/** * Process a dataset file for a clustering problem. * * @param nfexamples Name of the dataset file * @param train The dataset file is for training or for test * @throws java.io.IOException if there is any semantical, lexical or sintactical error in the * input file. */ public void processClusterDataset(String nfexamples, boolean train) throws IOException { try { // Load in memory a dataset that contains a classification problem IS.readSet(nfexamples, train); nData = IS.getNumInstances(); nInputs = Attributes.getInputNumAttributes(); nVariables = nInputs + Attributes.getOutputNumAttributes(); if (Attributes.getOutputNumAttributes() != 0) { System.out.println("This algorithm can not process datasets with outputs"); System.out.println("All outputs will be removed"); } // Initialize and fill our own tables X = new double[nData][nInputs]; missing = new boolean[nData][nInputs]; // Maximum and minimum of inputs iMaximum = new double[nInputs]; iMinimum = new double[nInputs]; // Maximum and minimum for output data oMaximum = 0; oMinimum = 0; // All values are casted into double/integer nClasses = 0; for (int i = 0; i < X.length; i++) { Instance inst = IS.getInstance(i); for (int j = 0; j < nInputs; j++) { X[i][j] = IS.getInputNumericValue(i, j); missing[i][j] = inst.getInputMissingValues(j); if (X[i][j] > iMaximum[j] || i == 0) { iMaximum[j] = X[i][j]; } if (X[i][j] < iMinimum[j] || i == 0) { iMinimum[j] = X[i][j]; } } } } catch (Exception e) { System.out.println("DBG: Exception in readSet"); e.printStackTrace(); } }
/** * Process a dataset file for a classification problem. * * @param nfejemplos Name of the dataset file * @param train The dataset file is for training or for test * @throws java.io.IOException if there is any semantical, lexical or sintactical error in the * input file. */ public void processClassifierDataset(String nfejemplos, boolean train) throws IOException { try { // Load in memory a dataset that contains a classification problem IS.readSet(nfejemplos, train); nData = IS.getNumInstances(); nInputs = Attributes.getInputNumAttributes(); nVariables = nInputs + Attributes.getOutputNumAttributes(); // Check that there is only one output variable and // it is nominal if (Attributes.getOutputNumAttributes() > 1) { System.out.println("This algorithm can not process MIMO datasets"); System.out.println("All outputs but the first one will be removed"); } boolean noOutputs = false; if (Attributes.getOutputNumAttributes() < 1) { System.out.println("This algorithm can not process datasets without outputs"); System.out.println("Zero-valued output generated"); noOutputs = true; } // Initialize and fill our own tables X = new double[nData][nInputs]; missing = new boolean[nData][nInputs]; C = new int[nData]; // Maximum and minimum of inputs iMaximum = new double[nInputs]; iMinimum = new double[nInputs]; // Maximum and minimum for output data oMaximum = 0; oMinimum = 0; // All values are casted into double/integer nClasses = 0; for (int i = 0; i < X.length; i++) { Instance inst = IS.getInstance(i); for (int j = 0; j < nInputs; j++) { X[i][j] = IS.getInputNumericValue(i, j); missing[i][j] = inst.getInputMissingValues(j); if (X[i][j] > iMaximum[j] || i == 0) { iMaximum[j] = X[i][j]; } if (X[i][j] < iMinimum[j] || i == 0) { iMinimum[j] = X[i][j]; } } if (noOutputs) { C[i] = 0; } else { C[i] = (int) IS.getOutputNumericValue(i, 0); } if (C[i] > nClasses) { nClasses = C[i]; } } nClasses++; System.out.println("Number of classes=" + nClasses); } catch (Exception e) { System.out.println("DBG: Exception in readSet"); e.printStackTrace(); } }