/**
* Checks if an instance contains an item set.
*
* @param instance the instance to be tested
* @return true if the given instance contains this item set
*/
public boolean containedByTreatZeroAsMissing(Instance instance) {
if (instance instanceof weka.core.SparseInstance) {
int numInstVals = instance.numValues();
int numItemSetVals = m_items.length;
for (int p1 = 0, p2 = 0; p1 < numInstVals || p2 < numItemSetVals; ) {
int instIndex = Integer.MAX_VALUE;
if (p1 < numInstVals) {
instIndex = instance.index(p1);
}
int itemIndex = p2;
if (m_items[itemIndex] > -1) {
if (itemIndex != instIndex) {
return false;
} else {
if (instance.isMissingSparse(p1)) {
return false;
}
if (m_items[itemIndex] != (int) instance.valueSparse(p1)) {
return false;
}
}
p1++;
p2++;
} else {
if (itemIndex < instIndex) {
p2++;
} else if (itemIndex == instIndex) {
p2++;
p1++;
}
}
}
} else {
for (int i = 0; i < instance.numAttributes(); i++) {
if (m_items[i] > -1) {
if (instance.isMissing(i) || (int) instance.value(i) == 0) {
return false;
}
if (m_items[i] != (int) instance.value(i)) {
return false;
}
}
}
}
return true;
}
/**
* 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_headerInfo = new Instances(instances, 0);
m_numClasses = instances.numClasses();
m_numAttributes = instances.numAttributes();
m_probOfWordGivenClass = new double[m_numClasses][];
/*
initialising the matrix of word counts
NOTE: Laplace estimator introduced in case a word that does not appear for a class in the
training set does so for the test set
*/
for (int c = 0; c < m_numClasses; c++) {
m_probOfWordGivenClass[c] = new double[m_numAttributes];
for (int att = 0; att < m_numAttributes; att++) {
m_probOfWordGivenClass[c][att] = 1;
}
}
// enumerate through the instances
Instance instance;
int classIndex;
double numOccurences;
double[] docsPerClass = new double[m_numClasses];
double[] wordsPerClass = new double[m_numClasses];
java.util.Enumeration<Instance> enumInsts = instances.enumerateInstances();
while (enumInsts.hasMoreElements()) {
instance = (Instance) enumInsts.nextElement();
classIndex = (int) instance.value(instance.classIndex());
docsPerClass[classIndex] += instance.weight();
for (int a = 0; a < instance.numValues(); a++)
if (instance.index(a) != instance.classIndex()) {
if (!instance.isMissingSparse(a)) {
numOccurences = instance.valueSparse(a) * instance.weight();
if (numOccurences < 0)
throw new Exception("Numeric attribute values must all be greater or equal to zero.");
wordsPerClass[classIndex] += numOccurences;
m_probOfWordGivenClass[classIndex][instance.index(a)] += numOccurences;
}
}
}
/*
normalising probOfWordGivenClass values
and saving each value as the log of each value
*/
for (int c = 0; c < m_numClasses; c++)
for (int v = 0; v < m_numAttributes; v++)
m_probOfWordGivenClass[c][v] =
Math.log(m_probOfWordGivenClass[c][v] / (wordsPerClass[c] + m_numAttributes - 1));
/*
calculating Pr(H)
NOTE: Laplace estimator introduced in case a class does not get mentioned in the set of
training instances
*/
final double numDocs = instances.sumOfWeights() + m_numClasses;
m_probOfClass = new double[m_numClasses];
for (int h = 0; h < m_numClasses; h++)
m_probOfClass[h] = (double) (docsPerClass[h] + 1) / numDocs;
}
