List of usage examples for weka.core Instances numClasses
publicint numClasses()
From source file:BaggingImprove.java
/** * Bagging method./* w ww. j a va2s . com*/ * * @param data the training data to be used for generating the bagged * classifier. * @throws Exception if the classifier could not be built successfully */ public void buildClassifier(Instances data) throws Exception { // can classifier handle the data? getCapabilities().testWithFail(data); // remove instances with missing class data = new Instances(data); //data.deleteWithMissingClass(); super.buildClassifier(data); if (m_CalcOutOfBag && (m_BagSizePercent != 100)) { throw new IllegalArgumentException( "Bag size needs to be 100% if " + "out-of-bag error is to be calculated!"); } //+ System.out.println("Classifier length" + m_Classifiers.length); int bagSize = data.numInstances() * m_BagSizePercent / 100; //+ System.out.println("Bag Size " + bagSize); Random random = new Random(m_Seed); boolean[][] inBag = null; if (m_CalcOutOfBag) { inBag = new boolean[m_Classifiers.length][]; } //+ //inisialisasi nama penamaan model BufferedWriter writer = new BufferedWriter(new FileWriter("Bootstrap.txt")); for (int j = 0; j < m_Classifiers.length; j++) { Instances bagData = null; // create the in-bag dataset if (m_CalcOutOfBag) { inBag[j] = new boolean[data.numInstances()]; //System.out.println("Inbag1 " + inBag[0][1]); //bagData = resampleWithWeights(data, random, inBag[j]); bagData = data.resampleWithWeights(random, inBag[j]); //System.out.println("num after resample " + bagData.numInstances()); //+ // for (int k = 0; k < bagData.numInstances(); k++) { // System.out.println("Bag Data after resample [calc out bag]" + bagData.instance(k)); // } } else { //+ System.out.println("Not m_Calc out of bag"); System.out.println("Please configure code inside!"); bagData = data.resampleWithWeights(random); if (bagSize < data.numInstances()) { bagData.randomize(random); Instances newBagData = new Instances(bagData, 0, bagSize); bagData = newBagData; } } if (m_Classifier instanceof Randomizable) { //+ System.out.println("Randomizable"); ((Randomizable) m_Classifiers[j]).setSeed(random.nextInt()); } //write bootstrap into file writer.write("Bootstrap " + j); writer.newLine(); writer.write(bagData.toString()); writer.newLine(); System.out.println("Berhasil menyimpan bootstrap ke file "); System.out.println("Bootstrap " + j + 1); // textarea.append("\nBootsrap " + (j + 1)); //System.out.println("num instance kedua kali "+bagData.numInstances()); for (int b = 1; b < bagData.numInstances(); b++) { System.out.println("" + bagData.instance(b)); // textarea.append("\n" + bagData.instance(b)); } // //+ // build the classifier m_Classifiers[j].buildClassifier(bagData); // //+ // // SerializationHelper serialization = new SerializationHelper(); // serialization.write("KnnData"+model+".model", m_Classifiers[j]); // System.out.println("Finish write into model"); // model++; } writer.flush(); writer.close(); // calc OOB error? if (getCalcOutOfBag()) { double outOfBagCount = 0.0; double errorSum = 0.0; boolean numeric = data.classAttribute().isNumeric(); for (int i = 0; i < data.numInstances(); i++) { double vote; double[] votes; if (numeric) { votes = new double[1]; } else { votes = new double[data.numClasses()]; } // determine predictions for instance int voteCount = 0; for (int j = 0; j < m_Classifiers.length; j++) { if (inBag[j][i]) { continue; } voteCount++; // double pred = m_Classifiers[j].classifyInstance(data.instance(i)); if (numeric) { // votes[0] += pred; votes[0] = m_Classifiers[j].classifyInstance(data.instance(i)); } else { // votes[(int) pred]++; double[] newProbs = m_Classifiers[j].distributionForInstance(data.instance(i)); //- // for(double a : newProbs) // { // System.out.println("Double new probs %.f "+a); // } // average the probability estimates for (int k = 0; k < newProbs.length; k++) { votes[k] += newProbs[k]; } } } System.out.println("Vote count %d" + voteCount); // "vote" if (numeric) { vote = votes[0]; if (voteCount > 0) { vote /= voteCount; // average } } else { if (Utils.eq(Utils.sum(votes), 0)) { } else { Utils.normalize(votes); } vote = Utils.maxIndex(votes); // predicted class //- System.out.println("Vote " + vote); } // error for instance outOfBagCount += data.instance(i).weight(); if (numeric) { errorSum += StrictMath.abs(vote - data.instance(i).classValue()) * data.instance(i).weight(); } else if (vote != data.instance(i).classValue()) { //+ System.out.println("Vote terakhir" + data.instance(i).classValue()); errorSum += data.instance(i).weight(); } } m_OutOfBagError = errorSum / outOfBagCount; } else { m_OutOfBagError = 0; } }
From source file:REPTree.java
License:Open Source License
/** * Builds classifier./* w ww.jav a2 s .com*/ * * @param data the data to train with * @throws Exception if building fails */ public void buildClassifier(Instances data) throws Exception { // can classifier handle the data? getCapabilities().testWithFail(data); // remove instances with missing class data = new Instances(data); data.deleteWithMissingClass(); Random random = new Random(m_Seed); m_zeroR = null; if (data.numAttributes() == 1) { m_zeroR = new ZeroR(); m_zeroR.buildClassifier(data); return; } // Randomize and stratify data.randomize(random); if (data.classAttribute().isNominal()) { data.stratify(m_NumFolds); } // Split data into training and pruning set Instances train = null; Instances prune = null; if (!m_NoPruning) { train = data.trainCV(m_NumFolds, 0, random); prune = data.testCV(m_NumFolds, 0); } else { train = data; } // Create array of sorted indices and weights int[][][] sortedIndices = new int[1][train.numAttributes()][0]; double[][][] weights = new double[1][train.numAttributes()][0]; double[] vals = new double[train.numInstances()]; for (int j = 0; j < train.numAttributes(); j++) { if (j != train.classIndex()) { weights[0][j] = new double[train.numInstances()]; if (train.attribute(j).isNominal()) { // Handling nominal attributes. Putting indices of // instances with missing values at the end. sortedIndices[0][j] = new int[train.numInstances()]; int count = 0; for (int i = 0; i < train.numInstances(); i++) { Instance inst = train.instance(i); if (!inst.isMissing(j)) { sortedIndices[0][j][count] = i; weights[0][j][count] = inst.weight(); count++; } } for (int i = 0; i < train.numInstances(); i++) { Instance inst = train.instance(i); if (inst.isMissing(j)) { sortedIndices[0][j][count] = i; weights[0][j][count] = inst.weight(); count++; } } } else { // Sorted indices are computed for numeric attributes for (int i = 0; i < train.numInstances(); i++) { Instance inst = train.instance(i); vals[i] = inst.value(j); } sortedIndices[0][j] = Utils.sort(vals); for (int i = 0; i < train.numInstances(); i++) { weights[0][j][i] = train.instance(sortedIndices[0][j][i]).weight(); } } } } // Compute initial class counts double[] classProbs = new double[train.numClasses()]; double totalWeight = 0, totalSumSquared = 0; for (int i = 0; i < train.numInstances(); i++) { Instance inst = train.instance(i); if (data.classAttribute().isNominal()) { classProbs[(int) inst.classValue()] += inst.weight(); totalWeight += inst.weight(); } else { classProbs[0] += inst.classValue() * inst.weight(); totalSumSquared += inst.classValue() * inst.classValue() * inst.weight(); totalWeight += inst.weight(); } } m_Tree = new Tree(); double trainVariance = 0; if (data.classAttribute().isNumeric()) { trainVariance = m_Tree.singleVariance(classProbs[0], totalSumSquared, totalWeight) / totalWeight; classProbs[0] /= totalWeight; } // Build tree m_Tree.buildTree(sortedIndices, weights, train, totalWeight, classProbs, new Instances(train, 0), m_MinNum, m_MinVarianceProp * trainVariance, 0, m_MaxDepth); // Insert pruning data and perform reduced error pruning if (!m_NoPruning) { m_Tree.insertHoldOutSet(prune); m_Tree.reducedErrorPrune(); m_Tree.backfitHoldOutSet(); } }
From source file:TreeNode.java
License:Common Public License
public double calculateEntropy(Instances instances) { if (instances.numClasses() <= 1) return 0; else {/*from w w w . j av a2 s . com*/ int numInstances = instances.numInstances(); int numClasses = instances.numClasses(); //Count how many in each class int[] classCounts = new int[numClasses]; for (int i = 0; i < numInstances; i++) { classCounts[(int) instances.instance(i).classValue()]++; } //Calculate the entropy double entropy = 0; double quotient; for (int i = 0; i < numClasses; i++) { double result; if (classCounts[i] == 0) { result = 0; } else { quotient = (double) classCounts[i] / (double) numInstances; result = (quotient * Math.log(quotient) / Math.log(numClasses)); assert (Double.isNaN(result) && result <= 1); } entropy = entropy - result; } return entropy; } }
From source file:Pair.java
License:Open Source License
/** * Boosting method.// www . j a v a2s . c om * * @param data the training data to be used for generating the * boosted classifier. * @exception Exception if the classifier could not be built successfully */ public void buildClassifier(Instances data) throws Exception { super.buildClassifier(data); if (data.checkForStringAttributes()) { throw new UnsupportedAttributeTypeException("Cannot handle string attributes!"); } data = new Instances(data); data.deleteWithMissingClass(); if (data.numInstances() == 0) { throw new Exception("No train instances without class missing!"); } if (!data.classAttribute().isNumeric()) { throw new UnsupportedClassTypeException("TrAdaBoostR2 can only handle a numeric class!"); } if (m_SourceInstances == null) { throw new Exception("Source data has not been specified!"); } m_NumClasses = data.numClasses(); try { doCV(data); } catch (Exception e) { e.printStackTrace(); } }
From source file:REPRandomTree.java
License:Open Source License
/** * Builds classifier.//from w w w . j a v a 2s .co m * * @param data the data to train with * @throws Exception if building fails */ public void buildClassifier(Instances data) throws Exception { // can classifier handle the data? getCapabilities().testWithFail(data); // remove instances with missing class data = new Instances(data); data.deleteWithMissingClass(); Random random = new Random(m_Seed); m_zeroR = null; if (data.numAttributes() == 1) { m_zeroR = new ZeroR(); m_zeroR.buildClassifier(data); return; } // Randomize and stratify data.randomize(random); if (data.classAttribute().isNominal()) { data.stratify(m_NumFolds); } // Split data into training and pruning set Instances train = null; Instances prune = null; if (!m_NoPruning) { train = data.trainCV(m_NumFolds, 0, random); prune = data.testCV(m_NumFolds, 0); } else { train = data; } // Create array of sorted indices and weights int[][][] sortedIndices = new int[1][train.numAttributes()][0]; double[][][] weights = new double[1][train.numAttributes()][0]; double[] vals = new double[train.numInstances()]; for (int j = 0; j < train.numAttributes(); j++) { if (j != train.classIndex()) { weights[0][j] = new double[train.numInstances()]; if (train.attribute(j).isNominal()) { // Handling nominal attributes. Putting indices of // instances with missing values at the end. sortedIndices[0][j] = new int[train.numInstances()]; int count = 0; for (int i = 0; i < train.numInstances(); i++) { Instance inst = train.instance(i); if (!inst.isMissing(j)) { sortedIndices[0][j][count] = i; weights[0][j][count] = inst.weight(); count++; } } for (int i = 0; i < train.numInstances(); i++) { Instance inst = train.instance(i); if (inst.isMissing(j)) { sortedIndices[0][j][count] = i; weights[0][j][count] = inst.weight(); count++; } } } else { // Sorted indices are computed for numeric attributes for (int i = 0; i < train.numInstances(); i++) { Instance inst = train.instance(i); vals[i] = inst.value(j); } sortedIndices[0][j] = Utils.sort(vals); for (int i = 0; i < train.numInstances(); i++) { weights[0][j][i] = train.instance(sortedIndices[0][j][i]).weight(); } } } } // Compute initial class counts double[] classProbs = new double[train.numClasses()]; double totalWeight = 0, totalSumSquared = 0; for (int i = 0; i < train.numInstances(); i++) { Instance inst = train.instance(i); if (data.classAttribute().isNominal()) { classProbs[(int) inst.classValue()] += inst.weight(); totalWeight += inst.weight(); } else { classProbs[0] += inst.classValue() * inst.weight(); totalSumSquared += inst.classValue() * inst.classValue() * inst.weight(); totalWeight += inst.weight(); } } m_Tree = new Tree(); double trainVariance = 0; if (data.classAttribute().isNumeric()) { trainVariance = m_Tree.singleVariance(classProbs[0], totalSumSquared, totalWeight) / totalWeight; classProbs[0] /= totalWeight; } // Build tree m_Tree.buildTree(sortedIndices, weights, train, totalWeight, classProbs, new Instances(train, 0), m_MinNum, m_MinVarianceProp * trainVariance, 0, m_MaxDepth, m_FeatureFrac, random); // Insert pruning data and perform reduced error pruning if (!m_NoPruning) { m_Tree.insertHoldOutSet(prune); m_Tree.reducedErrorPrune(); m_Tree.backfitHoldOutSet(); } }
From source file:MultiClassClassifier.java
License:Open Source License
/** * Builds the classifiers./*from w ww . java 2 s. c o m*/ * * @param insts the training data. * @throws Exception if a classifier can't be built */ public void buildClassifier(Instances insts) throws Exception { Instances newInsts; // can classifier handle the data? getCapabilities().testWithFail(insts); // remove instances with missing class insts = new Instances(insts); insts.deleteWithMissingClass(); if (m_Classifier == null) { throw new Exception("No base classifier has been set!"); } m_ZeroR = new ZeroR(); m_ZeroR.buildClassifier(insts); m_TwoClassDataset = null; int numClassifiers = insts.numClasses(); if (numClassifiers <= 2) { m_Classifiers = Classifier.makeCopies(m_Classifier, 1); m_Classifiers[0].buildClassifier(insts); m_ClassFilters = null; } else if (m_Method == METHOD_1_AGAINST_1) { // generate fastvector of pairs FastVector pairs = new FastVector(); for (int i = 0; i < insts.numClasses(); i++) { for (int j = 0; j < insts.numClasses(); j++) { if (j <= i) continue; int[] pair = new int[2]; pair[0] = i; pair[1] = j; pairs.addElement(pair); } } numClassifiers = pairs.size(); m_Classifiers = Classifier.makeCopies(m_Classifier, numClassifiers); m_ClassFilters = new Filter[numClassifiers]; m_SumOfWeights = new double[numClassifiers]; // generate the classifiers for (int i = 0; i < numClassifiers; i++) { RemoveWithValues classFilter = new RemoveWithValues(); classFilter.setAttributeIndex("" + (insts.classIndex() + 1)); classFilter.setModifyHeader(true); classFilter.setInvertSelection(true); classFilter.setNominalIndicesArr((int[]) pairs.elementAt(i)); Instances tempInstances = new Instances(insts, 0); tempInstances.setClassIndex(-1); classFilter.setInputFormat(tempInstances); newInsts = Filter.useFilter(insts, classFilter); if (newInsts.numInstances() > 0) { newInsts.setClassIndex(insts.classIndex()); m_Classifiers[i].buildClassifier(newInsts); m_ClassFilters[i] = classFilter; m_SumOfWeights[i] = newInsts.sumOfWeights(); } else { m_Classifiers[i] = null; m_ClassFilters[i] = null; } } // construct a two-class header version of the dataset m_TwoClassDataset = new Instances(insts, 0); int classIndex = m_TwoClassDataset.classIndex(); m_TwoClassDataset.setClassIndex(-1); m_TwoClassDataset.deleteAttributeAt(classIndex); FastVector classLabels = new FastVector(); classLabels.addElement("class0"); classLabels.addElement("class1"); m_TwoClassDataset.insertAttributeAt(new Attribute("class", classLabels), classIndex); m_TwoClassDataset.setClassIndex(classIndex); } else { // use error correcting code style methods Code code = null; switch (m_Method) { case METHOD_ERROR_EXHAUSTIVE: code = new ExhaustiveCode(numClassifiers); break; case METHOD_ERROR_RANDOM: code = new RandomCode(numClassifiers, (int) (numClassifiers * m_RandomWidthFactor), insts); break; case METHOD_1_AGAINST_ALL: code = new StandardCode(numClassifiers); break; default: throw new Exception("Unrecognized correction code type"); } numClassifiers = code.size(); m_Classifiers = Classifier.makeCopies(m_Classifier, numClassifiers); m_ClassFilters = new MakeIndicator[numClassifiers]; for (int i = 0; i < m_Classifiers.length; i++) { m_ClassFilters[i] = new MakeIndicator(); MakeIndicator classFilter = (MakeIndicator) m_ClassFilters[i]; classFilter.setAttributeIndex("" + (insts.classIndex() + 1)); classFilter.setValueIndices(code.getIndices(i)); classFilter.setNumeric(false); classFilter.setInputFormat(insts); newInsts = Filter.useFilter(insts, m_ClassFilters[i]); m_Classifiers[i].buildClassifier(newInsts); } } m_ClassAttribute = insts.classAttribute(); }
From source file:GrowTree.java
public boolean homogeneous(Instances D) { distribution = new double[D.numClasses()]; Enumeration eninst = D.enumerateInstances(); while (eninst.hasMoreElements()) { Instance ele = (Instance) eninst.nextElement(); distribution[(int) ele.classValue()]++; }//from w ww. ja va 2 s . co m int cnt = 0; for (int i = 0; i < D.numClasses(); i++) { if (distribution[i] > 0) cnt++; } if (cnt <= 1) // if all instances are of single class return true; else return false; }
From source file:GrowTree.java
public double imp(Instances data) { double localdistribution[] = new double[data.numClasses()]; Enumeration eninst = data.enumerateInstances(); while (eninst.hasMoreElements()) { Instance ele = (Instance) eninst.nextElement(); localdistribution[(int) ele.classValue()]++; }//from w w w .j av a 2s. c o m return imp; }
From source file:SMO.java
License:Open Source License
/** * Method for building the classifier. Implements a one-against-one * wrapper for multi-class problems.//from w ww . ja v a2 s .c o m * * @param insts the set of training instances * @throws Exception if the classifier can't be built successfully */ public void buildClassifier(Instances insts) throws Exception { if (!m_checksTurnedOff) { // can classifier handle the data? getCapabilities().testWithFail(insts); // remove instances with missing class insts = new Instances(insts); insts.deleteWithMissingClass(); /* Removes all the instances with weight equal to 0. MUST be done since condition (8) of Keerthi's paper is made with the assertion Ci > 0 (See equation (3a). */ Instances data = new Instances(insts, insts.numInstances()); for (int i = 0; i < insts.numInstances(); i++) { if (insts.instance(i).weight() > 0) data.add(insts.instance(i)); } if (data.numInstances() == 0) { throw new Exception("No training instances left after removing " + "instances with weight 0!"); } insts = data; } if (!m_checksTurnedOff) { m_Missing = new ReplaceMissingValues(); m_Missing.setInputFormat(insts); insts = Filter.useFilter(insts, m_Missing); } else { m_Missing = null; } if (getCapabilities().handles(Capability.NUMERIC_ATTRIBUTES)) { boolean onlyNumeric = true; if (!m_checksTurnedOff) { for (int i = 0; i < insts.numAttributes(); i++) { if (i != insts.classIndex()) { if (!insts.attribute(i).isNumeric()) { onlyNumeric = false; break; } } } } if (!onlyNumeric) { m_NominalToBinary = new NominalToBinary(); m_NominalToBinary.setInputFormat(insts); insts = Filter.useFilter(insts, m_NominalToBinary); } else { m_NominalToBinary = null; } } else { m_NominalToBinary = null; } if (m_filterType == FILTER_STANDARDIZE) { m_Filter = new Standardize(); m_Filter.setInputFormat(insts); insts = Filter.useFilter(insts, m_Filter); } else if (m_filterType == FILTER_NORMALIZE) { m_Filter = new Normalize(); m_Filter.setInputFormat(insts); insts = Filter.useFilter(insts, m_Filter); } else { m_Filter = null; } m_classIndex = insts.classIndex(); m_classAttribute = insts.classAttribute(); m_KernelIsLinear = (m_kernel instanceof PolyKernel) && (((PolyKernel) m_kernel).getExponent() == 1.0); // Generate subsets representing each class Instances[] subsets = new Instances[insts.numClasses()]; for (int i = 0; i < insts.numClasses(); i++) { subsets[i] = new Instances(insts, insts.numInstances()); } for (int j = 0; j < insts.numInstances(); j++) { Instance inst = insts.instance(j); subsets[(int) inst.classValue()].add(inst); } for (int i = 0; i < insts.numClasses(); i++) { subsets[i].compactify(); } // Build the binary classifiers Random rand = new Random(m_randomSeed); m_classifiers = new BinarySMO[insts.numClasses()][insts.numClasses()]; for (int i = 0; i < insts.numClasses(); i++) { for (int j = i + 1; j < insts.numClasses(); j++) { m_classifiers[i][j] = new BinarySMO(); m_classifiers[i][j].setKernel(Kernel.makeCopy(getKernel())); Instances data = new Instances(insts, insts.numInstances()); for (int k = 0; k < subsets[i].numInstances(); k++) { data.add(subsets[i].instance(k)); } for (int k = 0; k < subsets[j].numInstances(); k++) { data.add(subsets[j].instance(k)); } data.compactify(); data.randomize(rand); m_classifiers[i][j].buildClassifier(data, i, j, m_fitLogisticModels, m_numFolds, m_randomSeed); } } }
From source file:ID3Chi.java
License:Open Source License
private void MakeALeaf(Instances data) { data.deleteWithMissing(m_Attribute); if (data.numInstances() == 0) { SetNullDistribution(data);//from www . j av a 2 s . c om return; } m_Distribution = new double[data.numClasses()]; Enumeration instEnum = data.enumerateInstances(); while (instEnum.hasMoreElements()) { Instance inst = (Instance) instEnum.nextElement(); m_Distribution[(int) inst.classValue()]++; } Utils.normalize(m_Distribution); m_ClassValue = Utils.maxIndex(m_Distribution); m_ClassAttribute = data.classAttribute(); // set m_Attribute to null to mark this node as a leaf m_Attribute = null; }