List of usage examples for weka.core Instances readInstance
@Deprecated public boolean readInstance(Reader reader) throws IOException
From source file:GClass.EvaluationInternal.java
License:Open Source License
/** * Evaluates a classifier with the options given in an array of * strings. <p>//from ww w . j av a2 s . c o m * * Valid options are: <p> * * -t name of training file <br> * Name of the file with the training data. (required) <p> * * -T name of test file <br> * Name of the file with the test data. If missing a cross-validation * is performed. <p> * * -c class index <br> * Index of the class attribute (1, 2, ...; default: last). <p> * * -x number of folds <br> * The number of folds for the cross-validation (default: 10). <p> * * -s random number seed <br> * Random number seed for the cross-validation (default: 1). <p> * * -m file with cost matrix <br> * The name of a file containing a cost matrix. <p> * * -l name of model input file <br> * Loads classifier from the given file. <p> * * -d name of model output file <br> * Saves classifier built from the training data into the given file. <p> * * -v <br> * Outputs no statistics for the training data. <p> * * -o <br> * Outputs statistics only, not the classifier. <p> * * -i <br> * Outputs detailed information-retrieval statistics per class. <p> * * -k <br> * Outputs information-theoretic statistics. <p> * * -p <br> * Outputs predictions for test instances (and nothing else). <p> * * -r <br> * Outputs cumulative margin distribution (and nothing else). <p> * * -g <br> * Only for classifiers that implement "Graphable." Outputs * the graph representation of the classifier (and nothing * else). <p> * * @param classifier machine learning classifier * @param options the array of string containing the options * @exception Exception if model could not be evaluated successfully * @return a string describing the results */ public static String[] evaluateModel(Classifier classifier, String trainFileName, String objectOutputFileName) throws Exception { Instances train = null, tempTrain, test = null, template = null; int seed = 1, folds = 10, classIndex = -1; String testFileName, sourceClass, classIndexString, seedString, foldsString, objectInputFileName, attributeRangeString; boolean IRstatistics = false, noOutput = false, printClassifications = false, trainStatistics = true, printMargins = false, printComplexityStatistics = false, printGraph = false, classStatistics = false, printSource = false; StringBuffer text = new StringBuffer(); BufferedReader trainReader = null, testReader = null; ObjectInputStream objectInputStream = null; CostMatrix costMatrix = null; StringBuffer schemeOptionsText = null; Range attributesToOutput = null; long trainTimeStart = 0, trainTimeElapsed = 0, testTimeStart = 0, testTimeElapsed = 0; try { String[] options = null; // Get basic options (options the same for all schemes) classIndexString = Utils.getOption('c', options); if (classIndexString.length() != 0) { classIndex = Integer.parseInt(classIndexString); } // trainFileName = Utils.getOption('t', options); objectInputFileName = Utils.getOption('l', options); // objectOutputFileName = Utils.getOption('d', options); testFileName = Utils.getOption('T', options); if (trainFileName.length() == 0) { if (objectInputFileName.length() == 0) { throw new Exception("No training file and no object " + "input file given."); } if (testFileName.length() == 0) { throw new Exception("No training file and no test " + "file given."); } } else if ((objectInputFileName.length() != 0) && ((!(classifier instanceof UpdateableClassifier)) || (testFileName.length() == 0))) { throw new Exception("Classifier not incremental, or no " + "test file provided: can't " + "use both train and model file."); } try { if (trainFileName.length() != 0) { trainReader = new BufferedReader(new FileReader(trainFileName)); } if (testFileName.length() != 0) { testReader = new BufferedReader(new FileReader(testFileName)); } if (objectInputFileName.length() != 0) { InputStream is = new FileInputStream(objectInputFileName); if (objectInputFileName.endsWith(".gz")) { is = new GZIPInputStream(is); } objectInputStream = new ObjectInputStream(is); } } catch (Exception e) { throw new Exception("Can't open file " + e.getMessage() + '.'); } if (testFileName.length() != 0) { template = test = new Instances(testReader, 1); if (classIndex != -1) { test.setClassIndex(classIndex - 1); } else { test.setClassIndex(test.numAttributes() - 1); } if (classIndex > test.numAttributes()) { throw new Exception("Index of class attribute too large."); } } if (trainFileName.length() != 0) { if ((classifier instanceof UpdateableClassifier) && (testFileName.length() != 0)) { train = new Instances(trainReader, 1); } else { train = new Instances(trainReader); } template = train; if (classIndex != -1) { train.setClassIndex(classIndex - 1); } else { train.setClassIndex(train.numAttributes() - 1); } if ((testFileName.length() != 0) && !test.equalHeaders(train)) { throw new IllegalArgumentException("Train and test file not compatible!"); } if (classIndex > train.numAttributes()) { throw new Exception("Index of class attribute too large."); } //train = new Instances(train); } if (template == null) { throw new Exception("No actual dataset provided to use as template"); } seedString = Utils.getOption('s', options); if (seedString.length() != 0) { seed = Integer.parseInt(seedString); } foldsString = Utils.getOption('x', options); if (foldsString.length() != 0) { folds = Integer.parseInt(foldsString); } costMatrix = handleCostOption(Utils.getOption('m', options), template.numClasses()); classStatistics = Utils.getFlag('i', options); noOutput = Utils.getFlag('o', options); trainStatistics = !Utils.getFlag('v', options); printComplexityStatistics = Utils.getFlag('k', options); printMargins = Utils.getFlag('r', options); printGraph = Utils.getFlag('g', options); sourceClass = Utils.getOption('z', options); printSource = (sourceClass.length() != 0); // Check -p option try { attributeRangeString = Utils.getOption('p', options); } catch (Exception e) { throw new Exception(e.getMessage() + "\nNOTE: the -p option has changed. " + "It now expects a parameter specifying a range of attributes " + "to list with the predictions. Use '-p 0' for none."); } if (attributeRangeString.length() != 0) { printClassifications = true; if (!attributeRangeString.equals("0")) { attributesToOutput = new Range(attributeRangeString); } } // If a model file is given, we can't process // scheme-specific options if (objectInputFileName.length() != 0) { Utils.checkForRemainingOptions(options); } else { // Set options for classifier if (classifier instanceof OptionHandler) { /* for (int i = 0; i < options.length; i++) { if (options[i].length() != 0) { if (schemeOptionsText == null) { schemeOptionsText = new StringBuffer(); } if (options[i].indexOf(' ') != -1) { schemeOptionsText.append('"' + options[i] + "\" "); } else { schemeOptionsText.append(options[i] + " "); } } } */ ((OptionHandler) classifier).setOptions(options); } } Utils.checkForRemainingOptions(options); } catch (Exception e) { throw new Exception("\nWeka exception: " + e.getMessage() + makeOptionString(classifier)); } // Setup up evaluation objects EvaluationInternal trainingEvaluation = new EvaluationInternal(new Instances(template, 0), costMatrix); EvaluationInternal testingEvaluation = new EvaluationInternal(new Instances(template, 0), costMatrix); if (objectInputFileName.length() != 0) { // Load classifier from file classifier = (Classifier) objectInputStream.readObject(); objectInputStream.close(); } // Build the classifier if no object file provided if ((classifier instanceof UpdateableClassifier) && (testFileName.length() != 0) && (costMatrix == null) && (trainFileName.length() != 0)) { // Build classifier incrementally trainingEvaluation.setPriors(train); testingEvaluation.setPriors(train); trainTimeStart = System.currentTimeMillis(); if (objectInputFileName.length() == 0) { classifier.buildClassifier(train); } while (train.readInstance(trainReader)) { trainingEvaluation.updatePriors(train.instance(0)); testingEvaluation.updatePriors(train.instance(0)); ((UpdateableClassifier) classifier).updateClassifier(train.instance(0)); train.delete(0); } trainTimeElapsed = System.currentTimeMillis() - trainTimeStart; trainReader.close(); } else if (objectInputFileName.length() == 0) { // Build classifier in one go tempTrain = new Instances(train); trainingEvaluation.setPriors(tempTrain); testingEvaluation.setPriors(tempTrain); trainTimeStart = System.currentTimeMillis(); classifier.buildClassifier(tempTrain); trainTimeElapsed = System.currentTimeMillis() - trainTimeStart; } // Save the classifier if an object output file is provided if (objectOutputFileName.length() != 0) { OutputStream os = new FileOutputStream(objectOutputFileName); if (objectOutputFileName.endsWith(".gz")) { os = new GZIPOutputStream(os); } ObjectOutputStream objectOutputStream = new ObjectOutputStream(os); objectOutputStream.writeObject(classifier); objectOutputStream.flush(); objectOutputStream.close(); } /* // If classifier is drawable output string describing graph if ((classifier instanceof Drawable) && (printGraph)) { return ((Drawable) classifier).graph(); } // Output the classifier as equivalent source if ((classifier instanceof Sourcable) && (printSource)) { return wekaStaticWrapper((Sourcable) classifier, sourceClass); } // Output test instance predictions only if (printClassifications) { return printClassifications(classifier, new Instances(template, 0), testFileName, classIndex, attributesToOutput); } */ // Output model if (!(noOutput || printMargins)) { if (classifier instanceof OptionHandler) { if (schemeOptionsText != null) { text.append("\nOptions: " + schemeOptionsText); text.append("\n"); } } text.append("\n" + classifier.toString() + "\n"); } if (!printMargins && (costMatrix != null)) { text.append("\n=== Evaluation Cost Matrix ===\n\n").append(costMatrix.toString()); } // Compute error estimate from training data if ((trainStatistics) && (trainFileName.length() != 0)) { if ((classifier instanceof UpdateableClassifier) && (testFileName.length() != 0) && (costMatrix == null)) { // Classifier was trained incrementally, so we have to // reopen the training data in order to test on it. trainReader = new BufferedReader(new FileReader(trainFileName)); // Incremental testing train = new Instances(trainReader, 1); if (classIndex != -1) { train.setClassIndex(classIndex - 1); } else { train.setClassIndex(train.numAttributes() - 1); } testTimeStart = System.currentTimeMillis(); while (train.readInstance(trainReader)) { trainingEvaluation.evaluateModelOnce((Classifier) classifier, train.instance(0)); train.delete(0); } testTimeElapsed = System.currentTimeMillis() - testTimeStart; trainReader.close(); } else { testTimeStart = System.currentTimeMillis(); trainingEvaluation.evaluateModel(classifier, train); testTimeElapsed = System.currentTimeMillis() - testTimeStart; } // Print the results of the training evaluation // if (printMargins) { // return trainingEvaluation.toCumulativeMarginDistributionString(); // } else { text.append("\nTime taken to build model: " + Utils.doubleToString(trainTimeElapsed / 1000.0, 2) + " seconds"); text.append("\nTime taken to test model on training data: " + Utils.doubleToString(testTimeElapsed / 1000.0, 2) + " seconds"); text.append(trainingEvaluation.toSummaryString("\n\n=== Error on training" + " data ===\n", printComplexityStatistics)); if (template.classAttribute().isNominal()) { if (classStatistics) { text.append("\n\n" + trainingEvaluation.toClassDetailsString()); } text.append("\n\n" + trainingEvaluation.toMatrixString()); } // } } // Compute proper error estimates if (testFileName.length() != 0) { // Testing is on the supplied test data while (test.readInstance(testReader)) { testingEvaluation.evaluateModelOnce((Classifier) classifier, test.instance(0)); test.delete(0); } testReader.close(); text.append("\n\n" + testingEvaluation.toSummaryString("=== Error on test data ===\n", printComplexityStatistics)); } else if (trainFileName.length() != 0) { // Testing is via cross-validation on training data Random random = new Random(seed); testingEvaluation.crossValidateModel(classifier, train, folds, random); if (template.classAttribute().isNumeric()) { text.append("\n\n\n" + testingEvaluation.toSummaryString("=== Cross-validation ===\n", printComplexityStatistics)); } else { text.append("\n\n\n" + testingEvaluation .toSummaryString("=== Stratified " + "cross-validation ===\n", printComplexityStatistics)); } } if (template.classAttribute().isNominal()) { if (classStatistics) { text.append("\n\n" + testingEvaluation.toClassDetailsString()); } text.append("\n\n" + testingEvaluation.toMatrixString()); } String result = "\t" + Utils.doubleToString(trainingEvaluation.pctCorrect(), 12, 4) + " %"; result += " " + Utils.doubleToString(testingEvaluation.pctCorrect(), 12, 4) + " %"; String[] returnString = { text.toString(), result }; return returnString; }
From source file:GClass.EvaluationInternal.java
License:Open Source License
/** * Prints the predictions for the given dataset into a String variable. *///w w w .j a v a2 s . com protected static String printClassifications(Classifier classifier, Instances train, String testFileName, int classIndex, Range attributesToOutput) throws Exception { StringBuffer text = new StringBuffer(); if (testFileName.length() != 0) { BufferedReader testReader = null; try { testReader = new BufferedReader(new FileReader(testFileName)); } catch (Exception e) { throw new Exception("Can't open file " + e.getMessage() + '.'); } Instances test = new Instances(testReader, 1); if (classIndex != -1) { test.setClassIndex(classIndex - 1); } else { test.setClassIndex(test.numAttributes() - 1); } int i = 0; while (test.readInstance(testReader)) { Instance instance = test.instance(0); Instance withMissing = (Instance) instance.copy(); withMissing.setDataset(test); double predValue = ((Classifier) classifier).classifyInstance(withMissing); if (test.classAttribute().isNumeric()) { if (Instance.isMissingValue(predValue)) { text.append(i + " missing "); } else { text.append(i + " " + predValue + " "); } if (instance.classIsMissing()) { text.append("missing"); } else { text.append(instance.classValue()); } text.append(" " + attributeValuesString(withMissing, attributesToOutput) + "\n"); } else { if (Instance.isMissingValue(predValue)) { text.append(i + " missing "); } else { text.append(i + " " + test.classAttribute().value((int) predValue) + " "); } if (Instance.isMissingValue(predValue)) { text.append("missing "); } else { text.append(classifier.distributionForInstance(withMissing)[(int) predValue] + " "); } text.append(instance.toString(instance.classIndex()) + " " + attributeValuesString(withMissing, attributesToOutput) + "\n"); } test.delete(0); i++; } testReader.close(); } return text.toString(); }
From source file:moa.streams.clustering.FileStream.java
License:Apache License
/** * @param ignoredAttributes Attributes that will be ignored * @return A list with min/max and diff=max-min values per attribute of the arff file *///from ww w. ja v a 2 s .co m protected ArrayList<Double[]> readMinMaxDiffValues(HashSet<Integer> ignoredAttributes) { ArrayList<Double[]> valuesMinMaxDiff = null; if (ignoredAttributes == null) ignoredAttributes = new HashSet<Integer>(); try { InputStream fileStream = new FileInputStream(arffFileOption.getFile()); InputStreamProgressMonitor fileProgressMonitor = new InputStreamProgressMonitor(fileStream); Reader fileReader = new BufferedReader(new InputStreamReader(fileProgressMonitor)); Instances instances = new Instances(fileReader, 1); valuesMinMaxDiff = new ArrayList<Double[]>(); for (int i = 0; i < instances.numAttributes() - ignoredAttributes.size(); i++) { Double[] values = { Double.POSITIVE_INFINITY, Double.NEGATIVE_INFINITY, 0.0 }; valuesMinMaxDiff.add(values); } System.out.print("Reading arff file for normalization..."); int counter = 0; while (instances.readInstance(fileReader)) { Instance instance = instances.instance(0); int a = 0; for (int i = 0; i < instances.numAttributes(); i++) { if (!ignoredAttributes.contains(i)) { double value = instance.value(i); if (value < valuesMinMaxDiff.get(a)[0]) valuesMinMaxDiff.get(a)[0] = value; if (value > valuesMinMaxDiff.get(a)[1]) valuesMinMaxDiff.get(a)[1] = value; a++; } } instances.delete(); //show some progress counter++; if (counter >= 10000) { counter = 0; System.out.print("."); } } if (fileReader != null) { fileReader.close(); fileReader = null; } System.out.println("done!"); for (int i = 0; i < valuesMinMaxDiff.size(); i++) { valuesMinMaxDiff.get(i)[2] = valuesMinMaxDiff.get(i)[1] - valuesMinMaxDiff.get(i)[0]; } return valuesMinMaxDiff; } catch (IOException ioe) { throw new RuntimeException("ArffFileStream failed to read instance from stream.", ioe); } }