List of usage examples for weka.classifiers Evaluation toMatrixString
public String toMatrixString() throws Exception
From source file:clases.Resultados.java
public static void imprimirResultados(Evaluation evaluador) { try {/*from ww w. java2 s. c o m*/ System.out.println("=================================================="); System.out.println("Las figuras de mrito del clasificador ptimo son:"); System.out.println("=================================================="); System.out.println(evaluador.toSummaryString()); System.out.println(evaluador.toClassDetailsString()); System.out.println(evaluador.toMatrixString()); } catch (Exception ex) { System.out.println("Error al mostrar los resultados: " + ex); } }
From source file:com.deafgoat.ml.prognosticator.AppClassifier.java
License:Apache License
/** * Write results to mongoDB//from ww w .j a v a2 s.com * * @param eval * The evaluation object holding data. * @throws Exception */ public void writeToMongoDB(Evaluation eval) throws Exception { MongoResult mongoResult = new MongoResult(_config._host, _config._port, _config._db, _config._modelCollection); mongoResult.writeExperiment(_config._relation, "summary", eval.toSummaryString()); try { mongoResult.writeExperiment(_config._relation, "class detail", eval.toClassDetailsString()); } catch (Exception e) { _logger.error("Can not create class details" + _config._classifier); } try { mongoResult.writeExperiment(_config._relation, "confusion matrix", eval.toMatrixString()); } catch (Exception e) { _logger.error("Can not create confusion matrix for " + _config._classifier); } mongoResult.close(); }
From source file:com.ivanrf.smsspam.SpamClassifier.java
License:Apache License
public static void evaluate(int wordsToKeep, String tokenizerOp, boolean useAttributeSelection, String classifierOp, boolean boosting, JTextArea log) { try {//from w ww . j a v a2 s .co m long start = System.currentTimeMillis(); String modelName = getModelName(wordsToKeep, tokenizerOp, useAttributeSelection, classifierOp, boosting); showEstimatedTime(false, modelName, log); Instances trainData = loadDataset("SMSSpamCollection.arff", log); trainData.setClassIndex(0); FilteredClassifier classifier = initFilterClassifier(wordsToKeep, tokenizerOp, useAttributeSelection, classifierOp, boosting); publishEstado("=== Performing cross-validation ===", log); Evaluation eval = new Evaluation(trainData); // eval.evaluateModel(classifier, trainData); eval.crossValidateModel(classifier, trainData, 10, new Random(1)); publishEstado(eval.toSummaryString(), log); publishEstado(eval.toClassDetailsString(), log); publishEstado(eval.toMatrixString(), log); publishEstado("=== Evaluation finished ===", log); publishEstado("Elapsed time: " + Utils.getDateHsMinSegString(System.currentTimeMillis() - start), log); } catch (Exception e) { e.printStackTrace(); publishEstado("Error found when evaluating", log); } }
From source file:com.sliit.rules.RuleContainer.java
public Map<String, String> evaluateModel() { Map<String, String> evaluationSummary = new HashMap<String, String>(); try {//from w w w . java 2s. co m instances.setClassIndex(instances.numAttributes() - 1); Evaluation evaluation = new Evaluation(instances); evaluation.evaluateModel(ruleMoldel, instances); ArrayList<Rule> rulesList = ruleMoldel.getRuleset(); String rules = ruleMoldel.toString(); evaluationSummary.put("rules", rules); evaluationSummary.put("summary", evaluation.toSummaryString()); evaluationSummary.put("confusion_matrix", evaluation.toMatrixString()); } catch (Exception e) { log.error("Error occurred:" + e.getLocalizedMessage()); } return evaluationSummary; }
From source file:de.tudarmstadt.ukp.alignment.framework.combined.WekaMachineLearning.java
License:Apache License
/** * * This method creates a serialized WEKA model file from an .arff file containing the annotated gold standard * * * @param gs_arff the annotated gold standard in an .arff file * @param model output file for the model * @param output_eval if true, the evaluation of the trained classifier is printed (10-fold cross validation) * @throws Exception/*from w ww . j a v a2 s.c o m*/ */ public static void createModelFromGoldstandard(String gs_arff, String model, boolean output_eval) throws Exception { DataSource source = new DataSource(gs_arff); Instances data = source.getDataSet(); if (data.classIndex() == -1) { data.setClassIndex(data.numAttributes() - 1); } Remove rm = new Remove(); rm.setAttributeIndices("1"); // remove ID attribute BayesNet bn = new BayesNet(); //Standard classifier; BNs proved most robust, but of course other classifiers are possible // meta-classifier FilteredClassifier fc = new FilteredClassifier(); fc.setFilter(rm); fc.setClassifier(bn); fc.buildClassifier(data); // build classifier SerializationHelper.write(model, fc); if (output_eval) { Evaluation eval = new Evaluation(data); eval.crossValidateModel(fc, data, 10, new Random(1)); System.out.println(eval.toSummaryString()); System.out.println(eval.toMatrixString()); System.out.println(eval.toClassDetailsString()); } }
From source file:dkpro.similarity.experiments.rte.util.Evaluator.java
License:Open Source License
public static void runClassifier(WekaClassifier wekaClassifier, Dataset trainDataset, Dataset testDataset) throws Exception { Classifier baseClassifier = ClassifierSimilarityMeasure.getClassifier(wekaClassifier); // Set up the random number generator long seed = new Date().getTime(); Random random = new Random(seed); // Add IDs to the train instances and get the instances AddID.main(new String[] { "-i", MODELS_DIR + "/" + trainDataset.toString() + ".arff", "-o", MODELS_DIR + "/" + trainDataset.toString() + "-plusIDs.arff" }); Instances train = DataSource.read(MODELS_DIR + "/" + trainDataset.toString() + "-plusIDs.arff"); train.setClassIndex(train.numAttributes() - 1); // Add IDs to the test instances and get the instances AddID.main(new String[] { "-i", MODELS_DIR + "/" + testDataset.toString() + ".arff", "-o", MODELS_DIR + "/" + testDataset.toString() + "-plusIDs.arff" }); Instances test = DataSource.read(MODELS_DIR + "/" + testDataset.toString() + "-plusIDs.arff"); test.setClassIndex(test.numAttributes() - 1); // Instantiate the Remove filter Remove removeIDFilter = new Remove(); removeIDFilter.setAttributeIndices("first"); // Randomize the data test.randomize(random);/*from w w w . j a va 2 s.c o m*/ // Apply log filter // Filter logFilter = new LogFilter(); // logFilter.setInputFormat(train); // train = Filter.useFilter(train, logFilter); // logFilter.setInputFormat(test); // test = Filter.useFilter(test, logFilter); // Copy the classifier Classifier classifier = AbstractClassifier.makeCopy(baseClassifier); // Instantiate the FilteredClassifier FilteredClassifier filteredClassifier = new FilteredClassifier(); filteredClassifier.setFilter(removeIDFilter); filteredClassifier.setClassifier(classifier); // Build the classifier filteredClassifier.buildClassifier(train); // Prepare the output buffer AbstractOutput output = new PlainText(); output.setBuffer(new StringBuffer()); output.setHeader(test); output.setAttributes("first"); Evaluation eval = new Evaluation(train); eval.evaluateModel(filteredClassifier, test, output); // Convert predictions to CSV // Format: inst#, actual, predicted, error, probability, (ID) String[] scores = new String[new Double(eval.numInstances()).intValue()]; double[] probabilities = new double[new Double(eval.numInstances()).intValue()]; for (String line : output.getBuffer().toString().split("\n")) { String[] linesplit = line.split("\\s+"); // If there's been an error, the length of linesplit is 6, otherwise 5, // due to the error flag "+" int id; String expectedValue, classification; double probability; if (line.contains("+")) { id = Integer.parseInt(linesplit[6].substring(1, linesplit[6].length() - 1)); expectedValue = linesplit[2].substring(2); classification = linesplit[3].substring(2); probability = Double.parseDouble(linesplit[5]); } else { id = Integer.parseInt(linesplit[5].substring(1, linesplit[5].length() - 1)); expectedValue = linesplit[2].substring(2); classification = linesplit[3].substring(2); probability = Double.parseDouble(linesplit[4]); } scores[id - 1] = classification; probabilities[id - 1] = probability; } System.out.println(eval.toSummaryString()); System.out.println(eval.toMatrixString()); // Output classifications StringBuilder sb = new StringBuilder(); for (String score : scores) sb.append(score.toString() + LF); FileUtils.writeStringToFile(new File(OUTPUT_DIR + "/" + testDataset.toString() + "/" + wekaClassifier.toString() + "/" + testDataset.toString() + ".csv"), sb.toString()); // Output probabilities sb = new StringBuilder(); for (Double probability : probabilities) sb.append(probability.toString() + LF); FileUtils.writeStringToFile(new File(OUTPUT_DIR + "/" + testDataset.toString() + "/" + wekaClassifier.toString() + "/" + testDataset.toString() + ".probabilities.csv"), sb.toString()); // Output predictions FileUtils.writeStringToFile(new File(OUTPUT_DIR + "/" + testDataset.toString() + "/" + wekaClassifier.toString() + "/" + testDataset.toString() + ".predictions.txt"), output.getBuffer().toString()); // Output meta information sb = new StringBuilder(); sb.append(classifier.toString() + LF); sb.append(eval.toSummaryString() + LF); sb.append(eval.toMatrixString() + LF); FileUtils.writeStringToFile(new File(OUTPUT_DIR + "/" + testDataset.toString() + "/" + wekaClassifier.toString() + "/" + testDataset.toString() + ".meta.txt"), sb.toString()); }
From source file:dkpro.similarity.experiments.rte.util.Evaluator.java
License:Open Source License
public static void runClassifierCV(WekaClassifier wekaClassifier, Dataset dataset) throws Exception { // Set parameters int folds = 10; Classifier baseClassifier = ClassifierSimilarityMeasure.getClassifier(wekaClassifier); // Set up the random number generator long seed = new Date().getTime(); Random random = new Random(seed); // Add IDs to the instances AddID.main(new String[] { "-i", MODELS_DIR + "/" + dataset.toString() + ".arff", "-o", MODELS_DIR + "/" + dataset.toString() + "-plusIDs.arff" }); Instances data = DataSource.read(MODELS_DIR + "/" + dataset.toString() + "-plusIDs.arff"); data.setClassIndex(data.numAttributes() - 1); // Instantiate the Remove filter Remove removeIDFilter = new Remove(); removeIDFilter.setAttributeIndices("first"); // Randomize the data data.randomize(random);//from www .j a v a 2 s.c o m // Perform cross-validation Instances predictedData = null; Evaluation eval = new Evaluation(data); for (int n = 0; n < folds; n++) { Instances train = data.trainCV(folds, n, random); Instances test = data.testCV(folds, n); // Apply log filter // Filter logFilter = new LogFilter(); // logFilter.setInputFormat(train); // train = Filter.useFilter(train, logFilter); // logFilter.setInputFormat(test); // test = Filter.useFilter(test, logFilter); // Copy the classifier Classifier classifier = AbstractClassifier.makeCopy(baseClassifier); // Instantiate the FilteredClassifier FilteredClassifier filteredClassifier = new FilteredClassifier(); filteredClassifier.setFilter(removeIDFilter); filteredClassifier.setClassifier(classifier); // Build the classifier filteredClassifier.buildClassifier(train); // Evaluate eval.evaluateModel(filteredClassifier, test); // Add predictions AddClassification filter = new AddClassification(); filter.setClassifier(classifier); filter.setOutputClassification(true); filter.setOutputDistribution(false); filter.setOutputErrorFlag(true); filter.setInputFormat(train); Filter.useFilter(train, filter); // trains the classifier Instances pred = Filter.useFilter(test, filter); // performs predictions on test set if (predictedData == null) predictedData = new Instances(pred, 0); for (int j = 0; j < pred.numInstances(); j++) predictedData.add(pred.instance(j)); } System.out.println(eval.toSummaryString()); System.out.println(eval.toMatrixString()); // Prepare output scores String[] scores = new String[predictedData.numInstances()]; for (Instance predInst : predictedData) { int id = new Double(predInst.value(predInst.attribute(0))).intValue() - 1; int valueIdx = predictedData.numAttributes() - 2; String value = predInst.stringValue(predInst.attribute(valueIdx)); scores[id] = value; } // Output classifications StringBuilder sb = new StringBuilder(); for (String score : scores) sb.append(score.toString() + LF); FileUtils.writeStringToFile(new File(OUTPUT_DIR + "/" + dataset.toString() + "/" + wekaClassifier.toString() + "/" + dataset.toString() + ".csv"), sb.toString()); // Output prediction arff DataSink.write(OUTPUT_DIR + "/" + dataset.toString() + "/" + wekaClassifier.toString() + "/" + dataset.toString() + ".predicted.arff", predictedData); // Output meta information sb = new StringBuilder(); sb.append(baseClassifier.toString() + LF); sb.append(eval.toSummaryString() + LF); sb.append(eval.toMatrixString() + LF); FileUtils.writeStringToFile(new File(OUTPUT_DIR + "/" + dataset.toString() + "/" + wekaClassifier.toString() + "/" + dataset.toString() + ".meta.txt"), sb.toString()); }
From source file:edu.teco.context.recognition.WekaManager.java
License:Apache License
public void testClassification() { // set class attribute (last attribute) testingData.setClassIndex(testingData.numAttributes() - 1); if (FrameworkContext.INFO) Log.i("WekaData", "Testing data:\n" + testingData.toString()); // Test the model Evaluation eTest; try {/*from w ww .j av a 2 s .c o m*/ eTest = new Evaluation(trainingData); eTest.evaluateModel(classifier, testingData); if (FrameworkContext.INFO) Log.i("WekaData", "\nClass detail:\n\n" + eTest.toClassDetailsString()); // Print the result la Weka explorer: String strSummary = eTest.toSummaryString(); if (FrameworkContext.INFO) Log.i("WekaData", "----- Summary -----\n" + strSummary); // print the confusion matrix if (FrameworkContext.INFO) Log.i("WekaData", "----- Confusion Matrix -----\n" + eTest.toMatrixString()); // print class details if (FrameworkContext.INFO) Log.i("WekaData", "----- Class Detail -----\n" + eTest.toClassDetailsString()); notifyTestCalculated(strSummary); } catch (Exception e) { e.printStackTrace(); } }
From source file:elh.eus.absa.WekaWrapper.java
License:Open Source License
/** * Prints the results stored in an Evaluation object to standard output * (summary, class results and confusion matrix) * //from www . j av a 2 s . c o m * @param Evaluation eval * @throws Exception */ public void printClassifierResults(Evaluation eval) throws Exception { // Print the result la Weka explorer: String strSummary = eval.toSummaryString(); System.out.println(strSummary); // Print per class results String resPerClass = eval.toClassDetailsString(); System.out.println(resPerClass); // Get the confusion matrix String cMatrix = eval.toMatrixString(); System.out.println(cMatrix); System.out.println(); }
From source file:epsi.i5.datamining.Weka.java
public void excutionAlgo() throws FileNotFoundException, IOException, Exception { BufferedReader reader = new BufferedReader(new FileReader("src/epsi/i5/data/" + fileOne + ".arff")); Instances data = new Instances(reader); reader.close();//from ww w. j ava 2 s .c o m //System.out.println(data.attribute(0)); data.setClass(data.attribute(0)); NaiveBayes NB = new NaiveBayes(); NB.buildClassifier(data); Evaluation naiveBayes = new Evaluation(data); naiveBayes.crossValidateModel(NB, data, 10, new Random(1)); naiveBayes.evaluateModel(NB, data); //System.out.println(test.confusionMatrix() + "1"); //System.out.println(test.correct() + "2"); System.out.println("*****************************"); System.out.println("******** Naive Bayes ********"); System.out.println(naiveBayes.toMatrixString()); System.out.println("*****************************"); System.out.println("**** Pourcentage Correct ****"); System.out.println(naiveBayes.pctCorrect()); System.out.println(""); J48 j = new J48(); j.buildClassifier(data); Evaluation jeval = new Evaluation(data); jeval.crossValidateModel(j, data, 10, new Random(1)); jeval.evaluateModel(j, data); System.out.println("*****************************"); System.out.println("************ J48 ************"); System.out.println(jeval.toMatrixString()); System.out.println("*****************************"); System.out.println("**** Pourcentage Correct ****"); System.out.println(jeval.pctCorrect()); System.out.println(""); DecisionTable DT = new DecisionTable(); DT.buildClassifier(data); Evaluation decisionTable = new Evaluation(data); decisionTable.crossValidateModel(DT, data, 10, new Random(1)); decisionTable.evaluateModel(DT, data); System.out.println("*****************************"); System.out.println("******* DecisionTable *******"); System.out.println(decisionTable.toMatrixString()); System.out.println("*****************************"); System.out.println("**** Pourcentage Correct ****"); System.out.println(decisionTable.pctCorrect()); System.out.println(""); OneR OR = new OneR(); OR.buildClassifier(data); Evaluation oneR = new Evaluation(data); oneR.crossValidateModel(OR, data, 10, new Random(1)); oneR.evaluateModel(OR, data); System.out.println("*****************************"); System.out.println("************ OneR ***********"); System.out.println(oneR.toMatrixString()); System.out.println("*****************************"); System.out.println("**** Pourcentage Correct ****"); System.out.println(oneR.pctCorrect()); //Polarit data.setClass(data.attribute(1)); System.out.println(""); M5Rules MR = new M5Rules(); MR.buildClassifier(data); Evaluation m5rules = new Evaluation(data); m5rules.crossValidateModel(MR, data, 10, new Random(1)); m5rules.evaluateModel(MR, data); System.out.println("*****************************"); System.out.println("********** M5Rules **********"); System.out.println(m5rules.correlationCoefficient()); System.out.println(""); LinearRegression LR = new LinearRegression(); LR.buildClassifier(data); Evaluation linearR = new Evaluation(data); linearR.crossValidateModel(LR, data, 10, new Random(1)); linearR.evaluateModel(LR, data); System.out.println("*****************************"); System.out.println("********** linearR **********"); System.out.println(linearR.correlationCoefficient()); }