static void checkDataset() { Attribute[] outputs = Attributes.getOutputAttributes(); if (outputs.length != 1) { LogManager.printErr("Only datasets with one output are supported"); System.exit(1); } if (outputs[0].getType() != Attribute.NOMINAL) { LogManager.printErr("Output attribute should be nominal"); System.exit(1); } Parameters.numClasses = outputs[0].getNumNominalValues(); Parameters.numAttributes = Attributes.getInputAttributes().length; }
/** * It does return a new header (not necessary the same header as the input file one). It only * includes the valid attributes, those ones defined in @inputs and @outputs (or taken as that * role following the keel format specification). * * @return a String with the new header */ public String getNewHeader() { String line = ""; Attribute[] attrs = null; // Getting the relation name and the attributes if (storeAttributesAsNonStatic && attributes != null) { line = "@relation " + attributes.getRelationName() + "\n"; attrs = attributes.getInputAttributes(); } else { line = "@relation " + Attributes.getRelationName() + "\n"; attrs = Attributes.getInputAttributes(); } for (int i = 0; i < attrs.length; i++) { line += attrs[i].toString() + "\n"; } // Gettin all the outputs attributes if (storeAttributesAsNonStatic && attributes != null) { attrs = attributes.getOutputAttributes(); line += attrs[0].toString() + "\n"; // Getting @inputs and @outputs line += attributes.getInputHeader() + "\n"; line += attributes.getOutputHeader() + "\n"; } else { attrs = Attributes.getOutputAttributes(); line += attrs[0].toString() + "\n"; // Getting @inputs and @outputs line += Attributes.getInputHeader() + "\n"; line += Attributes.getOutputHeader() + "\n"; } return line; } // end getNewHeader
/** * This function builds the data matrix for reference data and normalizes inputs values * * @throws keel.Algorithms.Preprocess.Basic.CheckException Can not be normalized. */ protected void normalizar() throws CheckException { int i, j, k; Instance temp; double caja[]; StringTokenizer tokens; boolean nulls[]; /*Check if dataset corresponding with a classification problem*/ if (Attributes.getOutputNumAttributes() < 1) { throw new CheckException( "This dataset haven?t outputs, so it not corresponding to a classification problem."); } else if (Attributes.getOutputNumAttributes() > 1) { throw new CheckException("This dataset have more of one output."); } if (Attributes.getOutputAttribute(0).getType() == Attribute.REAL) { throw new CheckException( "This dataset have an input attribute with floating values, so it not corresponding to a classification problem."); } entradas = Attributes.getInputAttributes(); salida = Attributes.getOutputAttribute(0); nEntradas = Attributes.getInputNumAttributes(); tokens = new StringTokenizer(training.getHeader(), " \n\r"); tokens.nextToken(); relation = tokens.nextToken(); datosTrain = new double[training.getNumInstances()][Attributes.getInputNumAttributes()]; clasesTrain = new int[training.getNumInstances()]; caja = new double[1]; nulosTrain = new boolean[training.getNumInstances()][Attributes.getInputNumAttributes()]; nominalTrain = new int[training.getNumInstances()][Attributes.getInputNumAttributes()]; realTrain = new double[training.getNumInstances()][Attributes.getInputNumAttributes()]; for (i = 0; i < training.getNumInstances(); i++) { temp = training.getInstance(i); nulls = temp.getInputMissingValues(); datosTrain[i] = training.getInstance(i).getAllInputValues(); for (j = 0; j < nulls.length; j++) if (nulls[j]) { datosTrain[i][j] = 0.0; nulosTrain[i][j] = true; } caja = training.getInstance(i).getAllOutputValues(); clasesTrain[i] = (int) caja[0]; for (k = 0; k < datosTrain[i].length; k++) { if (Attributes.getInputAttribute(k).getType() == Attribute.NOMINAL) { nominalTrain[i][k] = (int) datosTrain[i][k]; datosTrain[i][k] /= Attributes.getInputAttribute(k).getNominalValuesList().size() - 1; } else { realTrain[i][k] = datosTrain[i][k]; datosTrain[i][k] -= Attributes.getInputAttribute(k).getMinAttribute(); datosTrain[i][k] /= Attributes.getInputAttribute(k).getMaxAttribute() - Attributes.getInputAttribute(k).getMinAttribute(); if (Double.isNaN(datosTrain[i][k])) { datosTrain[i][k] = realTrain[i][k]; } } } } datosTest = new double[test.getNumInstances()][Attributes.getInputNumAttributes()]; clasesTest = new int[test.getNumInstances()]; caja = new double[1]; for (i = 0; i < test.getNumInstances(); i++) { temp = test.getInstance(i); nulls = temp.getInputMissingValues(); datosTest[i] = test.getInstance(i).getAllInputValues(); for (j = 0; j < nulls.length; j++) if (nulls[j]) { datosTest[i][j] = 0.0; } caja = test.getInstance(i).getAllOutputValues(); clasesTest[i] = (int) caja[0]; } } // end-method