/**
* Gets the classifier specification string, which contains the class name of the classifier and
* any options to the classifier
*
* @param index the index of the classifier string to retrieve, starting from 0.
* @return the classifier string, or the empty string if no classifier has been assigned (or the
* index given is out of range).
*/
protected String getClassifierSpec(int index) {
if (m_Classifiers.length < index) {
return "";
}
Classifier c = getClassifier(index);
return c.getClass().getName() + " " + Utils.joinOptions(((OptionHandler) c).getOptions());
}
/**
* Returns an enumeration describing the available options.
*
* @return an enumeration of all the available options.
*/
public Enumeration listOptions() {
Vector newVector = new Vector(7);
newVector.addElement(
new Option(
"\tThe index of the class attribute.\n" + "\t(default last)",
"c",
1,
"-c <class index>"));
newVector.addElement(
new Option(
"\tThe name of the arff file used for the decomposition.",
"t",
1,
"-t <name of arff file>"));
newVector.addElement(
new Option(
"\tThe number of instances placed in the training pool.\n"
+ "\tThe remainder will be used for testing. (default 100)",
"T",
1,
"-T <training pool size>"));
newVector.addElement(new Option("\tThe random number seed used.", "s", 1, "-s <seed>"));
newVector.addElement(
new Option(
"\tThe number of training repetitions used.\n" + "\t(default 50)", "x", 1, "-x <num>"));
newVector.addElement(new Option("\tTurn on debugging output.", "D", 0, "-D"));
newVector.addElement(
new Option(
"\tFull class name of the learner used in the decomposition.\n"
+ "\teg: weka.classifiers.bayes.NaiveBayes",
"W",
1,
"-W <classifier class name>"));
if ((m_Classifier != null) && (m_Classifier instanceof OptionHandler)) {
newVector.addElement(
new Option(
"",
"",
0,
"\nOptions specific to learner " + m_Classifier.getClass().getName() + ":"));
Enumeration enu = ((OptionHandler) m_Classifier).listOptions();
while (enu.hasMoreElements()) {
newVector.addElement(enu.nextElement());
}
}
return newVector.elements();
}
/**
* Test a feature collection where each feature will be in it's own bin.
*
* <p>Creates a feature collection with five features 1-5. Then uses the quantile function to put
* these features in 5 bins. Each bin should have a single feature.
*
* @throws Exception
*/
public void testSingleBin() throws Exception {
// create a feature collection with five features values 1-5
SimpleFeatureType dataType = DataUtilities.createType("classification.test1", "id:0,value:int");
int iVal[] = new int[] {1, 2, 3, 4, 5};
SimpleFeature[] myfeatures = new SimpleFeature[iVal.length];
for (int i = 0; i < iVal.length; i++) {
myfeatures[i] =
SimpleFeatureBuilder.build(
dataType,
new Object[] {new Integer(i + 1), new Integer(iVal[i])},
"classification.test1" + (i + 1));
}
MemoryDataStore store = new MemoryDataStore();
store.createSchema(dataType);
store.addFeatures(myfeatures);
FeatureCollection<SimpleFeatureType, SimpleFeature> myFeatureCollection =
store.getFeatureSource("test1").getFeatures();
// run the quantile function
org.opengis.filter.expression.Expression function =
ff.function("Quantile", ff.property("value"), ff.literal(5));
Classifier classifier = (Classifier) function.evaluate(myFeatureCollection);
// verify the results
assertNotNull(classifier);
assertEquals(classifier.getClass(), RangedClassifier.class);
RangedClassifier range = (RangedClassifier) classifier;
assertEquals(5, range.getSize());
for (int i = 0; i < 5; i++) {
assertTrue(i + 1 == ((Number) range.getMin(i)).doubleValue());
if (i != 4) {
assertTrue(i + 2 == ((Number) range.getMax(i)).doubleValue());
assertEquals((i + 1) + ".." + (i + 2), range.getTitle(i));
} else {
assertTrue(i + 1 == ((Number) range.getMax(i)).doubleValue());
assertEquals((i + 1) + ".." + (i + 1), range.getTitle(i));
}
}
}
