List of usage examples for weka.core Instances classAttribute
publicAttribute classAttribute()
From source file:classifyfromimage.java
private void jButton1ActionPerformed(java.awt.event.ActionEvent evt) {//GEN-FIRST:event_jButton1ActionPerformed this.name3 = IJ.getImage().getTitle(); this.name4 = this.name3.replaceFirst("[.][^.]+$", ""); System.out.println("hola " + this.name4); selectWindow(this.name3); System.out.println(this.name4); System.out.println(this.name3); RoiManager rm = RoiManager.getInstance(); IJ.run("Duplicate...", this.name3); IJ.run("Set Measurements...", "area perimeter fit shape limit scientific redirect=None decimal=5"); selectWindow(this.name3); IJ.run("Subtract Background...", "rolling=1.5"); IJ.run("Enhance Contrast...", "saturated=25 equalize"); IJ.run("Subtract Background...", "rolling=1.5"); IJ.run("Convolve...", "text1=[-1 -3 -4 -3 -1\n-3 0 6 0 -3\n-4 6 50 6 -4\n-3 0 6 0 -3\n-1 -3 -4 -3 -1\n] normalize"); IJ.run("8-bit", ""); IJ.run("Restore Selection", ""); IJ.run("Make Binary", ""); Prefs.blackBackground = false;/*from ww w . j a va 2s . c o m*/ IJ.run("Convert to Mask", ""); IJ.run("Restore Selection", ""); this.valor1 = this.interval3.getText(); this.valor2 = this.interval4.getText(); System.out.println("VECTOR-> punctua: " + this.valor1 + " " + this.valor2); this.text = "size=" + this.valor1 + "-" + this.valor2 + " pixel show=Outlines display include summarize add"; IJ.run("Analyze Particles...", this.text); IJ.saveAs("tif", this.name3 + "_processed"); String dest_filename1, dest_filename2, full; selectWindow("Results"); //dest_filename1 = this.name2 + "_complete.txt"; dest_filename2 = this.name3 + "_complete.csv"; //IJ.saveAs("Results", prova + File.separator + dest_filename1); IJ.run("Input/Output...", "jpeg=85 gif=-1 file=.csv copy_row save_column save_row"); //IJ.saveAs("Results", dir + File.separator + dest_filename2); IJ.saveAs("Results", this.name3 + "_complete.csv"); IJ.run("Restore Selection"); IJ.run("Clear Results"); //txtarea.setText("Converting, please wait... "); try { CSVLoader loader = new CSVLoader(); loader.setSource(new File(this.name3 + "_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); } //txtdata2.setText(this.name3); //txtarea.setText("Succesfully converted " + this.name3); //txtarea.setText("Analysing your data, please wait... "); 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(); 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.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); this.txtarea2.setText( "Your file:" + this.name3 + ".arff" + "\nhas been analysed, and it is composed by-> punctua: " + p + ", rods: " + r + ", networks: " + n); A_MachineLearning nf1 = new A_MachineLearning(); A_MachineLearning.txtresults1.setText(this.txtarea2.getText()); A_MachineLearning.txtresults1.setText(this.txtarea2.getText()); A_MachineLearning.txtresults1.setText(this.txtarea2.getText()); A_MachineLearning.txtresults1.append(this.txtarea2.getText()); A_MachineLearning.txtresults1.append(this.txtarea2.getText()); A_MachineLearning.txtresults1.append(this.txtarea2.getText()); nf1.setVisible(true); } 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.RoiManager("Delete"); 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:BaggingImprove.java
/** * Bagging method./*from w ww. j a va 2 s . c om*/ * * @param data the training data to be used for generating the bagged * classifier. * @throws Exception if the classifier could not be built successfully */ 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(); super.buildClassifier(data); if (m_CalcOutOfBag && (m_BagSizePercent != 100)) { throw new IllegalArgumentException( "Bag size needs to be 100% if " + "out-of-bag error is to be calculated!"); } //+ System.out.println("Classifier length" + m_Classifiers.length); int bagSize = data.numInstances() * m_BagSizePercent / 100; //+ System.out.println("Bag Size " + bagSize); Random random = new Random(m_Seed); boolean[][] inBag = null; if (m_CalcOutOfBag) { inBag = new boolean[m_Classifiers.length][]; } //+ //inisialisasi nama penamaan model BufferedWriter writer = new BufferedWriter(new FileWriter("Bootstrap.txt")); for (int j = 0; j < m_Classifiers.length; j++) { Instances bagData = null; // create the in-bag dataset if (m_CalcOutOfBag) { inBag[j] = new boolean[data.numInstances()]; //System.out.println("Inbag1 " + inBag[0][1]); //bagData = resampleWithWeights(data, random, inBag[j]); bagData = data.resampleWithWeights(random, inBag[j]); //System.out.println("num after resample " + bagData.numInstances()); //+ // for (int k = 0; k < bagData.numInstances(); k++) { // System.out.println("Bag Data after resample [calc out bag]" + bagData.instance(k)); // } } else { //+ System.out.println("Not m_Calc out of bag"); System.out.println("Please configure code inside!"); bagData = data.resampleWithWeights(random); if (bagSize < data.numInstances()) { bagData.randomize(random); Instances newBagData = new Instances(bagData, 0, bagSize); bagData = newBagData; } } if (m_Classifier instanceof Randomizable) { //+ System.out.println("Randomizable"); ((Randomizable) m_Classifiers[j]).setSeed(random.nextInt()); } //write bootstrap into file writer.write("Bootstrap " + j); writer.newLine(); writer.write(bagData.toString()); writer.newLine(); System.out.println("Berhasil menyimpan bootstrap ke file "); System.out.println("Bootstrap " + j + 1); // textarea.append("\nBootsrap " + (j + 1)); //System.out.println("num instance kedua kali "+bagData.numInstances()); for (int b = 1; b < bagData.numInstances(); b++) { System.out.println("" + bagData.instance(b)); // textarea.append("\n" + bagData.instance(b)); } // //+ // build the classifier m_Classifiers[j].buildClassifier(bagData); // //+ // // SerializationHelper serialization = new SerializationHelper(); // serialization.write("KnnData"+model+".model", m_Classifiers[j]); // System.out.println("Finish write into model"); // model++; } writer.flush(); writer.close(); // calc OOB error? if (getCalcOutOfBag()) { double outOfBagCount = 0.0; double errorSum = 0.0; boolean numeric = data.classAttribute().isNumeric(); for (int i = 0; i < data.numInstances(); i++) { double vote; double[] votes; if (numeric) { votes = new double[1]; } else { votes = new double[data.numClasses()]; } // determine predictions for instance int voteCount = 0; for (int j = 0; j < m_Classifiers.length; j++) { if (inBag[j][i]) { continue; } voteCount++; // double pred = m_Classifiers[j].classifyInstance(data.instance(i)); if (numeric) { // votes[0] += pred; votes[0] = m_Classifiers[j].classifyInstance(data.instance(i)); } else { // votes[(int) pred]++; double[] newProbs = m_Classifiers[j].distributionForInstance(data.instance(i)); //- // for(double a : newProbs) // { // System.out.println("Double new probs %.f "+a); // } // average the probability estimates for (int k = 0; k < newProbs.length; k++) { votes[k] += newProbs[k]; } } } System.out.println("Vote count %d" + voteCount); // "vote" if (numeric) { vote = votes[0]; if (voteCount > 0) { vote /= voteCount; // average } } else { if (Utils.eq(Utils.sum(votes), 0)) { } else { Utils.normalize(votes); } vote = Utils.maxIndex(votes); // predicted class //- System.out.println("Vote " + vote); } // error for instance outOfBagCount += data.instance(i).weight(); if (numeric) { errorSum += StrictMath.abs(vote - data.instance(i).classValue()) * data.instance(i).weight(); } else if (vote != data.instance(i).classValue()) { //+ System.out.println("Vote terakhir" + data.instance(i).classValue()); errorSum += data.instance(i).weight(); } } m_OutOfBagError = errorSum / outOfBagCount; } else { m_OutOfBagError = 0; } }
From source file:REPTree.java
License:Open Source License
/** * Builds classifier.//from w w w . jav a2 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); // Insert pruning data and perform reduced error pruning if (!m_NoPruning) { m_Tree.insertHoldOutSet(prune); m_Tree.reducedErrorPrune(); m_Tree.backfitHoldOutSet(); } }
From source file:A_MachineLearning.java
private void jButton7ActionPerformed(java.awt.event.ActionEvent evt) {//GEN-FIRST:event_jButton7ActionPerformed Instances data;//from w w w. ja v a 2 s . c o m try { data = new Instances(new BufferedReader(new FileReader(this.file2 + ".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.file2 + "_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.file2 + "arff" + "\nhas been analysed, and it is composed by-> punctua: " + p + ", rods: " + r + ", networks: " + n); txtresults1.setText( "Your file:" + this.file2 + "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.showMessage("analysing complete "); }
From source file:Pair.java
License:Open Source License
/** * Boosting method./* w ww.ja va2 s .c o 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 {/*w ww . ja v a2 s. c o m*/ 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:REPRandomTree.java
License:Open Source License
/** * Builds classifier./*from www . j a va 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:dialog1.java
private void jButton1ActionPerformed(java.awt.event.ActionEvent evt) {//GEN-FIRST:event_jButton1ActionPerformed try {//from w w w. j a v a2s .c o m 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:CJWeka.java
License:Open Source License
/** Convert a sting of floats separated by spaces into an Instance *//*from w w w .j av a 2 s .co m*/ private Instance floatstringToInst(String floatvalues, Instances ii, boolean hasClass) { String[] flostr = floatvalues.split(" "); int nvals = flostr.length; Instance i = new DenseInstance(nvals); int j; if (hasClass) nvals--; for (j = 0; j < nvals; j++) { if (!flostr[j].equals("")) { Float f = new Float(flostr[j]); i.setValue(j, f); } } i.setDataset(ii); if (hasClass) { Attribute clsAttrib = ii.classAttribute(); //clsAttrib.addStringValue(flostr[j]); i.setValue(clsAttrib, flostr[j]); } return i; }
From source file:CJWeka.java
License:Open Source License
/** * This function sets what the m_numeric flag to represent the passed class * it also performs the normalization of the attributes if applicable * and sets up the info to normalize the class. (note that regardless of * the options it will fill an array with the range and base, set to * normalize all attributes and the class to be between -1 and 1) * @param inst the instances.//from w ww . j a v a 2 s . com * @return The modified instances. This needs to be done. If the attributes * are normalized then deep copies will be made of all the instances which * will need to be passed back out. */ private Instances setClassType(Instances inst) throws Exception { if (inst != null) { // x bounds double min = Double.POSITIVE_INFINITY; double max = Double.NEGATIVE_INFINITY; double value; m_attributeRanges = new double[inst.numAttributes()]; m_attributeBases = new double[inst.numAttributes()]; for (int noa = 0; noa < inst.numAttributes(); noa++) { min = Double.POSITIVE_INFINITY; max = Double.NEGATIVE_INFINITY; for (int i = 0; i < inst.numInstances(); i++) { if (!inst.instance(i).isMissing(noa)) { value = inst.instance(i).value(noa); if (value < min) { min = value; } if (value > max) { max = value; } } } m_attributeRanges[noa] = (max - min) / 2; m_attributeBases[noa] = (max + min) / 2; if (noa != inst.classIndex() && m_normalizeAttributes) { for (int i = 0; i < inst.numInstances(); i++) { if (m_attributeRanges[noa] != 0) { inst.instance(i).setValue(noa, (inst.instance(i).value(noa) - m_attributeBases[noa]) / m_attributeRanges[noa]); } else { inst.instance(i).setValue(noa, inst.instance(i).value(noa) - m_attributeBases[noa]); } } } } if (inst.classAttribute().isNumeric()) { m_numeric = true; } else { m_numeric = false; } } return inst; }