/**
* 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.");
}
}
/**
* 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;
}
/**
* 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;
}
/**
* GetKs - return [K_1,K_2,...,K_L] where each Y_j \in {1,...,K_j}. In the multi-label case, K[j]
* = 2 for all j = 1,...,L.
*
* @param D a dataset
* @return an array of the number of values that each label can take
*/
private static int[] getKs(Instances D) {
int L = D.classIndex();
int K[] = new int[L];
for (int k = 0; k < L; k++) {
K[k] = D.attribute(k).numValues();
}
return K;
}
/**
* Processes the given data (may change the provided dataset) and returns the modified version.
* This method is called in batchFinished().
*
* @param instances the data to process
* @return the modified data
* @throws Exception in case the processing goes wrong
* @see #batchFinished()
*/
protected Instances process(Instances instances) throws Exception {
Instances result;
int i;
int n;
double[] values;
String value;
Instance inst;
Instance newInst;
// we need the complete input data!
if (!isFirstBatchDone()) setOutputFormat(determineOutputFormat(getInputFormat()));
result = new Instances(getOutputFormat());
for (i = 0; i < instances.numInstances(); i++) {
inst = instances.instance(i);
values = inst.toDoubleArray();
for (n = 0; n < values.length; n++) {
if (!m_Cols.isInRange(n) || !instances.attribute(n).isNumeric() || inst.isMissing(n))
continue;
// get index of value
if (instances.attribute(n).type() == Attribute.DATE) value = inst.stringValue(n);
else value = Utils.doubleToString(inst.value(n), MAX_DECIMALS);
values[n] = result.attribute(n).indexOfValue(value);
}
// generate new instance
if (inst instanceof SparseInstance) newInst = new SparseInstance(inst.weight(), values);
else newInst = new DenseInstance(inst.weight(), values);
// copy possible string, relational values
newInst.setDataset(getOutputFormat());
copyValues(newInst, false, inst.dataset(), getOutputFormat());
result.add(newInst);
}
return result;
}
/**
* 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();
}
/**
* 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();
}
/**
* Computes the difference between two given attribute values.
*
* @param index the attribute index
* @param val1 the first value
* @param val2 the second value
* @return the difference
*/
protected double difference(int index, double val1, double val2) {
switch (m_Data.attribute(index).type()) {
case Attribute.NOMINAL:
if (Utils.isMissingValue(val1)
|| Utils.isMissingValue(val2)
|| ((int) val1 != (int) val2)) {
return 1;
} else {
return 0;
}
case Attribute.NUMERIC:
if (Utils.isMissingValue(val1) || Utils.isMissingValue(val2)) {
if (Utils.isMissingValue(val1) && Utils.isMissingValue(val2)) {
if (!m_DontNormalize) {
return 1;
} else {
return (m_Ranges[index][R_MAX] - m_Ranges[index][R_MIN]);
}
} else {
double diff;
if (Utils.isMissingValue(val2)) {
diff = (!m_DontNormalize) ? norm(val1, index) : val1;
} else {
diff = (!m_DontNormalize) ? norm(val2, index) : val2;
}
if (!m_DontNormalize && diff < 0.5) {
diff = 1.0 - diff;
} else if (m_DontNormalize) {
if ((m_Ranges[index][R_MAX] - diff) > (diff - m_Ranges[index][R_MIN])) {
return m_Ranges[index][R_MAX] - diff;
} else {
return diff - m_Ranges[index][R_MIN];
}
}
return diff;
}
} else {
return (!m_DontNormalize) ? (norm(val1, index) - norm(val2, index)) : (val1 - val2);
}
default:
return 0;
}
}
/**
* 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]);
}
}
}
/**
* 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);
}
/**
* returns a description of the search as a String
*
* @return a description of the search
*/
public String toString() {
StringBuffer text = new StringBuffer();
text.append("\tRankSearch :\n");
text.append("\tAttribute evaluator : " + getAttributeEvaluator().getClass().getName() + " ");
if (m_ASEval instanceof OptionHandler) {
String[] evaluatorOptions = new String[0];
evaluatorOptions = ((OptionHandler) m_ASEval).getOptions();
for (int i = 0; i < evaluatorOptions.length; i++) {
text.append(evaluatorOptions[i] + ' ');
}
}
text.append("\n");
text.append("\tAttribute ranking : \n");
int rlength = (int) (Math.log(m_Ranking.length) / Math.log(10) + 1);
for (int i = 0; i < m_Ranking.length; i++) {
text.append(
"\t "
+ Utils.doubleToString((double) (m_Ranking[i] + 1), rlength, 0)
+ " "
+ m_Instances.attribute(m_Ranking[i]).name()
+ '\n');
}
text.append("\tMerit of best subset found : ");
int fieldwidth = 3;
double precision = (m_bestMerit - (int) m_bestMerit);
if (Math.abs(m_bestMerit) > 0) {
fieldwidth = (int) Math.abs((Math.log(Math.abs(m_bestMerit)) / Math.log(10))) + 2;
}
if (Math.abs(precision) > 0) {
precision = Math.abs((Math.log(Math.abs(precision)) / Math.log(10))) + 3;
} else {
precision = 2;
}
text.append(
Utils.doubleToString(Math.abs(m_bestMerit), fieldwidth + (int) precision, (int) precision)
+ "\n");
return text.toString();
}
/** Computes the difference between two given attribute values. */
protected double difference(int index, double val1, double val2) {
switch (m_instances.attribute(index).type()) {
case Attribute.NOMINAL:
// If attribute is nominal
if (Instance.isMissingValue(val1)
|| Instance.isMissingValue(val2)
|| ((int) val1 != (int) val2)) {
return 1;
} else {
return 0;
}
case Attribute.NUMERIC:
// If attribute is numeric
if (Instance.isMissingValue(val1) || Instance.isMissingValue(val2)) {
if (Instance.isMissingValue(val1) && Instance.isMissingValue(val2)) {
return 1;
} else {
double diff;
if (Instance.isMissingValue(val2)) {
diff = norm(val1, index);
} else {
diff = norm(val2, index);
}
if (diff < 0.5) {
diff = 1.0 - diff;
}
return diff;
}
} else {
return norm(val1, index) - norm(val2, index);
}
default:
return 0;
}
}
/**
* Returns a description of the classifier.
*
* @return a description of the classifier as a string.
*/
public String toString() {
if (m_entries == null) {
return "Decision Table: No model built yet.";
} else {
StringBuffer text = new StringBuffer();
text.append(
"Decision Table:"
+ "\n\nNumber of training instances: "
+ m_numInstances
+ "\nNumber of Rules : "
+ m_entries.size()
+ "\n");
if (m_useIBk) {
text.append("Non matches covered by IB1.\n");
} else {
text.append("Non matches covered by Majority class.\n");
}
text.append(m_search.toString());
/*text.append("Best first search for feature set,\nterminated after "+
m_maxStale+" non improving subsets.\n"); */
text.append("Evaluation (for feature selection): CV ");
if (m_CVFolds > 1) {
text.append("(" + m_CVFolds + " fold) ");
} else {
text.append("(leave one out) ");
}
text.append("\nFeature set: " + printFeatures());
if (m_displayRules) {
// find out the max column width
int maxColWidth = 0;
for (int i = 0; i < m_dtInstances.numAttributes(); i++) {
if (m_dtInstances.attribute(i).name().length() > maxColWidth) {
maxColWidth = m_dtInstances.attribute(i).name().length();
}
if (m_classIsNominal || (i != m_dtInstances.classIndex())) {
Enumeration e = m_dtInstances.attribute(i).enumerateValues();
while (e.hasMoreElements()) {
String ss = (String) e.nextElement();
if (ss.length() > maxColWidth) {
maxColWidth = ss.length();
}
}
}
}
text.append("\n\nRules:\n");
StringBuffer tm = new StringBuffer();
for (int i = 0; i < m_dtInstances.numAttributes(); i++) {
if (m_dtInstances.classIndex() != i) {
int d = maxColWidth - m_dtInstances.attribute(i).name().length();
tm.append(m_dtInstances.attribute(i).name());
for (int j = 0; j < d + 1; j++) {
tm.append(" ");
}
}
}
tm.append(m_dtInstances.attribute(m_dtInstances.classIndex()).name() + " ");
for (int i = 0; i < tm.length() + 10; i++) {
text.append("=");
}
text.append("\n");
text.append(tm);
text.append("\n");
for (int i = 0; i < tm.length() + 10; i++) {
text.append("=");
}
text.append("\n");
Enumeration e = m_entries.keys();
while (e.hasMoreElements()) {
DecisionTableHashKey tt = (DecisionTableHashKey) e.nextElement();
text.append(tt.toString(m_dtInstances, maxColWidth));
double[] ClassDist = (double[]) m_entries.get(tt);
if (m_classIsNominal) {
int m = Utils.maxIndex(ClassDist);
try {
text.append(m_dtInstances.classAttribute().value(m) + "\n");
} catch (Exception ee) {
System.out.println(ee.getMessage());
}
} else {
text.append((ClassDist[0] / ClassDist[1]) + "\n");
}
}
for (int i = 0; i < tm.length() + 10; i++) {
text.append("=");
}
text.append("\n");
text.append("\n");
}
return text.toString();
}
}
/**
* If we know in advance that the table is numeric, can optimize a lot... For example, on 9803 x
* 294 table, TableFileLoader.readNumeric takes 6s compared to 12s for WekaMine readFromTable.
*/
public static Instances readNumeric(String fileName, String relationName, String delimiter)
throws Exception {
int numAttributes = FileUtils.fastCountLines(fileName) - 1; // -1 exclude heading.
String[] attrNames = new String[numAttributes];
// Read the col headings and figure out the number of columns in the table..
BufferedReader reader = new BufferedReader(new FileReader(fileName), 4194304);
String line = reader.readLine();
String[] instanceNames = parseColNames(line, delimiter);
int numInstances = instanceNames.length;
System.err.print("reading " + numAttributes + " x " + numInstances + " table..");
// Create an array to hold the data as we read it in...
double dataArray[][] = new double[numAttributes][numInstances];
// Populate the matrix with values...
String valToken = "";
try {
int rowIdx = 0;
while ((line = reader.readLine()) != null) {
String[] tokens = line.split(delimiter, -1);
attrNames[rowIdx] = tokens[0].trim();
for (int colIdx = 0; colIdx < (tokens.length - 1); colIdx++) {
valToken = tokens[colIdx + 1];
double value;
if (valToken.equals("null")) {
value = Instance.missingValue();
} else if (valToken.equals("?")) {
value = Instance.missingValue();
} else if (valToken.equals("NA")) {
value = Instance.missingValue();
} else if (valToken.equals("")) {
value = Instance.missingValue();
// }else value = DoubleParser.lightningParse(valToken); // faster double parser with
// MANY assumptions
} else value = Double.parseDouble(valToken);
dataArray[rowIdx][colIdx] = value;
}
rowIdx++;
}
} catch (NumberFormatException e) {
System.err.println(e.toString());
System.err.println("Parsing line: " + line);
System.err.println("Parsing token: " + valToken);
}
// Set up attributes, which for colInstances will be the rowNames...
FastVector atts = new FastVector();
for (int a = 0; a < numAttributes; a++) {
atts.addElement(new Attribute(attrNames[a]));
}
// Create Instances object..
Instances data = new Instances(relationName, atts, 0);
data.setRelationName(relationName);
System.err.print("creating instances..");
// System.err.println("DEBUG: numAttributes "+numAttributes);
/** ***** CREATE INSTANCES ************* */
// Fill the instances with data...
// For each instance...
for (int c = 0; c < numInstances; c++) {
double[] vals =
new double[data.numAttributes()]; // Even nominal values are stored as double pointers.
for (int r = 0; r < numAttributes; r++) {
double val = dataArray[r][c];
vals[r] = val;
}
// Add the a newly minted instance with those attribute values...
data.add(new Instance(1.0, vals));
}
// System.err.println("DEBUG: data.numInstances: "+data.numInstances());
// System.err.println("DEBUG: data.numAttributes: "+data.numAttributes());
// System.err.println("DEBUG: data.relationNAme"+data.relationName());
System.err.print("add feature names..");
/** ***** ADD FEATURE NAMES ************* */
// takes basically zero time... all time is in previous 2 chunks.
Instances newData = new Instances(data);
newData.insertAttributeAt(new Attribute("ID", (FastVector) null), 0);
int attrIdx = newData.attribute("ID").index(); // Paranoid... should be 0
for (int c = 0; c < numInstances; c++) {
newData.instance(c).setValue(attrIdx, instanceNames[c]);
}
data = newData;
// System.err.println("DEBUG: data.numInstances: "+data.numInstances());
// System.err.println("DEBUG: data.numAttributes: "+data.numAttributes());
return (data);
}
/**
* ************************************************** Convert a table to a set of instances, with
* <b>rows</b> representing individual </b>instances</b> and <b>columns</b> representing
* <b>attributes</b>
*/
public Instances tableRowsToNominalInstances(Table t, String relationName) {
System.err.print("Converting table rows to instances...");
// Set up attributes, which for rowInstances will be the colNames...
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 c = 0; c < t.numCols; c++) {
// It's nominal... determine the range of values
isNominal.add(true);
FastVector attVals = getColValues(t, c);
atts.addElement(new Attribute(t.colNames[c], 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);
// Fill the instances with data...
// For each instance...
for (int r = 0; r < t.numRows; r++) {
double[] vals = new double[data.numAttributes()];
// for each attribute
for (int c = 0; c < t.numCols; c++) {
String val = (String) t.matrix.getQuick(r, c);
if (val == "?") vals[c] = Instance.missingValue();
else if (isNominal.get(c)) {
vals[c] = allAttVals.get(c).indexOf(val);
} else {
vals[c] = 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...");
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 r = 0; r < t.rowNames.length; r++) {
instanceNames.add(t.rowNames[r]);
newData.instance(r).setValue(attrIdx, t.rowNames[r]);
}
data = newData;
}
System.err.println("done.");
return (data);
}
/**
* ************************************************** 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);
}
/**
* 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);
}
/**
* 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;
}
/**
* 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;
}
}
/**
* Gets the string describing the attributes the split depends on. i.e. the left hand side of the
* description of the split.
*
* @param dataset the dataset that the split is based on
* @return a string describing the attributes
*/
public String attributeString(Instances dataset) {
return dataset.attribute(attIndex).name();
}
public void findAndSetSupportBoundForKnownAntecedents(
Instances thisClassifiersExtension, boolean allWeightsAreOne) {
if (m_Antds == null) return;
double maxPurity = Double.NEGATIVE_INFINITY;
boolean[] finishedAntecedents = new boolean[m_Antds.size()];
int numFinishedAntecedents = 0;
while (numFinishedAntecedents < m_Antds.size()) {
double maxPurityOfAllAntecedents = Double.NEGATIVE_INFINITY;
int bestAntecedentsIndex = -1;
double bestSupportBoundForAllAntecedents = Double.NaN;
Instances ext = new Instances(thisClassifiersExtension, 0);
for (int j = 0; j < m_Antds.size(); j++) {
if (finishedAntecedents[j]) continue;
ext = new Instances(thisClassifiersExtension);
/*
* Remove instances which are not relevant, because they are not covered
* by the _other_ antecedents.
*/
for (int k = 0; k < m_Antds.size(); k++) {
if (k == j) continue;
Antd exclusionAntd = ((Antd) m_Antds.elementAt(k));
for (int y = 0; y < ext.numInstances(); y++) {
if (exclusionAntd.covers(ext.instance(y)) == 0) {
ext.delete(y--);
}
}
}
if (ext.attribute(((Antd) m_Antds.elementAt(j)).att.index()).isNumeric()
&& ext.numInstances() > 0) {
NumericAntd currentAntd = (NumericAntd) ((NumericAntd) m_Antds.elementAt(j)).copy();
currentAntd.fuzzyYet = true;
ext.deleteWithMissing(currentAntd.att.index());
double sumOfWeights = ext.sumOfWeights();
if (!Utils.gr(sumOfWeights, 0.0)) return;
ext.sort(currentAntd.att.index());
double maxPurityForThisAntecedent = 0;
double bestFoundSupportBound = Double.NaN;
double lastAccu = 0;
double lastCover = 0;
// Test all possible edge points
if (currentAntd.value == 0) {
for (int k = 1; k < ext.numInstances(); k++) {
// break the loop if there is no gain (only works when all instances have weight 1)
if ((lastAccu + (ext.numInstances() - k - 1))
/ (lastCover + (ext.numInstances() - k - 1))
< maxPurityForThisAntecedent
&& allWeightsAreOne) {
break;
}
// Bag 1
if (currentAntd.splitPoint < ext.instance(k).value(currentAntd.att.index())
&& ext.instance(k).value(currentAntd.att.index())
!= ext.instance(k - 1).value(currentAntd.att.index())) {
currentAntd.supportBound = ext.instance(k).value(currentAntd.att.index());
double[] accuArray = new double[ext.numInstances()];
double[] coverArray = new double[ext.numInstances()];
for (int i = 0; i < ext.numInstances(); i++) {
coverArray[i] = ext.instance(i).weight();
double coverValue = currentAntd.covers(ext.instance(i));
if (coverArray[i] >= coverValue * ext.instance(i).weight()) {
coverArray[i] = coverValue * ext.instance(i).weight();
if (ext.instance(i).classValue() == m_Consequent) {
accuArray[i] = coverValue * ext.instance(i).weight();
}
}
}
double purity = (Utils.sum(accuArray)) / (Utils.sum(coverArray));
if (purity >= maxPurityForThisAntecedent) {
maxPurityForThisAntecedent = purity;
bestFoundSupportBound = currentAntd.supportBound;
}
lastAccu = Utils.sum(accuArray);
lastCover = Utils.sum(coverArray);
}
}
} else {
for (int k = ext.numInstances() - 2; k >= 0; k--) {
// break the loop if there is no gain (only works when all instances have weight 1)
if ((lastAccu + (k)) / (lastCover + (k)) < maxPurityForThisAntecedent
&& allWeightsAreOne) {
break;
}
// Bag 2
if (currentAntd.splitPoint > ext.instance(k).value(currentAntd.att.index())
&& ext.instance(k).value(currentAntd.att.index())
!= ext.instance(k + 1).value(currentAntd.att.index())) {
currentAntd.supportBound = ext.instance(k).value(currentAntd.att.index());
double[] accuArray = new double[ext.numInstances()];
double[] coverArray = new double[ext.numInstances()];
for (int i = 0; i < ext.numInstances(); i++) {
coverArray[i] = ext.instance(i).weight();
double coverValue = currentAntd.covers(ext.instance(i));
if (coverArray[i] >= coverValue * ext.instance(i).weight()) {
coverArray[i] = coverValue * ext.instance(i).weight();
if (ext.instance(i).classValue() == m_Consequent) {
accuArray[i] = coverValue * ext.instance(i).weight();
}
}
}
double purity = (Utils.sum(accuArray)) / (Utils.sum(coverArray));
if (purity >= maxPurityForThisAntecedent) {
maxPurityForThisAntecedent = purity;
bestFoundSupportBound = currentAntd.supportBound;
}
lastAccu = Utils.sum(accuArray);
lastCover = Utils.sum(coverArray);
}
}
}
if (maxPurityForThisAntecedent > maxPurityOfAllAntecedents) {
bestAntecedentsIndex = j;
bestSupportBoundForAllAntecedents = bestFoundSupportBound;
maxPurityOfAllAntecedents = maxPurityForThisAntecedent;
}
} else {
// Nominal Antd
finishedAntecedents[j] = true;
numFinishedAntecedents++;
continue;
}
}
if (bestAntecedentsIndex == -1) {
return;
}
if (maxPurity <= maxPurityOfAllAntecedents) {
if (Double.isNaN(bestSupportBoundForAllAntecedents)) {
((NumericAntd) m_Antds.elementAt(bestAntecedentsIndex)).supportBound =
((NumericAntd) m_Antds.elementAt(bestAntecedentsIndex)).splitPoint;
} else {
((NumericAntd) m_Antds.elementAt(bestAntecedentsIndex)).supportBound =
bestSupportBoundForAllAntecedents;
((NumericAntd) m_Antds.elementAt(bestAntecedentsIndex)).fuzzyYet = true;
}
maxPurity = maxPurityOfAllAntecedents;
}
finishedAntecedents[bestAntecedentsIndex] = true;
numFinishedAntecedents++;
}
}
/**
* 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;
}
/**
* evaluates an individual attribute by measuring the gain ratio of the class given the attribute.
*
* @param attribute the index of the attribute to be evaluated
* @return the gain ratio
* @throws Exception if the attribute could not be evaluated
*/
public double evaluateAttribute(int attribute) throws Exception {
int i, j, ii, jj;
int ni, nj;
double sum = 0.0;
ni = m_trainInstances.attribute(attribute).numValues() + 1;
nj = m_numClasses + 1;
double[] sumi, sumj;
Instance inst;
double temp = 0.0;
sumi = new double[ni];
sumj = new double[nj];
double[][] counts = new double[ni][nj];
sumi = new double[ni];
sumj = new double[nj];
for (i = 0; i < ni; i++) {
sumi[i] = 0.0;
for (j = 0; j < nj; j++) {
sumj[j] = 0.0;
counts[i][j] = 0.0;
}
}
// Fill the contingency table
for (i = 0; i < m_numInstances; i++) {
inst = m_trainInstances.instance(i);
if (inst.isMissing(attribute)) {
ii = ni - 1;
} else {
ii = (int) inst.value(attribute);
}
if (inst.isMissing(m_classIndex)) {
jj = nj - 1;
} else {
jj = (int) inst.value(m_classIndex);
}
counts[ii][jj]++;
}
// get the row totals
for (i = 0; i < ni; i++) {
sumi[i] = 0.0;
for (j = 0; j < nj; j++) {
sumi[i] += counts[i][j];
sum += counts[i][j];
}
}
// get the column totals
for (j = 0; j < nj; j++) {
sumj[j] = 0.0;
for (i = 0; i < ni; i++) {
sumj[j] += counts[i][j];
}
}
// distribute missing counts
if (m_missing_merge && (sumi[ni - 1] < m_numInstances) && (sumj[nj - 1] < m_numInstances)) {
double[] i_copy = new double[sumi.length];
double[] j_copy = new double[sumj.length];
double[][] counts_copy = new double[sumi.length][sumj.length];
for (i = 0; i < ni; i++) {
System.arraycopy(counts[i], 0, counts_copy[i], 0, sumj.length);
}
System.arraycopy(sumi, 0, i_copy, 0, sumi.length);
System.arraycopy(sumj, 0, j_copy, 0, sumj.length);
double total_missing = (sumi[ni - 1] + sumj[nj - 1] - counts[ni - 1][nj - 1]);
// do the missing i's
if (sumi[ni - 1] > 0.0) {
for (j = 0; j < nj - 1; j++) {
if (counts[ni - 1][j] > 0.0) {
for (i = 0; i < ni - 1; i++) {
temp = ((i_copy[i] / (sum - i_copy[ni - 1])) * counts[ni - 1][j]);
counts[i][j] += temp;
sumi[i] += temp;
}
counts[ni - 1][j] = 0.0;
}
}
}
sumi[ni - 1] = 0.0;
// do the missing j's
if (sumj[nj - 1] > 0.0) {
for (i = 0; i < ni - 1; i++) {
if (counts[i][nj - 1] > 0.0) {
for (j = 0; j < nj - 1; j++) {
temp = ((j_copy[j] / (sum - j_copy[nj - 1])) * counts[i][nj - 1]);
counts[i][j] += temp;
sumj[j] += temp;
}
counts[i][nj - 1] = 0.0;
}
}
}
sumj[nj - 1] = 0.0;
// do the both missing
if (counts[ni - 1][nj - 1] > 0.0 && total_missing != sum) {
for (i = 0; i < ni - 1; i++) {
for (j = 0; j < nj - 1; j++) {
temp = (counts_copy[i][j] / (sum - total_missing)) * counts_copy[ni - 1][nj - 1];
counts[i][j] += temp;
sumi[i] += temp;
sumj[j] += temp;
}
}
counts[ni - 1][nj - 1] = 0.0;
}
}
return ContingencyTables.gainRatio(counts);
}
