/** initializes the attribute indices. */
protected void initializeAttributeIndices() {
m_AttributeIndices.setUpper(m_Data.numAttributes() - 1);
m_ActiveIndices = new boolean[m_Data.numAttributes()];
for (int i = 0; i < m_ActiveIndices.length; i++) {
m_ActiveIndices[i] = m_AttributeIndices.isInRange(i);
}
}
/** @param args */
private void Init() {
testIns.setClassIndex(testIns.numAttributes() - 1);
labeledIns.setClassIndex(labeledIns.numAttributes() - 1);
unlabeledIns.setClassIndex(unlabeledIns.numAttributes() - 1);
class_Array[0] = classifier1;
class_Array[1] = classifier2;
class_Array[2] = classifier3;
}
protected void initMinMax(Instances data) {
m_Min = new double[data.numAttributes()];
m_Max = new double[data.numAttributes()];
for (int i = 0; i < data.numAttributes(); i++) {
m_Min[i] = m_Max[i] = Double.NaN;
}
for (int i = 0; i < data.numInstances(); i++) {
updateMinMax(data.instance(i));
}
}
/**
* Determines the output format based on the input format and returns this. In case the output
* format cannot be returned immediately, i.e., immediateOutputFormat() returns false, then this
* method will be called from batchFinished().
*
* @param inputFormat the input format to base the output format on
* @return the output format
* @throws Exception in case the determination goes wrong
* @see #hasImmediateOutputFormat()
* @see #batchFinished()
*/
protected Instances determineOutputFormat(Instances inputFormat) throws Exception {
Instances data;
Instances result;
FastVector atts;
FastVector values;
HashSet hash;
int i;
int n;
boolean isDate;
Instance inst;
Vector sorted;
m_Cols.setUpper(inputFormat.numAttributes() - 1);
data = new Instances(inputFormat);
atts = new FastVector();
for (i = 0; i < data.numAttributes(); i++) {
if (!m_Cols.isInRange(i) || !data.attribute(i).isNumeric()) {
atts.addElement(data.attribute(i));
continue;
}
// date attribute?
isDate = (data.attribute(i).type() == Attribute.DATE);
// determine all available attribtues in dataset
hash = new HashSet();
for (n = 0; n < data.numInstances(); n++) {
inst = data.instance(n);
if (inst.isMissing(i)) continue;
if (isDate) hash.add(inst.stringValue(i));
else hash.add(new Double(inst.value(i)));
}
// sort values
sorted = new Vector();
for (Object o : hash) sorted.add(o);
Collections.sort(sorted);
// create attribute from sorted values
values = new FastVector();
for (Object o : sorted) {
if (isDate) values.addElement(o.toString());
else values.addElement(Utils.doubleToString(((Double) o).doubleValue(), MAX_DECIMALS));
}
atts.addElement(new Attribute(data.attribute(i).name(), values));
}
result = new Instances(inputFormat.relationName(), atts, 0);
result.setClassIndex(inputFormat.classIndex());
return result;
}
/**
* Initializes the ranges using all instances of the dataset. Sets m_Ranges.
*
* @return the ranges
*/
public double[][] initializeRanges() {
if (m_Data == null) {
m_Ranges = null;
return m_Ranges;
}
int numAtt = m_Data.numAttributes();
double[][] ranges = new double[numAtt][3];
if (m_Data.numInstances() <= 0) {
initializeRangesEmpty(numAtt, ranges);
m_Ranges = ranges;
return m_Ranges;
} else {
// initialize ranges using the first instance
updateRangesFirst(m_Data.instance(0), numAtt, ranges);
}
// update ranges, starting from the second
for (int i = 1; i < m_Data.numInstances(); i++) {
updateRanges(m_Data.instance(i), numAtt, ranges);
}
m_Ranges = ranges;
return m_Ranges;
}
/**
* Generate artificial training examples.
*
* @param artSize size of examples set to create
* @param data training data
* @return the set of unlabeled artificial examples
*/
protected Instances generateArtificialData(int artSize, Instances data) {
int numAttributes = data.numAttributes();
Instances artData = new Instances(data, artSize);
double[] att;
Instance artInstance;
for (int i = 0; i < artSize; i++) {
att = new double[numAttributes];
for (int j = 0; j < numAttributes; j++) {
if (data.attribute(j).isNominal()) {
// Select nominal value based on the frequency of occurence in the training data
double[] stats = (double[]) m_AttributeStats.get(j);
att[j] = (double) selectIndexProbabilistically(stats);
} else if (data.attribute(j).isNumeric()) {
// Generate numeric value from the Guassian distribution
// defined by the mean and std dev of the attribute
double[] stats = (double[]) m_AttributeStats.get(j);
att[j] = (m_Random.nextGaussian() * stats[1]) + stats[0];
} else System.err.println("Decorate can only handle numeric and nominal values.");
}
artInstance = new Instance(1.0, att);
artData.add(artInstance);
}
return artData;
}
/**
* wrap up various variables to save memeory and do some housekeeping after optimization has
* finished.
*
* @throws Exception if something goes wrong
*/
protected void wrapUp() throws Exception {
m_target = null;
m_nEvals = m_kernel.numEvals();
m_nCacheHits = m_kernel.numCacheHits();
if ((m_SVM.getKernel() instanceof PolyKernel)
&& ((PolyKernel) m_SVM.getKernel()).getExponent() == 1.0) {
// convert alpha's to weights
double[] weights = new double[m_data.numAttributes()];
for (int k = m_supportVectors.getNext(-1); k != -1; k = m_supportVectors.getNext(k)) {
for (int j = 0; j < weights.length; j++) {
if (j != m_classIndex) {
weights[j] += (m_alpha[k] - m_alphaStar[k]) * m_data.instance(k).value(j);
}
}
}
m_weights = weights;
// release memory
m_alpha = null;
m_alphaStar = null;
m_kernel = null;
}
m_bModelBuilt = true;
}
/**
* Compute and store statistics required for generating artificial data.
*
* @param data training instances
* @exception Exception if statistics could not be calculated successfully
*/
protected void computeStats(Instances data) throws Exception {
int numAttributes = data.numAttributes();
m_AttributeStats = new Vector(numAttributes); // use to map attributes to their stats
for (int j = 0; j < numAttributes; j++) {
if (data.attribute(j).isNominal()) {
// Compute the probability of occurence of each distinct value
int[] nomCounts = (data.attributeStats(j)).nominalCounts;
double[] counts = new double[nomCounts.length];
if (counts.length < 2)
throw new Exception("Nominal attribute has less than two distinct values!");
// Perform Laplace smoothing
for (int i = 0; i < counts.length; i++) counts[i] = nomCounts[i] + 1;
Utils.normalize(counts);
double[] stats = new double[counts.length - 1];
stats[0] = counts[0];
// Calculate cumulative probabilities
for (int i = 1; i < stats.length; i++) stats[i] = stats[i - 1] + counts[i];
m_AttributeStats.add(j, stats);
} else if (data.attribute(j).isNumeric()) {
// Get mean and standard deviation from the training data
double[] stats = new double[2];
stats[0] = data.meanOrMode(j);
stats[1] = Math.sqrt(data.variance(j));
m_AttributeStats.add(j, stats);
} else System.err.println("Decorate can only handle numeric and nominal values.");
}
}
/**
* 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);
}
/**
* Calculates the distance between two instances
*
* @param test the first instance
* @param train the second instance
* @return the distance between the two given instances, between 0 and 1
*/
protected double distance(Instance first, Instance second) {
double distance = 0;
int firstI, secondI;
for (int p1 = 0, p2 = 0; p1 < first.numValues() || p2 < second.numValues(); ) {
if (p1 >= first.numValues()) {
firstI = m_instances.numAttributes();
} else {
firstI = first.index(p1);
}
if (p2 >= second.numValues()) {
secondI = m_instances.numAttributes();
} else {
secondI = second.index(p2);
}
if (firstI == m_instances.classIndex()) {
p1++;
continue;
}
if (secondI == m_instances.classIndex()) {
p2++;
continue;
}
double diff;
if (firstI == secondI) {
diff = difference(firstI, first.valueSparse(p1), second.valueSparse(p2));
p1++;
p2++;
} else if (firstI > secondI) {
diff = difference(secondI, 0, second.valueSparse(p2));
p2++;
} else {
diff = difference(firstI, first.valueSparse(p1), 0);
p1++;
}
distance += diff * diff;
}
return Math.sqrt(distance / m_instances.numAttributes());
}
/**
* Parses a given list of options.
*
* <p>
* <!-- options-start -->
* Valid options are:
*
* <p>
*
* <pre> -i <the input file>
* The input file</pre>
*
* <pre> -o <the output file>
* The output file</pre>
*
* <pre> -c <the class index>
* The class index</pre>
*
* <!-- options-end -->
*
* @param options the list of options as an array of strings
* @throws Exception if an option is not supported
*/
public void setOptions(String[] options) throws Exception {
String outputString = Utils.getOption('o', options);
String inputString = Utils.getOption('i', options);
String indexString = Utils.getOption('c', options);
ArffLoader loader = new ArffLoader();
resetOptions();
// parse index
int index = -1;
if (indexString.length() != 0) {
if (indexString.equals("first")) index = 0;
else {
if (indexString.equals("last")) index = -1;
else index = Integer.parseInt(indexString);
}
}
if (inputString.length() != 0) {
try {
File input = new File(inputString);
loader.setFile(input);
Instances inst = loader.getDataSet();
if (index == -1) inst.setClassIndex(inst.numAttributes() - 1);
else inst.setClassIndex(index);
setInstances(inst);
} catch (Exception ex) {
throw new IOException(
"No data set loaded. Data set has to be arff format (Reason: " + ex.toString() + ").");
}
} else throw new IOException("No data set to save.");
if (outputString.length() != 0) {
// add appropriate file extension
if (!outputString.endsWith(getFileExtension())) {
if (outputString.lastIndexOf('.') != -1)
outputString =
(outputString.substring(0, outputString.lastIndexOf('.'))) + getFileExtension();
else outputString = outputString + getFileExtension();
}
try {
File output = new File(outputString);
setFile(output);
} catch (Exception ex) {
throw new IOException("Cannot create output file.");
}
}
if (index == -1) index = getInstances().numAttributes() - 1;
getInstances().setClassIndex(index);
}
/**
* Sets the format of the input instances.
*
* @param instanceInfo an Instances object containing the input instance structure (any instances
* contained in the object are ignored - only the structure is required).
* @return true if the outputFormat may be collected immediately
* @throws Exception if the format couldn't be set successfully
*/
public boolean setInputFormat(Instances instanceInfo) throws Exception {
super.setInputFormat(instanceInfo);
m_Insert.setUpper(instanceInfo.numAttributes());
Instances outputFormat = new Instances(instanceInfo, 0);
Attribute newAttribute = null;
switch (m_AttributeType) {
case Attribute.NUMERIC:
newAttribute = new Attribute(m_Name);
break;
case Attribute.NOMINAL:
newAttribute = new Attribute(m_Name, m_Labels);
break;
case Attribute.STRING:
newAttribute = new Attribute(m_Name, (FastVector) null);
break;
case Attribute.DATE:
newAttribute = new Attribute(m_Name, m_DateFormat);
break;
default:
throw new IllegalArgumentException("Unknown attribute type in Add");
}
if ((m_Insert.getIndex() < 0) || (m_Insert.getIndex() > getInputFormat().numAttributes())) {
throw new IllegalArgumentException("Index out of range");
}
outputFormat.insertAttributeAt(newAttribute, m_Insert.getIndex());
setOutputFormat(outputFormat);
// all attributes, except index of added attribute
// (otherwise the length of the input/output indices differ)
Range atts = new Range(m_Insert.getSingleIndex());
atts.setInvert(true);
atts.setUpper(outputFormat.numAttributes() - 1);
initOutputLocators(outputFormat, atts.getSelection());
return true;
}
/**
* Initializes a gain ratio attribute evaluator. Discretizes all attributes that are numeric.
*
* @param data set of instances serving as training data
* @throws Exception if the evaluator has not been generated successfully
*/
public void buildEvaluator(Instances data) throws Exception {
// can evaluator handle data?
getCapabilities().testWithFail(data);
m_trainInstances = data;
m_classIndex = m_trainInstances.classIndex();
m_numAttribs = m_trainInstances.numAttributes();
m_numInstances = m_trainInstances.numInstances();
Discretize disTransform = new Discretize();
disTransform.setUseBetterEncoding(true);
disTransform.setInputFormat(m_trainInstances);
m_trainInstances = Filter.useFilter(m_trainInstances, disTransform);
m_numClasses = m_trainInstances.attribute(m_classIndex).numValues();
}
/**
* Generates a clusterer by the mean of spectral clustering algorithm.
*
* @param data set of instances serving as training data
* @exception Exception if the clusterer has not been generated successfully
*/
public void buildClusterer(Instances data) throws java.lang.Exception {
m_Sequences = new Instances(data);
int n = data.numInstances();
int k = data.numAttributes();
DoubleMatrix2D w;
if (useSparseMatrix) w = DoubleFactory2D.sparse.make(n, n);
else w = DoubleFactory2D.dense.make(n, n);
double[][] v1 = new double[n][];
for (int i = 0; i < n; i++) v1[i] = data.instance(i).toDoubleArray();
v = DoubleFactory2D.dense.make(v1);
double sigma_sq = sigma * sigma;
// Sets up similarity matrix
for (int i = 0; i < n; i++)
for (int j = i; j < n; j++) {
/*double dist = distnorm2(v.viewRow(i), v.viewRow(j));
if((r == -1) || (dist < r)) {
double sim = Math.exp(- (dist * dist) / (2 * sigma_sq));
w.set(i, j, sim);
w.set(j, i, sim);
}*/
/* String [] key = {data.instance(i).stringValue(0), data.instance(j).stringValue(0)};
System.out.println(key[0]);
System.out.println(key[1]);
System.out.println(simScoreMap.containsKey(key));
Double simValue = simScoreMap.get(key);*/
double sim = sim_matrix[i][j];
w.set(i, j, sim);
w.set(j, i, sim);
}
// Partitions points
int[][] p = partition(w, alpha_star);
// Deploys results
numOfClusters = p.length;
cluster = new int[n];
for (int i = 0; i < p.length; i++) for (int j = 0; j < p[i].length; j++) cluster[p[i][j]] = i;
// System.out.println("Final partition:");
// UtilsJS.printMatrix(p);
// System.out.println("Cluster:\n");
// UtilsJS.printArray(cluster);
this.numOfClusters = cluster[Utils.maxIndex(cluster)] + 1;
// System.out.println("Num clusters:\t"+this.numOfClusters);
}
/**
* Prints out the classifier.
*
* @return a description of the classifier as a string
*/
public String toString() {
StringBuffer text = new StringBuffer();
text.append("SMOreg\n\n");
if (m_weights != null) {
text.append("weights (not support vectors):\n");
// it's a linear machine
for (int i = 0; i < m_data.numAttributes(); i++) {
if (i != m_classIndex) {
text.append(
(m_weights[i] >= 0 ? " + " : " - ")
+ Utils.doubleToString(Math.abs(m_weights[i]), 12, 4)
+ " * ");
if (m_SVM.getFilterType().getSelectedTag().getID() == SMOreg.FILTER_STANDARDIZE) {
text.append("(standardized) ");
} else if (m_SVM.getFilterType().getSelectedTag().getID() == SMOreg.FILTER_NORMALIZE) {
text.append("(normalized) ");
}
text.append(m_data.attribute(i).name() + "\n");
}
}
} else {
// non linear, print out all supportvectors
text.append("Support vectors:\n");
for (int i = 0; i < m_nInstances; i++) {
if (m_alpha[i] > 0) {
text.append("+" + m_alpha[i] + " * k[" + i + "]\n");
}
if (m_alphaStar[i] > 0) {
text.append("-" + m_alphaStar[i] + " * k[" + i + "]\n");
}
}
}
text.append((m_b <= 0 ? " + " : " - ") + Utils.doubleToString(Math.abs(m_b), 12, 4) + "\n\n");
text.append("\n\nNumber of kernel evaluations: " + m_nEvals);
if (m_nCacheHits >= 0 && m_nEvals > 0) {
double hitRatio = 1 - m_nEvals * 1.0 / (m_nCacheHits + m_nEvals);
text.append(" (" + Utils.doubleToString(hitRatio * 100, 7, 3).trim() + "% cached)");
}
return text.toString();
}
/**
* 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]);
}
}
}
/**
* Initializes the ranges of a subset of the instances of this dataset. Therefore m_Ranges is not
* set.
*
* @param instList list of indexes of the subset
* @return the ranges
* @throws Exception if something goes wrong
*/
public double[][] initializeRanges(int[] instList) throws Exception {
if (m_Data == null) {
throw new Exception("No instances supplied.");
}
int numAtt = m_Data.numAttributes();
double[][] ranges = new double[numAtt][3];
if (m_Data.numInstances() <= 0) {
initializeRangesEmpty(numAtt, ranges);
return ranges;
} else {
// initialize ranges using the first instance
updateRangesFirst(m_Data.instance(instList[0]), numAtt, ranges);
// update ranges, starting from the second
for (int i = 1; i < instList.length; i++) {
updateRanges(m_Data.instance(instList[i]), numAtt, ranges);
}
}
return ranges;
}
/**
* Generates an attribute evaluator. Has to initialise all fields of the evaluator that are not
* being set via options.
*
* @param data set of instances serving as training data
* @throws Exception if the evaluator has not been generated successfully
*/
public void buildEvaluator(Instances data) throws Exception {
// can evaluator handle data?
getCapabilities().testWithFail(data);
m_trainInstances = new Instances(data);
m_trainInstances.deleteWithMissingClass();
m_numAttribs = m_trainInstances.numAttributes();
m_numInstances = m_trainInstances.numInstances();
// if the data has no decision feature, m_classIndex is negative
m_classIndex = m_trainInstances.classIndex();
// supervised
if (m_classIndex >= 0) {
m_isNumeric = m_trainInstances.attribute(m_classIndex).isNumeric();
if (m_isNumeric) {
m_DecisionSimilarity = m_Similarity;
} else m_DecisionSimilarity = m_SimilarityEq;
}
m_Similarity.setInstances(m_trainInstances);
m_DecisionSimilarity.setInstances(m_trainInstances);
m_SimilarityEq.setInstances(m_trainInstances);
m_composition = m_Similarity.getTNorm();
m_FuzzyMeasure.set(
m_Similarity,
m_DecisionSimilarity,
m_TNorm,
m_composition,
m_Implicator,
m_SNorm,
m_numInstances,
m_numAttribs,
m_classIndex,
m_trainInstances);
}
/**
* return a string describing this clusterer
*
* @return a description of the clusterer as a string
*/
public String toString() {
StringBuffer temp = new StringBuffer();
temp.append("\n FarthestFirst\n==============\n");
temp.append("\nCluster centroids:\n");
for (int i = 0; i < m_NumClusters; i++) {
temp.append("\nCluster " + i + "\n\t");
for (int j = 0; j < m_ClusterCentroids.numAttributes(); j++) {
if (m_ClusterCentroids.attribute(j).isNominal()) {
temp.append(
" "
+ m_ClusterCentroids
.attribute(j)
.value((int) m_ClusterCentroids.instance(i).value(j)));
} else {
temp.append(" " + m_ClusterCentroids.instance(i).value(j));
}
}
}
temp.append("\n\n");
return temp.toString();
}
/**
* ************************************************** Convert a table to a set of instances, with
* <b>columns</b> representing individual </b>instances</b> and <b>rows</b> representing
* <b>attributes</b> (e.g. as is common with microarray data)
*/
public Instances tableColsToInstances(Table t, String relationName) {
System.err.print("Converting table cols to instances...");
// Set up attributes, which for colInstances will be the rowNames...
FastVector atts = new FastVector();
ArrayList<Boolean> isNominal = new ArrayList<Boolean>();
ArrayList<FastVector> allAttVals = new ArrayList<FastVector>(); // Save values for later...
System.err.print("creating attributes...");
for (int r = 0; r < t.numRows; r++) {
if (rowIsNumeric(t, r)) {
isNominal.add(false);
atts.addElement(new Attribute(t.rowNames[r]));
allAttVals.add(null); // No enumeration of attribute values.
} else {
// It's nominal... determine the range of values and create a nominal attribute...
isNominal.add(true);
FastVector attVals = getRowValues(t, r);
atts.addElement(new Attribute(t.rowNames[r], attVals));
// Save it for later
allAttVals.add(attVals);
}
}
System.err.print("creating instances...");
// Create Instances object..
Instances data = new Instances(relationName, atts, 0);
data.setRelationName(relationName);
/** ***** CREATE INSTANCES ************* */
// Fill the instances with data...
// For each instance...
for (int c = 0; c < t.numCols; c++) {
double[] vals =
new double[data.numAttributes()]; // Even nominal values are stored as double pointers.
// For each attribute fill in the numeric or attributeValue index...
for (int r = 0; r < t.numRows; r++) {
String val = (String) t.matrix.getQuick(r, c);
if (val == "?") vals[r] = Instance.missingValue();
else if (isNominal.get(r)) {
vals[r] = allAttVals.get(r).indexOf(val);
} else {
vals[r] = Double.parseDouble((String) val);
}
}
// Add the a newly minted instance with those attribute values...
data.add(new Instance(1.0, vals));
}
System.err.print("add feature names...");
/** ***** ADD FEATURE NAMES ************* */
// takes basically zero time... all time is in previous 2 chunks.
if (addInstanceNamesAsFeatures) {
Instances newData = new Instances(data);
newData.insertAttributeAt(new Attribute("ID", (FastVector) null), 0);
int attrIdx = newData.attribute("ID").index(); // Paranoid... should be 0
// We save the instanceNames in a list because it's handy later on...
instanceNames = new ArrayList<String>();
for (int c = 0; c < t.colNames.length; c++) {
instanceNames.add(t.colNames[c]);
newData.instance(c).setValue(attrIdx, t.colNames[c]);
}
data = newData;
}
System.err.println("done.");
return (data);
}
/**
* Calculates the distance between two instances. Offers speed up (if the distance function class
* in use supports it) in nearest neighbour search by taking into account the cutOff or maximum
* distance. Depending on the distance function class, post processing of the distances by
* postProcessDistances(double []) may be required if this function is used.
*
* @param first the first instance
* @param second the second instance
* @param cutOffValue If the distance being calculated becomes larger than cutOffValue then the
* rest of the calculation is discarded.
* @param stats the performance stats object
* @return the distance between the two given instances or Double.POSITIVE_INFINITY if the
* distance being calculated becomes larger than cutOffValue.
*/
@Override
public double distance(
Instance first, Instance second, double cutOffValue, PerformanceStats stats) {
double distance = 0;
int firstI, secondI;
int firstNumValues = first.numValues();
int secondNumValues = second.numValues();
int numAttributes = m_Data.numAttributes();
int classIndex = m_Data.classIndex();
validate();
for (int p1 = 0, p2 = 0; p1 < firstNumValues || p2 < secondNumValues; ) {
if (p1 >= firstNumValues) {
firstI = numAttributes;
} else {
firstI = first.index(p1);
}
if (p2 >= secondNumValues) {
secondI = numAttributes;
} else {
secondI = second.index(p2);
}
if (firstI == classIndex) {
p1++;
continue;
}
if ((firstI < numAttributes) && !m_ActiveIndices[firstI]) {
p1++;
continue;
}
if (secondI == classIndex) {
p2++;
continue;
}
if ((secondI < numAttributes) && !m_ActiveIndices[secondI]) {
p2++;
continue;
}
double diff;
if (firstI == secondI) {
diff = difference(firstI, first.valueSparse(p1), second.valueSparse(p2));
p1++;
p2++;
} else if (firstI > secondI) {
diff = difference(secondI, 0, second.valueSparse(p2));
p2++;
} else {
diff = difference(firstI, first.valueSparse(p1), 0);
p1++;
}
if (stats != null) {
stats.incrCoordCount();
}
distance = updateDistance(distance, diff);
if (distance > cutOffValue) {
return Double.POSITIVE_INFINITY;
}
}
return distance;
}
/**
* Writes a Batch of instances
*
* @throws IOException throws IOException if saving in batch mode is not possible
*/
public void writeBatch() throws IOException {
Instances instances = getInstances();
if (instances == null) throw new IOException("No instances to save");
if (instances.classIndex() == -1) {
instances.setClassIndex(instances.numAttributes() - 1);
System.err.println("No class specified. Last attribute is used as class attribute.");
}
if (instances.attribute(instances.classIndex()).isNumeric())
throw new IOException("To save in C4.5 format the class attribute cannot be numeric.");
if (getRetrieval() == INCREMENTAL)
throw new IOException("Batch and incremental saving cannot be mixed.");
setRetrieval(BATCH);
if (retrieveFile() == null || getWriter() == null) {
throw new IOException(
"C4.5 format requires two files. Therefore no output to standard out can be generated.\nPlease specifiy output files using the -o option.");
}
setWriteMode(WRITE);
// print names file
setFileExtension(".names");
PrintWriter outW = new PrintWriter(getWriter());
for (int i = 0; i < instances.attribute(instances.classIndex()).numValues(); i++) {
outW.write(instances.attribute(instances.classIndex()).value(i));
if (i < instances.attribute(instances.classIndex()).numValues() - 1) {
outW.write(",");
} else {
outW.write(".\n");
}
}
for (int i = 0; i < instances.numAttributes(); i++) {
if (i != instances.classIndex()) {
outW.write(instances.attribute(i).name() + ": ");
if (instances.attribute(i).isNumeric() || instances.attribute(i).isDate()) {
outW.write("continuous.\n");
} else {
Attribute temp = instances.attribute(i);
for (int j = 0; j < temp.numValues(); j++) {
outW.write(temp.value(j));
if (j < temp.numValues() - 1) {
outW.write(",");
} else {
outW.write(".\n");
}
}
}
}
}
outW.flush();
outW.close();
// print data file
String out = retrieveFile().getAbsolutePath();
setFileExtension(".data");
out = out.substring(0, out.lastIndexOf('.')) + getFileExtension();
File namesFile = new File(out);
try {
setFile(namesFile);
} catch (Exception ex) {
throw new IOException(
"Cannot create data file, only names file created (Reason: " + ex.toString() + ").");
}
if (retrieveFile() == null || getWriter() == null) {
throw new IOException("Cannot create data file, only names file created.");
}
outW = new PrintWriter(getWriter());
// print data file
for (int i = 0; i < instances.numInstances(); i++) {
Instance temp = instances.instance(i);
for (int j = 0; j < temp.numAttributes(); j++) {
if (j != instances.classIndex()) {
if (temp.isMissing(j)) {
outW.write("?,");
} else if (instances.attribute(j).isNominal() || instances.attribute(j).isString()) {
outW.write(instances.attribute(j).value((int) temp.value(j)) + ",");
} else {
outW.write("" + temp.value(j) + ",");
}
}
}
// write the class value
if (temp.isMissing(instances.classIndex())) {
outW.write("?");
} else {
outW.write(
instances
.attribute(instances.classIndex())
.value((int) temp.value(instances.classIndex())));
}
outW.write("\n");
}
outW.flush();
outW.close();
setFileExtension(".names");
setWriteMode(WAIT);
outW = null;
resetWriter();
setWriteMode(CANCEL);
}
/**
* This function fits the rule to the data which it overlaps. This way the rule can only
* interpolate but not extrapolate.
*
* @param instances The data to which the rule shall be fitted
*/
public void fitAndSetCoreBound(Instances instances) {
if (m_Antds == null) return;
boolean[] antExistingForDimension = new boolean[instances.numAttributes() - 1];
for (int i = 0; i < m_Antds.size(); i++) {
antExistingForDimension[((Antd) m_Antds.elementAt(i)).att.index()] = true;
}
FastVector newAntds = new FastVector(10);
// for (int i=0; i < instances.numAttributes()-1; i++){
for (int iterator = 0; iterator < m_Antds.size(); iterator++) {
int i = ((Antd) m_Antds.elementAt(iterator)).getAttr().index();
if (!antExistingForDimension[i]) continue; // Excluding non existant antecedents
Instances instancesWithoutMissingValues = new Instances(instances);
instancesWithoutMissingValues.deleteWithMissing(i);
if (instancesWithoutMissingValues.attribute(i).isNumeric()
&& instancesWithoutMissingValues.numInstances() > 0) {
boolean bag0AntdExists = false;
boolean bag1AntdExists = false;
for (int j = 0; j < m_Antds.size(); j++) {
if (((Antd) m_Antds.elementAt(j)).att.index() == i) {
if (((Antd) m_Antds.elementAt(j)).value == 0) {
bag0AntdExists = true;
} else {
bag1AntdExists = true;
}
newAntds.addElement((Antd) m_Antds.elementAt(j));
}
}
double higherCore = Double.NaN;
double lowerCore = Double.NaN;
if (!bag0AntdExists) {
if (Double.isNaN(higherCore))
higherCore =
instancesWithoutMissingValues.kthSmallestValue(
i, instancesWithoutMissingValues.numInstances());
NumericAntd antd;
antd = new NumericAntd(instancesWithoutMissingValues.attribute(i));
antd.value = 0;
antd.splitPoint = higherCore;
newAntds.addElement(antd);
}
if (!bag1AntdExists) {
if (Double.isNaN(lowerCore))
lowerCore = instancesWithoutMissingValues.kthSmallestValue(i, 1);
NumericAntd antd;
antd = new NumericAntd(instancesWithoutMissingValues.attribute(i));
antd.value = 1;
antd.splitPoint = lowerCore;
newAntds.addElement(antd);
}
} else {
for (int j = 0; j < m_Antds.size(); j++) {
if (((Antd) m_Antds.elementAt(j)).att.index() == i) {
newAntds.addElement(m_Antds.elementAt(j));
}
}
}
}
m_Antds = newAntds;
}
/**
* Saves an instances incrementally. Structure has to be set by using the setStructure() method or
* setInstances() method.
*
* @param inst the instance to save
* @throws IOException throws IOEXception if an instance cannot be saved incrementally.
*/
public void writeIncremental(Instance inst) throws IOException {
int writeMode = getWriteMode();
Instances structure = getInstances();
PrintWriter outW = null;
if (structure != null) {
if (structure.classIndex() == -1) {
structure.setClassIndex(structure.numAttributes() - 1);
System.err.println("No class specified. Last attribute is used as class attribute.");
}
if (structure.attribute(structure.classIndex()).isNumeric())
throw new IOException("To save in C4.5 format the class attribute cannot be numeric.");
}
if (getRetrieval() == BATCH || getRetrieval() == NONE)
throw new IOException("Batch and incremental saving cannot be mixed.");
if (retrieveFile() == null || getWriter() == null) {
throw new IOException(
"C4.5 format requires two files. Therefore no output to standard out can be generated.\nPlease specifiy output files using the -o option.");
}
outW = new PrintWriter(getWriter());
if (writeMode == WAIT) {
if (structure == null) {
setWriteMode(CANCEL);
if (inst != null)
System.err.println("Structure(Header Information) has to be set in advance");
} else setWriteMode(STRUCTURE_READY);
writeMode = getWriteMode();
}
if (writeMode == CANCEL) {
if (outW != null) outW.close();
cancel();
}
if (writeMode == STRUCTURE_READY) {
setWriteMode(WRITE);
// write header: here names file
for (int i = 0; i < structure.attribute(structure.classIndex()).numValues(); i++) {
outW.write(structure.attribute(structure.classIndex()).value(i));
if (i < structure.attribute(structure.classIndex()).numValues() - 1) {
outW.write(",");
} else {
outW.write(".\n");
}
}
for (int i = 0; i < structure.numAttributes(); i++) {
if (i != structure.classIndex()) {
outW.write(structure.attribute(i).name() + ": ");
if (structure.attribute(i).isNumeric() || structure.attribute(i).isDate()) {
outW.write("continuous.\n");
} else {
Attribute temp = structure.attribute(i);
for (int j = 0; j < temp.numValues(); j++) {
outW.write(temp.value(j));
if (j < temp.numValues() - 1) {
outW.write(",");
} else {
outW.write(".\n");
}
}
}
}
}
outW.flush();
outW.close();
writeMode = getWriteMode();
String out = retrieveFile().getAbsolutePath();
setFileExtension(".data");
out = out.substring(0, out.lastIndexOf('.')) + getFileExtension();
File namesFile = new File(out);
try {
setFile(namesFile);
} catch (Exception ex) {
throw new IOException("Cannot create data file, only names file created.");
}
if (retrieveFile() == null || getWriter() == null) {
throw new IOException("Cannot create data file, only names file created.");
}
outW = new PrintWriter(getWriter());
}
if (writeMode == WRITE) {
if (structure == null) throw new IOException("No instances information available.");
if (inst != null) {
// write instance: here data file
for (int j = 0; j < inst.numAttributes(); j++) {
if (j != structure.classIndex()) {
if (inst.isMissing(j)) {
outW.write("?,");
} else if (structure.attribute(j).isNominal() || structure.attribute(j).isString()) {
outW.write(structure.attribute(j).value((int) inst.value(j)) + ",");
} else {
outW.write("" + inst.value(j) + ",");
}
}
}
// write the class value
if (inst.isMissing(structure.classIndex())) {
outW.write("?");
} else {
outW.write(
structure
.attribute(structure.classIndex())
.value((int) inst.value(structure.classIndex())));
}
outW.write("\n");
// flushes every 100 instances
m_incrementalCounter++;
if (m_incrementalCounter > 100) {
m_incrementalCounter = 0;
outW.flush();
}
} else {
// close
if (outW != null) {
outW.flush();
outW.close();
}
setFileExtension(".names");
m_incrementalCounter = 0;
resetStructure();
outW = null;
resetWriter();
}
}
}
/**
* Tests a certain range of attributes of the given data, whether it can be processed by the
* handler, given its capabilities. Classifiers implementing the <code>
* MultiInstanceCapabilitiesHandler</code> interface are checked automatically for their
* multi-instance Capabilities (if no bags, then only the bag-structure, otherwise only the first
* bag).
*
* @param data the data to test
* @param fromIndex the range of attributes - start (incl.)
* @param toIndex the range of attributes - end (incl.)
* @return true if all the tests succeeded
* @see MultiInstanceCapabilitiesHandler
* @see #m_InstancesTest
* @see #m_MissingValuesTest
* @see #m_MissingClassValuesTest
* @see #m_MinimumNumberInstancesTest
*/
public boolean test(Instances data, int fromIndex, int toIndex) {
int i;
int n;
int m;
Attribute att;
Instance inst;
boolean testClass;
Capabilities cap;
boolean missing;
Iterator iter;
// shall we test the data?
if (!m_InstancesTest) return true;
// no Capabilities? -> warning
if ((m_Capabilities.size() == 0)
|| ((m_Capabilities.size() == 1) && handles(Capability.NO_CLASS)))
System.err.println(createMessage("No capabilities set!"));
// any attributes?
if (toIndex - fromIndex < 0) {
m_FailReason = new WekaException(createMessage("No attributes!"));
return false;
}
// do wee need to test the class attribute, i.e., is the class attribute
// within the range of attributes?
testClass =
(data.classIndex() > -1)
&& (data.classIndex() >= fromIndex)
&& (data.classIndex() <= toIndex);
// attributes
for (i = fromIndex; i <= toIndex; i++) {
att = data.attribute(i);
// class is handled separately
if (i == data.classIndex()) continue;
// check attribute types
if (!test(att)) return false;
}
// class
if (!handles(Capability.NO_CLASS) && (data.classIndex() == -1)) {
m_FailReason = new UnassignedClassException(createMessage("Class attribute not set!"));
return false;
}
// special case: no class attribute can be handled
if (handles(Capability.NO_CLASS) && (data.classIndex() > -1)) {
cap = getClassCapabilities();
cap.disable(Capability.NO_CLASS);
iter = cap.capabilities();
if (!iter.hasNext()) {
m_FailReason = new WekaException(createMessage("Cannot handle any class attribute!"));
return false;
}
}
if (testClass && !handles(Capability.NO_CLASS)) {
att = data.classAttribute();
if (!test(att, true)) return false;
// special handling of RELATIONAL class
// TODO: store additional Capabilities for this case
// missing class labels
if (m_MissingClassValuesTest) {
if (!handles(Capability.MISSING_CLASS_VALUES)) {
for (i = 0; i < data.numInstances(); i++) {
if (data.instance(i).classIsMissing()) {
m_FailReason =
new WekaException(createMessage("Cannot handle missing class values!"));
return false;
}
}
} else {
if (m_MinimumNumberInstancesTest) {
int hasClass = 0;
for (i = 0; i < data.numInstances(); i++) {
if (!data.instance(i).classIsMissing()) hasClass++;
}
// not enough instances with class labels?
if (hasClass < getMinimumNumberInstances()) {
m_FailReason =
new WekaException(
createMessage(
"Not enough training instances with class labels (required: "
+ getMinimumNumberInstances()
+ ", provided: "
+ hasClass
+ ")!"));
return false;
}
}
}
}
}
// missing values
if (m_MissingValuesTest) {
if (!handles(Capability.MISSING_VALUES)) {
missing = false;
for (i = 0; i < data.numInstances(); i++) {
inst = data.instance(i);
if (inst instanceof SparseInstance) {
for (m = 0; m < inst.numValues(); m++) {
n = inst.index(m);
// out of scope?
if (n < fromIndex) continue;
if (n > toIndex) break;
// skip class
if (n == inst.classIndex()) continue;
if (inst.isMissing(n)) {
missing = true;
break;
}
}
} else {
for (n = fromIndex; n <= toIndex; n++) {
// skip class
if (n == inst.classIndex()) continue;
if (inst.isMissing(n)) {
missing = true;
break;
}
}
}
if (missing) {
m_FailReason =
new NoSupportForMissingValuesException(
createMessage("Cannot handle missing values!"));
return false;
}
}
}
}
// instances
if (m_MinimumNumberInstancesTest) {
if (data.numInstances() < getMinimumNumberInstances()) {
m_FailReason =
new WekaException(
createMessage(
"Not enough training instances (required: "
+ getMinimumNumberInstances()
+ ", provided: "
+ data.numInstances()
+ ")!"));
return false;
}
}
// Multi-Instance? -> check structure (regardless of attribute range!)
if (handles(Capability.ONLY_MULTIINSTANCE)) {
// number of attributes?
if (data.numAttributes() != 3) {
m_FailReason =
new WekaException(
createMessage("Incorrect Multi-Instance format, must be 'bag-id, bag, class'!"));
return false;
}
// type of attributes and position of class?
if (!data.attribute(0).isNominal()
|| !data.attribute(1).isRelationValued()
|| (data.classIndex() != data.numAttributes() - 1)) {
m_FailReason =
new WekaException(
createMessage(
"Incorrect Multi-Instance format, must be 'NOMINAL att, RELATIONAL att, CLASS att'!"));
return false;
}
// check data immediately
if (getOwner() instanceof MultiInstanceCapabilitiesHandler) {
MultiInstanceCapabilitiesHandler handler = (MultiInstanceCapabilitiesHandler) getOwner();
cap = handler.getMultiInstanceCapabilities();
boolean result;
if (data.numInstances() > 0) result = cap.test(data.attribute(1).relation(0));
else result = cap.test(data.attribute(1).relation());
if (!result) {
m_FailReason = cap.m_FailReason;
return false;
}
}
}
// passed all tests!
return true;
}
/**
* Tests the given data, whether it can be processed by the handler, given its capabilities.
* Classifiers implementing the <code>MultiInstanceCapabilitiesHandler</code> interface are
* checked automatically for their multi-instance Capabilities (if no bags, then only the
* bag-structure, otherwise only the first bag).
*
* @param data the data to test
* @return true if all the tests succeeded
* @see #test(Instances, int, int)
*/
public boolean test(Instances data) {
return test(data, 0, data.numAttributes() - 1);
}
/**
* returns a Capabilities object specific for this data. The minimum number of instances is not
* set, the check for multi-instance data is optional.
*
* @param data the data to base the capabilities on
* @param multi if true then the structure is checked, too
* @return a data-specific capabilities object
* @throws Exception in case an error occurrs, e.g., an unknown attribute type
*/
public static Capabilities forInstances(Instances data, boolean multi) throws Exception {
Capabilities result;
Capabilities multiInstance;
int i;
int n;
int m;
Instance inst;
boolean missing;
result = new Capabilities(null);
// class
if (data.classIndex() == -1) {
result.enable(Capability.NO_CLASS);
} else {
switch (data.classAttribute().type()) {
case Attribute.NOMINAL:
if (data.classAttribute().numValues() == 1) result.enable(Capability.UNARY_CLASS);
else if (data.classAttribute().numValues() == 2) result.enable(Capability.BINARY_CLASS);
else result.enable(Capability.NOMINAL_CLASS);
break;
case Attribute.NUMERIC:
result.enable(Capability.NUMERIC_CLASS);
break;
case Attribute.STRING:
result.enable(Capability.STRING_CLASS);
break;
case Attribute.DATE:
result.enable(Capability.DATE_CLASS);
break;
case Attribute.RELATIONAL:
result.enable(Capability.RELATIONAL_CLASS);
break;
default:
throw new UnsupportedAttributeTypeException(
"Unknown class attribute type '" + data.classAttribute() + "'!");
}
// missing class values
for (i = 0; i < data.numInstances(); i++) {
if (data.instance(i).classIsMissing()) {
result.enable(Capability.MISSING_CLASS_VALUES);
break;
}
}
}
// attributes
for (i = 0; i < data.numAttributes(); i++) {
// skip class
if (i == data.classIndex()) continue;
switch (data.attribute(i).type()) {
case Attribute.NOMINAL:
result.enable(Capability.UNARY_ATTRIBUTES);
if (data.attribute(i).numValues() == 2) result.enable(Capability.BINARY_ATTRIBUTES);
else if (data.attribute(i).numValues() > 2) result.enable(Capability.NOMINAL_ATTRIBUTES);
break;
case Attribute.NUMERIC:
result.enable(Capability.NUMERIC_ATTRIBUTES);
break;
case Attribute.DATE:
result.enable(Capability.DATE_ATTRIBUTES);
break;
case Attribute.STRING:
result.enable(Capability.STRING_ATTRIBUTES);
break;
case Attribute.RELATIONAL:
result.enable(Capability.RELATIONAL_ATTRIBUTES);
break;
default:
throw new UnsupportedAttributeTypeException(
"Unknown attribute type '" + data.attribute(i).type() + "'!");
}
}
// missing values
missing = false;
for (i = 0; i < data.numInstances(); i++) {
inst = data.instance(i);
if (inst instanceof SparseInstance) {
for (m = 0; m < inst.numValues(); m++) {
n = inst.index(m);
// skip class
if (n == inst.classIndex()) continue;
if (inst.isMissing(n)) {
missing = true;
break;
}
}
} else {
for (n = 0; n < data.numAttributes(); n++) {
// skip class
if (n == inst.classIndex()) continue;
if (inst.isMissing(n)) {
missing = true;
break;
}
}
}
if (missing) {
result.enable(Capability.MISSING_VALUES);
break;
}
}
// multi-instance data?
if (multi) {
if ((data.numAttributes() == 3)
&& (data.attribute(0).isNominal()) // bag-id
&& (data.attribute(1).isRelationValued()) // bag
&& (data.classIndex() == data.numAttributes() - 1)) {
multiInstance = new Capabilities(null);
multiInstance.or(result.getClassCapabilities());
multiInstance.enable(Capability.NOMINAL_ATTRIBUTES);
multiInstance.enable(Capability.RELATIONAL_ATTRIBUTES);
multiInstance.enable(Capability.ONLY_MULTIINSTANCE);
result.assign(multiInstance);
}
}
return result;
}
public void buildClassifier(Instances insts) throws Exception {
// Compute mean of target value
double yMean = insts.meanOrMode(insts.classIndex());
// Choose best attribute
double minMsq = Double.MAX_VALUE;
m_attribute = null;
int chosen = -1;
double chosenSlope = Double.NaN;
double chosenIntercept = Double.NaN;
for (int i = 0; i < insts.numAttributes(); i++) {
if (i != insts.classIndex()) {
if (!insts.attribute(i).isNumeric()) {
throw new Exception("UnivariateLinearRegression: Only numeric attributes!");
}
m_attribute = insts.attribute(i);
// Compute slope and intercept
double xMean = insts.meanOrMode(i);
double sumWeightedXDiffSquared = 0;
double sumWeightedYDiffSquared = 0;
m_slope = 0;
for (int j = 0; j < insts.numInstances(); j++) {
Instance inst = insts.instance(j);
if (!inst.isMissing(i) && !inst.classIsMissing()) {
double xDiff = inst.value(i) - xMean;
double yDiff = inst.classValue() - yMean;
double weightedXDiff = inst.weight() * xDiff;
double weightedYDiff = inst.weight() * yDiff;
m_slope += weightedXDiff * yDiff;
sumWeightedXDiffSquared += weightedXDiff * xDiff;
sumWeightedYDiffSquared += weightedYDiff * yDiff;
}
}
// Skip attribute if not useful
if (sumWeightedXDiffSquared == 0) {
continue;
}
double numerator = m_slope;
m_slope /= sumWeightedXDiffSquared;
m_intercept = yMean - m_slope * xMean;
// Compute sum of squared errors
double msq = sumWeightedYDiffSquared - m_slope * numerator;
// Check whether this is the best attribute
if (msq < minMsq) {
minMsq = msq;
chosen = i;
chosenSlope = m_slope;
chosenIntercept = m_intercept;
}
}
}
// Set parameters
if (chosen == -1) {
System.err.println("----- no useful attribute found");
m_attribute = null;
m_slope = 0;
m_intercept = yMean;
} else {
m_attribute = insts.attribute(chosen);
m_slope = chosenSlope;
m_intercept = chosenIntercept;
}
}
/**
* Ranks attributes using the specified attribute evaluator and then searches the ranking using
* the supplied subset evaluator.
*
* @param ASEval the subset evaluator to guide the search
* @param data the training instances.
* @return an array (not necessarily ordered) of selected attribute indexes
* @throws Exception if the search can't be completed
*/
public int[] search(ASEvaluation ASEval, Instances data) throws Exception {
double best_merit = -Double.MAX_VALUE;
double temp_merit;
BitSet temp_group, best_group = null;
if (!(ASEval instanceof SubsetEvaluator)) {
throw new Exception(ASEval.getClass().getName() + " is not a " + "Subset evaluator!");
}
m_SubsetEval = ASEval;
m_Instances = data;
m_numAttribs = m_Instances.numAttributes();
/* if (m_ASEval instanceof AttributeTransformer) {
throw new Exception("Can't use an attribute transformer "
+"with RankSearch");
} */
if (m_ASEval instanceof UnsupervisedAttributeEvaluator
|| m_ASEval instanceof UnsupervisedSubsetEvaluator) {
m_hasClass = false;
/* if (!(m_SubsetEval instanceof UnsupervisedSubsetEvaluator)) {
throw new Exception("Must use an unsupervised subset evaluator.");
} */
} else {
m_hasClass = true;
m_classIndex = m_Instances.classIndex();
}
if (m_ASEval instanceof AttributeEvaluator) {
// generate the attribute ranking first
Ranker ranker = new Ranker();
m_ASEval.buildEvaluator(m_Instances);
if (m_ASEval instanceof AttributeTransformer) {
// get the transformed data a rebuild the subset evaluator
m_Instances = ((AttributeTransformer) m_ASEval).transformedData(m_Instances);
((ASEvaluation) m_SubsetEval).buildEvaluator(m_Instances);
}
m_Ranking = ranker.search(m_ASEval, m_Instances);
} else {
GreedyStepwise fs = new GreedyStepwise();
double[][] rankres;
fs.setGenerateRanking(true);
((ASEvaluation) m_ASEval).buildEvaluator(m_Instances);
fs.search(m_ASEval, m_Instances);
rankres = fs.rankedAttributes();
m_Ranking = new int[rankres.length];
for (int i = 0; i < rankres.length; i++) {
m_Ranking[i] = (int) rankres[i][0];
}
}
// now evaluate the attribute ranking
for (int i = m_startPoint; i < m_Ranking.length; i += m_add) {
temp_group = new BitSet(m_numAttribs);
for (int j = 0; j <= i; j++) {
temp_group.set(m_Ranking[j]);
}
temp_merit = ((SubsetEvaluator) m_SubsetEval).evaluateSubset(temp_group);
if (temp_merit > best_merit) {
best_merit = temp_merit;
;
best_group = temp_group;
}
}
m_bestMerit = best_merit;
return attributeList(best_group);
}
/**
* Build one rule using the growing data
*
* @param data the growing data used to build the rule
* @throws Exception if the consequent is not set yet
*/
public void grow(Instances data) throws Exception {
if (m_Consequent == -1) throw new Exception(" Consequent not set yet.");
Instances growData = data;
double sumOfWeights = growData.sumOfWeights();
if (!Utils.gr(sumOfWeights, 0.0)) return;
/* Compute the default accurate rate of the growing data */
double defAccu = computeDefAccu(growData);
double defAcRt = (defAccu + 1.0) / (sumOfWeights + 1.0);
/* Keep the record of which attributes have already been used*/
boolean[] used = new boolean[growData.numAttributes()];
for (int k = 0; k < used.length; k++) used[k] = false;
int numUnused = used.length;
// If there are already antecedents existing
for (int j = 0; j < m_Antds.size(); j++) {
Antd antdj = (Antd) m_Antds.elementAt(j);
if (!antdj.getAttr().isNumeric()) {
used[antdj.getAttr().index()] = true;
numUnused--;
}
}
double maxInfoGain;
while (Utils.gr(growData.numInstances(), 0.0) && (numUnused > 0) && Utils.sm(defAcRt, 1.0)) {
// We require that infoGain be positive
/*if(numAntds == originalSize)
maxInfoGain = 0.0; // At least one condition allowed
else
maxInfoGain = Utils.eq(defAcRt, 1.0) ?
defAccu/(double)numAntds : 0.0; */
maxInfoGain = 0.0;
/* Build a list of antecedents */
Antd oneAntd = null;
Instances coverData = null;
Enumeration enumAttr = growData.enumerateAttributes();
/* Build one condition based on all attributes not used yet*/
while (enumAttr.hasMoreElements()) {
AttributeWeka att = (AttributeWeka) (enumAttr.nextElement());
if (m_Debug) System.err.println("\nOne condition: size = " + growData.sumOfWeights());
Antd antd = null;
if (att.isNumeric()) antd = new NumericAntd(att);
else antd = new NominalAntd(att);
if (!used[att.index()]) {
/* Compute the best information gain for each attribute,
it's stored in the antecedent formed by this attribute.
This procedure returns the data covered by the antecedent*/
Instances coveredData = computeInfoGain(growData, defAcRt, antd);
if (coveredData != null) {
double infoGain = antd.getMaxInfoGain();
if (m_Debug)
System.err.println(
"Test of \'"
+ antd.toString()
+ "\': infoGain = "
+ infoGain
+ " | Accuracy = "
+ antd.getAccuRate()
+ "="
+ antd.getAccu()
+ "/"
+ antd.getCover()
+ " def. accuracy: "
+ defAcRt);
if (infoGain > maxInfoGain) {
oneAntd = antd;
coverData = coveredData;
maxInfoGain = infoGain;
}
}
}
}
if (oneAntd == null) break; // Cannot find antds
if (Utils.sm(oneAntd.getAccu(), m_MinNo)) break; // Too low coverage
// Numeric attributes can be used more than once
if (!oneAntd.getAttr().isNumeric()) {
used[oneAntd.getAttr().index()] = true;
numUnused--;
}
m_Antds.addElement(oneAntd);
growData = coverData; // Grow data size is shrinking
defAcRt = oneAntd.getAccuRate();
}
}
