Exemple #1
0
  /**
   * * Least-square solution y = X * b where: y_i = b_0 + b_1*x_1i + b_2*x_2i + ... + b_k*x_ki
   * including intercep term y_i = b_1*x_1i + b_2*x_2i + ... + b_k*x_ki without intercep term
   *
   * @param datay
   * @param dataX
   */
  private void multipleLinearRegression(Matrix datay, Matrix dataX) {
    Matrix X, y;
    try {
      X = dataX;
      y = datay;
      b = X.solve(y);
      coeffs = new double[b.getRowDimension()];
      for (int j = 0; j < b.getRowDimension(); j++) {
        coeffs[j] = b.get(j, 0);
        // System.out.println("coeff[" + j + "]=" + coeffs[j]);
      }

      // Residuals:
      Matrix r = X.times(b).minus(y);
      residuals = r.getColumnPackedCopy();
      // root mean square error (RMSE)
      rmse = Math.sqrt(MathUtils.sumSquared(residuals) / residuals.length);

      // Predicted values
      Matrix p = X.times(b);
      predictedValues = p.getColumnPackedCopy();

      // Correlation between original values and predicted ones
      correlation = MathUtils.correlation(predictedValues, y.getColumnPackedCopy());

    } catch (RuntimeException re) {
      throw new Error("Error solving Least-square solution: y = X * b");
    }
  }
Exemple #2
0
  // Given a set of coefficients and data predict values applying linear equation
  // This function can be used to test with data that was not used in training
  // c[] is the number of the columns in the file not the indexFeatures
  public void predictValues(
      String fileName, int indVariable, int[] c, boolean interceptTerm, int rowIni, int rowEnd) {
    try {
      BufferedReader reader = new BufferedReader(new FileReader(fileName));
      Matrix data = Matrix.read(reader);
      reader.close();
      int rows = data.getRowDimension() - 1;
      int cols = data.getColumnDimension() - 1;

      if (rowIni < 0 || rowIni > rows)
        throw new RuntimeException(
            "Problem reading file, rowIni=" + rowIni + "  and number of rows in file=" + rows);
      if (rowEnd < 0 || rowEnd > rows)
        throw new RuntimeException(
            "Problem reading file, rowIni=" + rowIni + "  and number of rows in file=" + rows);
      if (rowIni > rowEnd)
        throw new RuntimeException(
            "Problem reading file, rowIni < rowend" + rowIni + " < " + rowEnd);

      Matrix indVar =
          data.getMatrix(
              rowIni,
              rowEnd,
              indVariable,
              indVariable); // dataVowels(:,0) -> last col is the independent variable
      data =
          data.getMatrix(
              rowIni, rowEnd, c); // the dependent variables correspond to the column indices in c

      int numCoeff;
      if (interceptTerm) numCoeff = c.length + 1;
      else numCoeff = c.length;

      if (b != null) {
        if (b.getRowDimension() == numCoeff) {

          if (interceptTerm) { // first column of X is filled with 1s if b_0 != 0
            int row = data.getRowDimension();
            int col = data.getColumnDimension();

            Matrix B = new Matrix(row, col + 1);
            Matrix ones = new Matrix(row, 1);
            for (int i = 0; i < row; i++) ones.set(i, 0, 1.0);
            B.setMatrix(0, row - 1, 0, 0, ones);
            B.setMatrix(0, row - 1, 1, col, data);
            data = B;
          }

          // Residuals:
          Matrix r = data.times(b).minus(indVar);
          residuals = r.getColumnPackedCopy();
          // root mean square error (RMSE)
          rmse = Math.sqrt(MathUtils.sumSquared(residuals) / residuals.length);

          // Predicted values
          Matrix p = data.times(b);
          predictedValues = p.getColumnPackedCopy();
          for (int i = 0; i < predictedValues.length; i++)
            if (predictedValues[i] < 0.0)
              System.out.println(
                  "*** WARNING predictedValue < 0.0 : predictedValues["
                      + i
                      + "]="
                      + predictedValues[i]);

          // Correlation between original values and predicted ones
          correlation = MathUtils.correlation(predictedValues, indVar.getColumnPackedCopy());

          System.out.println("Correlation predicted values and real: " + correlation);
          System.out.println("RMSE (root mean square error): " + rmse);
        } else {
          throw new RuntimeException(
              "Number of columns of data is not the same as number of coeficients");
        }
      } else {
        throw new RuntimeException("Regression coefficients are not loaded");
      }

    } catch (Exception e) {
      throw new RuntimeException("Problem reading file " + fileName, e);
    }
  }