/** initializes the attribute indices. */
protected void initializeAttributeIndices() {
m_AttributeIndices.setUpper(m_Data.numAttributes() - 1);
m_ActiveIndices = new boolean[m_Data.numAttributes()];
for (int i = 0; i < m_ActiveIndices.length; i++) {
m_ActiveIndices[i] = m_AttributeIndices.isInRange(i);
}
}
/**
* Determines the output format based on the input format and returns this. In case the output
* format cannot be returned immediately, i.e., immediateOutputFormat() returns false, then this
* method will be called from batchFinished().
*
* @param inputFormat the input format to base the output format on
* @return the output format
* @throws Exception in case the determination goes wrong
* @see #hasImmediateOutputFormat()
* @see #batchFinished()
*/
protected Instances determineOutputFormat(Instances inputFormat) throws Exception {
Instances data;
Instances result;
FastVector atts;
FastVector values;
HashSet hash;
int i;
int n;
boolean isDate;
Instance inst;
Vector sorted;
m_Cols.setUpper(inputFormat.numAttributes() - 1);
data = new Instances(inputFormat);
atts = new FastVector();
for (i = 0; i < data.numAttributes(); i++) {
if (!m_Cols.isInRange(i) || !data.attribute(i).isNumeric()) {
atts.addElement(data.attribute(i));
continue;
}
// date attribute?
isDate = (data.attribute(i).type() == Attribute.DATE);
// determine all available attribtues in dataset
hash = new HashSet();
for (n = 0; n < data.numInstances(); n++) {
inst = data.instance(n);
if (inst.isMissing(i)) continue;
if (isDate) hash.add(inst.stringValue(i));
else hash.add(new Double(inst.value(i)));
}
// sort values
sorted = new Vector();
for (Object o : hash) sorted.add(o);
Collections.sort(sorted);
// create attribute from sorted values
values = new FastVector();
for (Object o : sorted) {
if (isDate) values.addElement(o.toString());
else values.addElement(Utils.doubleToString(((Double) o).doubleValue(), MAX_DECIMALS));
}
atts.addElement(new Attribute(data.attribute(i).name(), values));
}
result = new Instances(inputFormat.relationName(), atts, 0);
result.setClassIndex(inputFormat.classIndex());
return result;
}
/**
* Sets the format of the input instances.
*
* @param instanceInfo an Instances object containing the input instance structure (any instances
* contained in the object are ignored - only the structure is required).
* @return true if the outputFormat may be collected immediately
* @throws Exception if the format couldn't be set successfully
*/
public boolean setInputFormat(Instances instanceInfo) throws Exception {
super.setInputFormat(instanceInfo);
m_Insert.setUpper(instanceInfo.numAttributes());
Instances outputFormat = new Instances(instanceInfo, 0);
Attribute newAttribute = null;
switch (m_AttributeType) {
case Attribute.NUMERIC:
newAttribute = new Attribute(m_Name);
break;
case Attribute.NOMINAL:
newAttribute = new Attribute(m_Name, m_Labels);
break;
case Attribute.STRING:
newAttribute = new Attribute(m_Name, (FastVector) null);
break;
case Attribute.DATE:
newAttribute = new Attribute(m_Name, m_DateFormat);
break;
default:
throw new IllegalArgumentException("Unknown attribute type in Add");
}
if ((m_Insert.getIndex() < 0) || (m_Insert.getIndex() > getInputFormat().numAttributes())) {
throw new IllegalArgumentException("Index out of range");
}
outputFormat.insertAttributeAt(newAttribute, m_Insert.getIndex());
setOutputFormat(outputFormat);
// all attributes, except index of added attribute
// (otherwise the length of the input/output indices differ)
Range atts = new Range(m_Insert.getSingleIndex());
atts.setInvert(true);
atts.setUpper(outputFormat.numAttributes() - 1);
initOutputLocators(outputFormat, atts.getSelection());
return true;
}
