List of usage examples for weka.classifiers.meta FilteredClassifier buildClassifier
public void buildClassifier(Instances data) throws Exception
From source file:com.ivanrf.smsspam.SpamClassifier.java
License:Apache License
public static void train(int wordsToKeep, String tokenizerOp, boolean useAttributeSelection, String classifierOp, boolean boosting, JTextArea log) { try {//from w w w . j ava2 s . c o m long start = System.currentTimeMillis(); String modelName = getModelName(wordsToKeep, tokenizerOp, useAttributeSelection, classifierOp, boosting); showEstimatedTime(true, modelName, log); Instances trainData = loadDataset("SMSSpamCollection.arff", log); trainData.setClassIndex(0); FilteredClassifier classifier = initFilterClassifier(wordsToKeep, tokenizerOp, useAttributeSelection, classifierOp, boosting); publishEstado("=== Building the classifier on the filtered data ===", log); classifier.buildClassifier(trainData); publishEstado(classifier.toString(), log); publishEstado("=== Training done ===", log); saveModel(classifier, modelName, log); publishEstado("Elapsed time: " + Utils.getDateHsMinSegString(System.currentTimeMillis() - start), log); } catch (Exception e) { e.printStackTrace(); publishEstado("Error found when training", log); } }
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/* 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:de.tudarmstadt.ukp.similarity.experiments.coling2012.util.Evaluator.java
License:Open Source License
public static void runClassifierCV(WekaClassifier wekaClassifier, Dataset dataset) throws Exception { // Set parameters int folds = 10; Classifier baseClassifier = 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 a2s.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(filteredClassifier); 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)); } // Prepare output classification 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 StringBuilder sb = new StringBuilder(); for (String score : scores) sb.append(score.toString() + LF); FileUtils.writeStringToFile( new File(OUTPUT_DIR + "/" + dataset.toString() + "/" + wekaClassifier.toString() + "/output.csv"), sb.toString()); }
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 www .j a v a 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 w w w . j a v a 2 s . com*/ // 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:dkpro.similarity.experiments.sts2013.util.Evaluator.java
License:Open Source License
public static void runLinearRegressionCV(Mode mode, Dataset... datasets) throws Exception { for (Dataset dataset : datasets) { // Set parameters int folds = 10; Classifier baseClassifier = new LinearRegression(); // 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 + "/" + mode.toString().toLowerCase() + "/" + dataset.toString() + ".arff", "-o", MODELS_DIR + "/" + mode.toString().toLowerCase() + "/" + dataset.toString() + "-plusIDs.arff" }); Instances data = DataSource.read( MODELS_DIR + "/" + mode.toString().toLowerCase() + "/" + 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 w w w . j a va2 s. c om*/ // 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(classifier, 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)); } } // Prepare output scores double[] scores = new double[predictedData.numInstances()]; for (Instance predInst : predictedData) { int id = new Double(predInst.value(predInst.attribute(0))).intValue() - 1; int valueIdx = predictedData.numAttributes() - 2; double value = predInst.value(predInst.attribute(valueIdx)); scores[id] = value; // Limit to interval [0;5] if (scores[id] > 5.0) { scores[id] = 5.0; } if (scores[id] < 0.0) { scores[id] = 0.0; } } // Output StringBuilder sb = new StringBuilder(); for (Double score : scores) { sb.append(score.toString() + LF); } FileUtils.writeStringToFile( new File(OUTPUT_DIR + "/" + mode.toString().toLowerCase() + "/" + dataset.toString() + ".csv"), sb.toString()); } }
From source file:dkpro.similarity.experiments.sts2013baseline.util.Evaluator.java
License:Open Source License
public static void runLinearRegressionCV(Mode mode, Dataset... datasets) throws Exception { for (Dataset dataset : datasets) { // Set parameters int folds = 10; Classifier baseClassifier = new LinearRegression(); // 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 + "/" + mode.toString().toLowerCase() + "/" + dataset.toString() + ".arff", "-o", MODELS_DIR + "/" + mode.toString().toLowerCase() + "/" + dataset.toString() + "-plusIDs.arff" }); String location = MODELS_DIR + "/" + mode.toString().toLowerCase() + "/" + dataset.toString() + "-plusIDs.arff"; Instances data = DataSource.read(location); if (data == null) { throw new IOException("Could not load data from: " + location); }/*w w w . java 2 s .co m*/ data.setClassIndex(data.numAttributes() - 1); // Instantiate the Remove filter Remove removeIDFilter = new Remove(); removeIDFilter.setAttributeIndices("first"); // Randomize the data data.randomize(random); // 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(classifier, 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)); } } // Prepare output scores double[] scores = new double[predictedData.numInstances()]; for (Instance predInst : predictedData) { int id = new Double(predInst.value(predInst.attribute(0))).intValue() - 1; int valueIdx = predictedData.numAttributes() - 2; double value = predInst.value(predInst.attribute(valueIdx)); scores[id] = value; // Limit to interval [0;5] if (scores[id] > 5.0) { scores[id] = 5.0; } if (scores[id] < 0.0) { scores[id] = 0.0; } } // Output StringBuilder sb = new StringBuilder(); for (Double score : scores) { sb.append(score.toString() + LF); } FileUtils.writeStringToFile( new File(OUTPUT_DIR + "/" + mode.toString().toLowerCase() + "/" + dataset.toString() + ".csv"), sb.toString()); } }
From source file:gov.va.chir.tagline.TagLineTrainer.java
License:Open Source License
public void train(final Collection<Document> documents, final Feature... features) throws Exception { if (!DatasetUtil.hasLabels(documents)) { throw new IllegalArgumentException("All lines for training must have a label."); }//w ww .j a va 2 s.co m // Setup extractor for feature calculation extractor = new Extractor(); if (features != null && features.length > 0) { extractor.addFeatures(features); } else { extractor.addFeatures(Extractor.getDefaultFeatures()); } // Setup any features that require the entire corpus extractor.setupCorpusProcessors(documents); // Calculate features at both document and line level for (Document document : documents) { extractor.calculateFeatureValues(document); } // Create dataset instances = DatasetUtil.createDataset(documents); // Remove IDs from dataset final Remove remove = new Remove(); remove.setAttributeIndicesArray(new int[] { instances.attribute(DatasetUtil.DOC_ID).index(), instances.attribute(DatasetUtil.LINE_ID).index() }); final FilteredClassifier fc = new FilteredClassifier(); fc.setFilter(remove); fc.setClassifier(tagLineModel.getModel()); // Train model fc.buildClassifier(instances); tagLineModel.setModel(fc.getClassifier()); }
From source file:miRdup.WekaModule.java
License:Open Source License
public static void trainModel(File arff, String keyword) { dec.setMaximumFractionDigits(3);/*w w w . jav a2s .co m*/ System.out.println("\nTraining model on file " + arff); try { // load data DataSource source = new DataSource(arff.toString()); Instances data = source.getDataSet(); if (data.classIndex() == -1) { data.setClassIndex(data.numAttributes() - 1); } PrintWriter pwout = new PrintWriter(new FileWriter(keyword + Main.modelExtension + "Output")); PrintWriter pwroc = new PrintWriter(new FileWriter(keyword + Main.modelExtension + "roc.arff")); //remove ID row Remove rm = new Remove(); rm.setAttributeIndices("1"); FilteredClassifier fc = new FilteredClassifier(); fc.setFilter(rm); // // train model svm // weka.classifiers.functions.LibSVM model = new weka.classifiers.functions.LibSVM(); // model.setOptions(weka.core.Utils.splitOptions("-S 0 -K 2 -D 3 -G 0.0 -R 0.0 -N 0.5 -M 40.0 -C 1.0 -E 0.0010 -P 0.1 -B")); // train model MultilayerPerceptron // weka.classifiers.functions.MultilayerPerceptron model = new weka.classifiers.functions.MultilayerPerceptron(); // model.setOptions(weka.core.Utils.splitOptions("-L 0.3 -M 0.2 -N 500 -V 0 -S 0 -E 20 -H a")); // train model Adaboost on RIPPER // weka.classifiers.meta.AdaBoostM1 model = new weka.classifiers.meta.AdaBoostM1(); // model.setOptions(weka.core.Utils.splitOptions("weka.classifiers.meta.AdaBoostM1 -P 100 -S 1 -I 10 -W weka.classifiers.rules.JRip -- -F 10 -N 2.0 -O 5 -S 1")); // train model Adaboost on FURIA // weka.classifiers.meta.AdaBoostM1 model = new weka.classifiers.meta.AdaBoostM1(); // model.setOptions(weka.core.Utils.splitOptions("weka.classifiers.meta.AdaBoostM1 -P 100 -S 1 -I 10 -W weka.classifiers.rules.FURIA -- -F 10 -N 2.0 -O 5 -S 1 -p 0 -s 0")); //train model Adaboot on J48 trees // weka.classifiers.meta.AdaBoostM1 model = new weka.classifiers.meta.AdaBoostM1(); // model.setOptions( // weka.core.Utils.splitOptions( // "-P 100 -S 1 -I 10 -W weka.classifiers.trees.J48 -- -C 0.25 -M 2")); //train model Adaboot on Random Forest trees weka.classifiers.meta.AdaBoostM1 model = new weka.classifiers.meta.AdaBoostM1(); model.setOptions(weka.core.Utils .splitOptions("-P 100 -S 1 -I 10 -W weka.classifiers.trees.RandomForest -- -I 50 -K 0 -S 1")); if (Main.debug) { System.out.print("Model options: " + model.getClass().getName().trim() + " "); } System.out.print(model.getClass() + " "); for (String s : model.getOptions()) { System.out.print(s + " "); } pwout.print("Model options: " + model.getClass().getName().trim() + " "); for (String s : model.getOptions()) { pwout.print(s + " "); } //build model // model.buildClassifier(data); fc.setClassifier(model); fc.buildClassifier(data); // cross validation 10 times on the model Evaluation eval = new Evaluation(data); //eval.crossValidateModel(model, data, 10, new Random(1)); StringBuffer sb = new StringBuffer(); eval.crossValidateModel(fc, data, 10, new Random(1), sb, new Range("first,last"), false); //System.out.println(sb); pwout.println(sb); pwout.flush(); // output pwout.println("\n" + eval.toSummaryString()); System.out.println(eval.toSummaryString()); pwout.println(eval.toClassDetailsString()); System.out.println(eval.toClassDetailsString()); //calculate importants values String ev[] = eval.toClassDetailsString().split("\n"); String ptmp[] = ev[3].trim().split(" "); String ntmp[] = ev[4].trim().split(" "); String avgtmp[] = ev[5].trim().split(" "); ArrayList<String> p = new ArrayList<String>(); ArrayList<String> n = new ArrayList<String>(); ArrayList<String> avg = new ArrayList<String>(); for (String s : ptmp) { if (!s.trim().isEmpty()) { p.add(s); } } for (String s : ntmp) { if (!s.trim().isEmpty()) { n.add(s); } } for (String s : avgtmp) { if (!s.trim().isEmpty()) { avg.add(s); } } double tp = Double.parseDouble(p.get(0)); double fp = Double.parseDouble(p.get(1)); double tn = Double.parseDouble(n.get(0)); double fn = Double.parseDouble(n.get(1)); double auc = Double.parseDouble(avg.get(7)); pwout.println("\nTP=" + tp + "\nFP=" + fp + "\nTN=" + tn + "\nFN=" + fn); System.out.println("\nTP=" + tp + "\nFP=" + fp + "\nTN=" + tn + "\nFN=" + fn); //specificity, sensitivity, Mathew's correlation, Prediction accuracy double sp = ((tn) / (tn + fp)); double se = ((tp) / (tp + fn)); double acc = ((tp + tn) / (tp + tn + fp + fn)); double mcc = ((tp * tn) - (fp * fn)) / Math.sqrt((tp + fp) * (tn + fn) * (tp + fn) * tn + fp); String output = "\nse=" + dec.format(se).replace(",", ".") + "\nsp=" + dec.format(sp).replace(",", ".") + "\nACC=" + dec.format(acc).replace(",", ".") + "\nMCC=" + dec.format(mcc).replace(",", ".") + "\nAUC=" + dec.format(auc).replace(",", "."); pwout.println(output); System.out.println(output); pwout.println(eval.toMatrixString()); System.out.println(eval.toMatrixString()); pwout.flush(); pwout.close(); //Saving model System.out.println("Model saved: " + keyword + Main.modelExtension); weka.core.SerializationHelper.write(keyword + Main.modelExtension, fc.getClassifier() /*model*/); // get curve ThresholdCurve tc = new ThresholdCurve(); int classIndex = 0; Instances result = tc.getCurve(eval.predictions(), classIndex); pwroc.print(result.toString()); pwroc.flush(); pwroc.close(); // draw curve //rocCurve(eval); } catch (Exception e) { e.printStackTrace(); } }
From source file:mlpoc.MLPOC.java
/** * @param args the command line arguments *///from w ww. j a v a2 s. c o m public static void main(String[] args) { try { // TODO code application logic here BufferedReader br; br = new BufferedReader( new FileReader("D:/Extra/B.E Project/agrodeploy/webapp/Data/ClusterAutotrain12.arff")); Instances training_data = new Instances(br); br.close(); training_data.setClassIndex(training_data.numAttributes() - 1); br = new BufferedReader(new FileReader("D:/Extra/B.E Project/agrodeploy/webapp/Data/TestFinal.arff")); Instances testing_data = new Instances(br); br.close(); testing_data.setClassIndex(testing_data.numAttributes() - 1); String summary = training_data.toSummaryString(); int number_samples = training_data.numInstances(); int number_attributes_per_sample = training_data.numAttributes(); System.out.println("Number of attributes in model = " + number_attributes_per_sample); System.out.println("Number of samples = " + number_samples); System.out.println("Summary: " + summary); System.out.println(); J48 j48 = new J48(); FilteredClassifier fc = new FilteredClassifier(); fc.setClassifier(j48); fc.buildClassifier(training_data); System.out.println("Testing instances: " + testing_data.numInstances()); for (int i = 0; i < testing_data.numInstances(); i++) { double pred = fc.classifyInstance(testing_data.instance(i)); String s1 = testing_data.classAttribute().value((int) pred); System.out.println(testing_data.instance(i) + " Predicted value: " + s1); } Evaluation crossValidate = crossValidate( "D:/Extra/B.E Project/agrodeploy/webapp/Data/ClusterAutotrain12.arff"); DataSource source = new DataSource( "D:/Extra/B.E Project/agrodeploy/webapp/Data/ClusterAutotrain12.arff"); Instances data = source.getDataSet(); System.out.println(data.numInstances()); data.setClassIndex(data.numAttributes() - 1); // 1. meta-classifier useClassifier(data); // 2. filter useFilter(data); } catch (Exception ex) { Logger.getLogger(MLPOC.class.getName()).log(Level.SEVERE, null, ex); } }