/**
* Gets the current settings of WrapperSubsetEval.
*
* @return an array of strings suitable for passing to setOptions()
*/
public String[] getOptions() {
String[] evaluatorOptions = new String[0];
if ((m_ASEval != null) && (m_ASEval instanceof OptionHandler)) {
evaluatorOptions = ((OptionHandler) m_ASEval).getOptions();
}
String[] options = new String[8 + evaluatorOptions.length];
int current = 0;
options[current++] = "-S";
options[current++] = "" + getStepSize();
options[current++] = "-R";
options[current++] = "" + getStartPoint();
if (getAttributeEvaluator() != null) {
options[current++] = "-A";
options[current++] = getAttributeEvaluator().getClass().getName();
}
if (evaluatorOptions.length > 0) {
options[current++] = "--";
System.arraycopy(evaluatorOptions, 0, options, current, evaluatorOptions.length);
current += evaluatorOptions.length;
}
while (current < options.length) {
options[current++] = "";
}
return options;
}
/**
* Calculates the class membership probabilities for the given test instance.
*
* @param instance the instance to be classified
* @return predicted class probability distribution
* @throws Exception if distribution can't be computed
*/
public double[] distributionForInstance(Instance instance) throws Exception {
DecisionTableHashKey thekey;
double[] tempDist;
double[] normDist;
m_disTransform.input(instance);
m_disTransform.batchFinished();
instance = m_disTransform.output();
m_delTransform.input(instance);
m_delTransform.batchFinished();
instance = m_delTransform.output();
thekey = new DecisionTableHashKey(instance, instance.numAttributes(), false);
// if this one is not in the table
if ((tempDist = (double[]) m_entries.get(thekey)) == null) {
if (m_useIBk) {
tempDist = m_ibk.distributionForInstance(instance);
} else {
if (!m_classIsNominal) {
tempDist = new double[1];
tempDist[0] = m_majority;
} else {
tempDist = m_classPriors.clone();
/*tempDist = new double [m_theInstances.classAttribute().numValues()];
tempDist[(int)m_majority] = 1.0; */
}
}
} else {
if (!m_classIsNominal) {
normDist = new double[1];
normDist[0] = (tempDist[0] / tempDist[1]);
tempDist = normDist;
} else {
// normalise distribution
normDist = new double[tempDist.length];
System.arraycopy(tempDist, 0, normDist, 0, tempDist.length);
Utils.normalize(normDist);
tempDist = normDist;
}
}
return tempDist;
}
/**
* Gets the current settings of the Classifier.
*
* @return an array of strings suitable for passing to setOptions
*/
public String[] getOptions() {
String[] superOptions = super.getOptions();
String[] options = new String[superOptions.length + 4];
int current = 0;
options[current++] = "-E";
options[current++] = "" + getDesiredSize();
options[current++] = "-R";
options[current++] = "" + getArtificialSize();
System.arraycopy(superOptions, 0, options, current, superOptions.length);
current += superOptions.length;
while (current < options.length) {
options[current++] = "";
}
return options;
}
/**
* Gets the current settings of the classifier.
*
* @return an array of strings suitable for passing to setOptions
*/
public String[] getOptions() {
String[] superOptions = super.getOptions();
String[] options = new String[superOptions.length + 6];
int current = 0;
options[current++] = "-U";
options[current++] = "" + getWeightingKernel();
if ((getKNN() == 0) && m_UseAllK) {
options[current++] = "-K";
options[current++] = "-1";
} else {
options[current++] = "-K";
options[current++] = "" + getKNN();
}
options[current++] = "-A";
options[current++] =
m_NNSearch.getClass().getName() + " " + Utils.joinOptions(m_NNSearch.getOptions());
System.arraycopy(superOptions, 0, options, current, superOptions.length);
return options;
}
/**
* Returns the best cut of a graph w.r.t. the degree of dissimilarity between points of different
* partitions and the degree of similarity between points of the same partition.
*
* @param W the weight matrix of the graph
* @return an array of two elements, each of these contains the points of a partition
*/
protected static int[][] bestCut(DoubleMatrix2D W) {
int n = W.columns();
// Builds the diagonal matrices D and D^(-1/2) (represented as their diagonals)
DoubleMatrix1D d = DoubleFactory1D.dense.make(n);
DoubleMatrix1D d_minus_1_2 = DoubleFactory1D.dense.make(n);
for (int i = 0; i < n; i++) {
double d_i = W.viewRow(i).zSum();
d.set(i, d_i);
d_minus_1_2.set(i, 1 / Math.sqrt(d_i));
}
DoubleMatrix2D D = DoubleFactory2D.sparse.diagonal(d);
// System.out.println("DoubleMatrix2D :\n"+D.toString());
DoubleMatrix2D X = D.copy();
// System.out.println("DoubleMatrix2D copy :\n"+X.toString());
// X = D^(-1/2) * (D - W) * D^(-1/2)
X.assign(W, Functions.minus);
// System.out.println("DoubleMatrix2D X: (D-W) :\n"+X.toString());
for (int i = 0; i < n; i++)
for (int j = 0; j < n; j++)
X.set(i, j, X.get(i, j) * d_minus_1_2.get(i) * d_minus_1_2.get(j));
// Computes the eigenvalues and the eigenvectors of X
EigenvalueDecomposition e = new EigenvalueDecomposition(X);
DoubleMatrix1D lambda = e.getRealEigenvalues();
// Selects the eigenvector z_2 associated with the second smallest eigenvalue
// Creates a map that contains the pairs <index, eigenvalue>
AbstractIntDoubleMap map = new OpenIntDoubleHashMap(n);
for (int i = 0; i < n; i++) map.put(i, Math.abs(lambda.get(i)));
IntArrayList list = new IntArrayList();
// Sorts the map on the value
map.keysSortedByValue(list);
// Gets the index of the second smallest element
int i_2 = list.get(1);
// y_2 = D^(-1/2) * z_2
DoubleMatrix1D y_2 = e.getV().viewColumn(i_2).copy();
y_2.assign(d_minus_1_2, Functions.mult);
// Creates a map that contains the pairs <i, y_2[i]>
map.clear();
for (int i = 0; i < n; i++) map.put(i, y_2.get(i));
// Sorts the map on the value
map.keysSortedByValue(list);
// Search the element in the map previuosly ordered that minimizes the cut
// of the partition
double best_cut = Double.POSITIVE_INFINITY;
int[][] partition = new int[2][];
// The array v contains all the elements of the graph ordered by their
// projection on vector y_2
int[] v = list.elements();
// For each admissible splitting point i
for (int i = 1; i < n; i++) {
// The array a contains all the elements that have a projection on vector
// y_2 less or equal to the one of i-th element
// The array b contains the remaining elements
int[] a = new int[i];
int[] b = new int[n - i];
System.arraycopy(v, 0, a, 0, i);
System.arraycopy(v, i, b, 0, n - i);
double cut = Ncut(W, a, b, v);
if (cut < best_cut) {
best_cut = cut;
partition[0] = a;
partition[1] = b;
}
}
// System.out.println("Partition:");
// UtilsJS.printMatrix(partition);
return partition;
}
/**
* Merges two sets of points represented as integer vectors. The sets are not overlapped.
*
* @param a the first set of points
* @param b the second set of points
* @return the union of the two sets
*/
protected static int[] merge(int[] a, int[] b) {
int[] v = new int[a.length + b.length];
System.arraycopy(a, 0, v, 0, a.length);
System.arraycopy(b, 0, v, a.length, b.length);
return v;
}
/**
* 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);
}
/**
* Calculates the accuracy on a test fold for internal cross validation of feature sets
*
* @param fold set of instances to be "left out" and classified
* @param fs currently selected feature set
* @return the accuracy for the fold
* @throws Exception if something goes wrong
*/
double evaluateFoldCV(Instances fold, int[] fs) throws Exception {
int i;
int ruleCount = 0;
int numFold = fold.numInstances();
int numCl = m_theInstances.classAttribute().numValues();
double[][] class_distribs = new double[numFold][numCl];
double[] instA = new double[fs.length];
double[] normDist;
DecisionTableHashKey thekey;
double acc = 0.0;
int classI = m_theInstances.classIndex();
Instance inst;
if (m_classIsNominal) {
normDist = new double[numCl];
} else {
normDist = new double[2];
}
// first *remove* instances
for (i = 0; i < numFold; i++) {
inst = fold.instance(i);
for (int j = 0; j < fs.length; j++) {
if (fs[j] == classI) {
instA[j] = Double.MAX_VALUE; // missing for the class
} else if (inst.isMissing(fs[j])) {
instA[j] = Double.MAX_VALUE;
} else {
instA[j] = inst.value(fs[j]);
}
}
thekey = new DecisionTableHashKey(instA);
if ((class_distribs[i] = (double[]) m_entries.get(thekey)) == null) {
throw new Error("This should never happen!");
} else {
if (m_classIsNominal) {
class_distribs[i][(int) inst.classValue()] -= inst.weight();
} else {
class_distribs[i][0] -= (inst.classValue() * inst.weight());
class_distribs[i][1] -= inst.weight();
}
ruleCount++;
}
m_classPriorCounts[(int) inst.classValue()] -= inst.weight();
}
double[] classPriors = m_classPriorCounts.clone();
Utils.normalize(classPriors);
// now classify instances
for (i = 0; i < numFold; i++) {
inst = fold.instance(i);
System.arraycopy(class_distribs[i], 0, normDist, 0, normDist.length);
if (m_classIsNominal) {
boolean ok = false;
for (int j = 0; j < normDist.length; j++) {
if (Utils.gr(normDist[j], 1.0)) {
ok = true;
break;
}
}
if (!ok) { // majority class
normDist = classPriors.clone();
}
// if (ok) {
Utils.normalize(normDist);
if (m_evaluationMeasure == EVAL_AUC) {
m_evaluation.evaluateModelOnceAndRecordPrediction(normDist, inst);
} else {
m_evaluation.evaluateModelOnce(normDist, inst);
}
/* } else {
normDist[(int)m_majority] = 1.0;
if (m_evaluationMeasure == EVAL_AUC) {
m_evaluation.evaluateModelOnceAndRecordPrediction(normDist, inst);
} else {
m_evaluation.evaluateModelOnce(normDist, inst);
}
} */
} else {
if (Utils.eq(normDist[1], 0.0)) {
double[] temp = new double[1];
temp[0] = m_majority;
m_evaluation.evaluateModelOnce(temp, inst);
} else {
double[] temp = new double[1];
temp[0] = normDist[0] / normDist[1];
m_evaluation.evaluateModelOnce(temp, inst);
}
}
}
// now re-insert instances
for (i = 0; i < numFold; i++) {
inst = fold.instance(i);
m_classPriorCounts[(int) inst.classValue()] += inst.weight();
if (m_classIsNominal) {
class_distribs[i][(int) inst.classValue()] += inst.weight();
} else {
class_distribs[i][0] += (inst.classValue() * inst.weight());
class_distribs[i][1] += inst.weight();
}
}
return acc;
}
/**
* Classifies an instance for internal leave one out cross validation of feature sets
*
* @param instance instance to be "left out" and classified
* @param instA feature values of the selected features for the instance
* @return the classification of the instance
* @throws Exception if something goes wrong
*/
double evaluateInstanceLeaveOneOut(Instance instance, double[] instA) throws Exception {
DecisionTableHashKey thekey;
double[] tempDist;
double[] normDist;
thekey = new DecisionTableHashKey(instA);
if (m_classIsNominal) {
// if this one is not in the table
if ((tempDist = (double[]) m_entries.get(thekey)) == null) {
throw new Error("This should never happen!");
} else {
normDist = new double[tempDist.length];
System.arraycopy(tempDist, 0, normDist, 0, tempDist.length);
normDist[(int) instance.classValue()] -= instance.weight();
// update the table
// first check to see if the class counts are all zero now
boolean ok = false;
for (int i = 0; i < normDist.length; i++) {
if (Utils.gr(normDist[i], 1.0)) {
ok = true;
break;
}
}
// downdate the class prior counts
m_classPriorCounts[(int) instance.classValue()] -= instance.weight();
double[] classPriors = m_classPriorCounts.clone();
Utils.normalize(classPriors);
if (!ok) { // majority class
normDist = classPriors;
}
m_classPriorCounts[(int) instance.classValue()] += instance.weight();
// if (ok) {
Utils.normalize(normDist);
if (m_evaluationMeasure == EVAL_AUC) {
m_evaluation.evaluateModelOnceAndRecordPrediction(normDist, instance);
} else {
m_evaluation.evaluateModelOnce(normDist, instance);
}
return Utils.maxIndex(normDist);
/*} else {
normDist = new double [normDist.length];
normDist[(int)m_majority] = 1.0;
if (m_evaluationMeasure == EVAL_AUC) {
m_evaluation.evaluateModelOnceAndRecordPrediction(normDist, instance);
} else {
m_evaluation.evaluateModelOnce(normDist, instance);
}
return m_majority;
} */
}
// return Utils.maxIndex(tempDist);
} else {
// see if this one is already in the table
if ((tempDist = (double[]) m_entries.get(thekey)) != null) {
normDist = new double[tempDist.length];
System.arraycopy(tempDist, 0, normDist, 0, tempDist.length);
normDist[0] -= (instance.classValue() * instance.weight());
normDist[1] -= instance.weight();
if (Utils.eq(normDist[1], 0.0)) {
double[] temp = new double[1];
temp[0] = m_majority;
m_evaluation.evaluateModelOnce(temp, instance);
return m_majority;
} else {
double[] temp = new double[1];
temp[0] = normDist[0] / normDist[1];
m_evaluation.evaluateModelOnce(temp, instance);
return temp[0];
}
} else {
throw new Error("This should never happen!");
}
}
// shouldn't get here
// return 0.0;
}
/**
* Generates the classifier.
*
* @param data set of instances serving as training data
* @throws Exception if the classifier has not been generated successfully
*/
public void buildClassifier(Instances data) throws Exception {
// can classifier handle the data?
getCapabilities().testWithFail(data);
// remove instances with missing class
m_theInstances = new Instances(data);
m_theInstances.deleteWithMissingClass();
m_rr = new Random(1);
if (m_theInstances.classAttribute().isNominal()) { // Set up class priors
m_classPriorCounts = new double[data.classAttribute().numValues()];
Arrays.fill(m_classPriorCounts, 1.0);
for (int i = 0; i < data.numInstances(); i++) {
Instance curr = data.instance(i);
m_classPriorCounts[(int) curr.classValue()] += curr.weight();
}
m_classPriors = m_classPriorCounts.clone();
Utils.normalize(m_classPriors);
}
setUpEvaluator();
if (m_theInstances.classAttribute().isNumeric()) {
m_disTransform = new weka.filters.unsupervised.attribute.Discretize();
m_classIsNominal = false;
// use binned discretisation if the class is numeric
((weka.filters.unsupervised.attribute.Discretize) m_disTransform).setBins(10);
((weka.filters.unsupervised.attribute.Discretize) m_disTransform).setInvertSelection(true);
// Discretize all attributes EXCEPT the class
String rangeList = "";
rangeList += (m_theInstances.classIndex() + 1);
// System.out.println("The class col: "+m_theInstances.classIndex());
((weka.filters.unsupervised.attribute.Discretize) m_disTransform)
.setAttributeIndices(rangeList);
} else {
m_disTransform = new weka.filters.supervised.attribute.Discretize();
((weka.filters.supervised.attribute.Discretize) m_disTransform).setUseBetterEncoding(true);
m_classIsNominal = true;
}
m_disTransform.setInputFormat(m_theInstances);
m_theInstances = Filter.useFilter(m_theInstances, m_disTransform);
m_numAttributes = m_theInstances.numAttributes();
m_numInstances = m_theInstances.numInstances();
m_majority = m_theInstances.meanOrMode(m_theInstances.classAttribute());
// Perform the search
int[] selected = m_search.search(m_evaluator, m_theInstances);
m_decisionFeatures = new int[selected.length + 1];
System.arraycopy(selected, 0, m_decisionFeatures, 0, selected.length);
m_decisionFeatures[m_decisionFeatures.length - 1] = m_theInstances.classIndex();
// reduce instances to selected features
m_delTransform = new Remove();
m_delTransform.setInvertSelection(true);
// set features to keep
m_delTransform.setAttributeIndicesArray(m_decisionFeatures);
m_delTransform.setInputFormat(m_theInstances);
m_dtInstances = Filter.useFilter(m_theInstances, m_delTransform);
// reset the number of attributes
m_numAttributes = m_dtInstances.numAttributes();
// create hash table
m_entries = new Hashtable((int) (m_dtInstances.numInstances() * 1.5));
// insert instances into the hash table
for (int i = 0; i < m_numInstances; i++) {
Instance inst = m_dtInstances.instance(i);
insertIntoTable(inst, null);
}
// Replace the global table majority with nearest neighbour?
if (m_useIBk) {
m_ibk = new IBk();
m_ibk.buildClassifier(m_theInstances);
}
// Save memory
if (m_saveMemory) {
m_theInstances = new Instances(m_theInstances, 0);
m_dtInstances = new Instances(m_dtInstances, 0);
}
m_evaluation = null;
}