/**
* Input an instance for filtering.
*
* @param instance the input instance
* @return true if the filtered instance may now be collected with output().
* @throws Exception if the input format was not set or the date format cannot be parsed
*/
public boolean input(Instance instance) throws Exception {
if (getInputFormat() == null) {
throw new IllegalStateException("No input instance format defined");
}
if (m_NewBatch) {
resetQueue();
m_NewBatch = false;
}
Instance newInstance = (Instance) instance.copy();
int index = m_AttIndex.getIndex();
if (!newInstance.isMissing(index)) {
double value = instance.value(index);
try {
// Format and parse under the new format to force any required
// loss in precision.
value = m_OutputAttribute.parseDate(m_OutputAttribute.formatDate(value));
} catch (ParseException pe) {
throw new RuntimeException("Output date format couldn't parse its own output!!");
}
newInstance.setValue(index, value);
}
push(newInstance);
return true;
}
/**
* Sets instances that should be stored.
*
* @param instances the instances
*/
@Override
public void setInstances(Instances instances) {
m_ClassIndex.setUpper(instances.numAttributes() - 1);
instances.setClassIndex(m_ClassIndex.getIndex());
super.setInstances(instances);
}
/**
* 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 UnsupportedAttributeTypeException if the selected attribute is not nominal or if it
* only has one value.
* @throws Exception if the input format can't be set successfully
*/
@Override
public boolean setInputFormat(Instances instanceInfo) throws Exception {
super.setInputFormat(instanceInfo);
m_AttIndex.setUpper(instanceInfo.numAttributes() - 1);
m_FirstIndex.setUpper(instanceInfo.attribute(m_AttIndex.getIndex()).numValues() - 1);
m_SecondIndex.setUpper(instanceInfo.attribute(m_AttIndex.getIndex()).numValues() - 1);
if (!instanceInfo.attribute(m_AttIndex.getIndex()).isNominal()) {
throw new UnsupportedAttributeTypeException("Chosen attribute not nominal.");
}
if (instanceInfo.attribute(m_AttIndex.getIndex()).numValues() < 2) {
throw new UnsupportedAttributeTypeException(
"Chosen attribute has less than " + "two values.");
}
setOutputFormat();
return true;
}
/** 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);
}
/**
* 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 input format can't be set successfully
*/
public boolean setInputFormat(Instances instanceInfo) throws Exception {
super.setInputFormat(instanceInfo);
m_AttIndex.setUpper(instanceInfo.numAttributes() - 1);
if (!instanceInfo.attribute(m_AttIndex.getIndex()).isDate()) {
throw new UnsupportedAttributeTypeException("Chosen attribute not date.");
}
setOutputFormat();
return true;
}
/** Find the fold attribute within a dataset. */
private Attribute getAttribute(Instances data) {
SingleIndex index = new SingleIndex(super.getAttributeIndex());
index.setUpper(data.numAttributes() - 1);
Attribute att = data.attribute(index.getIndex());
if (att == null)
throw new NoSuchElementException(
"attribute #" + super.getAttributeIndex() + " does not exist");
if (!att.isNominal() && !att.isString())
throw new IllegalArgumentException("Attribute '" + att + "' is not nominal");
return att;
}
/**
* 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;
}
/**
* 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);
}
/**
* 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 input format can't be set successfully
*/
public boolean setInputFormat(Instances instanceInfo) throws Exception {
super.setInputFormat(instanceInfo);
// set input format
// m_InputFormat = new Instances(instanceInfo, 0);
m_AttIndex.setUpper(getInputFormat().numAttributes() - 1);
// set index of attribute to be changed
// test if nominal
if (!getInputFormat().attribute(m_AttIndex.getIndex()).isNominal()) {
throw new Exception("Adding noise is not possible:" + "Chosen attribute is numeric.");
}
// test if two values are given
if ((getInputFormat().attribute(m_AttIndex.getIndex()).numValues() < 2) && (!m_UseMissing)) {
throw new Exception(
"Adding noise is not possible:" + "Chosen attribute has less than two values.");
}
setOutputFormat(getInputFormat());
m_NewBatch = true;
return false;
}
/**
* Input an instance for filtering. The instance is processed and made available for output
* immediately.
*
* @param instance the input instance
* @return true if the filtered instance may now be collected with output().
* @throws IllegalStateException if no input structure has been defined.
*/
@Override
public boolean input(Instance instance) {
if (getInputFormat() == null) {
throw new IllegalStateException("No input instance format defined");
}
if (m_NewBatch) {
resetQueue();
m_NewBatch = false;
}
Instance newInstance = (Instance) instance.copy();
if (!newInstance.isMissing(m_AttIndex.getIndex())) {
if ((int) newInstance.value(m_AttIndex.getIndex()) == m_SecondIndex.getIndex()) {
newInstance.setValue(m_AttIndex.getIndex(), m_FirstIndex.getIndex());
} else if ((int) newInstance.value(m_AttIndex.getIndex()) == m_FirstIndex.getIndex()) {
newInstance.setValue(m_AttIndex.getIndex(), m_SecondIndex.getIndex());
}
}
push(newInstance, false); // No need to copy
return true;
}
/**
* Input an instance for filtering. The instance is processed and made available for output
* immediately.
*
* @param instance the input instance
* @return true if the filtered instance may now be collected with output().
* @throws IllegalStateException if no input format has been set.
*/
public boolean input(Instance instance) {
if (getInputFormat() == null) {
throw new IllegalStateException("No input instance format defined");
}
if (m_NewBatch) {
resetQueue();
m_NewBatch = false;
}
Instance newInstance = (Instance) instance.copy();
if ((int) newInstance.value(m_AttIndex.getIndex()) == m_SecondIndex.getIndex()) {
newInstance.setValue(m_AttIndex.getIndex(), (double) m_FirstIndex.getIndex());
} else if ((int) newInstance.value(m_AttIndex.getIndex()) > m_SecondIndex.getIndex()) {
newInstance.setValue(m_AttIndex.getIndex(), newInstance.value(m_AttIndex.getIndex()) - 1);
}
push(newInstance);
return true;
}
/**
* Signify that this batch of input to the filter is finished. If the filter requires all
* instances prior to filtering, output() may now be called to retrieve the filtered instances.
*
* @return true if there are instances pending output
* @throws Exception if no input structure has been defined
*/
public boolean batchFinished() throws Exception {
if (getInputFormat() == null) {
throw new Exception("No input instance format defined");
}
// Do the subsample, and clear the input instances.
addNoise(getInputFormat(), m_RandomSeed, m_Percent, m_AttIndex.getIndex(), m_UseMissing);
for (int i = 0; i < getInputFormat().numInstances(); i++) {
push((Instance) getInputFormat().instance(i).copy());
}
flushInput();
m_NewBatch = true;
m_FirstBatchDone = true;
return (numPendingOutput() != 0);
}
/**
* Input an instance for filtering. Ordinarily the instance is processed and made available for
* output immediately. Some filters require all instances be read before producing output.
*
* @param instance the input instance
* @return true if the filtered instance may now be collected with output().
* @throws IllegalStateException if no input format has been defined.
*/
public boolean input(Instance instance) {
if (getInputFormat() == null) {
throw new IllegalStateException("No input instance format defined");
}
if (m_NewBatch) {
resetQueue();
m_NewBatch = false;
}
Instance inst = (Instance) instance.copy();
// First copy string values from input to output
copyValues(inst, true, inst.dataset(), getOutputFormat());
// Insert the new attribute and reassign to output
inst.setDataset(null);
inst.insertAttributeAt(m_Insert.getIndex());
inst.setDataset(getOutputFormat());
push(inst);
return true;
}
/**
* 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 input format can't be set successfully
*/
public boolean setInputFormat(Instances instanceInfo) throws Exception {
super.setInputFormat(instanceInfo);
m_AttIndex.setUpper(instanceInfo.numAttributes() - 1);
m_FirstIndex.setUpper(instanceInfo.attribute(m_AttIndex.getIndex()).numValues() - 1);
m_SecondIndex.setUpper(instanceInfo.attribute(m_AttIndex.getIndex()).numValues() - 1);
if ((instanceInfo.classIndex() > -1) && (instanceInfo.classIndex() == m_AttIndex.getIndex())) {
throw new Exception("Cannot process class attribute.");
}
if (!instanceInfo.attribute(m_AttIndex.getIndex()).isNominal()) {
throw new UnsupportedAttributeTypeException("Chosen attribute not nominal.");
}
if (instanceInfo.attribute(m_AttIndex.getIndex()).numValues() < 2) {
throw new UnsupportedAttributeTypeException(
"Chosen attribute has less than " + "two values.");
}
if (m_SecondIndex.getIndex() <= m_FirstIndex.getIndex()) {
// XXX Maybe we should just swap the values??
throw new Exception("The second index has to be greater " + "than the first.");
}
setOutputFormat();
return true;
}
/**
* 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);
}
