List of usage examples for weka.filters.unsupervised.attribute Remove input
@Override public boolean input(Instance instance)
From source file:core.ClusterEvaluationEX.java
License:Open Source License
/** * Evaluates a clusterer with the options given in an array of * strings. It takes the string indicated by "-t" as training file, the * string indicated by "-T" as test file. * If the test file is missing, a stratified ten-fold * cross-validation is performed (distribution clusterers only). * Using "-x" you can change the number of * folds to be used, and using "-s" the random seed. * If the "-p" option is present it outputs the classification for * each test instance. If you provide the name of an object file using * "-l", a clusterer will be loaded from the given file. If you provide the * name of an object file using "-d", the clusterer built from the * training data will be saved to the given file. * * @param clusterer machine learning clusterer * @param options the array of string containing the options * @throws Exception if model could not be evaluated successfully * @return a string describing the results *///from w w w .ja va2 s .c o m public static String evaluateClusterer(Clusterer clusterer, String[] options) throws Exception { int seed = 1, folds = 10; boolean doXval = false; Instances train = null; Random random; String trainFileName, testFileName, seedString, foldsString; String objectInputFileName, objectOutputFileName, attributeRangeString; String graphFileName; String[] savedOptions = null; boolean printClusterAssignments = false; Range attributesToOutput = null; StringBuffer text = new StringBuffer(); int theClass = -1; // class based evaluation of clustering boolean updateable = (clusterer instanceof UpdateableClusterer); DataSource source = null; Instance inst; if (Utils.getFlag('h', options) || Utils.getFlag("help", options)) { // global info requested as well? boolean globalInfo = Utils.getFlag("synopsis", options) || Utils.getFlag("info", options); throw new Exception("Help requested." + makeOptionString(clusterer, globalInfo)); } try { // Get basic options (options the same for all clusterers //printClusterAssignments = Utils.getFlag('p', options); objectInputFileName = Utils.getOption('l', options); objectOutputFileName = Utils.getOption('d', options); trainFileName = Utils.getOption('t', options); testFileName = Utils.getOption('T', options); graphFileName = Utils.getOption('g', options); // Check -p option try { attributeRangeString = Utils.getOption('p', options); } catch (Exception e) { throw new Exception(e.getMessage() + "\nNOTE: the -p option has changed. " + "It now expects a parameter specifying a range of attributes " + "to list with the predictions. Use '-p 0' for none."); } if (attributeRangeString.length() != 0) { printClusterAssignments = true; if (!attributeRangeString.equals("0")) attributesToOutput = new Range(attributeRangeString); } if (trainFileName.length() == 0) { if (objectInputFileName.length() == 0) { throw new Exception("No training file and no object " + "input file given."); } if (testFileName.length() == 0) { throw new Exception("No training file and no test file given."); } } else { if ((objectInputFileName.length() != 0) && (printClusterAssignments == false)) { throw new Exception("Can't use both train and model file " + "unless -p specified."); } } seedString = Utils.getOption('s', options); if (seedString.length() != 0) { seed = Integer.parseInt(seedString); } foldsString = Utils.getOption('x', options); if (foldsString.length() != 0) { folds = Integer.parseInt(foldsString); doXval = true; } } catch (Exception e) { throw new Exception('\n' + e.getMessage() + makeOptionString(clusterer, false)); } try { if (trainFileName.length() != 0) { source = new DataSource(trainFileName); train = source.getStructure(); String classString = Utils.getOption('c', options); if (classString.length() != 0) { if (classString.compareTo("last") == 0) theClass = train.numAttributes(); else if (classString.compareTo("first") == 0) theClass = 1; else theClass = Integer.parseInt(classString); if (theClass != -1) { if (doXval || testFileName.length() != 0) throw new Exception("Can only do class based evaluation on the " + "training data"); if (objectInputFileName.length() != 0) throw new Exception("Can't load a clusterer and do class based " + "evaluation"); if (objectOutputFileName.length() != 0) throw new Exception("Can't do class based evaluation and save clusterer"); } } else { // if the dataset defines a class attribute, use it if (train.classIndex() != -1) { theClass = train.classIndex() + 1; System.err .println("Note: using class attribute from dataset, i.e., attribute #" + theClass); } } if (theClass != -1) { if (theClass < 1 || theClass > train.numAttributes()) throw new Exception("Class is out of range!"); if (!train.attribute(theClass - 1).isNominal()) throw new Exception("Class must be nominal!"); train.setClassIndex(theClass - 1); } } } catch (Exception e) { throw new Exception("ClusterEvaluation: " + e.getMessage() + '.'); } // Save options if (options != null) { savedOptions = new String[options.length]; System.arraycopy(options, 0, savedOptions, 0, options.length); } if (objectInputFileName.length() != 0) Utils.checkForRemainingOptions(options); // Set options for clusterer if (clusterer instanceof OptionHandler) ((OptionHandler) clusterer).setOptions(options); Utils.checkForRemainingOptions(options); Instances trainHeader = train; if (objectInputFileName.length() != 0) { // Load the clusterer from file // clusterer = (Clusterer) SerializationHelper.read(objectInputFileName); java.io.ObjectInputStream ois = new java.io.ObjectInputStream( new java.io.BufferedInputStream(new java.io.FileInputStream(objectInputFileName))); clusterer = (Clusterer) ois.readObject(); // try and get the training header try { trainHeader = (Instances) ois.readObject(); } catch (Exception ex) { // don't moan if we cant } } else { // Build the clusterer if no object file provided if (theClass == -1) { if (updateable) { clusterer.buildClusterer(source.getStructure()); while (source.hasMoreElements(train)) { inst = source.nextElement(train); ((UpdateableClusterer) clusterer).updateClusterer(inst); } ((UpdateableClusterer) clusterer).updateFinished(); } else { clusterer.buildClusterer(source.getDataSet()); } } else { Remove removeClass = new Remove(); removeClass.setAttributeIndices("" + theClass); removeClass.setInvertSelection(false); removeClass.setInputFormat(train); if (updateable) { Instances clusterTrain = Filter.useFilter(train, removeClass); clusterer.buildClusterer(clusterTrain); trainHeader = clusterTrain; while (source.hasMoreElements(train)) { inst = source.nextElement(train); removeClass.input(inst); removeClass.batchFinished(); Instance clusterTrainInst = removeClass.output(); ((UpdateableClusterer) clusterer).updateClusterer(clusterTrainInst); } ((UpdateableClusterer) clusterer).updateFinished(); } else { Instances clusterTrain = Filter.useFilter(source.getDataSet(), removeClass); clusterer.buildClusterer(clusterTrain); trainHeader = clusterTrain; } ClusterEvaluationEX ce = new ClusterEvaluationEX(); ce.setClusterer(clusterer); ce.evaluateClusterer(train, trainFileName); return "\n\n=== Clustering stats for training data ===\n\n" + ce.clusterResultsToString(); } } /* Output cluster predictions only (for the test data if specified, otherwise for the training data */ if (printClusterAssignments) { return printClusterings(clusterer, trainFileName, testFileName, attributesToOutput); } text.append(clusterer.toString()); text.append( "\n\n=== Clustering stats for training data ===\n\n" + printClusterStats(clusterer, trainFileName)); if (testFileName.length() != 0) { // check header compatibility DataSource test = new DataSource(testFileName); Instances testStructure = test.getStructure(); if (!trainHeader.equalHeaders(testStructure)) { throw new Exception("Training and testing data are not compatible\n"); } text.append("\n\n=== Clustering stats for testing data ===\n\n" + printClusterStats(clusterer, testFileName)); } if ((clusterer instanceof DensityBasedClusterer) && (doXval == true) && (testFileName.length() == 0) && (objectInputFileName.length() == 0)) { // cross validate the log likelihood on the training data random = new Random(seed); random.setSeed(seed); train = source.getDataSet(); train.randomize(random); text.append(crossValidateModel(clusterer.getClass().getName(), train, folds, savedOptions, random)); } // Save the clusterer if an object output file is provided if (objectOutputFileName.length() != 0) { //SerializationHelper.write(objectOutputFileName, clusterer); saveClusterer(objectOutputFileName, clusterer, trainHeader); } // If classifier is drawable output string describing graph if ((clusterer instanceof Drawable) && (graphFileName.length() != 0)) { BufferedWriter writer = new BufferedWriter(new FileWriter(graphFileName)); writer.write(((Drawable) clusterer).graph()); writer.newLine(); writer.flush(); writer.close(); } return text.toString(); }
From source file:edu.oregonstate.eecs.mcplan.abstraction.EvaluateSimilarityFunction.java
License:Open Source License
public static ClusterContingencyTable evaluateClassifier(final Classifier classifier, final Instances test) { try {//from ww w.j av a 2 s . c o m final Map<Integer, Set<RealVector>> Umap = new TreeMap<Integer, Set<RealVector>>(); final Map<Integer, Set<RealVector>> Vmap = new TreeMap<Integer, Set<RealVector>>(); final Remove rm_filter = new Remove(); rm_filter.setAttributeIndicesArray(new int[] { test.classIndex() }); rm_filter.setInputFormat(test); for (final Instance i : test) { rm_filter.input(i); final double[] phi = rm_filter.output().toDoubleArray(); // final double[] phi = WekaUtil.unlabeledFeatures( i ); final int cluster = (int) classifier.classifyInstance(i); Set<RealVector> u = Umap.get(cluster); if (u == null) { u = new HashSet<RealVector>(); Umap.put(cluster, u); } u.add(new ArrayRealVector(phi)); final int true_label = (int) i.classValue(); Set<RealVector> v = Vmap.get(true_label); if (v == null) { v = new HashSet<RealVector>(); Vmap.put(true_label, v); } v.add(new ArrayRealVector(phi)); } final ArrayList<Set<RealVector>> U = new ArrayList<Set<RealVector>>(); for (final Map.Entry<Integer, Set<RealVector>> e : Umap.entrySet()) { U.add(e.getValue()); } final ArrayList<Set<RealVector>> V = new ArrayList<Set<RealVector>>(); for (final Map.Entry<Integer, Set<RealVector>> e : Vmap.entrySet()) { V.add(e.getValue()); } return new ClusterContingencyTable(U, V); } catch (final RuntimeException ex) { throw ex; } catch (final Exception ex) { throw new RuntimeException(ex); } }
From source file:mulan.transformations.regression.ChainTransformation.java
License:Open Source License
/** * Transforms a single Instance in the same way as * {@link #transformInstance(Instance, int[], int)} transforms an Instances object. * /* www . j a v a 2 s . c o m*/ * @param instance the input instance * @param chain a chain (permutation) of the indices of the target attributes * @param numTargetsToKeep the number of target attributes from the beginning of the chain that * should be kept, 1<=numTargetsToKeep<=numOfTargets * @return the transformed Instance object. The input object is not modified. * @throws Exception Potential exception thrown. To be handled in an upper level. */ public static Instance transformInstance(Instance instance, int[] chain, int numTargetsToKeep) throws Exception { int numOfTargets = chain.length; // Indices of attributes to remove int[] indicesToRemove = new int[numOfTargets - numTargetsToKeep]; for (int i = 0; i < numOfTargets - numTargetsToKeep; i++) { indicesToRemove[i] = chain[numTargetsToKeep + i]; } Remove remove = new Remove(); remove.setAttributeIndicesArray(indicesToRemove); remove.setInputFormat(instance.dataset()); remove.input(instance); remove.batchFinished(); Instance transformed = remove.output(); return transformed; }