normalize.java

来自「Weka」· Java 代码 · 共 570 行 · 第 1/2 页

	      if (Double.isNaN(m_MinArray[i])) {
		m_MinArray[i] = m_MaxArray[i] = value[i];
	      }
	      else {
		if (value[i] < m_MinArray[i])
		  m_MinArray[i] = value[i];
		if (value[i] > m_MaxArray[i])
		  m_MaxArray[i] = value[i];
	      }
	    }
	  }
	} 
      }

      // Convert pending input instances
      for (int i = 0; i < input.numInstances(); i++)
	convertInstance(input.instance(i));
    } 
    // Free memory
    flushInput();

    m_NewBatch = true;
    return (numPendingOutput() != 0);
  }

  /**
   * Convert a single instance over. The converted instance is 
   * added to the end of the output queue.
   *
   * @param instance 	the instance to convert
   * @throws Exception 	if conversion fails
   */
  protected void convertInstance(Instance instance) throws Exception {
    Instance inst = null;
    if (instance instanceof SparseInstance) {
      double[] newVals = new double[instance.numAttributes()];
      int[] newIndices = new int[instance.numAttributes()];
      double[] vals = instance.toDoubleArray();
      int ind = 0;
      for (int j = 0; j < instance.numAttributes(); j++) {
	double value;
	if (instance.attribute(j).isNumeric() &&
	    (!Instance.isMissingValue(vals[j])) &&
	    (getInputFormat().classIndex() != j)) {
	  if (Double.isNaN(m_MinArray[j]) ||
	      (m_MaxArray[j] == m_MinArray[j])) {
	    value = 0;
	  }
	  else {
	    value = (vals[j] - m_MinArray[j]) / 
	      (m_MaxArray[j] - m_MinArray[j]) * m_Scale + m_Translation;
            if (Double.isNaN(value)) {
              throw new Exception("A NaN value was generated "
                                  + "while normalizing " 
                                  + instance.attribute(j).name());
            }
	  }
	  if (value != 0.0) {
	    newVals[ind] = value;
	    newIndices[ind] = j;
	    ind++;
	  }
	}
	else {
	  value = vals[j];
	  if (value != 0.0) {
	    newVals[ind] = value;
	    newIndices[ind] = j;
	    ind++;
	  }
	}
      }	
      double[] tempVals = new double[ind];
      int[] tempInd = new int[ind];
      System.arraycopy(newVals, 0, tempVals, 0, ind);
      System.arraycopy(newIndices, 0, tempInd, 0, ind);
      inst = new SparseInstance(instance.weight(), tempVals, tempInd,
                                instance.numAttributes());
    }
    else {
      double[] vals = instance.toDoubleArray();
      for (int j = 0; j < getInputFormat().numAttributes(); j++) {
	if (instance.attribute(j).isNumeric() &&
	    (!Instance.isMissingValue(vals[j])) &&
	    (getInputFormat().classIndex() != j)) {
	  if (Double.isNaN(m_MinArray[j]) ||
	      (m_MaxArray[j] == m_MinArray[j])) {
	    vals[j] = 0;
	  }
	  else {
	    vals[j] = (vals[j] - m_MinArray[j]) / 
	      (m_MaxArray[j] - m_MinArray[j]) * m_Scale + m_Translation;
            if (Double.isNaN(vals[j])) {
              throw new Exception("A NaN value was generated "
                                  + "while normalizing " 
                                  + instance.attribute(j).name());
            }
	  }
	}
      }	
      inst = new Instance(instance.weight(), vals);
    }
    inst.setDataset(instance.dataset());
    push(inst);
  }
  
  /**
   * Returns a string that describes the filter as source. The
   * filter will be contained in a class with the given name (there may
   * be auxiliary classes),
   * and will contain two methods with these signatures:
   * <pre><code>
   * // converts one row
   * public static Object[] filter(Object[] i);
   * // converts a full dataset (first dimension is row index)
   * public static Object[][] filter(Object[][] i);
   * </code></pre>
   * where the array <code>i</code> contains elements that are either
   * Double, String, with missing values represented as null. The generated
   * code is public domain and comes with no warranty.
   *
   * @param className   the name that should be given to the source class.
   * @param data	the dataset used for initializing the filter
   * @return            the object source described by a string
   * @throws Exception  if the source can't be computed
   */
  public String toSource(String className, Instances data) throws Exception {
    StringBuffer        result;
    boolean[]		process;
    int			i;
    
    result = new StringBuffer();
    
    // determine what attributes were processed
    process = new boolean[data.numAttributes()];
    for (i = 0; i < data.numAttributes(); i++) 
      process[i] = (data.attribute(i).isNumeric() && (i != data.classIndex()));
  
    result.append("class " + className + " {\n");
    result.append("\n");
    result.append("  /** lists which attributes will be processed */\n");
    result.append("  protected final static boolean[] PROCESS = new boolean[]{" + Utils.arrayToString(process) + "};\n");
    result.append("\n");
    result.append("  /** the minimum values for numeric values */\n");
    result.append("  protected final static double[] MIN = new double[]{" + Utils.arrayToString(m_MinArray).replaceAll("NaN", "Double.NaN") + "};\n");
    result.append("\n");
    result.append("  /** the maximum values for numeric values */\n");
    result.append("  protected final static double[] MAX = new double[]{" + Utils.arrayToString(m_MaxArray) + "};\n");
    result.append("\n");
    result.append("  /** the scale factor */\n");
    result.append("  protected final static double SCALE = " + m_Scale + ";\n");
    result.append("\n");
    result.append("  /** the translation */\n");
    result.append("  protected final static double TRANSLATION = " + m_Translation + ";\n");
    result.append("\n");
    result.append("  /**\n");
    result.append("   * filters a single row\n");
    result.append("   * \n");
    result.append("   * @param i the row to process\n");
    result.append("   * @return the processed row\n");
    result.append("   */\n");
    result.append("  public static Object[] filter(Object[] i) {\n");
    result.append("    Object[] result;\n");
    result.append("\n");
    result.append("    result = new Object[i.length];\n");
    result.append("    for (int n = 0; n < i.length; n++) {\n");
    result.append("      if (PROCESS[n] && (i[n] != null)) {\n");
    result.append("        if (Double.isNaN(MIN[n]) || (MIN[n] == MAX[n]))\n");
    result.append("          result[n] = 0;\n");
    result.append("        else\n");
    result.append("          result[n] = (((Double) i[n]) - MIN[n]) / (MAX[n] - MIN[n]) * SCALE + TRANSLATION;\n");
    result.append("      }\n");
    result.append("      else {\n");
    result.append("        result[n] = i[n];\n");
    result.append("      }\n");
    result.append("    }\n");
    result.append("\n");
    result.append("    return result;\n");
    result.append("  }\n");
    result.append("\n");
    result.append("  /**\n");
    result.append("   * filters multiple rows\n");
    result.append("   * \n");
    result.append("   * @param i the rows to process\n");
    result.append("   * @return the processed rows\n");
    result.append("   */\n");
    result.append("  public static Object[][] filter(Object[][] i) {\n");
    result.append("    Object[][] result;\n");
    result.append("\n");
    result.append("    result = new Object[i.length][];\n");
    result.append("    for (int n = 0; n < i.length; n++) {\n");
    result.append("      result[n] = filter(i[n]);\n");
    result.append("    }\n");
    result.append("\n");
    result.append("    return result;\n");
    result.append("  }\n");
    result.append("}\n");
    
    return result.toString();
  }

  /**
   * Returns the calculated minimum values for the attributes in the data.
   * 
   * @return		the array with the minimum values
   */
  public double[] getMinArray() {
    return m_MinArray;
  }

  /**
   * Returns the calculated maximum values for the attributes in the data.
   * 
   * @return		the array with the maximum values
   */
  public double[] getMaxArray() {
    return m_MaxArray;
  }

  /**
   * Returns the tip text for this property.
   *
   * @return 		tip text for this property suitable for
   * 			displaying in the explorer/experimenter gui
   */
  public String scaleTipText() {
    return "The factor for scaling the output range (default: 1).";
  }

  /**
   * Get the scaling factor.
   *
   * @return 		the factor
   */
  public double getScale() {
    return m_Scale;
  }

  /**
   * Sets the scaling factor.
   *
   * @param value 	the scaling factor
   */
  public void setScale(double value) {
    m_Scale = value;
  }

  /**
   * Returns the tip text for this property.
   *
   * @return 		tip text for this property suitable for
   * 			displaying in the explorer/experimenter gui
   */
  public String translationTipText() {
    return "The translation of the output range (default: 0).";
  }

  /**
   * Get the translation.
   *
   * @return 		the translation
   */
  public double getTranslation() {
    return m_Translation;
  }

  /**
   * Sets the translation.
   *
   * @param value 	the translation
   */
  public void setTranslation(double value) {
    m_Translation = value;
  }
  
  /**
   * Main method for running this filter.
   *
   * @param args 	should contain arguments to the filter, use -h for help
   */
  public static void main(String[] args) {
    runFilter(new Normalize(), args);
  }
}