matlabpca.java

wekaUT是 university texas austin 开发的基于weka的半指导学习(semi supervised learning)的分类器

  }
  

  /** Run matlab in command line with a given argument
   * @param inFile file to be input to Matlab
   * @param outFile file where results are stored
   */
  public void runMatlab(String inFile, String outFile) {
    // call matlab to do the dirty work
    try {
      int exitValue;
      do {
	Process proc = Runtime.getRuntime().exec("matlab -tty < " + inFile + " > " + outFile);
	exitValue = proc.waitFor();
	if (exitValue != 0) {
	  System.err.println("WARNING!!!!!  Matlab returned exit value 1, trying again later!");
	  Thread.sleep(300000);
	}
      } while (exitValue != 0);
      if (m_debug) System.out.println("Matlab process done, exitValue=" + exitValue);
    } catch (Exception e) {
      System.err.println("Problems running matlab: " + e);
    }
  } 
      

  /**
   * Return a summary of the analysis
   * @return a summary of the analysis.
   */
  private String principalComponentsSummary() {
    StringBuffer result = new StringBuffer();
    double cumulative = 0.0;
    Instances output = null;
    int numVectors=0;

    try {
      output = setOutputFormat();
      numVectors = (output.classIndex() < 0) 
	? output.numAttributes()
	: output.numAttributes()-1;
    } catch (Exception ex) {
    }

    //tomorrow
    result.append("eigenvalue\tproportion\tcumulative\n");
    for (int i = 0; i < numVectors; i++) {
      cumulative+=m_eigenvalues[i];
      result.append(Utils.doubleToString(m_eigenvalues[i],9,5) +"\t"+
		    Utils.doubleToString((m_eigenvalues[i] / m_sumOfEigenValues),9,5) +"\t"+
		    Utils.doubleToString((cumulative / m_sumOfEigenValues),9,5) +"\t"+
		    output.attribute(i).name()+"\n");
    }

    result.append("\nEigenvectors\n");
    for (int j = 1;j <= numVectors;j++) {
      result.append(" V"+j+'\t');
    }
    result.append("\n");
    for (int j = 0; j < m_numAttribs; j++) {
      for (int i = 0; i < numVectors; i++) {
	result.append(Utils.
		      doubleToString(m_eigenvectors[j][i],7,4)
		      +"\t");
      }
      result.append(m_trainInstances.attribute(j).name()+'\n');
    }

    if (m_transBackToOriginal) {
      result.append("\nPC space transformed back to original space.\n"
		    +"(Note: can't evaluate attributes in the original "
		    +"space)\n");
    }
    return result.toString();
  }

  /**
   * Returns a description of this attribute transformer
   * @return a String describing this attribute transformer
   */
  public String toString() {
    if (m_eigenvalues == null) {
      return "Principal components hasn't been built yet!";
    } else {
      return "\tPrincipal Components Attribute Transformer\n\n"
	+principalComponentsSummary();
    }
  }

  /**
   * Return a matrix as a String
   * @param matrix that is decribed as a string
   * @return a String describing a matrix
   */
  private String matrixToString(double [][] matrix) {
    StringBuffer result = new StringBuffer();
    int last = matrix.length - 1;

    for (int i = 0; i <= last; i++) {
      for (int j = 0; j <= last; j++) {
	result.append(Utils.doubleToString(matrix[i][j],6,2)+" ");
	if (j == last) {
	  result.append('\n');
	}
      }
    }
    return result.toString();
  }

  /**
   * Convert a pc transformed instance back to the original space
   */
  private Instance convertInstanceToOriginal(Instance inst)
    throws Exception {
    double[] newVals = null;

    if (m_hasClass) {
      newVals = new double[m_numAttribs+1];
    } else {
      newVals = new double[m_numAttribs];
    }

    if (m_hasClass) {
      // class is always appended as the last attribute
      newVals[m_numAttribs] = inst.value(inst.numAttributes() - 1);
    }

    for (int i = 0; i < m_eTranspose[0].length; i++) {
      double tempval = 0.0;
      for (int j = 1; j < m_eTranspose.length; j++) {
	tempval += (m_eTranspose[j][i] * 
		    inst.value(j - 1));
       }
      newVals[i] = tempval;
    }
    
    if (inst instanceof SparseInstance) {
      return new SparseInstance(inst.weight(), newVals);
    } else {
      return new Instance(inst.weight(), newVals);
    }      
  }

  /**
   * Transform an instance in original (unormalized) format. Convert back
   * to the original space if requested.
   * @param instance an instance in the original (unormalized) format
   * @return a transformed instance
   * @exception Exception if instance cant be transformed
   */
  public Instance convertInstance(Instance instance) throws Exception {

    if (m_eigenvalues == null) {
      throw new Exception("convertInstance: Principal components not "
			  +"built yet");
    }

    double[] newVals = new double[m_outputNumAtts];
    Instance tempInst = (Instance)instance.copy();
    if (!instance.equalHeaders(m_trainCopy.instance(0))) {
      throw new Exception("Can't convert instance: header's don't match: "
			  +"MatlabPCA");
    }

    m_replaceMissingFilter.input(tempInst);
    m_replaceMissingFilter.batchFinished();
    tempInst = m_replaceMissingFilter.output();

    if (m_normalize) {
      m_normalizeFilter.input(tempInst);
      m_normalizeFilter.batchFinished();
      tempInst = m_normalizeFilter.output();
    }

    if (m_attributeFilter != null) {
      m_attributeFilter.input(tempInst);
      m_attributeFilter.batchFinished();
      tempInst = m_attributeFilter.output();
    }

    //  double cumulative = 0;
    for (int i = 0; i < m_outputNumAtts; i++) {
      for (int j = 0; j < m_numAttribs; j++) {
	newVals[i] += (m_eigenvectors[j][i] * tempInst.value(j));
       }
    }

    if (m_hasClass) {
       newVals[m_outputNumAtts - 1] = instance.value(instance.classIndex());
    }
    
    if (!m_transBackToOriginal) {
      if (instance instanceof SparseInstance) {
	return new SparseInstance(instance.weight(), newVals);
      } else {
	return new Instance(instance.weight(), newVals);
      }      
    } else {
      if (instance instanceof SparseInstance) {
	return convertInstanceToOriginal(new SparseInstance(instance.weight(), 
							    newVals));
      } else {
	return convertInstanceToOriginal(new Instance(instance.weight(),
						      newVals));
      }
    }
  }

  protected String valsToString(double vals[]) {
    String s= new String("[ ");
    for (int i = 0 ; i < vals.length; i++) {
      s = s + vals[i] + "  ";
    }
    return (s + "]");
  }

  /**
   * Set up the header for the PC->original space dataset
   */
  private Instances setOutputFormatOriginal() throws Exception {
    FastVector attributes = new FastVector();
    
    for (int i = 0; i < m_numAttribs; i++) {
      String att = m_trainInstances.attribute(i).name();
      attributes.addElement(new Attribute(att));
    }
    
    if (m_hasClass) {
      attributes.addElement(m_trainCopy.classAttribute().copy());
    }

    Instances outputFormat = 
      new Instances(m_trainCopy.relationName()+"->PC->original space",
		    attributes, 0);
    
    // set the class to be the last attribute if necessary
    if (m_hasClass) {
      outputFormat.setClassIndex(outputFormat.numAttributes()-1);
    }

    return outputFormat;
  }

  /**
   * Set the format for the transformed data
   * @return a set of empty Instances (header only) in the new format
   * @exception Exception if the output format can't be set
   */
  private Instances setOutputFormat() throws Exception {
    if (m_eigenvalues == null) {
      return null;
    }

    double cumulative = 0.0;
    FastVector attributes = new FastVector();

    // Create the string representations for the new attributes
    // (only up to those that sum up to m_coverVariance
    for (int i = 0; i < m_numAttribs; i++) {
      StringBuffer attName = new StringBuffer();
      for (int j = 0; j < m_numAttribs; j++) {
	attName.append(Utils.doubleToString(m_eigenvectors[j][i], 5,3)
		       + m_trainInstances.attribute(j).name());
	if (j != m_numAttribs - 1) {
	  if (m_eigenvectors[j+1][i] >= 0) {
	    attName.append(" + ");
	  }
	}
      }
      attributes.addElement(new Attribute(attName.toString()));
      cumulative+=m_eigenvalues[i];
      
      if ((cumulative / m_sumOfEigenValues) >= m_coverVariance) {
	break;
      } 
    }

    System.err.println("PCA (" + m_coverVariance + "):  went from " + m_numAttribs +
		       " to " + attributes.size() + " attributes");
    if (m_hasClass) {
      attributes.addElement(m_trainCopy.classAttribute().copy());
    }

    Instances outputFormat = 
      new Instances(m_trainInstances.relationName()+"_principal components",
		    attributes, 0);

    // set the class to be the last attribute if necessary
    if (m_hasClass) {
      outputFormat.setClassIndex(outputFormat.numAttributes()-1);
    }
     
    m_outputNumAtts = outputFormat.numAttributes();
    return outputFormat;
  }


  /** Get a timestamp string as a weak uniqueid
   * @returns a timestamp string in the form "mmddhhmmssS"
   */     
  public static String getLogTimestamp() {
	Calendar cal = Calendar.getInstance(TimeZone.getDefault());
       	String DATE_FORMAT = "MMddHHmmssS";
	java.text.SimpleDateFormat sdf = new java.text.SimpleDateFormat(DATE_FORMAT);
	
	sdf.setTimeZone(TimeZone.getDefault());          
	return (sdf.format(cal.getTime()));
    }
  
  /**
   * Main method for testing this class
   * @param argv should contain the command line arguments to the
   * evaluator/transformer (see AttributeSelection)
   */
  public static void main(String [] argv) {
    try {
      System.out.println(AttributeSelection.
			 SelectAttributes(new MatlabPCA(), argv));
    }
    catch (Exception e) {
      e.printStackTrace();
      System.out.println(e.getMessage());
    }
  }
  
}