/**
* Builds the classifier.
*
* @param data the data to train with
* @throws Exception if classifier can't be built successfully
*/
public void buildClassifier(Instances data) throws Exception {
// can classifier handle the data?
getCapabilities().testWithFail(data);
// remove instances with missing class
Instances filteredData = new Instances(data);
filteredData.deleteWithMissingClass();
// replace missing values
m_replaceMissing = new ReplaceMissingValues();
m_replaceMissing.setInputFormat(filteredData);
filteredData = Filter.useFilter(filteredData, m_replaceMissing);
// possibly convert nominal attributes globally
if (m_convertNominal) {
m_nominalToBinary = new NominalToBinary();
m_nominalToBinary.setInputFormat(filteredData);
filteredData = Filter.useFilter(filteredData, m_nominalToBinary);
}
int minNumInstances = 2;
// create a FT tree root
if (m_modelType == 0)
m_tree =
new FTNode(
m_errorOnProbabilities,
m_numBoostingIterations,
m_minNumInstances,
m_weightTrimBeta,
m_useAIC);
// create a FTLeaves tree root
if (m_modelType == 1) {
m_tree =
new FTLeavesNode(
m_errorOnProbabilities,
m_numBoostingIterations,
m_minNumInstances,
m_weightTrimBeta,
m_useAIC);
}
// create a FTInner tree root
if (m_modelType == 2)
m_tree =
new FTInnerNode(
m_errorOnProbabilities,
m_numBoostingIterations,
m_minNumInstances,
m_weightTrimBeta,
m_useAIC);
// build tree
m_tree.buildClassifier(filteredData);
// prune tree
m_tree.prune();
m_tree.assignIDs(0);
m_tree.cleanup();
}
/**
* Returns a description of the classifier.
*
* @return a string representation of the classifier
*/
public String toString() {
if (m_tree != null) {
if (m_modelType == 0) return "FT tree \n------------------\n" + m_tree.toString();
else {
if (m_modelType == 1) return "FT Leaves tree \n------------------\n" + m_tree.toString();
else return "FT Inner tree \n------------------\n" + m_tree.toString();
}
} else {
return "No tree built";
}
}
/**
* Returns class probabilities for an instance.
*
* @param instance the instance to compute the distribution for
* @return the class probabilities
* @throws Exception if distribution can't be computed successfully
*/
public double[] distributionForInstance(Instance instance) throws Exception {
// replace missing values
m_replaceMissing.input(instance);
instance = m_replaceMissing.output();
// possibly convert nominal attributes
if (m_convertNominal) {
m_nominalToBinary.input(instance);
instance = m_nominalToBinary.output();
}
return m_tree.distributionForInstance(instance);
}
/**
* Returns the number of leaves in the tree
*
* @return the number of leaves in the tree
*/
public int measureNumLeaves() {
return m_tree.numLeaves();
}
/**
* Returns the size of the tree
*
* @return the size of the tree
*/
public int measureTreeSize() {
return m_tree.numNodes();
}
/**
* Returns graph describing the tree.
*
* @return the graph describing the tree
* @throws Exception if graph can't be computed
*/
public String graph() throws Exception {
return m_tree.graph();
}
