/**
* 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);
}
/**
* Splits the given set of instances into subsets.
*
* @exception Exception if something goes wrong
*/
public final Instances[] split(Instances data) throws Exception {
Instances[] instances = new Instances[m_numSubsets];
double[] weights;
double newWeight;
Instance instance;
int subset, i, j;
for (j = 0; j < m_numSubsets; j++)
instances[j] = new Instances((Instances) data, data.numInstances());
for (i = 0; i < data.numInstances(); i++) {
instance = ((Instances) data).instance(i);
weights = weights(instance);
subset = whichSubset(instance);
if (subset > -1) instances[subset].add(instance);
else
for (j = 0; j < m_numSubsets; j++)
if (Utils.gr(weights[j], 0)) {
newWeight = weights[j] * instance.weight();
instances[j].add(instance);
instances[j].lastInstance().setWeight(newWeight);
}
}
for (j = 0; j < m_numSubsets; j++) instances[j].compactify();
return instances;
}
/**
* Returns a vector with column names of the dataset, listed in "list". If a column cannot be
* found or the list is empty the ones from the default list are returned.
*
* @param list comma-separated list of attribute names
* @param defaultList the default list of attribute names
* @param inst the instances to get the attribute names from
* @return a vector containing attribute names
*/
protected Vector determineColumnNames(String list, String defaultList, Instances inst) {
Vector result;
Vector atts;
StringTokenizer tok;
int i;
String item;
// get attribute names
atts = new Vector();
for (i = 0; i < inst.numAttributes(); i++) atts.add(inst.attribute(i).name().toLowerCase());
// process list
result = new Vector();
tok = new StringTokenizer(list, ",");
while (tok.hasMoreTokens()) {
item = tok.nextToken().toLowerCase();
if (atts.contains(item)) {
result.add(item);
} else {
result.clear();
break;
}
}
// do we have to return defaults?
if (result.size() == 0) {
tok = new StringTokenizer(defaultList, ",");
while (tok.hasMoreTokens()) result.add(tok.nextToken().toLowerCase());
}
return result;
}
public void testTypical() {
Instances result = useFilter();
// Number of attributes and instances shouldn't change
assertEquals(m_Instances.numAttributes() + 5, result.numAttributes());
assertEquals(m_Instances.numInstances(), result.numInstances());
// Eibe can enhance this to check the binarizing is correct.
}
/**
* 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;
}
public static void wekaAlgorithms(Instances data) throws Exception {
classifier = new FilteredClassifier(); // new instance of tree
classifier.setClassifier(new NaiveBayes());
// classifier.setClassifier(new J48());
// classifier.setClassifier(new RandomForest());
// classifier.setClassifier(new ZeroR());
// classifier.setClassifier(new NaiveBayes());
// classifier.setClassifier(new IBk());
data.setClassIndex(data.numAttributes() - 1);
Evaluation eval = new Evaluation(data);
int folds = 10;
eval.crossValidateModel(classifier, data, folds, new Random(1));
System.out.println("===== Evaluating on filtered (training) dataset =====");
System.out.println(eval.toSummaryString());
System.out.println(eval.toClassDetailsString());
double[][] mat = eval.confusionMatrix();
System.out.println("========= Confusion Matrix =========");
for (int i = 0; i < mat.length; i++) {
for (int j = 0; j < mat.length; j++) {
System.out.print(mat[i][j] + " ");
}
System.out.println(" ");
}
}
/** trains the classifier */
@Override
public void train() throws Exception {
if (_train.classIndex() == -1) _train.setClassIndex(_train.numAttributes() - 1);
_cl.buildClassifier(_train);
// evaluate classifier and print some statistics
evaluate();
}
/**
* initializes the algorithm
*
* @param data the data to work with
* @throws Exception if m_SVM is null
*/
protected void init(Instances data) throws Exception {
if (m_SVM == null) {
throw new Exception("SVM not initialized in optimizer. Use RegOptimizer.setSVMReg()");
}
m_C = m_SVM.getC();
m_data = data;
m_classIndex = data.classIndex();
m_nInstances = data.numInstances();
// Initialize kernel
m_kernel = Kernel.makeCopy(m_SVM.getKernel());
m_kernel.buildKernel(data);
// init m_target
m_target = new double[m_nInstances];
for (int i = 0; i < m_nInstances; i++) {
m_target[i] = data.instance(i).classValue();
}
m_random = new Random(m_nSeed);
// initialize alpha and alpha* array to all zero
m_alpha = new double[m_target.length];
m_alphaStar = new double[m_target.length];
m_supportVectors = new SMOset(m_nInstances);
m_b = 0.0;
m_nEvals = 0;
m_nCacheHits = -1;
}
/**
* 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;
}
/**
* @param args
* @throws Exception
*/
public static void main(String[] args) throws Exception {
Instances isTrainingSet = createSet(4);
Instance instance1 = createInstance(new double[] {1, 0.7, 0.1, 0.7}, "S1", isTrainingSet);
Instance instance2 = createInstance(new double[] {0.1, 0.2, 1, 0.3}, "S2", isTrainingSet);
Instance instance22 = createInstance(new double[] {0, 0, 0, 0}, "S3", isTrainingSet);
isTrainingSet.add(instance1);
isTrainingSet.add(instance2);
isTrainingSet.add(instance22);
Instances isTestingSet = createSet(4);
Instance instance3 = createInstance(new double[] {1, 0.7, 0.1, 0.7}, "S1", isTrainingSet);
Instance instance4 = createInstance(new double[] {0.1, 0.2, 1, 0.3}, "S2", isTrainingSet);
isTestingSet.add(instance3);
isTestingSet.add(instance4);
// Create a naïve bayes classifier
Classifier cModel = (Classifier) new BayesNet(); // M5P
cModel.buildClassifier(isTrainingSet);
// Test the model
Evaluation eTest = new Evaluation(isTrainingSet);
eTest.evaluateModel(cModel, isTestingSet);
// Print the result à la Weka explorer:
String strSummary = eTest.toSummaryString();
System.out.println(strSummary);
// Get the likelihood of each classes
// fDistribution[0] is the probability of being “positive”
// fDistribution[1] is the probability of being “negative”
double[] fDistribution = cModel.distributionForInstance(instance4);
for (int i = 0; i < fDistribution.length; i++) {
System.out.println(fDistribution[i]);
}
}
/**
* Build the associator on the filtered data.
*
* @param data the training data
* @throws Exception if the Associator could not be built successfully
*/
public void buildAssociations(Instances data) throws Exception {
if (m_Associator == null) throw new Exception("No base associator has been set!");
// create copy and set class-index
data = new Instances(data);
if (getClassIndex() == 0) {
data.setClassIndex(data.numAttributes() - 1);
} else {
data.setClassIndex(getClassIndex() - 1);
}
if (getClassIndex() != -1) {
// remove instances with missing class
data.deleteWithMissingClass();
}
m_Filter.setInputFormat(data); // filter capabilities are checked here
data = Filter.useFilter(data, m_Filter);
// can associator handle the data?
getAssociator().getCapabilities().testWithFail(data);
m_FilteredInstances = data.stringFreeStructure();
m_Associator.buildAssociations(data);
}
/**
* Determines and returns (if possible) the structure (internally the header) of the data set as
* an empty set of instances.
*
* @return the structure of the data set as an empty set of Instances
* @throws IOException if an error occurs
*/
public Instances getStructure() throws IOException {
if (getDirectory() == null) {
throw new IOException("No directory/source has been specified");
}
// determine class labels, i.e., sub-dirs
if (m_structure == null) {
String directoryPath = getDirectory().getAbsolutePath();
ArrayList<Attribute> atts = new ArrayList<Attribute>();
ArrayList<String> classes = new ArrayList<String>();
File dir = new File(directoryPath);
String[] subdirs = dir.list();
for (int i = 0; i < subdirs.length; i++) {
File subdir = new File(directoryPath + File.separator + subdirs[i]);
if (subdir.isDirectory()) classes.add(subdirs[i]);
}
atts.add(new Attribute("text", (ArrayList<String>) null));
if (m_OutputFilename) atts.add(new Attribute("filename", (ArrayList<String>) null));
// make sure that the name of the class attribute is unlikely to
// clash with any attribute created via the StringToWordVector filter
atts.add(new Attribute("@@class@@", classes));
String relName = directoryPath.replaceAll("/", "_");
relName = relName.replaceAll("\\\\", "_").replaceAll(":", "_");
m_structure = new Instances(relName, atts, 0);
m_structure.setClassIndex(m_structure.numAttributes() - 1);
}
return m_structure;
}
/**
* Sets instances that should be stored.
*
* @param instances the instances
*/
@Override
public void setInstances(Instances instances) {
m_ClassIndex.setUpper(instances.numAttributes() - 1);
instances.setClassIndex(m_ClassIndex.getIndex());
super.setInstances(instances);
}
private double calcNodeScorePlain(int nNode) {
Instances instances = m_BayesNet.m_Instances;
ParentSet oParentSet = m_BayesNet.getParentSet(nNode);
// determine cardinality of parent set & reserve space for frequency counts
int nCardinality = oParentSet.getCardinalityOfParents();
int numValues = instances.attribute(nNode).numValues();
int[] nCounts = new int[nCardinality * numValues];
// initialize (don't need this?)
for (int iParent = 0; iParent < nCardinality * numValues; iParent++) {
nCounts[iParent] = 0;
}
// estimate distributions
Enumeration enumInsts = instances.enumerateInstances();
while (enumInsts.hasMoreElements()) {
Instance instance = (Instance) enumInsts.nextElement();
// updateClassifier;
double iCPT = 0;
for (int iParent = 0; iParent < oParentSet.getNrOfParents(); iParent++) {
int nParent = oParentSet.getParent(iParent);
iCPT = iCPT * instances.attribute(nParent).numValues() + instance.value(nParent);
}
nCounts[numValues * ((int) iCPT) + (int) instance.value(nNode)]++;
}
return calcScoreOfCounts(nCounts, nCardinality, numValues, instances);
} // CalcNodeScore
/** tests whether a URL can be loaded (via setURL(URL)). */
public void testURLSourcedLoader() {
Instances data;
if (!(getLoader() instanceof URLSourcedLoader)) {
return;
}
try {
// save
m_Saver.setInstances(m_Instances);
m_Saver.setFile(new File(m_ExportFilename));
m_Saver.writeBatch();
// load
((URLSourcedLoader) m_Loader).setURL(new File(m_ExportFilename).toURI().toURL().toString());
data = m_Loader.getDataSet();
// compare data
try {
if (m_Instances.classIndex() != data.classIndex()) {
data.setClassIndex(m_Instances.classIndex());
}
compareDatasets(m_Instances, data);
} catch (Exception e) {
fail("URL load failed (datasets differ): " + e.toString());
}
} catch (Exception e) {
e.printStackTrace();
fail("URL load failed: " + e.toString());
}
}
private static void writePredictedDistributions(
Classifier c, Instances data, int idIndex, Writer out) throws Exception {
// header
out.write("id");
for (int i = 0; i < data.numClasses(); i++) {
out.write(",\"");
out.write(data.classAttribute().value(i).replaceAll("[\"\\\\]", "_"));
out.write("\"");
}
out.write("\n");
// data
for (int i = 0; i < data.numInstances(); i++) {
final String id = data.instance(i).stringValue(idIndex);
double[] distribution = c.distributionForInstance(data.instance(i));
// final String label = data.attribute(classIndex).value();
out.write(id);
for (double probability : distribution) {
out.write(",");
out.write(String.valueOf(probability > 1e-5 ? (float) probability : 0f));
}
out.write("\n");
}
}
/** tests whether data can be loaded via setSource() with a file stream. */
public void testLoaderWithStream() {
Instances data;
try {
// save
m_Saver.setInstances(m_Instances);
m_Saver.setFile(new File(m_ExportFilename));
m_Saver.writeBatch();
// load
m_Loader.setSource(new FileInputStream(new File(m_ExportFilename)));
data = m_Loader.getDataSet();
// compare data
try {
if (m_Instances.classIndex() != data.classIndex()) {
data.setClassIndex(m_Instances.classIndex());
}
compareDatasets(m_Instances, data);
} catch (Exception e) {
fail("File stream loading failed (datasets differ): " + e.toString());
}
} catch (Exception e) {
e.printStackTrace();
fail("File stream loading failed: " + e.toString());
}
}
/**
* 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 UnsupportedAttributeTypeException if selected attributes are not numeric or nominal.
*/
public boolean setInputFormat(Instances instanceInfo) throws Exception {
if ((instanceInfo.classIndex() > 0) && (!getFillWithMissing())) {
throw new IllegalArgumentException(
"TimeSeriesTranslate: Need to fill in missing values "
+ "using appropriate option when class index is set.");
}
super.setInputFormat(instanceInfo);
// Create the output buffer
Instances outputFormat = new Instances(instanceInfo, 0);
for (int i = 0; i < instanceInfo.numAttributes(); i++) {
if (i != instanceInfo.classIndex()) {
if (m_SelectedCols.isInRange(i)) {
if (outputFormat.attribute(i).isNominal() || outputFormat.attribute(i).isNumeric()) {
outputFormat.renameAttribute(
i,
outputFormat.attribute(i).name()
+ (m_InstanceRange < 0 ? '-' : '+')
+ Math.abs(m_InstanceRange));
} else {
throw new UnsupportedAttributeTypeException(
"Only numeric and nominal attributes may be " + " manipulated in time series.");
}
}
}
}
outputFormat.setClassIndex(instanceInfo.classIndex());
setOutputFormat(outputFormat);
return true;
}
/**
* Analyses the given list of decision points according to the context specified. Furthermore, the
* context is provided with some visualization of the analysis result.
*
* @param decisionPoints the list of decision points to be analysed
* @param log the log to be analysed
* @param highLevelPN the simulation model to export discovered data dependencies
*/
public void analyse(ClusterDecisionAnalyzer cda) {
clusterDecisionAnalyzer = cda;
// create empty data set with attribute information
Instances data = cda.getDataInfo();
// in case no single learning instance can be provided (as decision
// point is never
// reached, or decision classes cannot specified properly) --> do not
// call algorithm
if (data.numInstances() == 0) {
System.out.println("No learning instances available");
}
// actually solve the classification problem
else {
try {
myClassifier.buildClassifier(data);
// build up result visualization
cda.setResultVisualization(createResultVisualization());
cda.setEvaluationVisualization(createEvaluationVisualization(data));
} catch (Exception ex) {
ex.printStackTrace();
cda.setResultVisualization(
createMessagePanel("Error while solving the classification problem"));
}
}
}
/**
* Calculates the area under the precision-recall curve (AUPRC).
*
* @param tcurve a previously extracted threshold curve Instances.
* @return the PRC area, or Double.NaN if you don't pass in a ThresholdCurve generated Instances.
*/
public static double getPRCArea(Instances tcurve) {
final int n = tcurve.numInstances();
if (!RELATION_NAME.equals(tcurve.relationName()) || (n == 0)) {
return Double.NaN;
}
final int pInd = tcurve.attribute(PRECISION_NAME).index();
final int rInd = tcurve.attribute(RECALL_NAME).index();
final double[] pVals = tcurve.attributeToDoubleArray(pInd);
final double[] rVals = tcurve.attributeToDoubleArray(rInd);
double area = 0;
double xlast = rVals[n - 1];
// start from the first real p/r pair (not the artificial zero point)
for (int i = n - 2; i >= 0; i--) {
double recallDelta = rVals[i] - xlast;
area += (pVals[i] * recallDelta);
xlast = rVals[i];
}
if (area == 0) {
return Utils.missingValue();
}
return area;
}
/**
* Returns a string containing java source code equivalent to the test made at this node. The
* instance being tested is called "i".
*
* @param index index of the nominal value tested
* @param data the data containing instance structure info
* @return a value of type 'String'
*/
public final String sourceExpression(int index, Instances data) {
StringBuffer expr = null;
if (index < 0) {
return "i[" + m_attIndex + "] == null";
}
if (data.attribute(m_attIndex).isNominal()) {
if (index == 0) {
expr = new StringBuffer("i[");
} else {
expr = new StringBuffer("!i[");
}
expr.append(m_attIndex).append("]");
expr.append(".equals(\"")
.append(data.attribute(m_attIndex).value((int) m_splitPoint))
.append("\")");
} else {
expr = new StringBuffer("((Double) i[");
expr.append(m_attIndex).append("])");
if (index == 0) {
expr.append(".doubleValue() <= ").append(m_splitPoint);
} else {
expr.append(".doubleValue() > ").append(m_splitPoint);
}
}
return expr.toString();
}
/**
* Calculates the area under the ROC curve as the Wilcoxon-Mann-Whitney statistic.
*
* @param tcurve a previously extracted threshold curve Instances.
* @return the ROC area, or Double.NaN if you don't pass in a ThresholdCurve generated Instances.
*/
public static double getROCArea(Instances tcurve) {
final int n = tcurve.numInstances();
if (!RELATION_NAME.equals(tcurve.relationName()) || (n == 0)) {
return Double.NaN;
}
final int tpInd = tcurve.attribute(TRUE_POS_NAME).index();
final int fpInd = tcurve.attribute(FALSE_POS_NAME).index();
final double[] tpVals = tcurve.attributeToDoubleArray(tpInd);
final double[] fpVals = tcurve.attributeToDoubleArray(fpInd);
double area = 0.0, cumNeg = 0.0;
final double totalPos = tpVals[0];
final double totalNeg = fpVals[0];
for (int i = 0; i < n; i++) {
double cip, cin;
if (i < n - 1) {
cip = tpVals[i] - tpVals[i + 1];
cin = fpVals[i] - fpVals[i + 1];
} else {
cip = tpVals[n - 1];
cin = fpVals[n - 1];
}
area += cip * (cumNeg + (0.5 * cin));
cumNeg += cin;
}
area /= (totalNeg * totalPos);
return area;
}
/**
* Find all the instances in the dataset covered/not covered by the rule in given index, and the
* correponding simple statistics and predicted class distributions are stored in the given double
* array, which can be obtained by getSimpleStats() and getDistributions().<br>
*
* @param index the given index, assuming correct
* @param insts the dataset to be covered by the rule
* @param stats the given double array to hold stats, side-effected
* @param dist the given array to hold class distributions, side-effected if null, the
* distribution is not necessary
* @return the instances covered and not covered by the rule
*/
private Instances[] computeSimpleStats(
int index, Instances insts, double[] stats, double[] dist) {
Rule rule = (Rule) m_Ruleset.elementAt(index);
Instances[] data = new Instances[2];
data[0] = new Instances(insts, insts.numInstances());
data[1] = new Instances(insts, insts.numInstances());
for (int i = 0; i < insts.numInstances(); i++) {
Instance datum = insts.instance(i);
double weight = datum.weight();
if (rule.covers(datum)) {
data[0].add(datum); // Covered by this rule
stats[0] += weight; // Coverage
if ((int) datum.classValue() == (int) rule.getConsequent())
stats[2] += weight; // True positives
else stats[4] += weight; // False positives
if (dist != null) dist[(int) datum.classValue()] += weight;
} else {
data[1].add(datum); // Not covered by this rule
stats[1] += weight;
if ((int) datum.classValue() != (int) rule.getConsequent())
stats[3] += weight; // True negatives
else stats[5] += weight; // False negatives
}
}
return data;
}
/**
* Tests the ThresholdCurve generation from the command line. The classifier is currently
* hardcoded. Pipe in an arff file.
*
* @param args currently ignored
*/
public static void main(String[] args) {
try {
Instances inst = new Instances(new java.io.InputStreamReader(System.in));
if (false) {
System.out.println(ThresholdCurve.getNPointPrecision(inst, 11));
} else {
inst.setClassIndex(inst.numAttributes() - 1);
ThresholdCurve tc = new ThresholdCurve();
EvaluationUtils eu = new EvaluationUtils();
Classifier classifier = new weka.classifiers.functions.Logistic();
FastVector predictions = new FastVector();
for (int i = 0; i < 2; i++) { // Do two runs.
eu.setSeed(i);
predictions.appendElements(eu.getCVPredictions(classifier, inst, 10));
// System.out.println("\n\n\n");
}
Instances result = tc.getCurve(predictions);
System.out.println(result);
}
} catch (Exception ex) {
ex.printStackTrace();
}
}
public static double CA(Instances odata, int[] clusters) {
double result = 0;
double[] tmpdclass = odata.attributeToDoubleArray(odata.numAttributes() - 1);
int[] oclass = new int[odata.numInstances()];
for (int i = 0; i < tmpdclass.length; ++i) {
oclass[i] = (int) tmpdclass[i];
}
int[] tmpclass = oclass.clone();
int[] tmpclusters = clusters.clone();
Arrays.sort(tmpclusters);
Arrays.sort(tmpclass);
int[][] M = new int[tmpclass[tmpclass.length - 1] + 1][tmpclusters[tmpclusters.length - 1] + 1];
for (int i = 0; i < clusters.length; ++i) {
M[oclass[i]][clusters[i]]++;
}
for (int i = 0; i < M.length; ++i) {
System.out.println(Arrays.toString(M[i]));
}
for (int i = 0; i < M.length; ++i) {
int maxindex = -1;
for (int j = 0; j < M[0].length - 1; ++j) {
if (M[i][j] < M[i][j + 1]) maxindex = j + 1;
}
M[i][0] = maxindex;
}
for (int i = 0; i < oclass.length; ++i) {
if (M[oclass[i]][0] == clusters[i]) result++;
}
return (double) result / (double) odata.numInstances();
}
/**
* Returns a string representation of the classifier.
*
* @return a string representation of the classifier
*/
public String toString() {
StringBuffer result =
new StringBuffer(
"The independent probability of a class\n--------------------------------------\n");
for (int c = 0; c < m_numClasses; c++)
result
.append(m_headerInfo.classAttribute().value(c))
.append("\t")
.append(Double.toString(m_probOfClass[c]))
.append("\n");
result.append(
"\nThe probability of a word given the class\n-----------------------------------------\n\t");
for (int c = 0; c < m_numClasses; c++)
result.append(m_headerInfo.classAttribute().value(c)).append("\t");
result.append("\n");
for (int w = 0; w < m_numAttributes; w++) {
result.append(m_headerInfo.attribute(w).name()).append("\t");
for (int c = 0; c < m_numClasses; c++)
result.append(Double.toString(Math.exp(m_probOfWordGivenClass[c][w]))).append("\t");
result.append("\n");
}
return result.toString();
}
/**
* Calculates the centroid pivot of a node based on the list of points that it contains (tbe two
* lists of its children are provided).
*
* @param list1 The point index list of first child.
* @param list2 The point index list of second child.
* @param insts The insts object on which the tree is being built (for header information).
* @return The centroid pivot of the node.
*/
public Instance calcPivot(MyIdxList list1, MyIdxList list2, Instances insts) {
int classIdx = m_Instances.classIndex();
double[] attrVals = new double[insts.numAttributes()];
Instance temp;
for (int i = 0; i < list1.length(); i++) {
temp = insts.instance(((ListNode) list1.get(i)).idx);
for (int k = 0; k < temp.numValues(); k++) {
if (temp.index(k) == classIdx) continue;
attrVals[k] += temp.valueSparse(k);
}
}
for (int j = 0; j < list2.length(); j++) {
temp = insts.instance(((ListNode) list2.get(j)).idx);
for (int k = 0; k < temp.numValues(); k++) {
if (temp.index(k) == classIdx) continue;
attrVals[k] += temp.valueSparse(k);
}
}
for (int j = 0, numInsts = list1.length() + list2.length(); j < attrVals.length; j++) {
attrVals[j] /= numInsts;
}
temp = new DenseInstance(1.0, attrVals);
return temp;
}
/** test the batch saving/loading (via setFile(File)). */
public void testBatch() {
Instances data;
try {
// save
m_Saver.setInstances(m_Instances);
m_Saver.setFile(new File(m_ExportFilename));
m_Saver.writeBatch();
// load
((AbstractFileLoader) m_Loader).setFile(new File(m_ExportFilename));
data = m_Loader.getDataSet();
// compare data
try {
if (m_Instances.classIndex() != data.classIndex()) {
data.setClassIndex(m_Instances.classIndex());
}
compareDatasets(m_Instances, data);
} catch (Exception e) {
fail("Incremental load failed (datasets differ): " + e.toString());
}
} catch (Exception e) {
e.printStackTrace();
fail("Batch save/load failed: " + e.toString());
}
}
/**
* Signify that this batch of input to the filter is finished.
*
* @return true if there are instances pending output
* @throws IllegalStateException if no input structure has been defined
*/
@Override
public boolean batchFinished() throws Exception {
if (getInputFormat() == null) {
throw new IllegalStateException("No input instance format defined");
}
if (!m_firstBatchFinished) {
Instances filtered;
if (m_numOfCrossValidationFolds < 2) {
filtered = cleanseTrain(getInputFormat());
} else {
filtered = cleanseCross(getInputFormat());
}
for (int i = 0; i < filtered.numInstances(); i++) {
push(filtered.instance(i));
}
m_firstBatchFinished = true;
flushInput();
}
m_NewBatch = true;
return (numPendingOutput() != 0);
}
/**
* Aggregate an object with this one
*
* @param toAggregate the object to aggregate
* @return the result of aggregation
* @throws Exception if the supplied object can't be aggregated for some reason
*/
@Override
public Logistic aggregate(Logistic toAggregate) throws Exception {
if (m_numModels == Integer.MIN_VALUE) {
throw new Exception(
"Can't aggregate further - model has already been " + "aggregated and finalized");
}
if (m_Par == null) {
throw new Exception("No model built yet, can't aggregate");
}
if (!m_structure.equalHeaders(toAggregate.m_structure)) {
throw new Exception(
"Can't aggregate - data headers dont match: "
+ m_structure.equalHeadersMsg(toAggregate.m_structure));
}
for (int i = 0; i < m_Par.length; i++) {
for (int j = 0; j < m_Par[i].length; j++) {
m_Par[i][j] += toAggregate.m_Par[i][j];
}
}
m_numModels++;
return this;
}
