/**
* Gets the raw output from the classifier
*
* @return the raw output from the classifier
*/
@Override
public String getRawResultOutput() {
StringBuffer result = new StringBuffer();
if (m_clusterer == null) {
return "<null> clusterer";
}
result.append(toString());
result.append("Clustering model: \n" + m_clusterer.toString() + '\n');
// append the performance statistics
if (m_result != null) {
// result.append(m_result);
if (m_doesProduce != null) {
for (int i = 0; i < m_doesProduce.length; i++) {
if (m_doesProduce[i]) {
try {
double dv =
((AdditionalMeasureProducer) m_clusterer).getMeasure(m_additionalMeasures[i]);
Double value = new Double(dv);
result.append(m_additionalMeasures[i] + " : " + value + '\n');
} catch (Exception ex) {
System.err.println(ex);
}
}
}
}
}
return result.toString();
}
/**
* Returns an enumeration describing the available options.
*
* @return an enumeration of all the available options.
*/
@Override
public Enumeration<Option> listOptions() {
Vector<Option> newVector = new Vector<Option>(2);
newVector.addElement(
new Option(
"\tSkips the determination of sizes (train/test/clusterer)\n"
+ "\t(default: sizes are determined)",
"no-size",
0,
"-no-size"));
newVector.addElement(
new Option(
"\tThe full class name of the density based clusterer.\n" + "\teg: weka.clusterers.EM",
"W",
1,
"-W <class name>"));
if ((m_clusterer != null) && (m_clusterer instanceof OptionHandler)) {
newVector.addElement(
new Option(
"",
"",
0,
"\nOptions specific to clusterer " + m_clusterer.getClass().getName() + ":"));
newVector.addAll(Collections.list(((OptionHandler) m_clusterer).listOptions()));
}
return newVector.elements();
}
/**
* Gets the key describing the current SplitEvaluator. For example This may contain the name of
* the classifier used for classifier predictive evaluation. The number of key fields must be
* constant for a given SplitEvaluator.
*
* @return an array of objects containing the key.
*/
@Override
public Object[] getKey() {
Object[] key = new Object[KEY_SIZE];
key[0] = m_clusterer.getClass().getName();
key[1] = m_clustererOptions;
key[2] = m_clustererVersion;
return key;
}
protected void updateOptions() {
if (m_clusterer instanceof OptionHandler) {
m_clustererOptions = Utils.joinOptions(((OptionHandler) m_clusterer).getOptions());
} else {
m_clustererOptions = "";
}
if (m_clusterer instanceof Serializable) {
ObjectStreamClass obs = ObjectStreamClass.lookup(m_clusterer.getClass());
m_clustererVersion = "" + obs.getSerialVersionUID();
} else {
m_clustererVersion = "";
}
}
/**
* Returns a text description of the split evaluator.
*
* @return a text description of the split evaluator.
*/
@Override
public String toString() {
String result = "DensityBasedClustererSplitEvaluator: ";
if (m_clusterer == null) {
return result + "<null> clusterer";
}
return result
+ m_clusterer.getClass().getName()
+ " "
+ m_clustererOptions
+ "(version "
+ m_clustererVersion
+ ")";
}
/**
* Returns the value of the named measure
*
* @param additionalMeasureName the name of the measure to query for its value
* @return the value of the named measure
* @exception IllegalArgumentException if the named measure is not supported
*/
@Override
public double getMeasure(String additionalMeasureName) {
if (m_clusterer instanceof AdditionalMeasureProducer) {
return ((AdditionalMeasureProducer) m_clusterer).getMeasure(additionalMeasureName);
} else {
throw new IllegalArgumentException(
"DensityBasedClustererSplitEvaluator: "
+ "Can't return value for : "
+ additionalMeasureName
+ ". "
+ m_clusterer.getClass().getName()
+ " "
+ "is not an AdditionalMeasureProducer");
}
}
/**
* Gets the results for the supplied train and test datasets.
*
* @param train the training Instances.
* @param test the testing Instances.
* @return the results stored in an array. The objects stored in the array may be Strings,
* Doubles, or null (for the missing value).
* @exception Exception if a problem occurs while getting the results
*/
@Override
public Object[] getResult(Instances train, Instances test) throws Exception {
if (m_clusterer == null) {
throw new Exception("No clusterer has been specified");
}
int addm = (m_additionalMeasures != null) ? m_additionalMeasures.length : 0;
int overall_length = RESULT_SIZE + addm;
if (m_removeClassColumn && train.classIndex() != -1) {
// remove the class column from the training and testing data
Remove r = new Remove();
r.setAttributeIndicesArray(new int[] {train.classIndex()});
r.setInvertSelection(false);
r.setInputFormat(train);
train = Filter.useFilter(train, r);
test = Filter.useFilter(test, r);
}
train.setClassIndex(-1);
test.setClassIndex(-1);
ClusterEvaluation eval = new ClusterEvaluation();
Object[] result = new Object[overall_length];
long trainTimeStart = System.currentTimeMillis();
m_clusterer.buildClusterer(train);
double numClusters = m_clusterer.numberOfClusters();
eval.setClusterer(m_clusterer);
long trainTimeElapsed = System.currentTimeMillis() - trainTimeStart;
long testTimeStart = System.currentTimeMillis();
eval.evaluateClusterer(test);
long testTimeElapsed = System.currentTimeMillis() - testTimeStart;
// m_result = eval.toSummaryString();
// The results stored are all per instance -- can be multiplied by the
// number of instances to get absolute numbers
int current = 0;
result[current++] = new Double(train.numInstances());
result[current++] = new Double(test.numInstances());
result[current++] = new Double(eval.getLogLikelihood());
result[current++] = new Double(numClusters);
// Timing stats
result[current++] = new Double(trainTimeElapsed / 1000.0);
result[current++] = new Double(testTimeElapsed / 1000.0);
// sizes
if (m_NoSizeDetermination) {
result[current++] = -1.0;
result[current++] = -1.0;
result[current++] = -1.0;
} else {
ByteArrayOutputStream bastream = new ByteArrayOutputStream();
ObjectOutputStream oostream = new ObjectOutputStream(bastream);
oostream.writeObject(m_clusterer);
result[current++] = new Double(bastream.size());
bastream = new ByteArrayOutputStream();
oostream = new ObjectOutputStream(bastream);
oostream.writeObject(train);
result[current++] = new Double(bastream.size());
bastream = new ByteArrayOutputStream();
oostream = new ObjectOutputStream(bastream);
oostream.writeObject(test);
result[current++] = new Double(bastream.size());
}
for (int i = 0; i < addm; i++) {
if (m_doesProduce[i]) {
try {
double dv = ((AdditionalMeasureProducer) m_clusterer).getMeasure(m_additionalMeasures[i]);
Double value = new Double(dv);
result[current++] = value;
} catch (Exception ex) {
System.err.println(ex);
}
} else {
result[current++] = null;
}
}
if (current != overall_length) {
throw new Error("Results didn't fit RESULT_SIZE");
}
return result;
}