List of usage examples for weka.classifiers Evaluation toSummaryString
public String toSummaryString(String title, boolean printComplexityStatistics)
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);// ww w. j av a2 s . co m Evaluation eval = new Evaluation(newTraining); eval.evaluateModel(knn, newTest); System.out.println(eval.toSummaryString("\nResults\n======\n", false)); }
From source file:lu.lippmann.cdb.datasetview.tabs.RegressionTreeTabView.java
License:Open Source License
/** * {@inheritDoc}/*from w w w . ja v a2s .co m*/ */ @SuppressWarnings("unchecked") @Override public void update0(final Instances dataSet) throws Exception { this.panel.removeAll(); //final Object[] attrNames=WekaDataStatsUtil.getNumericAttributesNames(dataSet).toArray(); final Object[] attrNames = WekaDataStatsUtil.getAttributeNames(dataSet).toArray(); final JComboBox xCombo = new JComboBox(attrNames); xCombo.setBorder(new TitledBorder("Attribute to evaluate")); final JXPanel comboPanel = new JXPanel(); comboPanel.setLayout(new GridLayout(1, 2)); comboPanel.add(xCombo); final JXButton jxb = new JXButton("Compute"); comboPanel.add(jxb); this.panel.add(comboPanel, BorderLayout.NORTH); jxb.addActionListener(new ActionListener() { @Override public void actionPerformed(ActionEvent e) { try { if (gv != null) panel.remove((Component) gv); dataSet.setClassIndex(xCombo.getSelectedIndex()); final REPTree rt = new REPTree(); rt.setNoPruning(true); //rt.setMaxDepth(3); rt.buildClassifier(dataSet); /*final M5P rt=new M5P(); rt.buildClassifier(dataSet);*/ final Evaluation eval = new Evaluation(dataSet); double[] d = eval.evaluateModel(rt, dataSet); System.out.println("PREDICTED -> " + FormatterUtil.buildStringFromArrayOfDoubles(d)); System.out.println(eval.errorRate()); System.out.println(eval.sizeOfPredictedRegions()); System.out.println(eval.toSummaryString("", true)); final GraphWithOperations gwo = GraphUtil .buildGraphWithOperationsFromWekaRegressionString(rt.graph()); final DecisionTree dt = new DecisionTree(gwo, eval.errorRate()); gv = DecisionTreeToGraphViewHelper.buildGraphView(dt, eventPublisher, commandDispatcher); gv.addMetaInfo("Size=" + dt.getSize(), ""); gv.addMetaInfo("Depth=" + dt.getDepth(), ""); gv.addMetaInfo("MAE=" + FormatterUtil.DECIMAL_FORMAT.format(eval.meanAbsoluteError()) + "", ""); gv.addMetaInfo("RMSE=" + FormatterUtil.DECIMAL_FORMAT.format(eval.rootMeanSquaredError()) + "", ""); final JCheckBox toggleDecisionTreeDetails = new JCheckBox("Toggle details"); toggleDecisionTreeDetails.addActionListener(new ActionListener() { @Override public void actionPerformed(ActionEvent e) { if (!tweakedGraph) { final Object[] mapRep = WekaDataStatsUtil .buildNodeAndEdgeRepartitionMap(dt.getGraphWithOperations(), dataSet); gv.updateVertexShapeTransformer((Map<CNode, Map<Object, Integer>>) mapRep[0]); gv.updateEdgeShapeRenderer((Map<CEdge, Float>) mapRep[1]); } else { gv.resetVertexAndEdgeShape(); } tweakedGraph = !tweakedGraph; } }); gv.addMetaInfoComponent(toggleDecisionTreeDetails); /*final JButton openInEditorButton = new JButton("Open in editor"); openInEditorButton.addActionListener(new ActionListener() { @Override public void actionPerformed(ActionEvent e) { GraphUtil.importDecisionTreeInEditor(dtFactory, dataSet, applicationContext, eventPublisher, commandDispatcher); } }); this.gv.addMetaInfoComponent(openInEditorButton);*/ final JButton showTextButton = new JButton("In text"); showTextButton.addActionListener(new ActionListener() { @Override public void actionPerformed(ActionEvent e) { JOptionPane.showMessageDialog(null, graphDsl.getDslString(dt.getGraphWithOperations())); } }); gv.addMetaInfoComponent(showTextButton); panel.add(gv.asComponent(), BorderLayout.CENTER); } catch (Exception e1) { e1.printStackTrace(); panel.add(new JXLabel("Error during computation: " + e1.getMessage()), BorderLayout.CENTER); } } }); }
From source file:lu.lippmann.cdb.dt.ModelTreeFactory.java
License:Open Source License
/** * Main method./* www . ja v a2 s. com*/ * @param args command line arguments */ public static void main(final String[] args) { try { //final String f="./samples/csv/uci/winequality-red-simplified.csv"; final String f = "./samples/csv/uci/winequality-white.csv"; //final String f="./samples/arff/UCI/crimepredict.arff"; final Instances dataSet = WekaDataAccessUtil.loadInstancesFromARFFOrCSVFile(new File(f)); System.out.println(dataSet.classAttribute().isNumeric()); final M5P rt = new M5P(); //rt.setUnpruned(true); rt.setMinNumInstances(1000); rt.buildClassifier(dataSet); System.out.println(rt); System.out.println(rt.graph()); final GraphWithOperations gwo = GraphUtil.buildGraphWithOperationsFromWekaRegressionString(rt.graph()); System.out.println(gwo); System.out.println(new ASCIIGraphDsl().getDslString(gwo)); final Evaluation eval = new Evaluation(dataSet); /*Field privateStringField = Evaluation.class.getDeclaredField("m_CoverageStatisticsAvailable"); privateStringField.setAccessible(true); //privateStringField.get boolean fieldValue = privateStringField.getBoolean(eval); System.out.println("fieldValue = " + fieldValue);*/ double[] d = eval.evaluateModel(rt, dataSet); System.out.println("PREDICTED -> " + FormatterUtil.buildStringFromArrayOfDoubles(d)); System.out.println(eval.errorRate()); System.out.println(eval.sizeOfPredictedRegions()); System.out.println(eval.toSummaryString("", true)); System.out.println(new DecisionTree(gwo, eval.errorRate())); } catch (Exception e) { e.printStackTrace(); } }
From source file:lu.lippmann.cdb.dt.RegressionTreeFactory.java
License:Open Source License
/** * Main method.//ww w . j a va2 s .co m * @param args command line arguments */ public static void main(final String[] args) { try { final String f = "./samples/csv/uci/winequality-red.csv"; //final String f="./samples/arff/UCI/crimepredict.arff"; final Instances dataSet = WekaDataAccessUtil.loadInstancesFromARFFOrCSVFile(new File(f)); System.out.println(dataSet.classAttribute().isNumeric()); final REPTree rt = new REPTree(); rt.setMaxDepth(3); rt.buildClassifier(dataSet); System.out.println(rt); //System.out.println(rt.graph()); final GraphWithOperations gwo = GraphUtil.buildGraphWithOperationsFromWekaRegressionString(rt.graph()); System.out.println(gwo); System.out.println(new ASCIIGraphDsl().getDslString(gwo)); final Evaluation eval = new Evaluation(dataSet); /*Field privateStringField = Evaluation.class.getDeclaredField("m_CoverageStatisticsAvailable"); privateStringField.setAccessible(true); //privateStringField.get boolean fieldValue = privateStringField.getBoolean(eval); System.out.println("fieldValue = " + fieldValue);*/ double[] d = eval.evaluateModel(rt, dataSet); System.out.println("PREDICTED -> " + FormatterUtil.buildStringFromArrayOfDoubles(d)); System.out.println(eval.errorRate()); System.out.println(eval.sizeOfPredictedRegions()); System.out.println(eval.toSummaryString("", true)); /*final String f2="./samples/csv/salary.csv"; final Instances dataSet2=WekaDataAccessUtil.loadInstancesFromARFFOrCSVFile(new File(f2)); final J48 j48=new J48(); j48.buildClassifier(dataSet2); System.out.println(j48.graph()); final GraphWithOperations gwo2=GraphUtil.buildGraphWithOperationsFromWekaString(j48.graph(),false); System.out.println(gwo2);*/ System.out.println(new DecisionTree(gwo, eval.errorRate())); } catch (Exception e) { e.printStackTrace(); } }
From source file:main.mFFNN.java
public static void main(String[] args) throws Exception { mFFNN m = new mFFNN(); BufferedReader breader = null; breader = new BufferedReader(new FileReader("src\\main\\iris.arff")); Instances fileTrain = new Instances(breader); fileTrain.setClassIndex(fileTrain.numAttributes() - 1); System.out.println(fileTrain); breader.close();// w w w.j av a2 s. c o m System.out.println("mFFNN!!!\n\n"); FeedForwardNeuralNetwork FFNN = new FeedForwardNeuralNetwork(); Evaluation eval = new Evaluation(fileTrain); FFNN.buildClassifier(fileTrain); eval.evaluateModel(FFNN, fileTrain); //OUTPUT Scanner scan = new Scanner(System.in); System.out.println(eval.toSummaryString("=== Stratified cross-validation ===\n" + "=== Summary ===", true)); System.out.println(eval.toClassDetailsString("=== Detailed Accuracy By Class ===")); System.out.println(eval.toMatrixString("===Confusion matrix===")); System.out.println(eval.fMeasure(1) + " " + eval.recall(1)); System.out.println("\nDo you want to save this model(1/0)? "); FFNN.distributionForInstance(fileTrain.get(0)); /* int c = scan.nextInt(); if (c == 1 ){ System.out.print("Please enter your file name (*.model) : "); String infile = scan.next(); m.saveModel(FFNN,infile); } else { System.out.print("Model not saved."); } */ }
From source file:mao.datamining.ModelProcess.java
private void testWithExtraDS(Classifier classifier, Instances finalTrainDataSet, Instances finalTestDataSet, FileOutputStream testCaseSummaryOut, TestResult result) { //Use final training dataset and final test dataset double confusionMatrix[][] = null; long start, end, trainTime = 0, testTime = 0; if (finalTestDataSet != null) { try {//from w w w . j a va2s .c o m //counting training time start = System.currentTimeMillis(); classifier.buildClassifier(finalTrainDataSet); end = System.currentTimeMillis(); trainTime += end - start; //counting test time start = System.currentTimeMillis(); Evaluation testEvalOnly = new Evaluation(finalTrainDataSet); testEvalOnly.evaluateModel(classifier, finalTestDataSet); end = System.currentTimeMillis(); testTime += end - start; testCaseSummaryOut.write("=====================================================\n".getBytes()); testCaseSummaryOut.write((testEvalOnly.toSummaryString("=== Test Summary ===", true)).getBytes()); testCaseSummaryOut.write("\n".getBytes()); testCaseSummaryOut .write((testEvalOnly.toClassDetailsString("=== Test Class Detail ===\n")).getBytes()); testCaseSummaryOut.write("\n".getBytes()); testCaseSummaryOut .write((testEvalOnly.toMatrixString("=== Confusion matrix for Test ===\n")).getBytes()); testCaseSummaryOut.flush(); confusionMatrix = testEvalOnly.confusionMatrix(); result.setConfusionMatrix4Test(confusionMatrix); result.setAUT(testEvalOnly.areaUnderROC(1)); result.setPrecision(testEvalOnly.precision(1)); result.setRecall(testEvalOnly.recall(1)); } catch (Exception e) { ModelProcess.logging(null, e); } result.setTrainingTime(trainTime); result.setTestTime(testTime); } //using test data set , end }
From source file:mao.datamining.ModelProcess.java
private void testCV(Classifier classifier, Instances finalTrainDataSet, FileOutputStream testCaseSummaryOut, TestResult result) {/*w ww .j a v a2 s. co m*/ long start, end, trainTime = 0, testTime = 0; Evaluation evalAll = null; double confusionMatrix[][] = null; // randomize data, and then stratify it into 10 groups Random rand = new Random(1); Instances randData = new Instances(finalTrainDataSet); randData.randomize(rand); if (randData.classAttribute().isNominal()) { //always run with 10 cross validation randData.stratify(folds); } try { evalAll = new Evaluation(randData); for (int i = 0; i < folds; i++) { Evaluation eval = new Evaluation(randData); Instances train = randData.trainCV(folds, i); Instances test = randData.testCV(folds, i); //counting traininig time start = System.currentTimeMillis(); Classifier j48ClassifierCopy = Classifier.makeCopy(classifier); j48ClassifierCopy.buildClassifier(train); end = System.currentTimeMillis(); trainTime += end - start; //counting test time start = System.currentTimeMillis(); eval.evaluateModel(j48ClassifierCopy, test); evalAll.evaluateModel(j48ClassifierCopy, test); end = System.currentTimeMillis(); testTime += end - start; } } catch (Exception e) { ModelProcess.logging(null, e); } //end test by cross validation // output evaluation try { ModelProcess.logging(""); //write into summary file testCaseSummaryOut .write((evalAll.toSummaryString("=== Cross Validation Summary ===", true)).getBytes()); testCaseSummaryOut.write("\n".getBytes()); testCaseSummaryOut.write( (evalAll.toClassDetailsString("=== " + folds + "-fold Cross-validation Class Detail ===\n")) .getBytes()); testCaseSummaryOut.write("\n".getBytes()); testCaseSummaryOut .write((evalAll.toMatrixString("=== Confusion matrix for all folds ===\n")).getBytes()); testCaseSummaryOut.flush(); confusionMatrix = evalAll.confusionMatrix(); result.setConfusionMatrix10Folds(confusionMatrix); } catch (Exception e) { ModelProcess.logging(null, e); } }
From source file:miRdup.WekaModule.java
License:Open Source License
public static void testModel(File testarff, String predictionsFile, String classifier, boolean predictMiRNA) { System.out.println("Testing model on " + predictionsFile + " adapted in " + testarff + ". Submitted to model " + classifier); try {//from w w w. j a v a 2 s . com //add predictions sequences to object ArrayList<MirnaObject> alobj = new ArrayList<MirnaObject>(); BufferedReader br = null; try { br = new BufferedReader(new FileReader(predictionsFile + ".folded")); } catch (FileNotFoundException fileNotFoundException) { br = new BufferedReader(new FileReader(predictionsFile)); } BufferedReader br2 = new BufferedReader(new FileReader(testarff)); String line2 = br2.readLine(); while (!line2.startsWith("@data")) { line2 = br2.readLine(); } String line = " "; int cpt = 0; while (br.ready()) { line = br.readLine(); line2 = br2.readLine(); String[] tab = line.split("\t"); MirnaObject m = new MirnaObject(); m.setArff(line2); m.setId(cpt++); m.setIdName(tab[0]); m.setMatureSequence(tab[1]); m.setPrecursorSequence(tab[2]); m.setStructure(tab[3]); alobj.add(m); } br.close(); br2.close(); // load data DataSource source = new DataSource(testarff.toString()); Instances data = source.getDataSet(); if (data.classIndex() == -1) { data.setClassIndex(data.numAttributes() - 1); } //remove ID row data.deleteAttributeAt(0); //load model Classifier model = (Classifier) weka.core.SerializationHelper.read(classifier); // evaluate dataset on the model Evaluation eval = new Evaluation(data); eval.evaluateModel(model, data); FastVector fv = eval.predictions(); // output PrintWriter pw = new PrintWriter(new FileWriter(predictionsFile + "." + classifier + ".miRdup.txt")); PrintWriter pwt = new PrintWriter( new FileWriter(predictionsFile + "." + classifier + ".miRdup.tab.txt")); PrintWriter pwout = new PrintWriter( new FileWriter(predictionsFile + "." + classifier + ".miRdupOutput.txt")); for (int i = 0; i < fv.size(); i++) { //System.out.println(fv.elementAt(i).toString()); String[] tab = fv.elementAt(i).toString().split(" "); int actual = Integer.valueOf(tab[1].substring(0, 1)); int predicted = Integer.valueOf(tab[2].substring(0, 1)); double score = 0.0; boolean validated = false; if (actual == predicted) { //case validated int s = tab[4].length(); try { score = Double.valueOf(tab[4]); //score = Double.valueOf(tab[4].substring(0, s - 1)); } catch (NumberFormatException numberFormatException) { score = 0.0; } validated = true; } else {// case not validated int s = tab[5].length(); try { score = Double.valueOf(tab[5]); //score = Double.valueOf(tab[5].substring(0, s - 1)); } catch (NumberFormatException numberFormatException) { score = 0.0; } validated = false; } MirnaObject m = alobj.get(i); m.setActual(actual); m.setPredicted(predicted); m.setScore(score); m.setValidated(validated); m.setNeedPrediction(predictMiRNA); String predictionMiRNA = ""; if (predictMiRNA && validated == false) { predictionMiRNA = miRdupPredictor.Predictor.predictionBySequence(m.getPrecursorSequence(), classifier, classifier + ".miRdupPrediction.txt"); try { m.setPredictedmiRNA(predictionMiRNA.split(",")[0]); m.setPredictedmiRNAstar(predictionMiRNA.split(",")[1]); } catch (Exception e) { m.setPredictedmiRNA(predictionMiRNA); m.setPredictedmiRNAstar(predictionMiRNA); } } pw.println(m.toStringFullPredictions()); pwt.println(m.toStringPredictions()); if (i % 100 == 0) { pw.flush(); pwt.flush(); } } //System.out.println(eval.toSummaryString("\nSummary results of predictions\n======\n", false)); String[] out = eval.toSummaryString("\nSummary results of predictions\n======\n", false).split("\n"); String info = out[0] + "\n" + out[1] + "\n" + out[2] + "\n" + out[4] + "\n" + out[5] + "\n" + out[6] + "\n" + out[7] + "\n" + out[11] + "\n"; System.out.println(info); //System.out.println("Predicted position of the miRNA by miRdup:"+predictionMiRNA); pwout.println( "File " + predictionsFile + " adapted in " + testarff + " submitted to model " + classifier); pwout.println(info); pw.flush(); pw.close(); pwt.flush(); pwt.close(); pwout.flush(); pwout.close(); System.out.println("Results in " + predictionsFile + "." + classifier + ".miRdup.txt"); // draw curve //rocCurve(eval); } catch (Exception e) { e.printStackTrace(); } }
From source file:mlpoc.MLPOC.java
public static Evaluation crossValidate(String filename) { Evaluation eval = null; try {//from w w w . jav a 2s .c o m BufferedReader br = new BufferedReader(new FileReader(filename)); // loads data and set class index Instances data = new Instances(br); br.close(); /*File csv=new File(filename); CSVLoader loader = new CSVLoader(); loader.setSource(csv); Instances data = loader.getDataSet();*/ data.setClassIndex(data.numAttributes() - 1); // classifier String[] tmpOptions; String classname = "weka.classifiers.trees.J48 -C 0.25"; tmpOptions = classname.split(" "); classname = "weka.classifiers.trees.J48"; tmpOptions[0] = ""; Classifier cls = (Classifier) Utils.forName(Classifier.class, classname, tmpOptions); // other options int seed = 2; int folds = 10; // randomize data Random rand = new Random(seed); Instances randData = new Instances(data); randData.randomize(rand); if (randData.classAttribute().isNominal()) randData.stratify(folds); // perform cross-validation eval = new Evaluation(randData); 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); // build and evaluate classifier Classifier clsCopy = Classifier.makeCopy(cls); clsCopy.buildClassifier(train); eval.evaluateModel(clsCopy, test); } // output evaluation System.out.println(); System.out.println("=== Setup ==="); System.out .println("Classifier: " + cls.getClass().getName() + " " + Utils.joinOptions(cls.getOptions())); System.out.println("Dataset: " + data.relationName()); System.out.println("Folds: " + folds); System.out.println("Seed: " + seed); System.out.println(); System.out.println(eval.toSummaryString("Summary for testing", true)); System.out.println("Correctly Classified Instances: " + eval.correct()); System.out.println("Percentage of Correctly Classified Instances: " + eval.pctCorrect()); System.out.println("InCorrectly Classified Instances: " + eval.incorrect()); System.out.println("Percentage of InCorrectly Classified Instances: " + eval.pctIncorrect()); } catch (Exception ex) { System.err.println(ex.getMessage()); } return eval; }
From source file:myclassifier.naiveBayes.java
public void TestData(Instances dataTest) throws Exception { if (data != null) { Instances train = data;/*from w w w. ja v a 2 s. c o m*/ // train classifier NBClassifier.buildClassifier(train); // evaluate classifier and print some statistics Evaluation eval = new Evaluation(dataTest); System.out.println(eval.toSummaryString("\nResults\n======\n", false)); System.out.println(eval.toClassDetailsString("\n=== Detailed Accuracy By Class ===\n")); System.out.println(eval.toMatrixString()); } else { System.out.println("Data is null"); } }