuralEnd[0]; m_numAttributes = 0; m_numClasses = 0; m_neuralNodes = new NeuralConnection[0]; m_selected = new ArrayList<NeuralConnection>(4); m_nextId = 0; m_stopIt = true; m_stopped = true; m_accepted = false; m_instances = new Instances(i); m_random = new Random(m_randomSeed); m_instances.randomize(m_random); if (m_useNomToBin) { m_nominalToBinaryFilter = new NominalToBinary(); m_nominalToBinaryFilter.setInputFormat(m_instances); m_instances = Filter.useFilter(m_instances, m_nominalToBinaryFilter); } m_numAttributes = m_instances.numAttributes() - 1; m_numClasses = m_instances.numClasses(); setClassType(m_instances); // this sets up the validation set. Instances valSet = null; // numinval is needed later int numInVal = (int) (m_valSize / 100.0 * m_instances.numInstances()); if (m_valSize > 0) { if (numInVal == 0) { numInVal = 1; } valSet = new Instances(m_instances, 0, numInVal); } // ///////// setupInputs(); setupOutputs(); if (m_autoBuild) { setupHiddenLayer(); } // /////////////////////////// // this sets up the gui for usage if (m_gui) { m_win = new JFrame(); m_win.addWindowListener(new WindowAdapter() { @Override public void windowClosing(WindowEvent e) { boolean k = m_stopIt; m_stopIt = true; int well = JOptionPane .showConfirmDialog(m_win, "Are You Sure...\n" + "Click Yes To Accept" + " The Neural Network" + "\n Click No To Return", "Accept Neural Network", JOptionPane.YES_NO_OPTION); if (well == 0) { m_win.setDefaultCloseOperation(JFrame.DISPOSE_ON_CLOSE); m_accepted = true; blocker(false); } else { m_win.setDefaultCloseOperation(JFrame.DO_NOTHING_ON_CLOSE); } m_stopIt = k; } }); m_win.getContentPane().setLayout(new BorderLayout()); m_win.setTitle("Neural Network"); m_nodePanel = new NodePanel(); // without the following two lines, the // NodePanel.paintComponents(Graphics) // method will go berserk if the network doesn't fit completely: it will // get called on a constant basis, using 100% of the CPU // see the following forum thread: // http://forum.java.sun.com/thread.jspa?threadID=580929&messageID=2945011 m_nodePanel.setPreferredSize(new Dimension(640, 480)); m_nodePanel.revalidate(); JScrollPane sp = new JScrollPane(m_nodePanel, JScrollPane.VERTICAL_SCROLLBAR_ALWAYS, JScrollPane.HORIZONTAL_SCROLLBAR_NEVER); m_controlPanel = new ControlPanel(); m_win.getContentPane().add(sp, BorderLayout.CENTER); m_win.getContentPane().add(m_controlPanel, BorderLayout.SOUTH); m_win.setSize(640, 480); m_win.setVisible(true); } // This sets up the initial state of the gui if (m_gui) { blocker(true); m_controlPanel.m_changeEpochs.setEnabled(false); m_controlPanel.m_changeLearning.setEnabled(false); m_controlPanel.m_changeMomentum.setEnabled(false); } // For silly situations in which the network gets accepted before training // commenses if (m_numeric) { setEndsToLinear(); } if (m_accepted) { m_win.dispose(); m_controlPanel = null; m_nodePanel = null; m_instances = new Instances(m_instances, 0); m_currentInstance = null; return; } // connections done. double right = 0; double driftOff = 0; double lastRight = Double.POSITIVE_INFINITY; double bestError = Double.POSITIVE_INFINITY; double tempRate; double totalWeight = 0; double totalValWeight = 0; double origRate = m_learningRate; // only used for when reset // ensure that at least 1 instance is trained through. if (numInVal == m_instances.numInstances()) { numInVal--; } if (numInVal < 0) { numInVal = 0; } for (int noa = numInVal; noa < m_instances.numInstances(); noa++) { if (!m_instances.instance(noa).classIsMissing()) { totalWeight += m_instances.instance(noa).weight(); } } if (m_valSize != 0) { for (int noa = 0; noa < valSet.numInstances(); noa++) { if (!valSet.instance(noa).classIsMissing()) { totalValWeight += valSet.instance(noa).weight(); } } } m_stopped = false; for (int noa = 1; noa < m_numEpochs + 1; noa++) { right = 0; for (int nob = numInVal; nob < m_instances.numInstances(); nob++) { m_currentInstance = m_instances.instance(nob); if (!m_currentInstance.classIsMissing()) { // this is where the network updating (and training occurs, for the // training set resetNetwork(); calculateOutputs(); tempRate = m_learningRate * m_currentInstance.weight(); if (m_decay) { tempRate /= noa; } right += (calculateErrors() / m_instances.numClasses()) * m_currentInstance.weight(); updateNetworkWeights(tempRate, m_momentum); } } right /= totalWeight; if (Double.isInfinite(right) || Double.isNaN(right)) { if (!m_reset) { m_instances = null; throw new Exception("Network cannot train. Try restarting with a" + " smaller learning rate."); } else { // reset the network if possible if (m_learningRate <= Utils.SMALL) { throw new IllegalStateException( "Learning rate got too small (" + m_learningRate + " <= " + Utils.SMALL + ")!"); } m_learningRate /= 2; buildClassifier(i); m_learningRate = origRate; m_instances = new Instances(m_instances, 0); m_currentInstance = null; return; } } // //////////////////////do validation testing if applicable if (m_valSize != 0) { right = 0; for (int nob = 0; nob < valSet.numInstances(); nob++) { m_currentInstance = valSet.instance(nob); if (!m_currentInstance.classIsMissing()) { // this is where the network updating occurs, for the validation set resetNetwork(); calculateOutputs(); right += (calculateErrors() / valSet.numClasses()) * m_currentInstance.weight(); // note 'right' could be calculated here just using // the calculate output values. This would be faster. // be less modular } } if (right < lastRight) { if (right < bestError) { bestError = right; // save the network weights at this point for (int noc = 0; noc < m_numClasses; noc++) { m_outputs[noc].saveWeights(); } driftOff = 0; } } else { driftOff++; } lastRight = right; if (driftOff > m_driftThreshold || noa + 1 >= m_numEpochs) { for (int noc = 0; noc < m_numClasses; noc++) { m_outputs[noc].restoreWeights(); } m_accepted = true; } right /= totalValWeight; } m_epoch = noa; m_error = right; // shows what the neuralnet is upto if a gui exists. updateDisplay(); // This junction controls what state the gui is in at the end of each // epoch, Such as if it is paused, if it is resumable etc... if (m_gui) { while ((m_stopIt || (m_epoch >= m_numEpochs && m_valSize == 0)) && !m_accepted) { m_stopIt = true; m_stopped = true; if (m_epoch >= m_numEpochs && m_valSize == 0) { m_controlPanel.m_startStop.setEnabled(false); } else { m_controlPanel.m_startStop.setEnabled(true); } m_controlPanel.m_startStop.setText("Start"); m_controlPanel.m_startStop.setActionCommand("Start"); m_controlPanel.m_changeEpochs.setEnabled(true); m_controlPanel.m_changeLearning.setEnabled(true); m_controlPanel.m_changeMomentum.setEnabled(true); blocker(true); if (m_numeric) { setEndsToLinear(); } } m_controlPanel.m_changeEpochs.setEnabled(false); m_controlPanel.m_changeLearning.setEnabled(false); m_controlPanel.m_changeMomentum.setEnabled(false); m_stopped = false; // if the network has been accepted stop the training loop if (m_accepted) { m_win.dispose(); m_controlPanel = null; m_nodePanel = null; m_instances = new Instances(m_instances, 0); m_currentInstance = null; return; } } if (m_accepted) { m_instances = new Instances(m_instances, 0); m_currentInstance = null; return; } } if (m_gui) { m_win.dispose(); m_controlPanel = null; m_nodePanel = null; } m_instances = new Instances(m_instances, 0); m_currentInstance = null; }