List of usage examples for weka.core Instances Instances
public Instances(Instances dataset)
From source file:Pair.java
License:Open Source License
/** * Set the data file for the source data for transfer * and get the source Instances from the file *///from w w w .j ava 2 s. c om public void setSourceFile(File sourceFile) throws Exception { m_SourceFile = sourceFile; m_SourceInstances = new Instances(new BufferedReader(new FileReader(sourceFile))); m_SourceInstances.setClassIndex(m_SourceInstances.numAttributes() - 1); }
From source file:Pair.java
License:Open Source License
/** * Boosting method.//from www.j av a 2 s .co m * * @param data the training data to be used for generating the * boosted classifier. * @exception Exception if the classifier could not be built successfully */ public void buildClassifier(Instances data) throws Exception { super.buildClassifier(data); if (data.checkForStringAttributes()) { throw new UnsupportedAttributeTypeException("Cannot handle string attributes!"); } data = new Instances(data); data.deleteWithMissingClass(); if (data.numInstances() == 0) { throw new Exception("No train instances without class missing!"); } if (!data.classAttribute().isNumeric()) { throw new UnsupportedClassTypeException("TrAdaBoostR2 can only handle a numeric class!"); } if (m_SourceInstances == null) { throw new Exception("Source data has not been specified!"); } m_NumClasses = data.numClasses(); try { doCV(data); } catch (Exception e) { e.printStackTrace(); } }
From source file:classificationPLugin.java
private void ClassifyActionPerformed(java.awt.event.ActionEvent evt) {//GEN-FIRST:event_ClassifyActionPerformed this.name = txtdirecotry2.getText(); System.out.println(this.name); try {/*from w w w . j a va 2s . c om*/ CSVLoader loader = new CSVLoader(); loader.setSource(new File(this.name)); Instances data = loader.getDataSet(); System.out.println(data); // save ARFF String arffile = this.name + ".arff"; System.out.println(arffile); ArffSaver saver = new ArffSaver(); saver.setInstances(data); saver.setFile(new File(arffile)); saver.writeBatch(); } catch (IOException ex) { Logger.getLogger(MachinLearningInterface.class.getName()).log(Level.SEVERE, null, ex); } try { FileReader reader = new FileReader(this.name + ".arff"); BufferedReader br = new BufferedReader(reader); instance.read(br, null); br.close(); instance.requestFocus(); } catch (Exception e2) { System.out.println(e2); } Instances data; try { data = new Instances(new BufferedReader(new FileReader(this.name + ".arff"))); Instances newData = null; Add filter; newData = new Instances(data); filter = new Add(); filter.setAttributeIndex("last"); filter.setNominalLabels("rods,punctua,networks"); filter.setAttributeName("target"); filter.setInputFormat(newData); newData = Filter.useFilter(newData, filter); System.out.print(newData); Vector vec = new Vector(); newData.setClassIndex(newData.numAttributes() - 1); if (!newData.equalHeaders(newData)) { throw new IllegalArgumentException("Train and test are not compatible!"); } URL urlToModel = this.getClass().getResource("/" + "Final.model"); InputStream stream = urlToModel.openStream(); Classifier cls = (Classifier) weka.core.SerializationHelper.read(stream); System.out.println("PROVANT MODEL.classifyInstance"); for (int i = 0; i < newData.numInstances(); i++) { double pred = cls.classifyInstance(newData.instance(i)); double[] dist = cls.distributionForInstance(newData.instance(i)); System.out.print((i + 1) + " - "); System.out.print(newData.classAttribute().value((int) pred) + " - "); //txtarea2.setText(Utils.arrayToString(dist)); System.out.println(Utils.arrayToString(dist)); vec.add(newData.classAttribute().value((int) pred)); } int p = 0, n = 0, r = 0; //txtarea2.append(Utils.arrayToString(this.target)); for (Object vec1 : vec) { if ("rods".equals(vec1.toString())) { r = r + 1; } if ("punctua".equals(vec1.toString())) { p = p + 1; } if ("networks".equals(vec1.toString())) { n = n + 1; } PrintWriter out = null; try { out = new PrintWriter(this.name + "_morphology.txt"); out.println(vec); out.close(); } catch (Exception ex) { ex.printStackTrace(); } //System.out.println(vec.get(i)); } System.out.println("VECTOR-> punctua: " + p + ", rods: " + r + ", networks: " + n); IJ.showMessage( "Your file:" + this.name + "arff" + "\nhas been analysed, and it is composed by-> \npunctua: " + p + ", rods: " + r + ", networks: " + n); classi.setText( "Your file:" + this.name + "arff" + "\nhas been analysed, and it is composed by: \npunctua: " + p + ", rods: " + r + ", networks: " + n); } catch (IOException ex) { Logger.getLogger(MachinLearningInterface.class.getName()).log(Level.SEVERE, null, ex); } catch (Exception ex) { Logger.getLogger(MachinLearningInterface.class.getName()).log(Level.SEVERE, null, ex); } IJ.run("Clear Results"); IJ.run("Clear Results"); IJ.run("Close All", ""); if (WindowManager.getFrame("Results") != null) { IJ.selectWindow("Results"); IJ.run("Close"); } if (WindowManager.getFrame("Summary") != null) { IJ.selectWindow("Summary"); IJ.run("Close"); } if (WindowManager.getFrame("Results") != null) { IJ.selectWindow("Results"); IJ.run("Close"); } if (WindowManager.getFrame("ROI Manager") != null) { IJ.selectWindow("ROI Manager"); IJ.run("Close"); } IJ.run("Close All", "roiManager"); IJ.run("Close All", ""); }
From source file:CopiaSeg3.java
public static Instances[] split(Instances data, int numberOfFolds) { Instances[] split = new Instances[2]; Random semilla = new Random(); int seed = semilla.nextInt(20); // Genera una semilla aleatorio entre 0 y 20 Random rand = new Random(seed); // Create seeded number generator Instances randData = new Instances(data); // Crea una copia de los datos originales randData.randomize(rand); // Ordena los datos de forma aleatoria split[0] = randData.trainCV(numberOfFolds, 0); split[1] = randData.testCV(numberOfFolds, 0); return split; }
From source file:CopiaSeg3.java
public static void main(String[] args) throws Exception { BufferedReader datafile = readDataFile("breast-cancer-wisconsin.arff"); Instances data = new Instances(datafile); data.setClassIndex(data.numAttributes() - 1); // Elije el nmero de particiones para la valicacin (4 = 75% Train, 25% Test) Instances[] split = split(data, 4);/* www. j a va2 s.co m*/ // Separa los conjuntos en los arrays trainning y testing Instances trainingSplits = split[0]; Instances testingSplits = split[1]; // Elegir un conjunto de clasificadores Classifier[] models = { new MultilayerPerceptron() //, new J48 //, ... }; FastVector fvWekaAttributes = new FastVector(9); // Ejecutar cada clasificador for (int j = 0; j < models.length; j++) { // Collect every group of predictions for current model in a FastVector FastVector predictions = new FastVector(); // For each training-testing split pair, train and test the classifier Evaluation validation = simpleClassify(models[j], trainingSplits, testingSplits); predictions.appendElements(validation.predictions()); // Uncomment to see the summary for each training-testing pair. System.out.println(models[j].toString()); // Calculate overall accuracy of current classifier on all splits double accuracy = calculateAccuracy(predictions); // // Print current classifier's name and accuracy in a complicated, but nice-looking way. System.out.println(models[j].getClass().getSimpleName() + " Accuracy: " + String.format("%.2f%%", accuracy) + "\n====================="); // // // Step 4: use the classifier // // For real world applications, the actual use of the classifier is the ultimate goal. Heres the simplest way to achieve that. Lets say weve built an instance (named iUse) as explained in step 2: // // Specify that the instance belong to the training set // // in order to inherit from the set description Instance iUse = new DenseInstance(9); iUse.setValue((Attribute) predictions.elementAt(0), 4); iUse.setValue((Attribute) predictions.elementAt(1), 8); iUse.setValue((Attribute) predictions.elementAt(2), 8); iUse.setValue((Attribute) predictions.elementAt(3), 5); iUse.setValue((Attribute) predictions.elementAt(4), 4); iUse.setValue((Attribute) predictions.elementAt(5), 5); iUse.setValue((Attribute) predictions.elementAt(6), 10); iUse.setValue((Attribute) predictions.elementAt(7), 4); iUse.setValue((Attribute) predictions.elementAt(8), 1); iUse.setDataset(trainingSplits); // // // Get the likelihood of each classes // fDistribution[0] is the probability of being positive? // fDistribution[1] is the probability of being negative? double[] fDistribution = models[j].distributionForInstance(iUse); System.out.println("Probabilidad positivo: " + fDistribution[0]); System.out.println("Probabilidad negativo: " + fDistribution[1]); } }
From source file:MLP.java
MLP() {
try {/*from ww w .ja v a2 s . c o m*/
FileReader trainreader = new FileReader("C:\\new.arff");
FileReader testreader = new FileReader("C:\\new.arff");
Instances train = new Instances(trainreader);
Instances test = new Instances(testreader);
train.setClassIndex(train.numAttributes() - 1);
test.setClassIndex(test.numAttributes() - 1);
MultilayerPerceptron mlp = new MultilayerPerceptron();
mlp.setOptions(Utils.splitOptions("-L 0.3 -M 0.2 -N 500 -V 0 -S 0 -E 20 -H 4"));
mlp.buildClassifier(train);
Evaluation eval = new Evaluation(train);
eval.evaluateModel(mlp, test);
System.out.println(eval.toSummaryString("\nResults\n======\n", false));
trainreader.close();
testreader.close();
} catch (Exception ex) {
ex.printStackTrace();
}
}
From source file:REPRandomTree.java
License:Open Source License
/** * Builds classifier.//from w w w.jav a 2 s . c o m * * @param data the data to train with * @throws Exception if building fails */ public void buildClassifier(Instances data) throws Exception { // can classifier handle the data? getCapabilities().testWithFail(data); // remove instances with missing class data = new Instances(data); data.deleteWithMissingClass(); Random random = new Random(m_Seed); m_zeroR = null; if (data.numAttributes() == 1) { m_zeroR = new ZeroR(); m_zeroR.buildClassifier(data); return; } // Randomize and stratify data.randomize(random); if (data.classAttribute().isNominal()) { data.stratify(m_NumFolds); } // Split data into training and pruning set Instances train = null; Instances prune = null; if (!m_NoPruning) { train = data.trainCV(m_NumFolds, 0, random); prune = data.testCV(m_NumFolds, 0); } else { train = data; } // Create array of sorted indices and weights int[][][] sortedIndices = new int[1][train.numAttributes()][0]; double[][][] weights = new double[1][train.numAttributes()][0]; double[] vals = new double[train.numInstances()]; for (int j = 0; j < train.numAttributes(); j++) { if (j != train.classIndex()) { weights[0][j] = new double[train.numInstances()]; if (train.attribute(j).isNominal()) { // Handling nominal attributes. Putting indices of // instances with missing values at the end. sortedIndices[0][j] = new int[train.numInstances()]; int count = 0; for (int i = 0; i < train.numInstances(); i++) { Instance inst = train.instance(i); if (!inst.isMissing(j)) { sortedIndices[0][j][count] = i; weights[0][j][count] = inst.weight(); count++; } } for (int i = 0; i < train.numInstances(); i++) { Instance inst = train.instance(i); if (inst.isMissing(j)) { sortedIndices[0][j][count] = i; weights[0][j][count] = inst.weight(); count++; } } } else { // Sorted indices are computed for numeric attributes for (int i = 0; i < train.numInstances(); i++) { Instance inst = train.instance(i); vals[i] = inst.value(j); } sortedIndices[0][j] = Utils.sort(vals); for (int i = 0; i < train.numInstances(); i++) { weights[0][j][i] = train.instance(sortedIndices[0][j][i]).weight(); } } } } // Compute initial class counts double[] classProbs = new double[train.numClasses()]; double totalWeight = 0, totalSumSquared = 0; for (int i = 0; i < train.numInstances(); i++) { Instance inst = train.instance(i); if (data.classAttribute().isNominal()) { classProbs[(int) inst.classValue()] += inst.weight(); totalWeight += inst.weight(); } else { classProbs[0] += inst.classValue() * inst.weight(); totalSumSquared += inst.classValue() * inst.classValue() * inst.weight(); totalWeight += inst.weight(); } } m_Tree = new Tree(); double trainVariance = 0; if (data.classAttribute().isNumeric()) { trainVariance = m_Tree.singleVariance(classProbs[0], totalSumSquared, totalWeight) / totalWeight; classProbs[0] /= totalWeight; } // Build tree m_Tree.buildTree(sortedIndices, weights, train, totalWeight, classProbs, new Instances(train, 0), m_MinNum, m_MinVarianceProp * trainVariance, 0, m_MaxDepth, m_FeatureFrac, random); // Insert pruning data and perform reduced error pruning if (!m_NoPruning) { m_Tree.insertHoldOutSet(prune); m_Tree.reducedErrorPrune(); m_Tree.backfitHoldOutSet(); } }
From source file:LabeledItemSet.java
License:Open Source License
/** * Splits the class attribute away. Depending on the invert flag, the instances without class attribute or only the class attribute of all instances is returned * @param instances the instances// w w w. jav a 2s . c om * @param invert flag; if true only the class attribute remains, otherweise the class attribute is the only attribute that is deleted. * @throws Exception exception if instances cannot be splitted * @return Instances without the class attribute or instances with only the class attribute */ public static Instances divide(Instances instances, boolean invert) throws Exception { Instances newInstances = new Instances(instances); if (instances.classIndex() < 0) throw new Exception("For class association rule mining a class attribute has to be specified."); if (invert) { for (int i = 0; i < newInstances.numAttributes(); i++) { if (i != newInstances.classIndex()) { newInstances.deleteAttributeAt(i); i--; } } return newInstances; } else { newInstances.setClassIndex(-1); newInstances.deleteAttributeAt(instances.classIndex()); return newInstances; } }
From source file:dialog1.java
private void jButton1ActionPerformed(java.awt.event.ActionEvent evt) {//GEN-FIRST:event_jButton1ActionPerformed try {/*from w w w . j av a 2 s .c om*/ CSVLoader loader = new CSVLoader(); loader.setSource(new File(txtfilename.getText() + "_complete.csv")); Instances data = loader.getDataSet(); System.out.println(data); // save ARFF String arffile = this.name3 + ".arff"; System.out.println(arffile); ArffSaver saver = new ArffSaver(); saver.setInstances(data); saver.setFile(new File(arffile)); saver.writeBatch(); } catch (IOException ex) { Logger.getLogger(MachinLearningInterface.class.getName()).log(Level.SEVERE, null, ex); } Instances data; try { data = new Instances(new BufferedReader(new FileReader(this.name3 + ".arff"))); Instances newData = null; Add filter; newData = new Instances(data); filter = new Add(); filter.setAttributeIndex("last"); filter.setNominalLabels("rods,punctua,networks"); filter.setAttributeName("target"); filter.setInputFormat(newData); newData = Filter.useFilter(newData, filter); System.out.print(newData); Vector vec = new Vector(); newData.setClassIndex(newData.numAttributes() - 1); if (!newData.equalHeaders(newData)) { throw new IllegalArgumentException("Train and test are not compatible!"); } /*URL urlToModel = this.getClass().getResource("/" + "Final.model"); InputStream stream = urlToModel.openStream();*/ InputStream stream = this.getClass().getResourceAsStream("/" + "Final.model"); Classifier cls = (Classifier) weka.core.SerializationHelper.read(stream); System.out.println("PROVANT MODEL.classifyInstance"); for (int i = 0; i < newData.numInstances(); i++) { double pred = cls.classifyInstance(newData.instance(i)); double[] dist = cls.distributionForInstance(newData.instance(i)); System.out.print((i + 1) + " - "); System.out.print(newData.classAttribute().value((int) pred) + " - "); //txtarea2.setText(Utils.arrayToString(dist)); System.out.println(Utils.arrayToString(dist)); vec.add(newData.classAttribute().value((int) pred)); //txtarea2.append(Utils.arrayToString(newData.classAttribute().value((int) pred))); //this.target2.add((i + 1) + " -); //this.target.add(newData.classAttribute().value((int) pred)); //for (String s : this.list) { //this.target2 += s + ","; } int p = 0, n = 0, r = 0; //txtarea2.append(Utils.arrayToString(this.target)); for (Object vec1 : vec) { if ("rods".equals(vec1.toString())) { r = r + 1; } if ("punctua".equals(vec1.toString())) { p = p + 1; } if ("networks".equals(vec1.toString())) { n = n + 1; } PrintWriter out = null; try { out = new PrintWriter(this.name3 + "_morphology.txt"); out.println(vec); out.close(); } catch (Exception ex) { ex.printStackTrace(); } //System.out.println(vec.get(i)); } System.out.println("VECTOR-> punctua: " + p + ", rods: " + r + ", networks: " + n); IJ.showMessage( "Your file:" + this.name3 + "arff" + "\nhas been analysed, and it is composed by-> punctua: " + p + ", rods: " + r + ", networks: " + n); //txtarea2.setText("Your file:" + this.name3 + ".arff" //+ "\nhas been analysed, and it is composed by-> punctua: " + p + ", rods: " + r + ", networks: " + n //+ "\n" //+ "\nAnalyse complete"); //txtarea.setText("Analyse complete"); } catch (IOException ex) { Logger.getLogger(MachinLearningInterface.class.getName()).log(Level.SEVERE, null, ex); } catch (Exception ex) { Logger.getLogger(MachinLearningInterface.class.getName()).log(Level.SEVERE, null, ex); } IJ.run("Clear Results"); IJ.run("Clear Results"); IJ.run("Close All", ""); if (WindowManager.getFrame("Results") != null) { IJ.selectWindow("Results"); IJ.run("Close"); } if (WindowManager.getFrame("Summary") != null) { IJ.selectWindow("Summary"); IJ.run("Close"); } if (WindowManager.getFrame("Results") != null) { IJ.selectWindow("Results"); IJ.run("Close"); } if (WindowManager.getFrame("ROI Manager") != null) { IJ.selectWindow("ROI Manager"); IJ.run("Close"); } IJ.run("Close All", "roiManager"); IJ.run("Close All", ""); setVisible(false); dispose();// TODO add your handling code here: setVisible(false); dispose();// TODO add your handling code here: // TODO add your handling code here: }
From source file:PredictMention.java
protected void setTestData(String title, String description, String keywords) { testData = new Instances(trainedData); testData.clear();//from w w w . j a v a 2 s. c o m Instance inst = new DenseInstance(4); inst.setDataset(testData); inst.setValue(0, title); inst.setValue(1, description); inst.setValue(2, keywords); inst.setMissing(3); testData.add(inst); }