/**
* Constructor that generates a sparse instance from the given instance. Reference to the dataset
* is set to null. (ie. the instance doesn't have access to information about the attribute types)
*
* @param instance the instance from which the attribute values and the weight are to be copied
*/
public SparseInstance(Instance instance) {
m_Weight = instance.weight();
m_Dataset = null;
m_NumAttributes = instance.numAttributes();
if (instance instanceof SparseInstance) {
m_AttValues = ((SparseInstance) instance).m_AttValues;
m_Indices = ((SparseInstance) instance).m_Indices;
} else {
double[] tempValues = new double[instance.numAttributes()];
int[] tempIndices = new int[instance.numAttributes()];
int vals = 0;
for (int i = 0; i < instance.numAttributes(); i++) {
if (instance.value(i) != 0) {
tempValues[vals] = instance.value(i);
tempIndices[vals] = i;
vals++;
}
}
m_AttValues = new double[vals];
m_Indices = new int[vals];
System.arraycopy(tempValues, 0, m_AttValues, 0, vals);
System.arraycopy(tempIndices, 0, m_Indices, 0, vals);
}
}
/**
* Inserts an instance into the hash table
*
* @param inst instance to be inserted
* @param instA to create the hash key from
* @throws Exception if the instance can't be inserted
*/
private void insertIntoTable(Instance inst, double[] instA) throws Exception {
double[] tempClassDist2;
double[] newDist;
DecisionTableHashKey thekey;
if (instA != null) {
thekey = new DecisionTableHashKey(instA);
} else {
thekey = new DecisionTableHashKey(inst, inst.numAttributes(), false);
}
// see if this one is already in the table
tempClassDist2 = (double[]) m_entries.get(thekey);
if (tempClassDist2 == null) {
if (m_classIsNominal) {
newDist = new double[m_theInstances.classAttribute().numValues()];
// Leplace estimation
for (int i = 0; i < m_theInstances.classAttribute().numValues(); i++) {
newDist[i] = 1.0;
}
newDist[(int) inst.classValue()] = inst.weight();
// add to the table
m_entries.put(thekey, newDist);
} else {
newDist = new double[2];
newDist[0] = inst.classValue() * inst.weight();
newDist[1] = inst.weight();
// add to the table
m_entries.put(thekey, newDist);
}
} else {
// update the distribution for this instance
if (m_classIsNominal) {
tempClassDist2[(int) inst.classValue()] += inst.weight();
// update the table
m_entries.put(thekey, tempClassDist2);
} else {
tempClassDist2[0] += (inst.classValue() * inst.weight());
tempClassDist2[1] += inst.weight();
// update the table
m_entries.put(thekey, tempClassDist2);
}
}
}
/**
* Merges this instance with the given instance and returns the result. Dataset is set to null.
*
* @param inst the instance to be merged with this one
* @return the merged instances
*/
public Instance mergeInstance(Instance inst) {
int[] indices = new int[numValues() + inst.numValues()];
int m = 0;
for (int j = 0; j < numValues(); j++) {
indices[m++] = index(j);
}
for (int j = 0; j < inst.numValues(); j++) {
if (inst.valueSparse(j) != 0) {
indices[m++] = inst.index(j) + inst.numAttributes();
}
}
if (m != indices.length) {
// Need to truncate
int[] newInd = new int[m];
System.arraycopy(indices, 0, newInd, 0, m);
indices = newInd;
}
return new BinarySparseInstance((float) 1.0, indices, numAttributes() + inst.numAttributes());
}
/**
* Merges this instance with the given instance and returns the result. Dataset is set to null.
*
* @param inst the instance to be merged with this one
* @return the merged instances
*/
public Instance mergeInstance(Instance inst) {
double[] values = new double[numValues() + inst.numValues()];
int[] indices = new int[numValues() + inst.numValues()];
int m = 0;
for (int j = 0; j < numValues(); j++, m++) {
values[m] = valueSparse(j);
indices[m] = index(j);
}
for (int j = 0; j < inst.numValues(); j++, m++) {
values[m] = inst.valueSparse(j);
indices[m] = numAttributes() + inst.index(j);
}
return new SparseInstance(1.0, values, indices, numAttributes() + inst.numAttributes());
}
/**
* Updates the minimum and maximum values for all the attributes based on a new instance.
*
* @param instance the new instance
*/
private void updateMinMax(Instance instance) {
for (int j = 0; j < instance.numAttributes(); j++) {
if (Double.isNaN(m_Min[j])) {
m_Min[j] = instance.value(j);
m_Max[j] = instance.value(j);
} else {
if (instance.value(j) < m_Min[j]) {
m_Min[j] = instance.value(j);
} else {
if (instance.value(j) > m_Max[j]) {
m_Max[j] = instance.value(j);
}
}
}
}
}
/**
* 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;
}
/**
* 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();
}
}
}
