List of usage examples for weka.classifiers.trees J48 classifyInstance
@Override public double classifyInstance(Instance instance) throws Exception
From source file:com.relationalcloud.main.Explanation.java
License:Open Source License
/** * @param args//from w w w . java 2s .c o m */ public static void main(String[] args) { // LOADING PROPERTY FILE AND DRIVER Properties ini = new Properties(); try { ini.load(new FileInputStream(System.getProperty("prop"))); } catch (FileNotFoundException e) { e.printStackTrace(); } catch (IOException e) { e.printStackTrace(); } // Register jdbcDriver try { Class.forName(ini.getProperty("driver")); } catch (ClassNotFoundException e) { e.printStackTrace(); } // LOAD PROPERTIES FROM CONFIGURATION FILE String connection = ini.getProperty("conn"); String schemaname = ini.getProperty("schema"); String user = ini.getProperty("user"); String password = ini.getProperty("password"); String txnLogTable = ini.getProperty("txnLogTable"); String numb_trans_to_process = ini.getProperty("Explanation.numTxnsToExtractTemplates"); int numPart = Integer.parseInt(ini.getProperty("numPartitions")); // Initialize the Justification Handler ExplanationHandler jh = new ExplanationHandler(ini); System.out.println("Loading and processing " + jh.schemaname + " traces... considering prop file :" + jh.dbPropertyFile); try { // CREATE A DB CONNEctioN Connection conn = DriverManager.getConnection(connection + schemaname, user, password); Connection infschema_conn = DriverManager.getConnection(connection + "information_schema", user, password); Schema schema = SchemaLoader.loadSchemaFromDB(infschema_conn, schemaname); // ANALYZE WORKLOADS EXTRACTING TABLES, ATTRIBUTES AND FREQUENCIES ExplanationWorkloadPrepocessor wa = ExplanationHandler.analyzeWorkload(txnLogTable, numb_trans_to_process, schemaname, conn, schema); // FOR EACH TABLE CLASSIFY AND POPULATE JUSTIFICATION COLUMN for (String tableProcessed : wa.getAllTableNames()) { System.out.println("-------------------------------------------"); System.out.println("ANALYZING TABLE " + tableProcessed); // FETCH THE INSTANCE FROM THE DB AND SAMPLE IT Instances data = jh.generateInstancesForTable(tableProcessed, wa.getFeatures(tableProcessed), conn); // IF THERE IS ONLY THE PARTITION LABEL, SKIP THE TABLE if (data.numAttributes() < 2) { System.out.println("No transactions touches this table, nothing to be done."); continue; } // INSTANTIATE THE CLASSIFIER String[] options; options = new String[3]; options[0] = "-P"; options[1] = "-C"; options[2] = ini.getProperty("Explanation.j48PruningConfidence"); J48 classifier = new J48(); // new instance of tree classifier.setOptions(options); // set the options Boolean attributeFilter = true; // ATTRIBUTE FILTERING Instances newData; if (data.numClasses() > 1 && attributeFilter) { AttributeSelection filter = new AttributeSelection(); //FIXME TRYING ALTERNATIVE ATTRIBUTE SELECTION STRATEGIES //InfoGainAttributeEval eval = new InfoGainAttributeEval(); //Ranker search = new Ranker(); //search.setNumToSelect(Integer.parseInt(ini.getProperty("Explanation.maxNumberOfAttribute","2"))); CfsSubsetEval eval = new CfsSubsetEval(); GreedyStepwise search = new GreedyStepwise(); search.setSearchBackwards(true); filter.setEvaluator(eval); filter.setSearch(search); filter.setInputFormat(data); newData = Filter.useFilter(data, filter); } else { newData = data; } String atts = ""; Enumeration e = newData.enumerateAttributes(); ArrayList<String> attributesForPopulation = new ArrayList<String>(); while (e.hasMoreElements()) { String s = ((Attribute) e.nextElement()).name(); attributesForPopulation.add(s); atts += s + ", "; } atts = atts.substring(0, atts.length() - 2); System.out.println("Attribute filtering reduced " + (data.numAttributes() - 1) + " to " + (newData.numAttributes() - 1) + " (" + atts + ")"); data = null; System.gc(); if (newData.numInstances() < 1) { System.err.println("The are no data in the table, skipping classification"); continue; } if (newData.numInstances() > 0) { if (newData.classAttribute().numValues() > 1) { // TRAIN THE CLASSIFIER AND PRINT OUT CLASSIFIER RULES ExplanationHandler.trainClassifier(newData, classifier); if (classifier.measureNumLeaves() == 1) { int partitionvalue = (int) classifier.classifyInstance(newData.firstInstance()); System.out.println( "The classifier decided to put all the tuplesi in the table in one partition: " + partitionvalue); if (Boolean.parseBoolean(ini.getProperty("Explanation.populateExplainedColumn"))) { jh.populateExplainedColumn(tableProcessed, partitionvalue, attributesForPopulation, conn); } } // POPULATING THE justifiedpartition column with the result of this // classifier if required else if (Boolean.parseBoolean(ini.getProperty("Explanation.populateExplainedColumn"))) { jh.populateJustifiedColumn(tableProcessed, classifier, attributesForPopulation, conn, numPart, newData.classAttribute().enumerateValues()); } } else { // easy case... the class attribute is unary!! int partitionvalue = ((int) newData.firstInstance() .value(newData.firstInstance().classIndex())); System.out.println("The table is all stored in one partition, no need to use classifier"); if (Boolean.parseBoolean(ini.getProperty("Explanation.populateExplainedColumn"))) { jh.populateExplainedColumn(tableProcessed, partitionvalue, attributesForPopulation, conn); } } } else throw new Exception("The Instances is empty"); } // SET HASH PARTITION / REPLICATED PARTITION if (Boolean.parseBoolean(ini.getProperty("Explanation.populateHashColumn"))) { jh.populateHashPartition(conn); } if (Boolean.parseBoolean(ini.getProperty("Explanation.populateReplicatedColumn"))) { jh.populateReplicatedPartition(conn, Boolean.parseBoolean(ini.getProperty("Explanation.defaultReplicate"))); } conn.close(); } catch (SQLException e) { e.printStackTrace(); } catch (Exception e) { // TODO Auto-generated catch block e.printStackTrace(); } }
From source file:controller.BothClassificationsServlet.java
@Override protected void doPost(HttpServletRequest request, HttpServletResponse response) throws ServletException, IOException { request.setCharacterEncoding("UTF-8"); String dir = "/data/"; String path = getServletContext().getRealPath(dir); String action = request.getParameter("action"); switch (action) { case "create": { String fileName = request.getParameter("file"); String aux = fileName.substring(0, fileName.indexOf(".")); String pathInput = path + "/" + request.getParameter("file"); String pathTrainingOutput = path + "/" + aux + "-training-arff.txt"; String pathTestOutput = path + "/" + aux + "-test-arff.txt"; String pathBothClassifications = path + "/" + aux + "-bothClassifications.txt"; String name = request.getParameter("name"); int range = Integer.parseInt(request.getParameter("range")); int size = Integer.parseInt(request.getParameter("counter")); String[] columns = new String[size]; String[] types = new String[size]; int[] positions = new int[size]; int counter = 0; for (int i = 0; i < size; i++) { if (request.getParameter("column-" + (i + 1)) != null) { columns[counter] = request.getParameter("column-" + (i + 1)); types[counter] = request.getParameter("type-" + (i + 1)); positions[counter] = Integer.parseInt(request.getParameter("position-" + (i + 1))); counter++;// w ww.j a v a 2 s . c om } } FormatFiles.convertTxtToArff(pathInput, pathTrainingOutput, pathTestOutput, name, columns, types, positions, counter, range); try { J48 j48 = new J48(); BufferedReader readerTraining = new BufferedReader(new FileReader(pathTrainingOutput)); Instances instancesTraining = new Instances(readerTraining); instancesTraining.setClassIndex(instancesTraining.numAttributes() - 1); j48.buildClassifier(instancesTraining); BufferedReader readerTest = new BufferedReader(new FileReader(pathTestOutput)); //BufferedReader readerTest = new BufferedReader(new FileReader(pathTrainingOutput)); Instances instancesTest = new Instances(readerTest); instancesTest.setClassIndex(instancesTest.numAttributes() - 1); int correctsDecisionTree = 0; for (int i = 0; i < instancesTest.size(); i++) { Instance instance = instancesTest.get(i); double correctValue = instance.value(instance.attribute(instancesTest.numAttributes() - 1)); double classification = j48.classifyInstance(instance); if (correctValue == classification) { correctsDecisionTree++; } } Evaluation eval = new Evaluation(instancesTraining); eval.evaluateModel(j48, instancesTest); PrintWriter writer = new PrintWriter( new BufferedWriter(new FileWriter(pathBothClassifications, false))); writer.println("?rvore de Deciso\n\n"); writer.println(j48.toString()); writer.println(""); writer.println(""); writer.println("Results"); writer.println(eval.toSummaryString()); NaiveBayes naiveBayes = new NaiveBayes(); naiveBayes.buildClassifier(instancesTraining); eval = new Evaluation(instancesTraining); eval.evaluateModel(naiveBayes, instancesTest); int correctsNaiveBayes = 0; for (int i = 0; i < instancesTest.size(); i++) { Instance instance = instancesTest.get(i); double correctValue = instance.value(instance.attribute(instancesTest.numAttributes() - 1)); double classification = naiveBayes.classifyInstance(instance); if (correctValue == classification) { correctsNaiveBayes++; } } writer.println("Naive Bayes\n\n"); writer.println(naiveBayes.toString()); writer.println(""); writer.println(""); writer.println("Results"); writer.println(eval.toSummaryString()); writer.close(); response.sendRedirect("BothClassifications?action=view&correctsDecisionTree=" + correctsDecisionTree + "&correctsNaiveBayes=" + correctsNaiveBayes + "&totalTest=" + instancesTest.size() + "&totalTrainig=" + instancesTraining.size() + "&range=" + range + "&fileName=" + aux + "-bothClassifications.txt"); } catch (Exception e) { System.out.println(e.getMessage()); response.sendRedirect("Navigation?action=decisionTree"); } break; } default: response.sendError(404); } }
From source file:controller.DecisionTreeServlet.java
@Override protected void doPost(HttpServletRequest request, HttpServletResponse response) throws ServletException, IOException { request.setCharacterEncoding("UTF-8"); String dir = "/data/"; String path = getServletContext().getRealPath(dir); String action = request.getParameter("action"); switch (action) { case "create": { String fileName = request.getParameter("file"); String aux = fileName.substring(0, fileName.indexOf(".")); String pathInput = path + "/" + request.getParameter("file"); String pathTrainingOutput = path + "/" + aux + "-training-arff.txt"; String pathTestOutput = path + "/" + aux + "-test-arff.txt"; String pathDecisionTree = path + "/" + aux + "-decisionTree.txt"; String name = request.getParameter("name"); int range = Integer.parseInt(request.getParameter("range")); int size = Integer.parseInt(request.getParameter("counter")); String[] columns = new String[size]; String[] types = new String[size]; int[] positions = new int[size]; int counter = 0; for (int i = 0; i < size; i++) { if (request.getParameter("column-" + (i + 1)) != null) { columns[counter] = request.getParameter("column-" + (i + 1)); types[counter] = request.getParameter("type-" + (i + 1)); positions[counter] = Integer.parseInt(request.getParameter("position-" + (i + 1))); counter++;/*from ww w .java 2s .co m*/ } } FormatFiles.convertTxtToArff(pathInput, pathTrainingOutput, pathTestOutput, name, columns, types, positions, counter, range); try { J48 j48 = new J48(); BufferedReader readerTraining = new BufferedReader(new FileReader(pathTrainingOutput)); Instances instancesTraining = new Instances(readerTraining); instancesTraining.setClassIndex(instancesTraining.numAttributes() - 1); j48.buildClassifier(instancesTraining); BufferedReader readerTest = new BufferedReader(new FileReader(pathTestOutput)); //BufferedReader readerTest = new BufferedReader(new FileReader(pathTrainingOutput)); Instances instancesTest = new Instances(readerTest); instancesTest.setClassIndex(instancesTest.numAttributes() - 1); int corrects = 0; int truePositive = 0; int trueNegative = 0; int falsePositive = 0; int falseNegative = 0; for (int i = 0; i < instancesTest.size(); i++) { Instance instance = instancesTest.get(i); double correctValue = instance.value(instance.attribute(instancesTest.numAttributes() - 1)); double classification = j48.classifyInstance(instance); if (correctValue == classification) { corrects++; } if (correctValue == 1 && classification == 1) { truePositive++; } if (correctValue == 1 && classification == 0) { falseNegative++; } if (correctValue == 0 && classification == 1) { falsePositive++; } if (correctValue == 0 && classification == 0) { trueNegative++; } } Evaluation eval = new Evaluation(instancesTraining); eval.evaluateModel(j48, instancesTest); PrintWriter writer = new PrintWriter(new BufferedWriter(new FileWriter(pathDecisionTree, false))); writer.println(j48.toString()); writer.println(""); writer.println(""); writer.println("Results"); writer.println(eval.toSummaryString()); writer.close(); response.sendRedirect("DecisionTree?action=view&corrects=" + corrects + "&totalTest=" + instancesTest.size() + "&totalTrainig=" + instancesTraining.size() + "&truePositive=" + truePositive + "&trueNegative=" + trueNegative + "&falsePositive=" + falsePositive + "&falseNegative=" + falseNegative + "&fileName=" + aux + "-decisionTree.txt"); } catch (Exception e) { System.out.println(e.getMessage()); response.sendRedirect("Navigation?action=decisionTree"); } break; } default: response.sendError(404); } }
From source file:cs.man.ac.uk.predict.Predictor.java
License:Open Source License
public static void makePredictionsEnsembleNew(String trainPath, String testPath, String resultPath) { System.out.println("Training set: " + trainPath); System.out.println("Test set: " + testPath); /**// w ww . j a v a 2 s. c o m * The ensemble classifiers. This is a heterogeneous ensemble. */ J48 learner1 = new J48(); SMO learner2 = new SMO(); NaiveBayes learner3 = new NaiveBayes(); MultilayerPerceptron learner5 = new MultilayerPerceptron(); System.out.println("Training Ensemble."); long startTime = System.nanoTime(); try { BufferedReader reader = new BufferedReader(new FileReader(trainPath)); Instances data = new Instances(reader); data.setClassIndex(data.numAttributes() - 1); System.out.println("Training data length: " + data.numInstances()); learner1.buildClassifier(data); learner2.buildClassifier(data); learner3.buildClassifier(data); learner5.buildClassifier(data); long endTime = System.nanoTime(); long nanoseconds = endTime - startTime; double seconds = (double) nanoseconds / 1000000000.0; System.out.println("Training Ensemble completed in " + nanoseconds + " (ns) or " + seconds + " (s)."); } catch (IOException e) { System.out.println("Could not train Ensemble classifier IOException on training data file."); } catch (Exception e) { System.out.println("Could not train Ensemble classifier Exception building model."); } try { String line = ""; // Read the file and display it line by line. BufferedReader in = null; // Read in and store each positive prediction in the tree map. try { //open stream to file in = new BufferedReader(new FileReader(testPath)); while ((line = in.readLine()) != null) { if (line.toLowerCase().contains("@data")) break; } } catch (Exception e) { } // A different ARFF loader used here (compared to above) as // the ARFF file may be extremely large. In which case the whole // file cannot be read in. Instead it is read in incrementally. ArffLoader loader = new ArffLoader(); loader.setFile(new File(testPath)); Instances data = loader.getStructure(); data.setClassIndex(data.numAttributes() - 1); System.out.println("Ensemble Classifier is ready."); System.out.println("Testing on all instances avaialable."); startTime = System.nanoTime(); int instanceNumber = 0; // label instances Instance current; while ((current = loader.getNextInstance(data)) != null) { instanceNumber += 1; line = in.readLine(); double classification1 = learner1.classifyInstance(current); double classification2 = learner2.classifyInstance(current); double classification3 = learner3.classifyInstance(current); double classification5 = learner5.classifyInstance(current); // All classifiers must agree. This is a very primitive ensemble strategy! if (classification1 == 1 && classification2 == 1 && classification3 == 1 && classification5 == 1) { if (line != null) { //System.out.println("Instance: "+instanceNumber+"\t"+line); //System.in.read(); } Writer.append(resultPath, instanceNumber + "\n"); } } in.close(); System.out.println("Test set instances: " + instanceNumber); long endTime = System.nanoTime(); long duration = endTime - startTime; double seconds = (double) duration / 1000000000.0; System.out.println("Testing Ensemble completed in " + duration + " (ns) or " + seconds + " (s)."); } catch (Exception e) { System.out.println("Could not test Ensemble classifier due to an error."); } }
From source file:cs.man.ac.uk.predict.Predictor.java
License:Open Source License
public static void makePredictionsEnsembleStream(String trainPath, String testPath, String resultPath) { System.out.println("Training set: " + trainPath); System.out.println("Test set: " + testPath); /**//from w w w. j av a 2 s . co m * The ensemble classifiers. This is a heterogeneous ensemble. */ J48 learner1 = new J48(); SMO learner2 = new SMO(); NaiveBayes learner3 = new NaiveBayes(); MultilayerPerceptron learner5 = new MultilayerPerceptron(); System.out.println("Training Ensemble."); long startTime = System.nanoTime(); try { BufferedReader reader = new BufferedReader(new FileReader(trainPath)); Instances data = new Instances(reader); data.setClassIndex(data.numAttributes() - 1); System.out.println("Training data length: " + data.numInstances()); learner1.buildClassifier(data); learner2.buildClassifier(data); learner3.buildClassifier(data); learner5.buildClassifier(data); long endTime = System.nanoTime(); long nanoseconds = endTime - startTime; double seconds = (double) nanoseconds / 1000000000.0; System.out.println("Training Ensemble completed in " + nanoseconds + " (ns) or " + seconds + " (s)."); } catch (IOException e) { System.out.println("Could not train Ensemble classifier IOException on training data file."); } catch (Exception e) { System.out.println("Could not train Ensemble classifier Exception building model."); } try { // A different ARFF loader used here (compared to above) as // the ARFF file may be extremely large. In which case the whole // file cannot be read in. Instead it is read in incrementally. ArffLoader loader = new ArffLoader(); loader.setFile(new File(testPath)); Instances data = loader.getStructure(); data.setClassIndex(data.numAttributes() - 1); System.out.println("Ensemble Classifier is ready."); System.out.println("Testing on all instances avaialable."); startTime = System.nanoTime(); int instanceNumber = 0; // label instances Instance current; while ((current = loader.getNextInstance(data)) != null) { instanceNumber += 1; double classification1 = learner1.classifyInstance(current); double classification2 = learner2.classifyInstance(current); double classification3 = learner3.classifyInstance(current); double classification5 = learner5.classifyInstance(current); // All classifiers must agree. This is a very primitive ensemble strategy! if (classification1 == 1 && classification2 == 1 && classification3 == 1 && classification5 == 1) { Writer.append(resultPath, instanceNumber + "\n"); } } System.out.println("Test set instances: " + instanceNumber); long endTime = System.nanoTime(); long duration = endTime - startTime; double seconds = (double) duration / 1000000000.0; System.out.println("Testing Ensemble completed in " + duration + " (ns) or " + seconds + " (s)."); } catch (Exception e) { System.out.println("Could not test Ensemble classifier due to an error."); } }
From source file:cs.man.ac.uk.predict.Predictor.java
License:Open Source License
public static void makePredictionsJ48(String trainPath, String testPath, String resultPath) { /**/*from w w w . j a v a2s .c om*/ * The decision tree classifier. */ J48 learner = new J48(); System.out.println("Training set: " + trainPath); System.out.println("Test set: " + testPath); System.out.println("Training J48"); long startTime = System.nanoTime(); try { BufferedReader reader = new BufferedReader(new FileReader(trainPath)); Instances data = new Instances(reader); data.setClassIndex(data.numAttributes() - 1); System.out.println("Training data length: " + data.numInstances()); learner.buildClassifier(data); long endTime = System.nanoTime(); long nanoseconds = endTime - startTime; double seconds = (double) nanoseconds / 1000000000.0; System.out.println("Training J48 completed in " + nanoseconds + " (ns) or " + seconds + " (s)"); } catch (IOException e) { System.out.println("Could not train J48 classifier IOException on training data file"); } catch (Exception e) { System.out.println("Could not train J48 classifier Exception building model"); } try { // Prepare data for testing //BufferedReader reader = new BufferedReader( new FileReader(testPath)); //Instances data = new Instances(reader); //data.setClassIndex(data.numAttributes() - 1); ArffLoader loader = new ArffLoader(); loader.setFile(new File(testPath)); Instances data = loader.getStructure(); data.setClassIndex(data.numAttributes() - 1); System.out.println("J48 Classifier is ready."); System.out.println("Testing on all instances avaialable."); System.out.println("Test set instances: " + data.numInstances()); startTime = System.nanoTime(); int instanceNumber = 0; // label instances Instance current; //for (int i = 0; i < data.numInstances(); i++) while ((current = loader.getNextInstance(data)) != null) { instanceNumber += 1; //double classification = learner.classifyInstance(data.instance(i)); double classification = learner.classifyInstance(current); //String instanceClass= Double.toString(data.instance(i).classValue()); if (classification == 1)// Predicted positive, actually negative { Writer.append(resultPath, instanceNumber + "\n"); } } long endTime = System.nanoTime(); long duration = endTime - startTime; double seconds = (double) duration / 1000000000.0; System.out.println("Testing J48 completed in " + duration + " (ns) or " + seconds + " (s)"); } catch (Exception e) { System.out.println("Could not test J48 classifier due to an error"); } }
From source file:DataMiningLogHistoriKIRI.DecisionTree.java
public String[] id3(Instances arff) { J48 tree = new J48(); try {/* www . j a va 2 s . c o m*/ tree.buildClassifier(arff); } catch (Exception ex) { Logger.getLogger(Controller.class.getName()).log(Level.SEVERE, null, ex); } System.out.println(tree.toString()); int nilaiBenar = 0, resultInt; float result = 0; for (int i = 0; i < arff.numInstances(); i++) { try { result = (float) tree.classifyInstance(arff.instance(i)); resultInt = Math.round(result); //System.out.println(dataAfterPreprocessing.get(i)[6] + " " + arff.instance(i).stringValue(6)); if (resultInt == Integer.parseInt(arff.instance(i).stringValue(6))) { nilaiBenar++; } } catch (Exception ex) { Logger.getLogger(Controller.class.getName()).log(Level.SEVERE, null, ex); } } System.out.println("nilai: " + nilaiBenar + " " + arff.numInstances()); double confident = nilaiBenar * 1.0 / arff.numInstances() * 100; System.out.println("Confident = " + confident + "%"); String[] result2 = new String[5]; return result2; }
From source file:edu.uga.cs.fluxbuster.classification.Classifier.java
License:Open Source License
/** * Executes the classifier.//from ww w .j av a 2s .c om * * @param prepfeatures the prepared features in arff format * @param modelfile the path to the serialized model * @param clusters the clusters to classify * @return a map of the classified clusters, the keys are the classes * and the values are lists of cluster id's belonging to those classes */ private Map<ClusterClass, List<StoredDomainCluster>> executeClassifier(String prepfeatures, String modelfile, List<StoredDomainCluster> clusters) { Map<ClusterClass, List<StoredDomainCluster>> retval = new HashMap<ClusterClass, List<StoredDomainCluster>>(); try { DataSource source = new DataSource(new ByteArrayInputStream(prepfeatures.getBytes())); Instances data = source.getDataSet(); if (data.classIndex() == -1) { data.setClassIndex(data.numAttributes() - 1); } String[] options = weka.core.Utils.splitOptions("-p 0"); J48 cls = (J48) weka.core.SerializationHelper.read(modelfile); cls.setOptions(options); for (int i = 0; i < data.numInstances(); i++) { double pred = cls.classifyInstance(data.instance(i)); ClusterClass clusClass = ClusterClass .valueOf(data.classAttribute().value((int) pred).toUpperCase()); if (!retval.containsKey(clusClass)) { retval.put(clusClass, new ArrayList<StoredDomainCluster>()); } retval.get(clusClass).add(clusters.get(i)); } } catch (Exception e) { if (log.isErrorEnabled()) { log.error("Error executing classifier.", e); } } return retval; }
From source file:ia02classificacao.IA02Classificacao.java
/** * @param args the command line arguments *///from w w w.j a v a2 s . c o m public static void main(String[] args) throws Exception { // abre o banco de dados arff e mostra a quantidade de instancias (linhas) DataSource arquivo = new DataSource("data/zoo.arff"); Instances dados = arquivo.getDataSet(); System.out.println("Instancias lidas: " + dados.numInstances()); // FILTER: remove o atributo nome do animal da classificao String[] parametros = new String[] { "-R", "1" }; Remove filtro = new Remove(); filtro.setOptions(parametros); filtro.setInputFormat(dados); dados = Filter.useFilter(dados, filtro); AttributeSelection selAtributo = new AttributeSelection(); InfoGainAttributeEval avaliador = new InfoGainAttributeEval(); Ranker busca = new Ranker(); selAtributo.setEvaluator(avaliador); selAtributo.setSearch(busca); selAtributo.SelectAttributes(dados); int[] indices = selAtributo.selectedAttributes(); System.out.println("Selected attributes: " + Utils.arrayToString(indices)); // Usa o algoritimo J48 e mostra a classificao dos dados em forma textual String[] opcoes = new String[1]; opcoes[0] = "-U"; J48 arvore = new J48(); arvore.setOptions(opcoes); arvore.buildClassifier(dados); System.out.println(arvore); // Usa o algoritimo J48 e mostra a classificao de dados em forma grafica /* TreeVisualizer tv = new TreeVisualizer(null, arvore.graph(), new PlaceNode2()); JFrame frame = new javax.swing.JFrame("?rvore de Conhecimento"); frame.setSize(800,500); frame.setDefaultCloseOperation(JFrame.EXIT_ON_CLOSE); frame.getContentPane().add(tv); frame.setVisible(true); tv.fitToScreen(); */ /* * Classificao de novos dados */ System.out.println("\n\nCLASSIFICAO DE NOVOS DADOS"); // criar atributos double[] vals = new double[dados.numAttributes()]; vals[0] = 1.0; // hair vals[1] = 0.0; // feathers vals[2] = 0.0; // eggs vals[3] = 1.0; // milk vals[4] = 1.0; // airborne vals[5] = 0.0; // aquatic vals[6] = 0.0; // predator vals[7] = 1.0; // toothed vals[8] = 1.0; // backbone vals[9] = 1.0; // breathes vals[10] = 0.0; // venomous vals[11] = 0.0; // fins vals[12] = 4.0; // legs vals[13] = 1.0; // tail vals[14] = 1.0; // domestic vals[15] = 1.0; // catsize // Criar uma instncia baseada nestes atributos Instance meuUnicornio = new DenseInstance(1.0, vals); // Adicionar a instncia nos dados meuUnicornio.setDataset(dados); // Classificar esta nova instncia double label = arvore.classifyInstance(meuUnicornio); // Imprimir o resultado da classificao System.out.println("Novo Animal: Unicrnio"); System.out.println("classificacao: " + dados.classAttribute().value((int) label)); /* * Avaliao e predio de erros de mtrica */ System.out.println("\n\nAVALIAO E PREDIO DE ERROS DE MTRICA"); Classifier cl = new J48(); Evaluation eval_roc = new Evaluation(dados); eval_roc.crossValidateModel(cl, dados, 10, new Random(1), new Object[] {}); System.out.println(eval_roc.toSummaryString()); /* * Matriz de confuso */ System.out.println("\n\nMATRIZ DE CONFUSO"); double[][] confusionMatrix = eval_roc.confusionMatrix(); System.out.println(eval_roc.toMatrixString()); }
From source file:ia03classificador.jFrClassificador.java
public void doClassificate() throws Exception { // Quando clicado, a variavel recebe 1, quando no clicado recebe 0 v00 = ((btn00.isSelected()) ? ((double) 1) : ((double) 0)); v01 = ((btn01.isSelected()) ? ((double) 1) : ((double) 0)); v02 = ((btn02.isSelected()) ? ((double) 1) : ((double) 0)); v03 = ((btn03.isSelected()) ? ((double) 1) : ((double) 0)); v04 = ((btn04.isSelected()) ? ((double) 1) : ((double) 0)); v05 = ((btn05.isSelected()) ? ((double) 1) : ((double) 0)); v06 = ((btn06.isSelected()) ? ((double) 1) : ((double) 0)); v07 = ((btn07.isSelected()) ? ((double) 1) : ((double) 0)); v08 = ((btn08.isSelected()) ? ((double) 1) : ((double) 0)); v09 = ((btn09.isSelected()) ? ((double) 1) : ((double) 0)); v10 = ((btn10.isSelected()) ? ((double) 1) : ((double) 0)); v11 = ((btn11.isSelected()) ? ((double) 1) : ((double) 0)); v13 = ((btn13.isSelected()) ? ((double) 1) : ((double) 0)); v14 = ((btn14.isSelected()) ? ((double) 1) : ((double) 0)); v15 = ((btn15.isSelected()) ? ((double) 1) : ((double) 0)); legs = txtLegs.getText();//from w w w. ja v a2 s .c o m legs = ((legs == null || legs.trim().isEmpty() ? "2" : legs)); name = txtName.getText(); // abre o banco de dados arff e guarda os registros no objeto dados ConverterUtils.DataSource arquivo = new ConverterUtils.DataSource("data/zoo.arff"); Instances dados = arquivo.getDataSet(); // FILTER: remove o atributo nome do animal da classificao String[] parametros = new String[] { "-R", "1" }; Remove filtro = new Remove(); filtro.setOptions(parametros); filtro.setInputFormat(dados); dados = Filter.useFilter(dados, filtro); AttributeSelection selAtributo = new AttributeSelection(); InfoGainAttributeEval avaliador = new InfoGainAttributeEval(); Ranker busca = new Ranker(); selAtributo.setEvaluator(avaliador); selAtributo.setSearch(busca); selAtributo.SelectAttributes(dados); int[] indices = selAtributo.selectedAttributes(); //System.out.println("Selected attributes: " + Utils.arrayToString(indices)); // Usa o algoritimo J48 para montar a arvore de dados String[] opcoes = new String[1]; opcoes[0] = "-U"; J48 arvore = new J48(); arvore.setOptions(opcoes); arvore.buildClassifier(dados); // cria o novo elemento para comparao double[] vals = new double[dados.numAttributes()]; vals[0] = v00; // hair vals[1] = v01; // feathers vals[2] = v02; // eggs vals[3] = v03; // milk vals[4] = v04; // airborne vals[5] = v05; // aquatic vals[6] = v06; // predator vals[7] = v07; // toothed vals[8] = v08; // backbone vals[9] = v09; // breathes vals[10] = v10; // venomous vals[11] = v11; // fins vals[12] = Double.parseDouble(legs); // legs vals[13] = v13; // tail vals[14] = v14; // domestic vals[15] = v15; // catsize // Criar uma instncia baseada nestes atributos Instance newAnimal = new DenseInstance(1.0, vals); // Adicionar a instncia nos dados newAnimal.setDataset(dados); // Classificar esta nova instncia double label = arvore.classifyInstance(newAnimal); // Imprimir o resultado da classificao lblClassification.setText(dados.classAttribute().value((int) label)); }