/**
* Determines the output format based on the input format and returns this.
*
* @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;
Attribute attSorted;
FastVector atts;
FastVector values;
Vector<String> sorted;
int i;
int n;
m_AttributeIndices.setUpper(inputFormat.numAttributes() - 1);
// determine sorted indices
atts = new FastVector();
m_NewOrder = new int[inputFormat.numAttributes()][];
for (i = 0; i < inputFormat.numAttributes(); i++) {
att = inputFormat.attribute(i);
if (!att.isNominal() || !m_AttributeIndices.isInRange(i)) {
m_NewOrder[i] = new int[0];
atts.addElement(inputFormat.attribute(i).copy());
continue;
}
// sort labels
sorted = new Vector<String>();
for (n = 0; n < att.numValues(); n++) sorted.add(att.value(n));
Collections.sort(sorted, m_Comparator);
// determine new indices
m_NewOrder[i] = new int[att.numValues()];
values = new FastVector();
for (n = 0; n < att.numValues(); n++) {
m_NewOrder[i][n] = sorted.indexOf(att.value(n));
values.addElement(sorted.get(n));
}
attSorted = new Attribute(att.name(), values);
attSorted.setWeight(att.weight());
atts.addElement(attSorted);
}
// generate new header
result = new Instances(inputFormat.relationName(), atts, 0);
result.setClassIndex(inputFormat.classIndex());
return result;
}
/**
* 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 currently defined cutpoints and m_InputFormat and calls
* setOutputFormat(Instances) appropriately.
*/
protected void setOutputFormat() {
if (m_CutPoints == null) {
setOutputFormat(null);
return;
}
ArrayList<Attribute> attributes = new ArrayList<Attribute>(getInputFormat().numAttributes());
int classIndex = getInputFormat().classIndex();
for (int i = 0, m = getInputFormat().numAttributes(); i < m; ++i) {
if ((m_DiscretizeCols.isInRange(i)) && (getInputFormat().attribute(i).isNumeric())) {
Set<String> cutPointsCheck = new HashSet<String>();
double[] cutPoints = m_CutPoints[i];
if (!m_MakeBinary) {
ArrayList<String> attribValues;
if (cutPoints == null) {
attribValues = new ArrayList<String>(1);
attribValues.add("'All'");
} else {
attribValues = new ArrayList<String>(cutPoints.length + 1);
if (m_UseBinNumbers) {
for (int j = 0, n = cutPoints.length; j <= n; ++j) {
attribValues.add("'B" + (j + 1) + "of" + (n + 1) + "'");
}
} else {
for (int j = 0, n = cutPoints.length; j <= n; ++j) {
String newBinRangeString = binRangeString(cutPoints, j, m_BinRangePrecision);
if (cutPointsCheck.contains(newBinRangeString)) {
throw new IllegalArgumentException(
"A duplicate bin range was detected. "
+ "Try increasing the bin range precision.");
}
attribValues.add("'" + newBinRangeString + "'");
}
}
}
Attribute newAtt = new Attribute(getInputFormat().attribute(i).name(), attribValues);
newAtt.setWeight(getInputFormat().attribute(i).weight());
attributes.add(newAtt);
} else {
if (cutPoints == null) {
ArrayList<String> attribValues = new ArrayList<String>(1);
attribValues.add("'All'");
Attribute newAtt = new Attribute(getInputFormat().attribute(i).name(), attribValues);
newAtt.setWeight(getInputFormat().attribute(i).weight());
attributes.add(newAtt);
} else {
if (i < getInputFormat().classIndex()) {
classIndex += cutPoints.length - 1;
}
for (int j = 0, n = cutPoints.length; j < n; ++j) {
ArrayList<String> attribValues = new ArrayList<String>(2);
if (m_UseBinNumbers) {
attribValues.add("'B1of2'");
attribValues.add("'B2of2'");
} else {
double[] binaryCutPoint = {cutPoints[j]};
String newBinRangeString1 = binRangeString(binaryCutPoint, 0, m_BinRangePrecision);
String newBinRangeString2 = binRangeString(binaryCutPoint, 1, m_BinRangePrecision);
if (newBinRangeString1.equals(newBinRangeString2)) {
throw new IllegalArgumentException(
"A duplicate bin range was detected. "
+ "Try increasing the bin range precision.");
}
attribValues.add("'" + newBinRangeString1 + "'");
attribValues.add("'" + newBinRangeString2 + "'");
}
Attribute newAtt =
new Attribute(getInputFormat().attribute(i).name() + "_" + (j + 1), attribValues);
newAtt.setWeight(getInputFormat().attribute(i).weight());
attributes.add(newAtt);
}
}
}
} else {
attributes.add((Attribute) getInputFormat().attribute(i).copy());
}
}
Instances outputFormat = new Instances(getInputFormat().relationName(), attributes, 0);
outputFormat.setClassIndex(classIndex);
setOutputFormat(outputFormat);
}
/**
* 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);
}