List of usage examples for weka.classifiers Evaluation Evaluation
public Evaluation(Instances data) throws Exception
From source file:id3classifier.Main.java
public static void main(String[] args) throws Exception { ConverterUtils.DataSource source = new ConverterUtils.DataSource(file); Instances dataSet = source.getDataSet(); // discretize the dataset Discretize filter = new Discretize(); filter.setInputFormat(dataSet);/*from w w w. j av a 2s.c om*/ dataSet = Filter.useFilter(dataSet, filter); // standardize the dataset Standardize standardizedData = new Standardize(); standardizedData.setInputFormat(dataSet); dataSet = Filter.useFilter(dataSet, standardizedData); // randomize the dataset dataSet.setClassIndex(dataSet.numAttributes() - 1); dataSet.randomize(new Debug.Random()); // get the sizes of the training and testing sets and split int trainingSize = (int) Math.round(dataSet.numInstances() * .7); int testSize = dataSet.numInstances() - trainingSize; Instances training = new Instances(dataSet, 0, trainingSize); Instances test = new Instances(dataSet, trainingSize, testSize); // set up the ID3 classifier on the training data ID3Classifiers classifier = new ID3Classifiers(); classifier.buildClassifier(training); // set up the evaluation and test using the classifier and test set Evaluation eval = new Evaluation(dataSet); eval.evaluateModel(classifier, test); // outup and kill, important to exit here to stop javaFX System.out.println(eval.toSummaryString("\nResults\n======\n", false)); System.exit(0); }
From source file:id3j48.WekaAccess.java
public static Evaluation testModel(Classifier classifier, Instances data, Instances test) throws Exception { Evaluation evaluation = new Evaluation(data); evaluation.evaluateModel(classifier, test); return evaluation; }
From source file:id3j48.WekaAccess.java
public static Evaluation tenFoldCrossValidation(Instances data, Classifier classifier) throws Exception { Evaluation eval = new Evaluation(data); eval.crossValidateModel(classifier, data, 10, new Random(1)); return eval;//ww w . jav a 2s . co m }
From source file:irisdata.IrisData.java
/** * @param args the command line arguments * @throws java.lang.Exception //from w w w . ja v a 2s . c om */ public static void main(String[] args) throws Exception { String file = "/Users/paul/Desktop/BYU-Idaho/Spring2015/CS450/iris.csv"; DataSource source = new DataSource(file); Instances data = source.getDataSet(); if (data.classIndex() == -1) { data.setClassIndex(data.numAttributes() - 1); } data.randomize(new Random(1)); // set training set to 70% RemovePercentage remove = new RemovePercentage(); remove.setPercentage(30); remove.setInputFormat(data); Instances trainingSet = Filter.useFilter(data, remove); // set the rest for the testing set remove.setInvertSelection(true); Instances testSet = Filter.useFilter(data, remove); // train classifier - kind of HardCodedClassifier classifier = new HardCodedClassifier(); classifier.buildClassifier(trainingSet); // this does nothing right now // Evaluate classifier Evaluation eval = new Evaluation(trainingSet); eval.evaluateModel(classifier, testSet); //eval.crossValidateModel(classifier, data, 10, new Random(1)); // Print some statistics System.out.println("Results: " + eval.toSummaryString()); }
From source file:it.unisa.gitdm.evaluation.WekaEvaluator.java
private static void evaluateModel(String baseFolderPath, String projectName, Classifier pClassifier, Instances pInstances, String pModelName, String pClassifierName) throws Exception { // other options int folds = 10; // randomize data Random rand = new Random(42); Instances randData = new Instances(pInstances); randData.randomize(rand);// w w w . ja v a 2 s. c o m if (randData.classAttribute().isNominal()) { randData.stratify(folds); } // perform cross-validation and add predictions Instances predictedData = null; Evaluation eval = new Evaluation(randData); int positiveValueIndexOfClassFeature = 0; for (int n = 0; n < folds; n++) { Instances train = randData.trainCV(folds, n); Instances test = randData.testCV(folds, n); // the above code is used by the StratifiedRemoveFolds filter, the // code below by the Explorer/Experimenter: // Instances train = randData.trainCV(folds, n, rand); int classFeatureIndex = 0; for (int i = 0; i < train.numAttributes(); i++) { if (train.attribute(i).name().equals("isBuggy")) { classFeatureIndex = i; break; } } Attribute classFeature = train.attribute(classFeatureIndex); for (int i = 0; i < classFeature.numValues(); i++) { if (classFeature.value(i).equals("TRUE")) { positiveValueIndexOfClassFeature = i; } } train.setClassIndex(classFeatureIndex); test.setClassIndex(classFeatureIndex); // build and evaluate classifier pClassifier.buildClassifier(train); eval.evaluateModel(pClassifier, test); // add predictions // AddClassification filter = new AddClassification(); // filter.setClassifier(pClassifier); // filter.setOutputClassification(true); // filter.setOutputDistribution(true); // filter.setOutputErrorFlag(true); // filter.setInputFormat(train); // Filter.useFilter(train, filter); // Instances pred = Filter.useFilter(test, filter); // if (predictedData == null) // predictedData = new Instances(pred, 0); // // for (int j = 0; j < pred.numInstances(); j++) // predictedData.add(pred.instance(j)); } double accuracy = (eval.numTruePositives(positiveValueIndexOfClassFeature) + eval.numTrueNegatives(positiveValueIndexOfClassFeature)) / (eval.numTruePositives(positiveValueIndexOfClassFeature) + eval.numFalsePositives(positiveValueIndexOfClassFeature) + eval.numFalseNegatives(positiveValueIndexOfClassFeature) + eval.numTrueNegatives(positiveValueIndexOfClassFeature)); double fmeasure = 2 * ((eval.precision(positiveValueIndexOfClassFeature) * eval.recall(positiveValueIndexOfClassFeature)) / (eval.precision(positiveValueIndexOfClassFeature) + eval.recall(positiveValueIndexOfClassFeature))); File wekaOutput = new File(baseFolderPath + projectName + "/predictors.csv"); PrintWriter pw1 = new PrintWriter(wekaOutput); pw1.write(accuracy + ";" + eval.precision(positiveValueIndexOfClassFeature) + ";" + eval.recall(positiveValueIndexOfClassFeature) + ";" + fmeasure + ";" + eval.areaUnderROC(positiveValueIndexOfClassFeature)); System.out.println(projectName + ";" + pClassifierName + ";" + pModelName + ";" + eval.numTruePositives(positiveValueIndexOfClassFeature) + ";" + eval.numFalsePositives(positiveValueIndexOfClassFeature) + ";" + eval.numFalseNegatives(positiveValueIndexOfClassFeature) + ";" + eval.numTrueNegatives(positiveValueIndexOfClassFeature) + ";" + accuracy + ";" + eval.precision(positiveValueIndexOfClassFeature) + ";" + eval.recall(positiveValueIndexOfClassFeature) + ";" + fmeasure + ";" + eval.areaUnderROC(positiveValueIndexOfClassFeature) + "\n"); }
From source file:j48.NBTreeNoSplit.java
License:Open Source License
/** * Utility method for fast 5-fold cross validation of a naive bayes * model// w w w .j a va2 s . c om * * @param fullModel a <code>NaiveBayesUpdateable</code> value * @param trainingSet an <code>Instances</code> value * @param r a <code>Random</code> value * @return a <code>double</code> value * @exception Exception if an error occurs */ public static double crossValidate(NaiveBayesUpdateable fullModel, Instances trainingSet, Random r) throws Exception { // make some copies for fast evaluation of 5-fold xval Classifier[] copies = Classifier.makeCopies(fullModel, 5); Evaluation eval = new Evaluation(trainingSet); // make some splits for (int j = 0; j < 5; j++) { Instances test = trainingSet.testCV(5, j); // unlearn these test instances for (int k = 0; k < test.numInstances(); k++) { test.instance(k).setWeight(-test.instance(k).weight()); ((NaiveBayesUpdateable) copies[j]).updateClassifier(test.instance(k)); // reset the weight back to its original value test.instance(k).setWeight(-test.instance(k).weight()); } eval.evaluateModel(copies[j], test); } return eval.incorrect(); }
From source file:kfst.classifier.WekaClassifier.java
License:Open Source License
/** * This method builds and evaluates the support vector machine(SVM) * classifier. The SMO are used as the SVM classifier implemented in the * Weka software.//from w w w . ja va 2 s. c o m * * @param pathTrainData the path of the train set * @param pathTestData the path of the test set * @param svmKernel the kernel to use * * @return the classification accuracy */ public static double SVM(String pathTrainData, String pathTestData, String svmKernel) { double resultValue = 0; try { BufferedReader readerTrain = new BufferedReader(new FileReader(pathTrainData)); Instances dataTrain = new Instances(readerTrain); readerTrain.close(); dataTrain.setClassIndex(dataTrain.numAttributes() - 1); BufferedReader readerTest = new BufferedReader(new FileReader(pathTestData)); Instances dataTest = new Instances(readerTest); readerTest.close(); dataTest.setClassIndex(dataTest.numAttributes() - 1); SMO svm = new SMO(); if (svmKernel.equals("Polynomial kernel")) { svm.setKernel(weka.classifiers.functions.supportVector.PolyKernel.class.newInstance()); } else if (svmKernel.equals("RBF kernel")) { svm.setKernel(weka.classifiers.functions.supportVector.RBFKernel.class.newInstance()); } else { svm.setKernel(weka.classifiers.functions.supportVector.Puk.class.newInstance()); } svm.buildClassifier(dataTrain); Evaluation eval = new Evaluation(dataTest); eval.evaluateModel(svm, dataTest); resultValue = 100 - (eval.errorRate() * 100); } catch (Exception ex) { Logger.getLogger(WekaClassifier.class.getName()).log(Level.SEVERE, null, ex); } return resultValue; }
From source file:kfst.classifier.WekaClassifier.java
License:Open Source License
/** * This method builds and evaluates the naiveBayes(NB) classifier. * The naiveBayes are used as the NB classifier implemented in the Weka * software./*w w w . ja v a 2s .co m*/ * * @param pathTrainData the path of the train set * @param pathTestData the path of the test set * * @return the classification accuracy */ public static double naiveBayes(String pathTrainData, String pathTestData) { double resultValue = 0; try { BufferedReader readerTrain = new BufferedReader(new FileReader(pathTrainData)); Instances dataTrain = new Instances(readerTrain); readerTrain.close(); dataTrain.setClassIndex(dataTrain.numAttributes() - 1); BufferedReader readerTest = new BufferedReader(new FileReader(pathTestData)); Instances dataTest = new Instances(readerTest); readerTest.close(); dataTest.setClassIndex(dataTest.numAttributes() - 1); NaiveBayes nb = new NaiveBayes(); nb.buildClassifier(dataTrain); Evaluation eval = new Evaluation(dataTest); eval.evaluateModel(nb, dataTest); resultValue = 100 - (eval.errorRate() * 100); } catch (Exception ex) { Logger.getLogger(WekaClassifier.class.getName()).log(Level.SEVERE, null, ex); } return resultValue; }
From source file:kfst.classifier.WekaClassifier.java
License:Open Source License
/** * This method builds and evaluates the decision tree(DT) classifier. * The j48 are used as the DT classifier implemented in the Weka software. * * @param pathTrainData the path of the train set * @param pathTestData the path of the test set * @param confidenceValue The confidence factor used for pruning * @param minNumSampleInLeaf The minimum number of instances per leaf * /*from www . j av a 2s .co m*/ * @return the classification accuracy */ public static double dTree(String pathTrainData, String pathTestData, double confidenceValue, int minNumSampleInLeaf) { double resultValue = 0; try { BufferedReader readerTrain = new BufferedReader(new FileReader(pathTrainData)); Instances dataTrain = new Instances(readerTrain); readerTrain.close(); dataTrain.setClassIndex(dataTrain.numAttributes() - 1); BufferedReader readerTest = new BufferedReader(new FileReader(pathTestData)); Instances dataTest = new Instances(readerTest); readerTest.close(); dataTest.setClassIndex(dataTest.numAttributes() - 1); J48 decisionTree = new J48(); decisionTree.setConfidenceFactor((float) confidenceValue); decisionTree.setMinNumObj(minNumSampleInLeaf); decisionTree.buildClassifier(dataTrain); Evaluation eval = new Evaluation(dataTest); eval.evaluateModel(decisionTree, dataTest); resultValue = 100 - (eval.errorRate() * 100); } catch (Exception ex) { Logger.getLogger(WekaClassifier.class.getName()).log(Level.SEVERE, null, ex); } return resultValue; }
From source file:knnclassifier.Main.java
public static void main(String[] args) throws Exception { DataSource source = new DataSource(file); Instances dataSet = source.getDataSet(); //Set up data dataSet.setClassIndex(dataSet.numAttributes() - 1); dataSet.randomize(new Random()); int trainingSize = (int) Math.round(dataSet.numInstances() * .7); int testSize = dataSet.numInstances() - trainingSize; Instances training = new Instances(dataSet, 0, trainingSize); Instances test = new Instances(dataSet, trainingSize, testSize); Standardize standardizedData = new Standardize(); standardizedData.setInputFormat(training); Instances newTest = Filter.useFilter(test, standardizedData); Instances newTraining = Filter.useFilter(training, standardizedData); KNNClassifier knn = new KNNClassifier(); knn.buildClassifier(newTraining);/*from ww w. j a va 2s .c om*/ Evaluation eval = new Evaluation(newTraining); eval.evaluateModel(knn, newTest); System.out.println(eval.toSummaryString("\nResults\n======\n", false)); }