/**
* Calculates the class membership probabilities for the given test instance.
*
* @param instance the instance to be classified
* @return predicted class probability distribution
* @exception Exception if distribution can't be computed
*/
@Override
public double[] distributionForInstance(Instance instance) throws Exception {
double[] probs = new double[instance.numClasses()];
int attIndex;
for (int j = 0; j < instance.numClasses(); j++) {
probs[j] = 1;
Enumeration<Attribute> enumAtts = instance.enumerateAttributes();
attIndex = 0;
while (enumAtts.hasMoreElements()) {
Attribute attribute = enumAtts.nextElement();
if (!instance.isMissing(attribute)) {
if (attribute.isNominal()) {
probs[j] *= m_Counts[j][attIndex][(int) instance.value(attribute)];
} else {
probs[j] *=
normalDens(instance.value(attribute), m_Means[j][attIndex], m_Devs[j][attIndex]);
}
}
attIndex++;
}
probs[j] *= m_Priors[j];
}
// Normalize probabilities
Utils.normalize(probs);
return probs;
}
/**
* Sets up the structure for the plot instances. Sets m_PlotInstances to null if instances are not
* saved for visualization.
*
* @see #getSaveForVisualization()
*/
protected void determineFormat() {
FastVector hv;
Attribute predictedClass;
Attribute classAt;
FastVector attVals;
int i;
if (!m_SaveForVisualization) {
m_PlotInstances = null;
return;
}
hv = new FastVector();
classAt = m_Instances.attribute(m_ClassIndex);
if (classAt.isNominal()) {
attVals = new FastVector();
for (i = 0; i < classAt.numValues(); i++) attVals.addElement(classAt.value(i));
predictedClass = new Attribute("predicted" + classAt.name(), attVals);
} else {
predictedClass = new Attribute("predicted" + classAt.name());
}
for (i = 0; i < m_Instances.numAttributes(); i++) {
if (i == m_Instances.classIndex()) hv.addElement(predictedClass);
hv.addElement(m_Instances.attribute(i).copy());
}
m_PlotInstances =
new Instances(m_Instances.relationName() + "_predicted", hv, m_Instances.numInstances());
m_PlotInstances.setClassIndex(m_ClassIndex + 1);
}
/**
* Método que inicializa uma regra com os valores obtidos atraves do Apriori.
*
* @param b Corpo da regre
* @param h Cabecao da regra
* @param conf Confianca da regra
* @param e Lista com os atributos da regra
* @param c Atributo da classe da regra
*/
public Regra(ItemSet b, ItemSet h, double conf, Enumeration<Attribute> e, Attribute c)
throws Exception {
cabeca = h.itemAt(0);
confianca = conf;
int corpoTemp[] = b.items();
atributosNaoVazios = 0;
corpo = new Atributo[corpoTemp.length];
int i = 0;
while (e.hasMoreElements()) {
Attribute att = (Attribute) e.nextElement();
// attributes.add(att);
if (att.isNominal()) {
if (corpoTemp[i] == -1) {
AtributoNominal vazio = new AtributoNominal(true, att, i);
corpo[i++] = vazio;
} else {
AtributoNominal nominal =
new AtributoNominal(corpoTemp[i], AtributoNominal.igual, att, i);
corpo[i++] = nominal;
}
} else {
throw new Exception("Atributo não nominal!");
}
}
classe = c;
matrizContigencia = new MatrizContingencia();
getNumAtributosNaoVazios();
}
/** Computes average class values for each attribute and value */
private void computeAverageClassValues() {
double totalCounts, sum;
Instance instance;
double[] counts;
double[][] avgClassValues = new double[getInputFormat().numAttributes()][0];
m_Indices = new int[getInputFormat().numAttributes()][0];
for (int j = 0; j < getInputFormat().numAttributes(); j++) {
Attribute att = getInputFormat().attribute(j);
if (att.isNominal()) {
avgClassValues[j] = new double[att.numValues()];
counts = new double[att.numValues()];
for (int i = 0; i < getInputFormat().numInstances(); i++) {
instance = getInputFormat().instance(i);
if (!instance.classIsMissing() && (!instance.isMissing(j))) {
counts[(int) instance.value(j)] += instance.weight();
avgClassValues[j][(int) instance.value(j)] += instance.weight() * instance.classValue();
}
}
sum = Utils.sum(avgClassValues[j]);
totalCounts = Utils.sum(counts);
if (Utils.gr(totalCounts, 0)) {
for (int k = 0; k < att.numValues(); k++) {
if (Utils.gr(counts[k], 0)) {
avgClassValues[j][k] /= counts[k];
} else {
avgClassValues[j][k] = sum / totalCounts;
}
}
}
m_Indices[j] = Utils.sort(avgClassValues[j]);
}
}
}
/**
* Compute the number of all possible conditions that could appear in a rule of a given data. For
* nominal attributes, it's the number of values that could appear; for numeric attributes, it's
* the number of values * 2, i.e. <= and >= are counted as different possible conditions.
*
* @param data the given data
* @return number of all conditions of the data
*/
public static double numAllConditions(Instances data) {
double total = 0;
Enumeration attEnum = data.enumerateAttributes();
while (attEnum.hasMoreElements()) {
Attribute att = (Attribute) attEnum.nextElement();
if (att.isNominal()) total += (double) att.numValues();
else total += 2.0 * (double) data.numDistinctValues(att);
}
return total;
}
/** Find the fold attribute within a dataset. */
private Attribute getAttribute(Instances data) {
SingleIndex index = new SingleIndex(super.getAttributeIndex());
index.setUpper(data.numAttributes() - 1);
Attribute att = data.attribute(index.getIndex());
if (att == null)
throw new NoSuchElementException(
"attribute #" + super.getAttributeIndex() + " does not exist");
if (!att.isNominal() && !att.isString())
throw new IllegalArgumentException("Attribute '" + att + "' is not nominal");
return att;
}
/**
* Constructs an instance suitable for passing to the model for scoring
*
* @param incoming the incoming instance
* @return an instance with values mapped to be consistent with what the model is expecting
*/
protected Instance mapIncomingFieldsToModelFields(Instance incoming) {
Instances modelHeader = m_model.getHeader();
double[] vals = new double[modelHeader.numAttributes()];
for (int i = 0; i < modelHeader.numAttributes(); i++) {
if (m_attributeMap[i] < 0) {
// missing or type mismatch
vals[i] = Utils.missingValue();
continue;
}
Attribute modelAtt = modelHeader.attribute(i);
Attribute incomingAtt = incoming.dataset().attribute(m_attributeMap[i]);
if (incoming.isMissing(incomingAtt.index())) {
vals[i] = Utils.missingValue();
continue;
}
if (modelAtt.isNumeric()) {
vals[i] = incoming.value(m_attributeMap[i]);
} else if (modelAtt.isNominal()) {
String incomingVal = incoming.stringValue(m_attributeMap[i]);
int modelIndex = modelAtt.indexOfValue(incomingVal);
if (modelIndex < 0) {
vals[i] = Utils.missingValue();
} else {
vals[i] = modelIndex;
}
} else if (modelAtt.isString()) {
vals[i] = 0;
modelAtt.setStringValue(incoming.stringValue(m_attributeMap[i]));
}
}
if (modelHeader.classIndex() >= 0) {
// set class to missing value
vals[modelHeader.classIndex()] = Utils.missingValue();
}
Instance newInst = null;
if (incoming instanceof SparseInstance) {
newInst = new SparseInstance(incoming.weight(), vals);
} else {
newInst = new DenseInstance(incoming.weight(), vals);
}
newInst.setDataset(modelHeader);
return newInst;
}
/**
* Convert a single instance over if the class is nominal. The converted instance is added to the
* end of the output queue.
*
* @param instance the instance to convert
*/
private void convertInstanceNominal(Instance instance) {
if (!m_needToTransform) {
push(instance);
return;
}
double[] vals = new double[outputFormatPeek().numAttributes()];
int attSoFar = 0;
for (int j = 0; j < getInputFormat().numAttributes(); j++) {
Attribute att = getInputFormat().attribute(j);
if ((!att.isNominal()) || (j == getInputFormat().classIndex())) {
vals[attSoFar] = instance.value(j);
attSoFar++;
} else {
if ((att.numValues() <= 2) && (!m_TransformAll)) {
vals[attSoFar] = instance.value(j);
attSoFar++;
} else {
if (instance.isMissing(j)) {
for (int k = 0; k < att.numValues(); k++) {
vals[attSoFar + k] = instance.value(j);
}
} else {
for (int k = 0; k < att.numValues(); k++) {
if (k == (int) instance.value(j)) {
vals[attSoFar + k] = 1;
} else {
vals[attSoFar + k] = 0;
}
}
}
attSoFar += att.numValues();
}
}
}
Instance inst = null;
if (instance instanceof SparseInstance) {
inst = new SparseInstance(instance.weight(), vals);
} else {
inst = new DenseInstance(instance.weight(), vals);
}
inst.setDataset(getOutputFormat());
copyValues(inst, false, instance.dataset(), getOutputFormat());
inst.setDataset(getOutputFormat());
push(inst);
}
/**
* Determines the output format based on the input format and returns this.
*
* @param inputFormat the input format to base the output format on
* @return the output format
* @throws Exception in case the determination goes wrong
*/
protected Instances determineOutputFormat(Instances inputFormat) throws Exception {
Instances result;
Attribute att;
Attribute attSorted;
FastVector atts;
FastVector values;
Vector<String> sorted;
int i;
int n;
m_AttributeIndices.setUpper(inputFormat.numAttributes() - 1);
// determine sorted indices
atts = new FastVector();
m_NewOrder = new int[inputFormat.numAttributes()][];
for (i = 0; i < inputFormat.numAttributes(); i++) {
att = inputFormat.attribute(i);
if (!att.isNominal() || !m_AttributeIndices.isInRange(i)) {
m_NewOrder[i] = new int[0];
atts.addElement(inputFormat.attribute(i).copy());
continue;
}
// sort labels
sorted = new Vector<String>();
for (n = 0; n < att.numValues(); n++) sorted.add(att.value(n));
Collections.sort(sorted, m_Comparator);
// determine new indices
m_NewOrder[i] = new int[att.numValues()];
values = new FastVector();
for (n = 0; n < att.numValues(); n++) {
m_NewOrder[i][n] = sorted.indexOf(att.value(n));
values.addElement(sorted.get(n));
}
attSorted = new Attribute(att.name(), values);
attSorted.setWeight(att.weight());
atts.addElement(attSorted);
}
// generate new header
result = new Instances(inputFormat.relationName(), atts, 0);
result.setClassIndex(inputFormat.classIndex());
return result;
}
/**
* Returns a description of the classifier.
*
* @return a description of the classifier as a string.
*/
@Override
public String toString() {
if (m_Instances == null) {
return "Naive Bayes (simple): No model built yet.";
}
try {
StringBuffer text = new StringBuffer("Naive Bayes (simple)");
int attIndex;
for (int i = 0; i < m_Instances.numClasses(); i++) {
text.append(
"\n\nClass "
+ m_Instances.classAttribute().value(i)
+ ": P(C) = "
+ Utils.doubleToString(m_Priors[i], 10, 8)
+ "\n\n");
Enumeration<Attribute> enumAtts = m_Instances.enumerateAttributes();
attIndex = 0;
while (enumAtts.hasMoreElements()) {
Attribute attribute = enumAtts.nextElement();
text.append("Attribute " + attribute.name() + "\n");
if (attribute.isNominal()) {
for (int j = 0; j < attribute.numValues(); j++) {
text.append(attribute.value(j) + "\t");
}
text.append("\n");
for (int j = 0; j < attribute.numValues(); j++) {
text.append(Utils.doubleToString(m_Counts[i][attIndex][j], 10, 8) + "\t");
}
} else {
text.append("Mean: " + Utils.doubleToString(m_Means[i][attIndex], 10, 8) + "\t");
text.append("Standard Deviation: " + Utils.doubleToString(m_Devs[i][attIndex], 10, 8));
}
text.append("\n\n");
attIndex++;
}
}
return text.toString();
} catch (Exception e) {
return "Can't print Naive Bayes classifier!";
}
}
/**
* Set the output format. Takes the current average class values and m_InputFormat and calls
* setOutputFormat(Instances) appropriately.
*/
private void setOutputFormat() {
Instances newData;
FastVector newAtts;
// Compute new attributes
newAtts = new FastVector(getInputFormat().numAttributes());
for (int j = 0; j < getInputFormat().numAttributes(); j++) {
Attribute att = getInputFormat().attribute(j);
if (!att.isNominal() || !m_AttIndex.isInRange(j)) newAtts.addElement(att);
else newAtts.addElement(new Attribute(att.name(), (FastVector) null));
}
// Construct new header
newData = new Instances(getInputFormat().relationName(), newAtts, 0);
newData.setClassIndex(getInputFormat().classIndex());
setOutputFormat(newData);
}
/**
* processes the given instance (may change the provided instance) and returns the modified
* version.
*
* @param instance the instance to process
* @return the modified data
* @throws Exception in case the processing goes wrong
*/
protected Instance process(Instance instance) throws Exception {
Instance result;
Attribute att;
double[] values;
int i;
// adjust indices
values = new double[instance.numAttributes()];
for (i = 0; i < instance.numAttributes(); i++) {
att = instance.attribute(i);
if (!att.isNominal() || !m_AttributeIndices.isInRange(i) || instance.isMissing(i))
values[i] = instance.value(i);
else values[i] = m_NewOrder[i][(int) instance.value(i)];
}
// create new instance
result = new DenseInstance(instance.weight(), values);
return result;
}
/**
* The procedure implementing the SMOTE algorithm. The output instances are pushed onto the output
* queue for collection.
*
* @throws Exception if provided options cannot be executed on input instances
*/
protected void doSMOTE() throws Exception {
int minIndex = 0;
int min = Integer.MAX_VALUE;
if (m_DetectMinorityClass) {
// find minority class
int[] classCounts =
getInputFormat().attributeStats(getInputFormat().classIndex()).nominalCounts;
for (int i = 0; i < classCounts.length; i++) {
if (classCounts[i] != 0 && classCounts[i] < min) {
min = classCounts[i];
minIndex = i;
}
}
} else {
String classVal = getClassValue();
if (classVal.equalsIgnoreCase("first")) {
minIndex = 1;
} else if (classVal.equalsIgnoreCase("last")) {
minIndex = getInputFormat().numClasses();
} else {
minIndex = Integer.parseInt(classVal);
}
if (minIndex > getInputFormat().numClasses()) {
throw new Exception("value index must be <= the number of classes");
}
minIndex--; // make it an index
}
int nearestNeighbors;
if (min <= getNearestNeighbors()) {
nearestNeighbors = min - 1;
} else {
nearestNeighbors = getNearestNeighbors();
}
if (nearestNeighbors < 1) throw new Exception("Cannot use 0 neighbors!");
// compose minority class dataset
// also push all dataset instances
Instances sample = getInputFormat().stringFreeStructure();
Enumeration instanceEnum = getInputFormat().enumerateInstances();
while (instanceEnum.hasMoreElements()) {
Instance instance = (Instance) instanceEnum.nextElement();
push((Instance) instance.copy());
if ((int) instance.classValue() == minIndex) {
sample.add(instance);
}
}
// compute Value Distance Metric matrices for nominal features
Map vdmMap = new HashMap();
Enumeration attrEnum = getInputFormat().enumerateAttributes();
while (attrEnum.hasMoreElements()) {
Attribute attr = (Attribute) attrEnum.nextElement();
if (!attr.equals(getInputFormat().classAttribute())) {
if (attr.isNominal() || attr.isString()) {
double[][] vdm = new double[attr.numValues()][attr.numValues()];
vdmMap.put(attr, vdm);
int[] featureValueCounts = new int[attr.numValues()];
int[][] featureValueCountsByClass =
new int[getInputFormat().classAttribute().numValues()][attr.numValues()];
instanceEnum = getInputFormat().enumerateInstances();
while (instanceEnum.hasMoreElements()) {
Instance instance = (Instance) instanceEnum.nextElement();
int value = (int) instance.value(attr);
int classValue = (int) instance.classValue();
featureValueCounts[value]++;
featureValueCountsByClass[classValue][value]++;
}
for (int valueIndex1 = 0; valueIndex1 < attr.numValues(); valueIndex1++) {
for (int valueIndex2 = 0; valueIndex2 < attr.numValues(); valueIndex2++) {
double sum = 0;
for (int classValueIndex = 0;
classValueIndex < getInputFormat().numClasses();
classValueIndex++) {
double c1i = featureValueCountsByClass[classValueIndex][valueIndex1];
double c2i = featureValueCountsByClass[classValueIndex][valueIndex2];
double c1 = featureValueCounts[valueIndex1];
double c2 = featureValueCounts[valueIndex2];
double term1 = c1i / c1;
double term2 = c2i / c2;
sum += Math.abs(term1 - term2);
}
vdm[valueIndex1][valueIndex2] = sum;
}
}
}
}
}
// use this random source for all required randomness
Random rand = new Random(getRandomSeed());
// find the set of extra indices to use if the percentage is not evenly
// divisible by 100
List extraIndices = new LinkedList();
double percentageRemainder = (getPercentage() / 100) - Math.floor(getPercentage() / 100.0);
int extraIndicesCount = (int) (percentageRemainder * sample.numInstances());
if (extraIndicesCount >= 1) {
for (int i = 0; i < sample.numInstances(); i++) {
extraIndices.add(i);
}
}
Collections.shuffle(extraIndices, rand);
extraIndices = extraIndices.subList(0, extraIndicesCount);
Set extraIndexSet = new HashSet(extraIndices);
// the main loop to handle computing nearest neighbors and generating SMOTE
// examples from each instance in the original minority class data
Instance[] nnArray = new Instance[nearestNeighbors];
for (int i = 0; i < sample.numInstances(); i++) {
Instance instanceI = sample.instance(i);
// find k nearest neighbors for each instance
List distanceToInstance = new LinkedList();
for (int j = 0; j < sample.numInstances(); j++) {
Instance instanceJ = sample.instance(j);
if (i != j) {
double distance = 0;
attrEnum = getInputFormat().enumerateAttributes();
while (attrEnum.hasMoreElements()) {
Attribute attr = (Attribute) attrEnum.nextElement();
if (!attr.equals(getInputFormat().classAttribute())) {
double iVal = instanceI.value(attr);
double jVal = instanceJ.value(attr);
if (attr.isNumeric()) {
distance += Math.pow(iVal - jVal, 2);
} else {
distance += ((double[][]) vdmMap.get(attr))[(int) iVal][(int) jVal];
}
}
}
distance = Math.pow(distance, .5);
distanceToInstance.add(new Object[] {distance, instanceJ});
}
}
// sort the neighbors according to distance
Collections.sort(
distanceToInstance,
new Comparator() {
public int compare(Object o1, Object o2) {
double distance1 = (Double) ((Object[]) o1)[0];
double distance2 = (Double) ((Object[]) o2)[0];
return Double.compare(distance1, distance2);
}
});
// populate the actual nearest neighbor instance array
Iterator entryIterator = distanceToInstance.iterator();
int j = 0;
while (entryIterator.hasNext() && j < nearestNeighbors) {
nnArray[j] = (Instance) ((Object[]) entryIterator.next())[1];
j++;
}
// create synthetic examples
int n = (int) Math.floor(getPercentage() / 100);
while (n > 0 || extraIndexSet.remove(i)) {
double[] values = new double[sample.numAttributes()];
int nn = rand.nextInt(nearestNeighbors);
attrEnum = getInputFormat().enumerateAttributes();
while (attrEnum.hasMoreElements()) {
Attribute attr = (Attribute) attrEnum.nextElement();
if (!attr.equals(getInputFormat().classAttribute())) {
if (attr.isNumeric()) {
double dif = nnArray[nn].value(attr) - instanceI.value(attr);
double gap = rand.nextDouble();
values[attr.index()] = (instanceI.value(attr) + gap * dif);
} else if (attr.isDate()) {
double dif = nnArray[nn].value(attr) - instanceI.value(attr);
double gap = rand.nextDouble();
values[attr.index()] = (long) (instanceI.value(attr) + gap * dif);
} else {
int[] valueCounts = new int[attr.numValues()];
int iVal = (int) instanceI.value(attr);
valueCounts[iVal]++;
for (int nnEx = 0; nnEx < nearestNeighbors; nnEx++) {
int val = (int) nnArray[nnEx].value(attr);
valueCounts[val]++;
}
int maxIndex = 0;
int max = Integer.MIN_VALUE;
for (int index = 0; index < attr.numValues(); index++) {
if (valueCounts[index] > max) {
max = valueCounts[index];
maxIndex = index;
}
}
values[attr.index()] = maxIndex;
}
}
}
values[sample.classIndex()] = minIndex;
Instance synthetic = new Instance(1.0, values);
push(synthetic);
n--;
}
}
}
/**
* Generates the classifier.
*
* @param instances set of instances serving as training data
* @exception Exception if the classifier has not been generated successfully
*/
@Override
public void buildClassifier(Instances instances) throws Exception {
int attIndex = 0;
double sum;
// can classifier handle the data?
getCapabilities().testWithFail(instances);
// remove instances with missing class
instances = new Instances(instances);
instances.deleteWithMissingClass();
m_Instances = new Instances(instances, 0);
// Reserve space
m_Counts = new double[instances.numClasses()][instances.numAttributes() - 1][0];
m_Means = new double[instances.numClasses()][instances.numAttributes() - 1];
m_Devs = new double[instances.numClasses()][instances.numAttributes() - 1];
m_Priors = new double[instances.numClasses()];
Enumeration<Attribute> enu = instances.enumerateAttributes();
while (enu.hasMoreElements()) {
Attribute attribute = enu.nextElement();
if (attribute.isNominal()) {
for (int j = 0; j < instances.numClasses(); j++) {
m_Counts[j][attIndex] = new double[attribute.numValues()];
}
} else {
for (int j = 0; j < instances.numClasses(); j++) {
m_Counts[j][attIndex] = new double[1];
}
}
attIndex++;
}
// Compute counts and sums
Enumeration<Instance> enumInsts = instances.enumerateInstances();
while (enumInsts.hasMoreElements()) {
Instance instance = enumInsts.nextElement();
if (!instance.classIsMissing()) {
Enumeration<Attribute> enumAtts = instances.enumerateAttributes();
attIndex = 0;
while (enumAtts.hasMoreElements()) {
Attribute attribute = enumAtts.nextElement();
if (!instance.isMissing(attribute)) {
if (attribute.isNominal()) {
m_Counts[(int) instance.classValue()][attIndex][(int) instance.value(attribute)]++;
} else {
m_Means[(int) instance.classValue()][attIndex] += instance.value(attribute);
m_Counts[(int) instance.classValue()][attIndex][0]++;
}
}
attIndex++;
}
m_Priors[(int) instance.classValue()]++;
}
}
// Compute means
Enumeration<Attribute> enumAtts = instances.enumerateAttributes();
attIndex = 0;
while (enumAtts.hasMoreElements()) {
Attribute attribute = enumAtts.nextElement();
if (attribute.isNumeric()) {
for (int j = 0; j < instances.numClasses(); j++) {
if (m_Counts[j][attIndex][0] < 2) {
throw new Exception(
"attribute "
+ attribute.name()
+ ": less than two values for class "
+ instances.classAttribute().value(j));
}
m_Means[j][attIndex] /= m_Counts[j][attIndex][0];
}
}
attIndex++;
}
// Compute standard deviations
enumInsts = instances.enumerateInstances();
while (enumInsts.hasMoreElements()) {
Instance instance = enumInsts.nextElement();
if (!instance.classIsMissing()) {
enumAtts = instances.enumerateAttributes();
attIndex = 0;
while (enumAtts.hasMoreElements()) {
Attribute attribute = enumAtts.nextElement();
if (!instance.isMissing(attribute)) {
if (attribute.isNumeric()) {
m_Devs[(int) instance.classValue()][attIndex] +=
(m_Means[(int) instance.classValue()][attIndex] - instance.value(attribute))
* (m_Means[(int) instance.classValue()][attIndex]
- instance.value(attribute));
}
}
attIndex++;
}
}
}
enumAtts = instances.enumerateAttributes();
attIndex = 0;
while (enumAtts.hasMoreElements()) {
Attribute attribute = enumAtts.nextElement();
if (attribute.isNumeric()) {
for (int j = 0; j < instances.numClasses(); j++) {
if (m_Devs[j][attIndex] <= 0) {
throw new Exception(
"attribute "
+ attribute.name()
+ ": standard deviation is 0 for class "
+ instances.classAttribute().value(j));
} else {
m_Devs[j][attIndex] /= m_Counts[j][attIndex][0] - 1;
m_Devs[j][attIndex] = Math.sqrt(m_Devs[j][attIndex]);
}
}
}
attIndex++;
}
// Normalize counts
enumAtts = instances.enumerateAttributes();
attIndex = 0;
while (enumAtts.hasMoreElements()) {
Attribute attribute = enumAtts.nextElement();
if (attribute.isNominal()) {
for (int j = 0; j < instances.numClasses(); j++) {
sum = Utils.sum(m_Counts[j][attIndex]);
for (int i = 0; i < attribute.numValues(); i++) {
m_Counts[j][attIndex][i] =
(m_Counts[j][attIndex][i] + 1) / (sum + attribute.numValues());
}
}
}
attIndex++;
}
// Normalize priors
sum = Utils.sum(m_Priors);
for (int j = 0; j < instances.numClasses(); j++) {
m_Priors[j] = (m_Priors[j] + 1) / (sum + instances.numClasses());
}
}
@Override
public void init(Instances structure, Environment env) {
super.init(structure, env);
m_resolvedLhsName = m_lhsAttributeName;
m_resolvedRhsOperand = m_rhsOperand;
try {
m_resolvedLhsName = m_env.substitute(m_resolvedLhsName);
m_resolvedRhsOperand = m_env.substitute(m_resolvedRhsOperand);
} catch (Exception ex) {
}
Attribute lhs = null;
// try as an index or "special" label first
if (m_resolvedLhsName.toLowerCase().startsWith("/first")) {
lhs = structure.attribute(0);
} else if (m_resolvedLhsName.toLowerCase().startsWith("/last")) {
lhs = structure.attribute(structure.numAttributes() - 1);
} else {
// try as an index
try {
int indx = Integer.parseInt(m_resolvedLhsName);
indx--;
lhs = structure.attribute(indx);
} catch (NumberFormatException ex) {
}
}
if (lhs == null) {
lhs = structure.attribute(m_resolvedLhsName);
}
if (lhs == null) {
throw new IllegalArgumentException(
"Data does not contain attribute " + "\"" + m_resolvedLhsName + "\"");
}
m_lhsAttIndex = lhs.index();
if (m_rhsIsAttribute) {
Attribute rhs = null;
// try as an index or "special" label first
if (m_resolvedRhsOperand.toLowerCase().equals("/first")) {
rhs = structure.attribute(0);
} else if (m_resolvedRhsOperand.toLowerCase().equals("/last")) {
rhs = structure.attribute(structure.numAttributes() - 1);
} else {
// try as an index
try {
int indx = Integer.parseInt(m_resolvedRhsOperand);
indx--;
rhs = structure.attribute(indx);
} catch (NumberFormatException ex) {
}
}
if (rhs == null) {
rhs = structure.attribute(m_resolvedRhsOperand);
}
if (rhs == null) {
throw new IllegalArgumentException(
"Data does not contain attribute " + "\"" + m_resolvedRhsOperand + "\"");
}
m_rhsAttIndex = rhs.index();
} else if (m_operator != ExpressionType.CONTAINS
&& m_operator != ExpressionType.STARTSWITH
&& m_operator != ExpressionType.ENDSWITH
&& m_operator != ExpressionType.REGEX
&& m_operator != ExpressionType.ISMISSING) {
// make sure the operand is parseable as a number (unless missing has
// been specified - equals only)
if (lhs.isNominal()) {
m_numericOperand = lhs.indexOfValue(m_resolvedRhsOperand);
if (m_numericOperand < 0) {
throw new IllegalArgumentException(
"Unknown nominal value '"
+ m_resolvedRhsOperand
+ "' for attribute '"
+ lhs.name()
+ "'");
}
} else {
try {
m_numericOperand = Double.parseDouble(m_resolvedRhsOperand);
} catch (NumberFormatException e) {
throw new IllegalArgumentException(
"\"" + m_resolvedRhsOperand + "\" is not parseable as a number!");
}
}
}
if (m_operator == ExpressionType.REGEX) {
m_regexPattern = Pattern.compile(m_resolvedRhsOperand);
}
}
/** Set the output format if the class is numeric. */
private void setOutputFormatNumeric() {
if (m_Indices == null) {
setOutputFormat(null);
return;
}
ArrayList<Attribute> newAtts;
int newClassIndex;
StringBuffer attributeName;
Instances outputFormat;
ArrayList<String> vals;
// Compute new attributes
m_needToTransform = false;
for (int i = 0; i < getInputFormat().numAttributes(); i++) {
Attribute att = getInputFormat().attribute(i);
if (att.isNominal() && (att.numValues() > 2 || m_Numeric || m_TransformAll)) {
m_needToTransform = true;
break;
}
}
if (!m_needToTransform) {
setOutputFormat(getInputFormat());
return;
}
newClassIndex = getInputFormat().classIndex();
newAtts = new ArrayList<Attribute>();
for (int j = 0; j < getInputFormat().numAttributes(); j++) {
Attribute att = getInputFormat().attribute(j);
if ((!att.isNominal()) || (j == getInputFormat().classIndex())) {
newAtts.add((Attribute) att.copy());
} else {
if (j < getInputFormat().classIndex()) {
newClassIndex += att.numValues() - 2;
}
// Compute values for new attributes
for (int k = 1; k < att.numValues(); k++) {
attributeName = new StringBuffer(att.name() + "=");
for (int l = k; l < att.numValues(); l++) {
if (l > k) {
attributeName.append(',');
}
attributeName.append(att.value(m_Indices[j][l]));
}
if (m_Numeric) {
newAtts.add(new Attribute(attributeName.toString()));
} else {
vals = new ArrayList<String>(2);
vals.add("f");
vals.add("t");
newAtts.add(new Attribute(attributeName.toString(), vals));
}
}
}
}
outputFormat = new Instances(getInputFormat().relationName(), newAtts, 0);
outputFormat.setClassIndex(newClassIndex);
setOutputFormat(outputFormat);
}
public MappingInfo(Instances dataSet, MiningSchema miningSchema, Logger log) throws Exception {
m_log = log;
// miningSchema.convertStringAttsToNominal();
Instances fieldsI = miningSchema.getMiningSchemaAsInstances();
m_fieldsMap = new int[fieldsI.numAttributes()];
m_nominalValueMaps = new int[fieldsI.numAttributes()][];
for (int i = 0; i < fieldsI.numAttributes(); i++) {
String schemaAttName = fieldsI.attribute(i).name();
boolean found = false;
for (int j = 0; j < dataSet.numAttributes(); j++) {
if (dataSet.attribute(j).name().equals(schemaAttName)) {
Attribute miningSchemaAtt = fieldsI.attribute(i);
Attribute incomingAtt = dataSet.attribute(j);
// check type match
if (miningSchemaAtt.type() != incomingAtt.type()) {
throw new Exception(
"[MappingInfo] type mismatch for field "
+ schemaAttName
+ ". Mining schema type "
+ miningSchemaAtt.toString()
+ ". Incoming type "
+ incomingAtt.toString()
+ ".");
}
// check nominal values (number, names...)
if (miningSchemaAtt.numValues() != incomingAtt.numValues()) {
String warningString =
"[MappingInfo] WARNING: incoming nominal attribute "
+ incomingAtt.name()
+ " does not have the same "
+ "number of values as the corresponding mining "
+ "schema attribute.";
if (m_log != null) {
m_log.logMessage(warningString);
} else {
System.err.println(warningString);
}
}
if (miningSchemaAtt.isNominal() || miningSchemaAtt.isString()) {
int[] valuesMap = new int[incomingAtt.numValues()];
for (int k = 0; k < incomingAtt.numValues(); k++) {
String incomingNomVal = incomingAtt.value(k);
int indexInSchema = miningSchemaAtt.indexOfValue(incomingNomVal);
if (indexInSchema < 0) {
String warningString =
"[MappingInfo] WARNING: incoming nominal attribute "
+ incomingAtt.name()
+ " has value "
+ incomingNomVal
+ " that doesn't occur in the mining schema.";
if (m_log != null) {
m_log.logMessage(warningString);
} else {
System.err.println(warningString);
}
valuesMap[k] = UNKNOWN_NOMINAL_VALUE;
} else {
valuesMap[k] = indexInSchema;
}
}
m_nominalValueMaps[i] = valuesMap;
}
/*if (miningSchemaAtt.isNominal()) {
for (int k = 0; k < miningSchemaAtt.numValues(); k++) {
if (!miningSchemaAtt.value(k).equals(incomingAtt.value(k))) {
throw new Exception("[PMMLUtils] value " + k + " (" +
miningSchemaAtt.value(k) + ") does not match " +
"incoming value (" + incomingAtt.value(k) +
") for attribute " + miningSchemaAtt.name() +
".");
}
}
}*/
found = true;
m_fieldsMap[i] = j;
}
}
if (!found) {
throw new Exception(
"[MappingInfo] Unable to find a match for mining schema "
+ "attribute "
+ schemaAttName
+ " in the "
+ "incoming instances!");
}
}
// check class attribute (if set)
if (fieldsI.classIndex() >= 0) {
if (dataSet.classIndex() < 0) {
// first see if we can find a matching class
String className = fieldsI.classAttribute().name();
Attribute classMatch = dataSet.attribute(className);
if (classMatch == null) {
throw new Exception(
"[MappingInfo] Can't find match for target field "
+ className
+ "in incoming instances!");
}
dataSet.setClass(classMatch);
} else if (!fieldsI.classAttribute().name().equals(dataSet.classAttribute().name())) {
throw new Exception(
"[MappingInfo] class attribute in mining schema does not match "
+ "class attribute in incoming instances!");
}
}
// Set up the textual description of the mapping
fieldsMappingString(fieldsI, dataSet);
}