コード例 #1
0
ファイル: Prism.java プロジェクト: Navieclipse/KEEL
  /** Creates the total selector's set for get all the possible rules */
  private Complejo hazSelectores(Dataset train) {

    Complejo almacenSelectores;
    int nClases = train.getnclases();
    almacenSelectores =
        new Complejo(nClases); // Aqui voy a almacenar los selectores (numVariable,operador,valor)
    Attribute[] atributos = null;
    int num_atributos, type;
    Vector nominalValues;
    atributos = Attributes.getAttributes();
    num_atributos = Attributes.getNumAttributes();
    Selector s;

    for (int i = 0; i < train.getnentradas(); i++) {
      type = atributos[i].getType();
      switch (type) {
        case 0: // NOMINAL
          nominalValues = atributos[i].getNominalValuesList();
          // System.out.print("{");
          for (int j = 0; j < nominalValues.size(); j++) {
            // System.out.print ((String)nominalValues.elementAt(j)+"  ");
            s = new Selector(i, 0, (String) nominalValues.elementAt(j), true); // [atr,op,valor]
            // incluimos tb los valores en double para facilitar algunas funciones
            s.setValor((double) j);
            almacenSelectores.addSelector(s);
            // s.print();
          }
          // System.out.println("}");
          break;
      }
      // System.out.println(num_atributos);
    }
    return almacenSelectores;
  }
コード例 #2
0
ファイル: ProcessDataset.java プロジェクト: RubelAhmed57/KEEL
  /**
   * 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();
    }
  }
コード例 #3
0
ファイル: ABB.java プロジェクト: Navieclipse/KEEL
  /** Method interface for Automatic Branch and Bound */
  public void ejecutar() {
    String resultado;
    int i, numFeatures;
    Date d;

    d = new Date();
    resultado =
        "RESULTS generated at "
            + String.valueOf((Date) d)
            + " \n--------------------------------------------------\n";
    resultado += "Algorithm Name: " + params.nameAlgorithm + "\n";

    /* call of ABB algorithm */
    runABB();

    resultado += "\nPARTITION Filename: " + params.trainFileNameInput + "\n---------------\n\n";
    resultado += "Features selected: \n";

    for (i = numFeatures = 0; i < features.length; i++)
      if (features[i] == true) {
        resultado += Attributes.getInputAttribute(i).getName() + " - ";
        numFeatures++;
      }

    resultado +=
        "\n\n"
            + String.valueOf(numFeatures)
            + " features of "
            + Attributes.getInputNumAttributes()
            + "\n\n";

    resultado +=
        "Error in test (using train for prediction): "
            + String.valueOf(data.validacionCruzada(features))
            + "\n";
    resultado +=
        "Error in test (using test for prediction): "
            + String.valueOf(data.LVOTest(features))
            + "\n";

    resultado += "---------------\n";

    System.out.println("Experiment completed successfully");

    /* creates the new training and test datasets only with the selected features */
    Files.writeFile(params.extraFileNameOutput, resultado);
    data.generarFicherosSalida(params.trainFileNameOutput, params.testFileNameOutput, features);
  }
コード例 #4
0
ファイル: TableVar.java プロジェクト: Navieclipse/KEEL
  /**
   * Fill TableVar with the characteristics of the variables and creates characteristics and
   * intervals for the fuzzy sets
   *
   * @param size Number of variables of the dataset
   */
  public void Load(int size) {
    num_vars = size; // Stores the number of variables of the dataset
    var = new TypeVar[num_vars]; // Creates space for the structure

    // For each variable of the dataset
    for (int i = 0; i < num_vars; i++) {
      var[i] = new TypeVar(); // Creates space for the variable chars
      var[i].setName(Attributes.getInputAttribute(i).getName());

      if (Attributes.getInputAttribute(i).getType() == Attribute.NOMINAL) {
        var[i].setType('e');
        var[i].setContinuous(false);
        var[i].initValues(Attributes.getInputAttribute(i).getNominalValuesList());
        var[i].setMin(
            0); // Enumerated values are translated into values from 0 to number of elements - 1
        var[i].setMax(Attributes.getInputAttribute(i).getNumNominalValues() - 1);
        var[i].setNLabels(Attributes.getInputAttribute(i).getNumNominalValues());
        // Update max number of values for discrete vars
        if (var[i].getNLabels() > MaxValores) MaxValores = var[i].getNLabels();
      } else if (Attributes.getInputAttribute(i).getType() == Attribute.REAL) {
        // Real: Continuous type
        var[i].setType('r');
        var[i].setContinuous(true);
        var[i].setMin((float) Attributes.getInputAttribute(i).getMinAttribute());
        var[i].setMax((float) Attributes.getInputAttribute(i).getMaxAttribute());
        var[i].setNLabels(n_etiq);
        // Update the max number of labels for cont variables and number of values
        if (var[i].getNLabels() > MaxEtiquetas) MaxEtiquetas = var[i].getNLabels();
        if (var[i].getNLabels() > MaxValores) MaxValores = var[i].getNLabels();
      } else {
        // Integer: Continuous type
        var[i].setType('i');
        var[i].setContinuous(true);
        var[i].setMin((float) Attributes.getInputAttribute(i).getMinAttribute());
        var[i].setMax((float) Attributes.getInputAttribute(i).getMaxAttribute());
        var[i].setNLabels(n_etiq);
        // Update the max number of labels for cont variables and number of values
        if (var[i].getNLabels() > MaxEtiquetas) MaxEtiquetas = var[i].getNLabels();
        if (var[i].getNLabels() > MaxValores) MaxValores = var[i].getNLabels();
      }
    }

    // Creates "Fuzzy" characteristics and intervals
    BaseDatos = new Fuzzy[num_vars][MaxValores];
    for (int x = 0; x < num_vars; x++)
      for (int y = 0; y < MaxValores; y++) BaseDatos[x][y] = new Fuzzy();
  }
コード例 #5
0
ファイル: ABB.java プロジェクト: Navieclipse/KEEL
  /**
   * Creates a boolean array with all values to true
   *
   * @return returns a boolean vector with all values to true
   */
  private boolean[] startSolution() {
    boolean fv[];

    fv = new boolean[Attributes.getInputNumAttributes()];

    for (int i = 0; i < fv.length; i++) fv[i] = true;

    return fv;
  }
コード例 #6
0
ファイル: LVQ.java プロジェクト: triguero/Keel3.0
  private void normalizarTest() {

    int i, j, cont = 0, k;
    Instance temp;
    boolean hecho;
    double caja[];
    StringTokenizer tokens;
    boolean nulls[];

    /* Check if dataset corresponding with a classification problem */

    if (Attributes.getOutputNumAttributes() < 1) {
      System.err.println(
          "This dataset haven´t outputs, so it not corresponding to a classification problem.");
      System.exit(-1);
    } else if (Attributes.getOutputNumAttributes() > 1) {
      System.err.println("This dataset have more of one output.");
      System.exit(-1);
    }

    if (Attributes.getOutputAttribute(0).getType() == Attribute.REAL) {
      System.err.println(
          "This dataset have an input attribute with floating values, so it not corresponding to a classification problem.");
      System.exit(-1);
    }

    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];
      for (k = 0; k < datosTest[i].length; k++) {
        if (Attributes.getInputAttribute(k).getType() == Attribute.NOMINAL) {
          datosTest[i][k] /= Attributes.getInputAttribute(k).getNominalValuesList().size() - 1;
        } else {
          datosTest[i][k] -= Attributes.getInputAttribute(k).getMinAttribute();
          datosTest[i][k] /=
              Attributes.getInputAttribute(k).getMaxAttribute()
                  - Attributes.getInputAttribute(k).getMinAttribute();
        }
      }
    }
  }
コード例 #7
0
ファイル: LVQ.java プロジェクト: triguero/Keel3.0
  private void normalizarReferencia() throws CheckException {

    int i, j, cont = 0, k;
    Instance temp;
    boolean hecho;
    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.");
    }

    datosReferencia = new double[referencia.getNumInstances()][Attributes.getInputNumAttributes()];
    clasesReferencia = new int[referencia.getNumInstances()];
    caja = new double[1];

    /*Get the number of instances that have a null value*/
    for (i = 0; i < referencia.getNumInstances(); i++) {
      temp = referencia.getInstance(i);
      nulls = temp.getInputMissingValues();
      datosReferencia[i] = referencia.getInstance(i).getAllInputValues();
      for (j = 0; j < nulls.length; j++) if (nulls[j]) datosReferencia[i][j] = 0.0;
      caja = referencia.getInstance(i).getAllOutputValues();
      clasesReferencia[i] = (int) caja[0];
      for (k = 0; k < datosReferencia[i].length; k++) {
        if (Attributes.getInputAttribute(k).getType() == Attribute.NOMINAL) {
          datosReferencia[i][k] /=
              Attributes.getInputAttribute(k).getNominalValuesList().size() - 1;
        } else {
          datosReferencia[i][k] -= Attributes.getInputAttribute(k).getMinAttribute();
          datosReferencia[i][k] /=
              Attributes.getInputAttribute(k).getMaxAttribute()
                  - Attributes.getInputAttribute(k).getMinAttribute();
        }
      }
    }
  }
コード例 #8
0
ファイル: kmeansImpute.java プロジェクト: Navieclipse/KEEL
  /**
   * Computes the distance between two instances (without previous normalization)
   *
   * @param i First instance
   * @param j Second instance
   * @return The Euclidean distance between i and j
   */
  private double distance(Instance i, Instance j) {
    double dist = 0;
    int in = 0;
    int out = 0;

    for (int l = 0; l < nvariables; l++) {
      Attribute a = Attributes.getAttribute(l);

      direccion = a.getDirectionAttribute();
      tipo = a.getType();

      if (direccion == Attribute.INPUT) {
        if (tipo != Attribute.NOMINAL && !i.getInputMissingValues(in)) {
          // real value, apply euclidean distance
          dist +=
              (i.getInputRealValues(in) - j.getInputRealValues(in))
                  * (i.getInputRealValues(in) - j.getInputRealValues(in));
        } else {
          if (!i.getInputMissingValues(in)
              && i.getInputNominalValues(in) != j.getInputNominalValues(in)) dist += 1;
        }
        in++;
      } else {
        if (direccion == Attribute.OUTPUT) {
          if (tipo != Attribute.NOMINAL && !i.getOutputMissingValues(out)) {
            dist +=
                (i.getOutputRealValues(out) - j.getOutputRealValues(out))
                    * (i.getOutputRealValues(out) - j.getOutputRealValues(out));
          } else {
            if (!i.getOutputMissingValues(out)
                && i.getOutputNominalValues(out) != j.getOutputNominalValues(out)) dist += 1;
          }
          out++;
        }
      }
    }
    return dist;
  }
コード例 #9
0
ファイル: LVQ.java プロジェクト: triguero/Keel3.0
  public void ejecutar() {

    int i, j, l, m;
    double alfai;
    int nClases;

    int claseObt;

    boolean marcas[];
    boolean notFound;

    int init;
    int clasSel[];

    int baraje[];

    int pos, tmp;
    String instanciasIN[];
    String instanciasOUT[];

    long tiempo = System.currentTimeMillis();

    /* Getting the number of differents classes */

    nClases = 0;

    for (i = 0; i < clasesTrain.length; i++) if (clasesTrain[i] > nClases) nClases = clasesTrain[i];

    nClases++;

    /* Shuffle the train set */

    baraje = new int[datosTrain.length];

    Randomize.setSeed(semilla);

    for (i = 0; i < datosTrain.length; i++) baraje[i] = i;

    for (i = 0; i < datosTrain.length; i++) {

      pos = Randomize.Randint(i, datosTrain.length - 1);

      tmp = baraje[i];

      baraje[i] = baraje[pos];

      baraje[pos] = tmp;
    }

    /*
     * Inicialization of the flagged instaces vector for a posterior
     * elimination
     */

    marcas = new boolean[datosTrain.length];

    for (i = 0; i < datosTrain.length; i++) marcas[i] = false;

    if (datosTrain.length > 0) {

      // marcas[baraje[0]] = true; //the first instance is included always

      nSel = n_p;
      if (nSel < nClases) nSel = nClases;

    } else {

      System.err.println("Input dataset is empty");

      nSel = 0;
    }
    clasSel = new int[nClases];
    System.out.print("Selecting initial neurons... ");
    // at least, there must be 1 neuron of each class at the beginning
    init = nClases;
    for (i = 0; i < nClases && i < datosTrain.length; i++) {
      pos = Randomize.Randint(0, datosTrain.length - 1);
      tmp = 0;
      while ((clasesTrain[pos] != i || marcas[pos]) && tmp < datosTrain.length) {
        pos = (pos + 1) % datosTrain.length;
        tmp++;
      }
      if (tmp < datosTrain.length) marcas[pos] = true;
      else init--;
      // clasSel[i] = i;
    }
    for (i = init; i < Math.min(nSel, datosTrain.length); i++) {
      tmp = 0;
      pos = Randomize.Randint(0, datosTrain.length - 1);
      while (marcas[pos]) {
        pos = (pos + 1) % datosTrain.length;
        tmp++;
      }
      // if(i<nClases){
      // notFound = true;
      // do{
      // for(j=i-1;j>=0 && notFound;j--){
      // if(clasSel[j] == clasesTrain[pos])
      // notFound = false;
      // }
      // if(!notFound)
      // pos = Randomize.Randint (0, datosTrain.length-1);
      // }while(!notFound);
      // }
      // clasSel[i] = clasesTrain[pos];
      marcas[pos] = true;
      init++;
    }
    nSel = init;
    System.out.println("Initial neurons selected: " + nSel);

    /* Building of the S set from the flags */

    conjS = new double[nSel][datosTrain[0].length];

    clasesS = new int[nSel];

    for (m = 0, l = 0; m < datosTrain.length; m++) {

      if (marcas[m]) { // the instance must be copied to the solution

        for (j = 0; j < datosTrain[0].length; j++) {

          conjS[l][j] = datosTrain[m][j];
        }

        clasesS[l] = clasesTrain[m];

        l++;
      }
    }

    alfai = alpha;
    boolean change = true;
    /* Body of the LVQ algorithm. */

    // Train the network
    for (int it = 0; it < T && change; it++) {
      change = false;
      alpha = alfai;
      for (i = 1; i < datosTrain.length; i++) {
        // search for the nearest neuron to training instance
        pos = NN(nSel, conjS, datosTrain[baraje[i]]);
        // nearest neuron labels correctly the class of training
        // instance?

        if (clasesS[pos] != clasesTrain[baraje[i]]) { // NO - repel
          // the neuron
          for (j = 0; j < conjS[pos].length; j++) {
            conjS[pos][j] = conjS[pos][j] - alpha * (datosTrain[baraje[i]][j] - conjS[pos][j]);
          }
          change = true;
        } else { // YES - migrate the neuron towards the input vector
          for (j = 0; j < conjS[pos].length; j++) {
            conjS[pos][j] = conjS[pos][j] + alpha * (datosTrain[baraje[i]][j] - conjS[pos][j]);
          }
        }
        alpha = nu * alpha;
      }
      // Shuffle again the training partition
      baraje = new int[datosTrain.length];

      for (i = 0; i < datosTrain.length; i++) baraje[i] = i;

      for (i = 0; i < datosTrain.length; i++) {

        pos = Randomize.Randint(i, datosTrain.length - 1);

        tmp = baraje[i];

        baraje[i] = baraje[pos];

        baraje[pos] = tmp;
      }
    }
    System.out.println(
        "LVQ " + relation + " " + (double) (System.currentTimeMillis() - tiempo) / 1000.0 + "s");
    // Classify the train data set
    instanciasIN = new String[datosReferencia.length];
    instanciasOUT = new String[datosReferencia.length];
    for (i = 0; i < datosReferencia.length; i++) {
      /* Classify the instance selected in this iteration */
      Attribute a = Attributes.getOutputAttribute(0);

      int tipo = a.getType();
      claseObt = KNN.evaluacionKNN2(1, conjS, clasesS, datosReferencia[i], nClases);
      if (tipo != Attribute.NOMINAL) {
        instanciasIN[i] = new String(String.valueOf(clasesReferencia[i]));
        instanciasOUT[i] = new String(String.valueOf(claseObt));
      } else {
        instanciasIN[i] = new String(a.getNominalValue(clasesReferencia[i]));
        instanciasOUT[i] = new String(a.getNominalValue(claseObt));
      }
    }

    escribeSalida(
        ficheroSalida[0], instanciasIN, instanciasOUT, entradas, salida, nEntradas, relation);

    // Classify the test data set
    normalizarTest();
    instanciasIN = new String[datosTest.length];
    instanciasOUT = new String[datosTest.length];
    for (i = 0; i < datosTest.length; i++) {
      /* Classify the instance selected in this iteration */
      Attribute a = Attributes.getOutputAttribute(0);

      int tipo = a.getType();

      claseObt = KNN.evaluacionKNN2(1, conjS, clasesS, datosTest[i], nClases);
      if (tipo != Attribute.NOMINAL) {
        instanciasIN[i] = new String(String.valueOf(clasesTest[i]));
        instanciasOUT[i] = new String(String.valueOf(claseObt));
      } else {
        instanciasIN[i] = new String(a.getNominalValue(clasesTest[i]));
        instanciasOUT[i] = new String(a.getNominalValue(claseObt));
      }
    }

    escribeSalida(
        ficheroSalida[1], instanciasIN, instanciasOUT, entradas, salida, nEntradas, relation);

    // Print the network to a file
    printNetworkToFile(ficheroSalida[2], referencia.getHeader());
  }
コード例 #10
0
ファイル: CNN_TomekLinks.java プロジェクト: RubelAhmed57/KEEL
  /**
   * 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
コード例 #11
0
ファイル: ProcessDataset.java プロジェクト: RubelAhmed57/KEEL
  /**
   * 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();
    }
  }
コード例 #12
0
ファイル: kmeansImpute.java プロジェクト: Navieclipse/KEEL
  /** Process the training and test files provided in the parameters file to the constructor. */
  public void process() {
    // declarations
    double[] outputs;
    double[] outputs2;
    Instance neighbor;
    double dist, mean;
    int actual;
    Randomize rnd = new Randomize();
    Instance ex;
    gCenter kmeans = null;
    int iterations = 0;
    double E;
    double prevE;
    int totalMissing = 0;
    boolean allMissing = true;

    rnd.setSeed(semilla);
    // PROCESS
    try {

      // Load in memory a dataset that contains a classification problem
      IS.readSet(input_train_name, true);
      int in = 0;
      int out = 0;

      ndatos = IS.getNumInstances();
      nvariables = Attributes.getNumAttributes();
      nentradas = Attributes.getInputNumAttributes();
      nsalidas = Attributes.getOutputNumAttributes();

      X = new String[ndatos][nvariables]; // matrix with transformed data
      kmeans = new gCenter(K, ndatos, nvariables);

      timesSeen = new FreqList[nvariables];
      mostCommon = new String[nvariables];

      // first, we choose k 'means' randomly from all
      // instances
      totalMissing = 0;
      for (int i = 0; i < ndatos; i++) {
        Instance inst = IS.getInstance(i);
        if (inst.existsAnyMissingValue()) totalMissing++;
      }
      if (totalMissing == ndatos) allMissing = true;
      else allMissing = false;
      for (int numMeans = 0; numMeans < K; numMeans++) {
        do {
          actual = (int) (ndatos * rnd.Rand());
          ex = IS.getInstance(actual);
        } while (ex.existsAnyMissingValue() && !allMissing);

        kmeans.copyCenter(ex, numMeans);
      }

      // now, iterate adjusting clusters' centers and
      // instances to them
      prevE = 0;
      iterations = 0;
      do {
        for (int i = 0; i < ndatos; i++) {
          Instance inst = IS.getInstance(i);

          kmeans.setClusterOf(inst, i);
        }
        // set new centers
        kmeans.recalculateCenters(IS);
        // compute RMSE
        E = 0;
        for (int i = 0; i < ndatos; i++) {
          Instance inst = IS.getInstance(i);

          E += kmeans.distance(inst, kmeans.getClusterOf(i));
        }
        iterations++;
        // System.out.println(iterations+"\t"+E);
        if (Math.abs(prevE - E) == 0) iterations = maxIter;
        else prevE = E;
      } while (E > minError && iterations < maxIter);
      for (int i = 0; i < ndatos; i++) {
        Instance inst = IS.getInstance(i);

        in = 0;
        out = 0;

        for (int j = 0; j < nvariables; j++) {
          Attribute a = Attributes.getAttribute(j);

          direccion = a.getDirectionAttribute();
          tipo = a.getType();

          if (direccion == Attribute.INPUT) {
            if (tipo != Attribute.NOMINAL && !inst.getInputMissingValues(in)) {
              X[i][j] = new String(String.valueOf(inst.getInputRealValues(in)));
            } else {
              if (!inst.getInputMissingValues(in)) X[i][j] = inst.getInputNominalValues(in);
              else {
                actual = kmeans.getClusterOf(i);
                X[i][j] = new String(kmeans.valueAt(actual, j));
              }
            }
            in++;
          } else {
            if (direccion == Attribute.OUTPUT) {
              if (tipo != Attribute.NOMINAL && !inst.getOutputMissingValues(out)) {
                X[i][j] = new String(String.valueOf(inst.getOutputRealValues(out)));
              } else {
                if (!inst.getOutputMissingValues(out)) X[i][j] = inst.getOutputNominalValues(out);
                else {
                  actual = kmeans.getClusterOf(i);
                  X[i][j] = new String(kmeans.valueAt(actual, j));
                }
              }
              out++;
            }
          }
        }
      }
    } catch (Exception e) {
      System.out.println("Dataset exception = " + e);
      e.printStackTrace();
      System.exit(-1);
    }
    write_results(output_train_name);
    /** ************************************************************************************ */
    // does a test file associated exist?
    if (input_train_name.compareTo(input_test_name) != 0) {
      try {

        // Load in memory a dataset that contains a classification problem
        IStest.readSet(input_test_name, false);
        int in = 0;
        int out = 0;

        ndatos = IStest.getNumInstances();
        nvariables = Attributes.getNumAttributes();
        nentradas = Attributes.getInputNumAttributes();
        nsalidas = Attributes.getOutputNumAttributes();

        for (int i = 0; i < ndatos; i++) {
          Instance inst = IStest.getInstance(i);

          in = 0;
          out = 0;

          for (int j = 0; j < nvariables; j++) {
            Attribute a = Attributes.getAttribute(j);

            direccion = a.getDirectionAttribute();
            tipo = a.getType();

            if (direccion == Attribute.INPUT) {
              if (tipo != Attribute.NOMINAL && !inst.getInputMissingValues(in)) {
                X[i][j] = new String(String.valueOf(inst.getInputRealValues(in)));
              } else {
                if (!inst.getInputMissingValues(in)) X[i][j] = inst.getInputNominalValues(in);
                else {
                  actual = kmeans.getClusterOf(i);
                  X[i][j] = new String(kmeans.valueAt(actual, j));
                }
              }
              in++;
            } else {
              if (direccion == Attribute.OUTPUT) {
                if (tipo != Attribute.NOMINAL && !inst.getOutputMissingValues(out)) {
                  X[i][j] = new String(String.valueOf(inst.getOutputRealValues(out)));
                } else {
                  if (!inst.getOutputMissingValues(out)) X[i][j] = inst.getOutputNominalValues(out);
                  else {
                    actual = kmeans.getClusterOf(i);
                    X[i][j] = new String(kmeans.valueAt(actual, j));
                  }
                }
                out++;
              }
            }
          }
        }
      } catch (Exception e) {
        System.out.println("Dataset exception = " + e);
        e.printStackTrace();
        System.exit(-1);
      }
      write_results(output_test_name);
    }
  }