/**
* Adds this tree recursively to the buffer.
*
* @param id the unqiue id for the method
* @param buffer the buffer to add the source code to
* @return the last ID being used
* @throws Exception if something goes wrong
*/
protected int toSource(int id, StringBuffer buffer) throws Exception {
int result;
int i;
int newID;
StringBuffer[] subBuffers;
buffer.append("\n");
buffer.append(" protected static double node" + id + "(Object[] i) {\n");
// leaf?
if (m_Attribute == null) {
result = id;
if (Double.isNaN(m_ClassValue)) buffer.append(" return Double.NaN;");
else buffer.append(" return " + m_ClassValue + ";");
if (m_ClassAttribute != null)
buffer.append(" // " + m_ClassAttribute.value((int) m_ClassValue));
buffer.append("\n");
buffer.append(" }\n");
} else {
buffer.append(" // " + m_Attribute.name() + "\n");
// subtree calls
subBuffers = new StringBuffer[m_Attribute.numValues()];
newID = id;
for (i = 0; i < m_Attribute.numValues(); i++) {
newID++;
buffer.append(" ");
if (i > 0) buffer.append("else ");
buffer.append(
"if (((String) i["
+ m_Attribute.index()
+ "]).equals(\""
+ m_Attribute.value(i)
+ "\"))\n");
buffer.append(" return node" + newID + "(i);\n");
subBuffers[i] = new StringBuffer();
newID = m_Successors[i].toSource(newID, subBuffers[i]);
}
buffer.append(" else\n");
buffer.append(
" throw new IllegalArgumentException(\"Value '\" + i["
+ m_Attribute.index()
+ "] + \"' is not allowed!\");\n");
buffer.append(" }\n");
// output subtree code
for (i = 0; i < m_Attribute.numValues(); i++) {
buffer.append(subBuffers[i].toString());
}
subBuffers = null;
result = newID;
}
return result;
}
public double classifyInstance(Instance inst) throws Exception {
if (m_attribute == null) {
return m_intercept;
} else {
if (inst.isMissing(m_attribute.index())) {
throw new Exception("UnivariateLinearRegression: No missing values!");
}
return m_intercept + m_slope * inst.value(m_attribute.index());
}
}
/**
* Method for building an Id3 tree.
*
* @param data the training data
* @exception Exception if decision tree can't be built successfully
*/
private void makeTree(Instances data) throws Exception {
// Check if no instances have reached this node.
if (data.numInstances() == 0) {
m_Attribute = null;
m_ClassValue = Utils.missingValue();
m_Distribution = new double[data.numClasses()];
return;
}
// Compute attribute with maximum information gain.
double[] infoGains = new double[data.numAttributes()];
Enumeration attEnum = data.enumerateAttributes();
while (attEnum.hasMoreElements()) {
Attribute att = (Attribute) attEnum.nextElement();
infoGains[att.index()] = computeInfoGain(data, att);
}
m_Attribute = data.attribute(Utils.maxIndex(infoGains));
// Make leaf if information gain is zero.
// Otherwise create successors.
if (Utils.eq(infoGains[m_Attribute.index()], 0)) {
m_Attribute = null;
m_Distribution = new double[data.numClasses()];
Enumeration instEnum = data.enumerateInstances();
while (instEnum.hasMoreElements()) {
Instance inst = (Instance) instEnum.nextElement();
m_Distribution[(int) inst.classValue()]++;
}
Utils.normalize(m_Distribution);
m_ClassValue = Utils.maxIndex(m_Distribution);
m_ClassAttribute = data.classAttribute();
} else {
Instances[] splitData = splitData(data, m_Attribute);
m_Successors = new Id3[m_Attribute.numValues()];
for (int j = 0; j < m_Attribute.numValues(); j++) {
m_Successors[j] = new Id3();
m_Successors[j].makeTree(splitData[j]);
}
}
}
/** Main method for testing this class. */
public static void main(String[] options) {
try {
// Create numeric attributes "length" and "weight"
Attribute length = new Attribute("length");
Attribute weight = new Attribute("weight");
// Create vector to hold nominal values "first", "second", "third"
ArrayList<String> my_nominal_values = new ArrayList<String>(3);
my_nominal_values.add("first");
my_nominal_values.add("second");
my_nominal_values.add("third");
// Create nominal attribute "position"
Attribute position = new Attribute("position", my_nominal_values);
// Create vector of the above attributes
ArrayList<Attribute> attributes = new ArrayList<Attribute>(3);
attributes.add(length);
attributes.add(weight);
attributes.add(position);
// Create the empty dataset "race" with above attributes
Instances race = new Instances("race", attributes, 0);
// Make position the class attribute
race.setClassIndex(position.index());
// Create empty instance with three attribute values
SparseInstance inst = new SparseInstance(3);
// Set instance's values for the attributes "length", "weight", and "position"
inst.setValue(length, 5.3);
inst.setValue(weight, 300);
inst.setValue(position, "first");
// Set instance's dataset to be the dataset "race"
inst.setDataset(race);
// Print the instance
System.out.println("The instance: " + inst);
// Print the first attribute
System.out.println("First attribute: " + inst.attribute(0));
// Print the class attribute
System.out.println("Class attribute: " + inst.classAttribute());
// Print the class index
System.out.println("Class index: " + inst.classIndex());
// Say if class is missing
System.out.println("Class is missing: " + inst.classIsMissing());
// Print the instance's class value in internal format
System.out.println("Class value (internal format): " + inst.classValue());
// Print a shallow copy of this instance
SparseInstance copy = (SparseInstance) inst.copy();
System.out.println("Shallow copy: " + copy);
// Set dataset for shallow copy
copy.setDataset(inst.dataset());
System.out.println("Shallow copy with dataset set: " + copy);
// Print out all values in internal format
System.out.print("All stored values in internal format: ");
for (int i = 0; i < inst.numValues(); i++) {
if (i > 0) {
System.out.print(",");
}
System.out.print(inst.valueSparse(i));
}
System.out.println();
// Set all values to zero
System.out.print("All values set to zero: ");
while (inst.numValues() > 0) {
inst.setValueSparse(0, 0);
}
for (int i = 0; i < inst.numValues(); i++) {
if (i > 0) {
System.out.print(",");
}
System.out.print(inst.valueSparse(i));
}
System.out.println();
// Set all values to one
System.out.print("All values set to one: ");
for (int i = 0; i < inst.numAttributes(); i++) {
inst.setValue(i, 1);
}
for (int i = 0; i < inst.numValues(); i++) {
if (i > 0) {
System.out.print(",");
}
System.out.print(inst.valueSparse(i));
}
System.out.println();
// Unset dataset for copy, delete first attribute, and insert it again
copy.setDataset(null);
copy.deleteAttributeAt(0);
copy.insertAttributeAt(0);
copy.setDataset(inst.dataset());
System.out.println("Copy with first attribute deleted and inserted: " + copy);
// Same for second attribute
copy.setDataset(null);
copy.deleteAttributeAt(1);
copy.insertAttributeAt(1);
copy.setDataset(inst.dataset());
System.out.println("Copy with second attribute deleted and inserted: " + copy);
// Same for last attribute
copy.setDataset(null);
copy.deleteAttributeAt(2);
copy.insertAttributeAt(2);
copy.setDataset(inst.dataset());
System.out.println("Copy with third attribute deleted and inserted: " + copy);
// Enumerate attributes (leaving out the class attribute)
System.out.println("Enumerating attributes (leaving out class):");
Enumeration enu = inst.enumerateAttributes();
while (enu.hasMoreElements()) {
Attribute att = (Attribute) enu.nextElement();
System.out.println(att);
}
// Headers are equivalent?
System.out.println("Header of original and copy equivalent: " + inst.equalHeaders(copy));
// Test for missing values
System.out.println("Length of copy missing: " + copy.isMissing(length));
System.out.println("Weight of copy missing: " + copy.isMissing(weight.index()));
System.out.println("Length of copy missing: " + Utils.isMissingValue(copy.value(length)));
// Prints number of attributes and classes
System.out.println("Number of attributes: " + copy.numAttributes());
System.out.println("Number of classes: " + copy.numClasses());
// Replace missing values
double[] meansAndModes = {2, 3, 0};
copy.replaceMissingValues(meansAndModes);
System.out.println("Copy with missing value replaced: " + copy);
// Setting and getting values and weights
copy.setClassMissing();
System.out.println("Copy with missing class: " + copy);
copy.setClassValue(0);
System.out.println("Copy with class value set to first value: " + copy);
copy.setClassValue("third");
System.out.println("Copy with class value set to \"third\": " + copy);
copy.setMissing(1);
System.out.println("Copy with second attribute set to be missing: " + copy);
copy.setMissing(length);
System.out.println("Copy with length set to be missing: " + copy);
copy.setValue(0, 0);
System.out.println("Copy with first attribute set to 0: " + copy);
copy.setValue(weight, 1);
System.out.println("Copy with weight attribute set to 1: " + copy);
copy.setValue(position, "second");
System.out.println("Copy with position set to \"second\": " + copy);
copy.setValue(2, "first");
System.out.println("Copy with last attribute set to \"first\": " + copy);
System.out.println("Current weight of instance copy: " + copy.weight());
copy.setWeight(2);
System.out.println("Current weight of instance copy (set to 2): " + copy.weight());
System.out.println("Last value of copy: " + copy.toString(2));
System.out.println("Value of position for copy: " + copy.toString(position));
System.out.println("Last value of copy (internal format): " + copy.value(2));
System.out.println("Value of position for copy (internal format): " + copy.value(position));
} catch (Exception e) {
e.printStackTrace();
}
}
