/**
* Generates the classifier.
*
* @param instances set of instances serving as training data
* @throws Exception if the classifier has not been generated successfully
*/
public void buildClassifier(Instances instances) throws Exception {
if (!(m_Classifier instanceof WeightedInstancesHandler)) {
throw new IllegalArgumentException("Classifier must be a " + "WeightedInstancesHandler!");
}
// can classifier handle the data?
getCapabilities().testWithFail(instances);
// remove instances with missing class
instances = new Instances(instances);
instances.deleteWithMissingClass();
// only class? -> build ZeroR model
if (instances.numAttributes() == 1) {
System.err.println(
"Cannot build model (only class attribute present in data!), "
+ "using ZeroR model instead!");
m_ZeroR = new weka.classifiers.rules.ZeroR();
m_ZeroR.buildClassifier(instances);
return;
} else {
m_ZeroR = null;
}
m_Train = new Instances(instances, 0, instances.numInstances());
m_NNSearch.setInstances(m_Train);
}
/**
* Adds the supplied instance to the training set.
*
* @param instance the instance to add
* @throws Exception if instance could not be incorporated successfully
*/
public void updateClassifier(Instance instance) throws Exception {
if (m_Train.equalHeaders(instance.dataset()) == false) {
throw new Exception("Incompatible instance types");
}
if (instance.classIsMissing()) {
return;
}
m_Train.add(instance);
m_NNSearch.update(instance);
m_kNNValid = false;
if ((m_WindowSize > 0) && (m_Train.numInstances() > m_WindowSize)) {
boolean deletedInstance = false;
while (m_Train.numInstances() > m_WindowSize) {
m_Train.delete(0);
deletedInstance = true;
}
// rebuild datastructure KDTree currently can't delete
if (deletedInstance == true) m_NNSearch.setInstances(m_Train);
}
}
/**
* Generates the classifier.
*
* @param instances set of instances serving as training data
* @throws Exception if the classifier has not been generated 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();
m_NumClasses = instances.numClasses();
m_ClassType = instances.classAttribute().type();
m_Train = new Instances(instances, 0, instances.numInstances());
// Throw away initial instances until within the specified window size
if ((m_WindowSize > 0) && (instances.numInstances() > m_WindowSize)) {
m_Train = new Instances(m_Train, m_Train.numInstances() - m_WindowSize, m_WindowSize);
}
m_NumAttributesUsed = 0.0;
for (int i = 0; i < m_Train.numAttributes(); i++) {
if ((i != m_Train.classIndex())
&& (m_Train.attribute(i).isNominal() || m_Train.attribute(i).isNumeric())) {
m_NumAttributesUsed += 1.0;
}
}
m_NNSearch.setInstances(m_Train);
// Invalidate any currently cross-validation selected k
m_kNNValid = false;
m_defaultModel = new ZeroR();
m_defaultModel.buildClassifier(instances);
m_defaultModel.setOptions(getOptions());
// System.out.println("hello world");
}
/**
* Calculates the class membership probabilities for the given test instance.
*
* @param instance the instance to be classified
* @return predicted class probability distribution
* @throws Exception if an error occurred during the prediction
*/
public double[] distributionForInstance(Instance instance) throws Exception {
NaiveBayes nb = new NaiveBayes();
// System.out.println("number of instances "+m_Train.numInstances());
if (m_Train.numInstances() == 0) {
// throw new Exception("No training instances!");
return m_defaultModel.distributionForInstance(instance);
}
if ((m_WindowSize > 0) && (m_Train.numInstances() > m_WindowSize)) {
m_kNNValid = false;
boolean deletedInstance = false;
while (m_Train.numInstances() > m_WindowSize) {
m_Train.delete(0);
}
// rebuild datastructure KDTree currently can't delete
if (deletedInstance == true) m_NNSearch.setInstances(m_Train);
}
// Select k by cross validation
if (!m_kNNValid && (m_CrossValidate) && (m_kNNUpper >= 1)) {
crossValidate();
}
m_NNSearch.addInstanceInfo(instance);
m_kNN = 1000;
Instances neighbours = m_NNSearch.kNearestNeighbours(instance, m_kNN);
double[] distances = m_NNSearch.getDistances();
// System.out.println("--------------classify instance--------- ");
// System.out.println("neighbours.numInstances"+neighbours.numInstances());
// System.out.println("distances.length"+distances.length);
// System.out.println("--------------classify instance--------- ");
/* for (int k = 0; k < distances.length; k++) {
//System.out.println("-------");
//System.out.println("distance of "+k+" "+distances[k]);
//System.out.println("instance of "+k+" "+neighbours.instance(k));
//distances[k] = distances[k]+0.1;
//System.out.println("------- after add 0.1");
//System.out.println("distance of "+k+" "+distances[k]);
}
*/
Instances instances = new Instances(m_Train);
// int attrnum = instances.numAttributes();
instances.deleteWithMissingClass();
Instances newm_Train = new Instances(instances, 0, instances.numInstances());
for (int k = 0; k < neighbours.numInstances(); k++) {
// System.out.println("-------");
// Instance in = new Instance();
Instance insk = neighbours.instance(k);
// System.out.println("instance "+k+" "+neighbours.instance(k));
// System.out.println("-------");
double dis = distances[k] + 0.1;
// System.out.println("dis "+dis);
dis = (1 / dis) * 10;
// System.out.println("1/dis "+dis);
int weightnum = (int) dis;
// System.out.println("weightnum "+weightnum);
for (int s = 0; s < weightnum; s++) {
newm_Train.add(insk);
}
}
// System.out.println("number of instances "+newm_Train.numInstances());
/* for (int k = 0; k < newm_Train.numInstances(); k++) {
System.out.println("-------");
System.out.println("instance "+k+" "+newm_Train.instance(k));
System.out.println("-------");
}
/*
for (int k = 0; k < distances.length; k++) {
System.out.println("-------");
System.out.println("distance of "+k+" "+distances[k]);
System.out.println("-------");
}*/
nb.buildClassifier(newm_Train);
double[] dis = nb.distributionForInstance(instance);
// double[] distribution = makeDistribution(neighbours, distances);
return dis;
// return distribution;
}