/**
* Determines the output format based on the input format and returns this. In case the output
* format cannot be returned immediately, i.e., hasImmediateOutputFormat() returns false, then
* this method will called from batchFinished() after the call of preprocess(Instances), in which,
* e.g., statistics for the actual processing step can be gathered.
*
* @param inputFormat the input format to base the output format on
* @return the output format
* @throws Exception in case the determination goes wrong
*/
protected Instances determineOutputFormat(Instances inputFormat) throws Exception {
Instances result;
Attribute att;
ArrayList<Attribute> atts;
int i;
m_AttributeIndices.setUpper(inputFormat.numAttributes() - 1);
// generate new header
atts = new ArrayList<Attribute>();
for (i = 0; i < inputFormat.numAttributes(); i++) {
att = inputFormat.attribute(i);
if (m_AttributeIndices.isInRange(i)) {
if (m_ReplaceAll) atts.add(att.copy(att.name().replaceAll(m_Find, m_Replace)));
else atts.add(att.copy(att.name().replaceFirst(m_Find, m_Replace)));
} else {
atts.add((Attribute) att.copy());
}
}
result = new Instances(inputFormat.relationName(), atts, 0);
result.setClassIndex(inputFormat.classIndex());
return result;
}
/** Set the output format. Changes the format of the specified date attribute. */
private void setOutputFormat() {
// Create new attributes
FastVector newAtts = new FastVector(getInputFormat().numAttributes());
for (int j = 0; j < getInputFormat().numAttributes(); j++) {
Attribute att = getInputFormat().attribute(j);
if (j == m_AttIndex.getIndex()) {
newAtts.addElement(new Attribute(att.name(), getDateFormat().toPattern()));
} else {
newAtts.addElement(att.copy());
}
}
// Create new header
Instances newData = new Instances(getInputFormat().relationName(), newAtts, 0);
newData.setClassIndex(getInputFormat().classIndex());
m_OutputAttribute = newData.attribute(m_AttIndex.getIndex());
setOutputFormat(newData);
}
/**
* Set the output format. Swapss the desired nominal attribute values in the header and calls
* setOutputFormat(Instances) appropriately.
*/
private void setOutputFormat() {
Instances newData;
ArrayList<Attribute> newAtts;
ArrayList<String> newVals;
// Compute new attributes
newAtts = new ArrayList<Attribute>(getInputFormat().numAttributes());
for (int j = 0; j < getInputFormat().numAttributes(); j++) {
Attribute att = getInputFormat().attribute(j);
if (j != m_AttIndex.getIndex()) {
newAtts.add((Attribute) att.copy());
} else {
// Compute list of attribute values
newVals = new ArrayList<String>(att.numValues());
for (int i = 0; i < att.numValues(); i++) {
if (i == m_FirstIndex.getIndex()) {
newVals.add(att.value(m_SecondIndex.getIndex()));
} else if (i == m_SecondIndex.getIndex()) {
newVals.add(att.value(m_FirstIndex.getIndex()));
} else {
newVals.add(att.value(i));
}
}
Attribute newAtt = new Attribute(att.name(), newVals);
newAtt.setWeight(att.weight());
newAtts.add(newAtt);
}
}
// Construct new header
newData = new Instances(getInputFormat().relationName(), newAtts, 0);
newData.setClassIndex(getInputFormat().classIndex());
setOutputFormat(newData);
}
/**
* Set the output format. Takes the current average class values and m_InputFormat and calls
* setOutputFormat(Instances) appropriately.
*/
private void setOutputFormat() {
Instances newData;
FastVector newAtts, newVals;
boolean firstEndsWithPrime = false, secondEndsWithPrime = false;
StringBuffer text = new StringBuffer();
// Compute new attributes
newAtts = new FastVector(getInputFormat().numAttributes());
for (int j = 0; j < getInputFormat().numAttributes(); j++) {
Attribute att = getInputFormat().attribute(j);
if (j != m_AttIndex.getIndex()) {
newAtts.addElement(att.copy());
} else {
// Compute new value
if (att.value(m_FirstIndex.getIndex()).endsWith("'")) {
firstEndsWithPrime = true;
}
if (att.value(m_SecondIndex.getIndex()).endsWith("'")) {
secondEndsWithPrime = true;
}
if (firstEndsWithPrime || secondEndsWithPrime) {
text.append("'");
}
if (firstEndsWithPrime) {
text.append(
((String) att.value(m_FirstIndex.getIndex()))
.substring(1, ((String) att.value(m_FirstIndex.getIndex())).length() - 1));
} else {
text.append((String) att.value(m_FirstIndex.getIndex()));
}
text.append('_');
if (secondEndsWithPrime) {
text.append(
((String) att.value(m_SecondIndex.getIndex()))
.substring(1, ((String) att.value(m_SecondIndex.getIndex())).length() - 1));
} else {
text.append((String) att.value(m_SecondIndex.getIndex()));
}
if (firstEndsWithPrime || secondEndsWithPrime) {
text.append("'");
}
// Compute list of attribute values
newVals = new FastVector(att.numValues() - 1);
for (int i = 0; i < att.numValues(); i++) {
if (i == m_FirstIndex.getIndex()) {
newVals.addElement(text.toString());
} else if (i != m_SecondIndex.getIndex()) {
newVals.addElement(att.value(i));
}
}
Attribute newAtt = new Attribute(att.name(), newVals);
newAtt.setWeight(getInputFormat().attribute(j).weight());
newAtts.addElement(newAtt);
}
}
// Construct new header
newData = new Instances(getInputFormat().relationName(), newAtts, 0);
newData.setClassIndex(getInputFormat().classIndex());
setOutputFormat(newData);
}
/** Set the output format if the class is numeric. */
private void setOutputFormatNumeric() {
if (m_Indices == null) {
setOutputFormat(null);
return;
}
ArrayList<Attribute> newAtts;
int newClassIndex;
StringBuffer attributeName;
Instances outputFormat;
ArrayList<String> vals;
// Compute new attributes
m_needToTransform = false;
for (int i = 0; i < getInputFormat().numAttributes(); i++) {
Attribute att = getInputFormat().attribute(i);
if (att.isNominal() && (att.numValues() > 2 || m_Numeric || m_TransformAll)) {
m_needToTransform = true;
break;
}
}
if (!m_needToTransform) {
setOutputFormat(getInputFormat());
return;
}
newClassIndex = getInputFormat().classIndex();
newAtts = new ArrayList<Attribute>();
for (int j = 0; j < getInputFormat().numAttributes(); j++) {
Attribute att = getInputFormat().attribute(j);
if ((!att.isNominal()) || (j == getInputFormat().classIndex())) {
newAtts.add((Attribute) att.copy());
} else {
if (j < getInputFormat().classIndex()) {
newClassIndex += att.numValues() - 2;
}
// Compute values for new attributes
for (int k = 1; k < att.numValues(); k++) {
attributeName = new StringBuffer(att.name() + "=");
for (int l = k; l < att.numValues(); l++) {
if (l > k) {
attributeName.append(',');
}
attributeName.append(att.value(m_Indices[j][l]));
}
if (m_Numeric) {
newAtts.add(new Attribute(attributeName.toString()));
} else {
vals = new ArrayList<String>(2);
vals.add("f");
vals.add("t");
newAtts.add(new Attribute(attributeName.toString(), vals));
}
}
}
}
outputFormat = new Instances(getInputFormat().relationName(), newAtts, 0);
outputFormat.setClassIndex(newClassIndex);
setOutputFormat(outputFormat);
}