/**
* loading training data
*
* @param mergedAlgSimVec algebra instances normally for applying the remove useless and
* standardization filtering
* @return
* @throws Exception
*/
public static AttributeFilterMeta refineInstances(Instances mergedAlgSimVec) throws Exception {
AttributeFilterMeta res = new AttributeFilterMeta();
Map<String, Integer> attributeIndex = new HashMap<String, Integer>();
// List<Attribute> atts = new ArrayList<Attribute>();
// mergedAlgSimVecClass.attribute(0).
for (int i = 0; i < mergedAlgSimVec.numAttributes(); i++) {
attributeIndex.put(mergedAlgSimVec.attribute(i).name(), i);
}
Instances mergedUselessFilteredAlgSimVecClass = removeUseless(mergedAlgSimVec);
Standardize stdFilter = new Standardize(); // kepp in meta
stdFilter.setInputFormat(
mergedUselessFilteredAlgSimVecClass); // initializing the filter once with training set
Instances stdFilterdInstances = standardize(mergedUselessFilteredAlgSimVecClass, stdFilter);
// record removed attributes/columns in a matrix
Set<String> selectedAtt = new HashSet<String>();
for (int i = 0; i < stdFilterdInstances.numAttributes(); i++) {
selectedAtt.add(stdFilterdInstances.attribute(i).name());
}
List<Integer> deletedAttIndex = new ArrayList<Integer>();
for (Entry<String, Integer> e : attributeIndex.entrySet()) {
if (selectedAtt.contains(e.getKey()) == false) {
deletedAttIndex.add(e.getValue());
}
}
int[] removedAttributes = Ints.toArray(deletedAttIndex);
res.setInstances(stdFilterdInstances);
res.setRemovedAttributes(removedAttributes);
res.setStandardizeFilter(stdFilter);
return res;
}
/**
* Method for building the classifier.
*
* @param instances the set of training instances
* @throws Exception if the classifier can't be built successfully
*/
public void buildClassifier(Instances instances) throws Exception {
// can classifier handle the data?
getCapabilities().testWithFail(instances);
// remove instances with missing class
instances = new Instances(instances);
instances.deleteWithMissingClass();
// Removes all the instances with weight equal to 0.
// MUST be done since condition (8) of Keerthi's paper
// is made with the assertion Ci > 0 (See equation (3a).
Instances data = new Instances(instances, 0);
for (int i = 0; i < instances.numInstances(); i++) {
if (instances.instance(i).weight() > 0) {
data.add(instances.instance(i));
}
}
if (data.numInstances() == 0) {
throw new Exception(
"No training instances left after removing "
+ "instance with either a weight null or a missing class!");
}
instances = data;
m_onlyNumeric = true;
for (int i = 0; i < instances.numAttributes(); i++) {
if (i != instances.classIndex()) {
if (!instances.attribute(i).isNumeric()) {
m_onlyNumeric = false;
break;
}
}
}
m_Missing = new ReplaceMissingValues();
m_Missing.setInputFormat(instances);
instances = Filter.useFilter(instances, m_Missing);
if (getCapabilities().handles(Capability.NUMERIC_ATTRIBUTES)) {
if (!m_onlyNumeric) {
m_NominalToBinary = new NominalToBinary();
m_NominalToBinary.setInputFormat(instances);
instances = Filter.useFilter(instances, m_NominalToBinary);
} else {
m_NominalToBinary = null;
}
} else {
m_NominalToBinary = null;
}
// retrieve two different class values used to determine filter transformation
double y0 = instances.instance(0).classValue();
int index = 1;
while (index < instances.numInstances() && instances.instance(index).classValue() == y0) {
index++;
}
if (index == instances.numInstances()) {
// degenerate case, all class values are equal
// we don't want to deal with this, too much hassle
throw new Exception(
"All class values are the same. At least two class values should be different");
}
double y1 = instances.instance(index).classValue();
// apply filters
if (m_filterType == FILTER_STANDARDIZE) {
m_Filter = new Standardize();
((Standardize) m_Filter).setIgnoreClass(true);
m_Filter.setInputFormat(instances);
instances = Filter.useFilter(instances, m_Filter);
} else if (m_filterType == FILTER_NORMALIZE) {
m_Filter = new Normalize();
((Normalize) m_Filter).setIgnoreClass(true);
m_Filter.setInputFormat(instances);
instances = Filter.useFilter(instances, m_Filter);
} else {
m_Filter = null;
}
if (m_Filter != null) {
double z0 = instances.instance(0).classValue();
double z1 = instances.instance(index).classValue();
m_x1 =
(y0 - y1) / (z0 - z1); // no division by zero, since y0 != y1 guaranteed => z0 != z1 ???
m_x0 = (y0 - m_x1 * z0); // = y1 - m_x1 * z1
} else {
m_x1 = 1.0;
m_x0 = 0.0;
}
m_optimizer.setSMOReg(this);
m_optimizer.buildClassifier(instances);
}