// 将一个文本数据转换成weka可以识别的Instance
private Instance makeInstance(String text, Instances data) {
Instance instance = new Instance(2);
Attribute messageAtt = data.attribute("Message");
instance.setValue(messageAtt, messageAtt.addStringValue(text));
instance.setDataset(data);
return instance;
}
public void restart() {
IMDb = 0L;
Oracle = 0L;
try {
clearRecords();
recordsSelect = "SELECT " + userColumn + ", " + objectColumn + ", ";
for (Attribute attr : attributes) {
if (attr.isRelationValued() || attr.name().isEmpty()) continue;
recordsSelect += attr.name() + " ,";
}
recordsSelect = recordsSelect.substring(0, recordsSelect.length() - 1);
recordsSelect += " FROM " + recordsTable;
if (betweenCondition != null) {
recordsSelect += " WHERE " + betweenCondition;
}
if (userID != null) {
// We add where clause, if it is not present
if (betweenCondition == null || !recordsSelect.endsWith(betweenCondition))
recordsSelect += " WHERE ";
// AND if where is already there
else recordsSelect += " AND ";
recordsSelect += userColumn + " = " + userID;
}
recordsStatement = provider.getConn().prepareStatement(recordsSelect);
records = recordsStatement.executeQuery();
records.next();
} catch (Exception e) {
e.printStackTrace();
}
getAttributes();
}
/**
* Método que inicializa uma regra com os valores obtidos atraves do Apriori.
*
* @param b Corpo da regre
* @param h Cabecao da regra
* @param conf Confianca da regra
* @param e Lista com os atributos da regra
* @param c Atributo da classe da regra
*/
public Regra(ItemSet b, ItemSet h, double conf, Enumeration<Attribute> e, Attribute c)
throws Exception {
cabeca = h.itemAt(0);
confianca = conf;
int corpoTemp[] = b.items();
atributosNaoVazios = 0;
corpo = new Atributo[corpoTemp.length];
int i = 0;
while (e.hasMoreElements()) {
Attribute att = (Attribute) e.nextElement();
// attributes.add(att);
if (att.isNominal()) {
if (corpoTemp[i] == -1) {
AtributoNominal vazio = new AtributoNominal(true, att, i);
corpo[i++] = vazio;
} else {
AtributoNominal nominal =
new AtributoNominal(corpoTemp[i], AtributoNominal.igual, att, i);
corpo[i++] = nominal;
}
} else {
throw new Exception("Atributo não nominal!");
}
}
classe = c;
matrizContigencia = new MatrizContingencia();
getNumAtributosNaoVazios();
}
@Override
public String classify(User user, Sample sample) {
Instances trainingSet =
new TrainingSetBuilder()
.setAttributes(user.getBssids())
.setClassAttribute(
"Location",
user.getLocations().stream().map(Location::getName).collect(Collectors.toList()))
.build("TrainingSet", 1);
// Create instance
Map<String, Integer> BSSIDLevelMap = getBSSIDLevelMap(sample);
Instance instance = new Instance(trainingSet.numAttributes());
for (Enumeration e = trainingSet.enumerateAttributes(); e.hasMoreElements(); ) {
Attribute attribute = (Attribute) e.nextElement();
String bssid = attribute.name();
int level = (BSSIDLevelMap.containsKey(bssid)) ? BSSIDLevelMap.get(bssid) : 0;
instance.setValue(attribute, level);
}
if (sample.getLocation() != null)
instance.setValue(trainingSet.classAttribute(), sample.getLocation());
instance.setDataset(trainingSet);
trainingSet.add(instance);
int predictedClass = classify(fromBase64(user.getClassifiers()), instance);
return trainingSet.classAttribute().value(predictedClass);
}
/**
* Input an instance for filtering.
*
* @param instance the input instance
* @return true if the filtered instance may now be collected with output().
* @throws Exception if the input format was not set or the date format cannot be parsed
*/
public boolean input(Instance instance) throws Exception {
if (getInputFormat() == null) {
throw new IllegalStateException("No input instance format defined");
}
if (m_NewBatch) {
resetQueue();
m_NewBatch = false;
}
Instance newInstance = (Instance) instance.copy();
int index = m_AttIndex.getIndex();
if (!newInstance.isMissing(index)) {
double value = instance.value(index);
try {
// Format and parse under the new format to force any required
// loss in precision.
value = m_OutputAttribute.parseDate(m_OutputAttribute.formatDate(value));
} catch (ParseException pe) {
throw new RuntimeException("Output date format couldn't parse its own output!!");
}
newInstance.setValue(index, value);
}
push(newInstance);
return true;
}
@Override
public List<Classifier> buildClassifiers(User user, List<Sample> validSamples) {
Instances trainingSet =
new TrainingSetBuilder()
.setAttributes(user.getBssids())
.setClassAttribute(
"Location",
user.getLocations().stream().map(Location::getName).collect(Collectors.toList()))
.build("TrainingSet", validSamples.size());
// Create instances
validSamples.forEach(
sample -> {
Map<String, Integer> BSSIDLevelMap = getBSSIDLevelMap(sample);
Instance instance = new Instance(trainingSet.numAttributes());
for (Enumeration e = trainingSet.enumerateAttributes(); e.hasMoreElements(); ) {
Attribute attribute = (Attribute) e.nextElement();
String bssid = attribute.name();
int level = (BSSIDLevelMap.containsKey(bssid)) ? BSSIDLevelMap.get(bssid) : 0;
instance.setValue(attribute, level);
}
instance.setValue(trainingSet.classAttribute(), sample.getLocation());
instance.setDataset(trainingSet);
trainingSet.add(instance);
});
// Build classifiers
List<Classifier> classifiers = buildClassifiers(trainingSet);
return classifiers;
}
/**
* Calculates the class membership probabilities for the given test instance.
*
* @param instance the instance to be classified
* @return predicted class probability distribution
* @exception Exception if distribution can't be computed
*/
@Override
public double[] distributionForInstance(Instance instance) throws Exception {
double[] probs = new double[instance.numClasses()];
int attIndex;
for (int j = 0; j < instance.numClasses(); j++) {
probs[j] = 1;
Enumeration<Attribute> enumAtts = instance.enumerateAttributes();
attIndex = 0;
while (enumAtts.hasMoreElements()) {
Attribute attribute = enumAtts.nextElement();
if (!instance.isMissing(attribute)) {
if (attribute.isNominal()) {
probs[j] *= m_Counts[j][attIndex][(int) instance.value(attribute)];
} else {
probs[j] *=
normalDens(instance.value(attribute), m_Means[j][attIndex], m_Devs[j][attIndex]);
}
}
attIndex++;
}
probs[j] *= m_Priors[j];
}
// Normalize probabilities
Utils.normalize(probs);
return probs;
}
/** Computes average class values for each attribute and value */
private void computeAverageClassValues() {
double totalCounts, sum;
Instance instance;
double[] counts;
double[][] avgClassValues = new double[getInputFormat().numAttributes()][0];
m_Indices = new int[getInputFormat().numAttributes()][0];
for (int j = 0; j < getInputFormat().numAttributes(); j++) {
Attribute att = getInputFormat().attribute(j);
if (att.isNominal()) {
avgClassValues[j] = new double[att.numValues()];
counts = new double[att.numValues()];
for (int i = 0; i < getInputFormat().numInstances(); i++) {
instance = getInputFormat().instance(i);
if (!instance.classIsMissing() && (!instance.isMissing(j))) {
counts[(int) instance.value(j)] += instance.weight();
avgClassValues[j][(int) instance.value(j)] += instance.weight() * instance.classValue();
}
}
sum = Utils.sum(avgClassValues[j]);
totalCounts = Utils.sum(counts);
if (Utils.gr(totalCounts, 0)) {
for (int k = 0; k < att.numValues(); k++) {
if (Utils.gr(counts[k], 0)) {
avgClassValues[j][k] /= counts[k];
} else {
avgClassValues[j][k] = sum / totalCounts;
}
}
}
m_Indices[j] = Utils.sort(avgClassValues[j]);
}
}
}
/**
* Compute the number of all possible conditions that could appear in a rule of a given data. For
* nominal attributes, it's the number of values that could appear; for numeric attributes, it's
* the number of values * 2, i.e. <= and >= are counted as different possible conditions.
*
* @param data the given data
* @return number of all conditions of the data
*/
public static double numAllConditions(Instances data) {
double total = 0;
Enumeration attEnum = data.enumerateAttributes();
while (attEnum.hasMoreElements()) {
Attribute att = (Attribute) attEnum.nextElement();
if (att.isNominal()) total += (double) att.numValues();
else total += 2.0 * (double) data.numDistinctValues(att);
}
return total;
}
/** Find the fold attribute within a dataset. */
private Attribute getAttribute(Instances data) {
SingleIndex index = new SingleIndex(super.getAttributeIndex());
index.setUpper(data.numAttributes() - 1);
Attribute att = data.attribute(index.getIndex());
if (att == null)
throw new NoSuchElementException(
"attribute #" + super.getAttributeIndex() + " does not exist");
if (!att.isNominal() && !att.isString())
throw new IllegalArgumentException("Attribute '" + att + "' is not nominal");
return att;
}
/** Helper method to represent an Attribute as a single-element vector. */
private int[] toValueIndexArray(Attribute attribute) {
TIntArrayList out = new TIntArrayList();
for (String value : values) {
int valueIndex = attribute.indexOfValue(value);
if (valueIndex < 0)
throw new NoSuchElementException(
"no such value: '" + value + "' in attribute '" + attribute.toString() + "'");
out.add(valueIndex);
}
return out.toNativeArray();
}
public double classifyInstance(Instance inst) throws Exception {
if (m_attribute == null) {
return m_intercept;
} else {
if (inst.isMissing(m_attribute.index())) {
throw new Exception("UnivariateLinearRegression: No missing values!");
}
return m_intercept + m_slope * inst.value(m_attribute.index());
}
}
/**
* Adds this tree recursively to the buffer.
*
* @param id the unqiue id for the method
* @param buffer the buffer to add the source code to
* @return the last ID being used
* @throws Exception if something goes wrong
*/
protected int toSource(int id, StringBuffer buffer) throws Exception {
int result;
int i;
int newID;
StringBuffer[] subBuffers;
buffer.append("\n");
buffer.append(" protected static double node" + id + "(Object[] i) {\n");
// leaf?
if (m_Attribute == null) {
result = id;
if (Double.isNaN(m_ClassValue)) buffer.append(" return Double.NaN;");
else buffer.append(" return " + m_ClassValue + ";");
if (m_ClassAttribute != null)
buffer.append(" // " + m_ClassAttribute.value((int) m_ClassValue));
buffer.append("\n");
buffer.append(" }\n");
} else {
buffer.append(" // " + m_Attribute.name() + "\n");
// subtree calls
subBuffers = new StringBuffer[m_Attribute.numValues()];
newID = id;
for (i = 0; i < m_Attribute.numValues(); i++) {
newID++;
buffer.append(" ");
if (i > 0) buffer.append("else ");
buffer.append(
"if (((String) i["
+ m_Attribute.index()
+ "]).equals(\""
+ m_Attribute.value(i)
+ "\"))\n");
buffer.append(" return node" + newID + "(i);\n");
subBuffers[i] = new StringBuffer();
newID = m_Successors[i].toSource(newID, subBuffers[i]);
}
buffer.append(" else\n");
buffer.append(
" throw new IllegalArgumentException(\"Value '\" + i["
+ m_Attribute.index()
+ "] + \"' is not allowed!\");\n");
buffer.append(" }\n");
// output subtree code
for (i = 0; i < m_Attribute.numValues(); i++) {
buffer.append(subBuffers[i].toString());
}
subBuffers = null;
result = newID;
}
return result;
}
/**
* Splits a dataset according to the values of a nominal attribute.
*
* @param data the data which is to be split
* @param att the attribute to be used for splitting
* @return the sets of instances produced by the split
*/
private Instances[] splitData(Instances data, Attribute att) {
Instances[] splitData = new Instances[att.numValues()];
for (int j = 0; j < att.numValues(); j++) {
splitData[j] = new Instances(data, data.numInstances());
}
Enumeration instEnum = data.enumerateInstances();
while (instEnum.hasMoreElements()) {
Instance inst = (Instance) instEnum.nextElement();
splitData[(int) inst.value(att)].add(inst);
}
for (int i = 0; i < splitData.length; i++) {
splitData[i].compactify();
}
return splitData;
}
@Override
public int compare(InstanceHolder o1, InstanceHolder o2) {
// both missing is equal
if (o1.m_instance.isMissing(m_attribute) && o2.m_instance.isMissing(m_attribute)) {
return 0;
}
// one missing - missing instances should all be at the end
// regardless of whether order is ascending or descending
if (o1.m_instance.isMissing(m_attribute)) {
return 1;
}
if (o2.m_instance.isMissing(m_attribute)) {
return -1;
}
int cmp = 0;
if (!m_attribute.isString() && !m_attribute.isRelationValued()) {
double val1 = o1.m_instance.value(m_attribute);
double val2 = o2.m_instance.value(m_attribute);
cmp = Double.compare(val1, val2);
} else if (m_attribute.isString()) {
String val1 = o1.m_stringVals.get(m_attribute.name());
String val2 = o2.m_stringVals.get(m_attribute.name());
/*
* String val1 = o1.stringValue(m_attribute); String val2 =
* o2.stringValue(m_attribute);
*/
// TODO case insensitive?
cmp = val1.compareTo(val2);
} else {
throw new IllegalArgumentException(
"Can't sort according to " + "relation-valued attribute values!");
}
if (m_descending) {
return -cmp;
}
return cmp;
}
/**
* Cálculo da precisão de Laplace
*
* @return Precisão de Laplace
*/
public double getLaplace() {
double temp = matrizContigencia.getB();
int numClasses = classe.numValues();
if (temp != 0) laplace = (matrizContigencia.getH_B() + 1) / (temp + numClasses);
else laplace = 0;
return laplace;
}
/**
* Convert a single instance over if the class is numeric. The converted instance is added to the
* end of the output queue.
*
* @param instance the instance to convert
*/
private void convertInstanceNumeric(Instance instance) {
if (!m_needToTransform) {
push(instance);
return;
}
double[] vals = new double[outputFormatPeek().numAttributes()];
int attSoFar = 0;
for (int j = 0; j < getInputFormat().numAttributes(); j++) {
Attribute att = getInputFormat().attribute(j);
if ((!att.isNominal()) || (j == getInputFormat().classIndex())) {
vals[attSoFar] = instance.value(j);
attSoFar++;
} else {
if (instance.isMissing(j)) {
for (int k = 0; k < att.numValues() - 1; k++) {
vals[attSoFar + k] = instance.value(j);
}
} else {
int k = 0;
while ((int) instance.value(j) != m_Indices[j][k]) {
vals[attSoFar + k] = 1;
k++;
}
while (k < att.numValues() - 1) {
vals[attSoFar + k] = 0;
k++;
}
}
attSoFar += att.numValues() - 1;
}
}
Instance inst = null;
if (instance instanceof SparseInstance) {
inst = new SparseInstance(instance.weight(), vals);
} else {
inst = new DenseInstance(instance.weight(), vals);
}
inst.setDataset(getOutputFormat());
copyValues(inst, false, instance.dataset(), getOutputFormat());
inst.setDataset(getOutputFormat());
push(inst);
}
/**
* Set the output format. Takes the current average class values and m_InputFormat and calls
* setOutputFormat(Instances) appropriately.
*/
private void setOutputFormat() {
Instances newData;
FastVector newAtts;
// Compute new attributes
newAtts = new FastVector(getInputFormat().numAttributes());
for (int j = 0; j < getInputFormat().numAttributes(); j++) {
Attribute att = getInputFormat().attribute(j);
if (!att.isNominal() || !m_AttIndex.isInRange(j)) newAtts.addElement(att);
else newAtts.addElement(new Attribute(att.name(), (FastVector) null));
}
// Construct new header
newData = new Instances(getInputFormat().relationName(), newAtts, 0);
newData.setClassIndex(getInputFormat().classIndex());
setOutputFormat(newData);
}
/**
* Calculate metric value
*
* @param mlData Multi-label dataset to which calculate the metric
* @return Value of the metric
*/
public double calculate(MultiLabelInstances mlData) {
Instances instances = mlData.getDataSet();
int nInstances = mlData.getNumInstances();
double avg;
double var2;
double var4;
double val;
int nNumeric = 0;
double mean = 0;
Set<Attribute> attributesSet = mlData.getFeatureAttributes();
for (Attribute att : attributesSet) {
if (att.isNumeric()) {
nNumeric++;
avg = instances.meanOrMode(att);
var2 = 0;
var4 = 0;
for (Instance inst : instances) {
val = inst.value(att);
var2 += Math.pow(val - avg, 2);
var4 += Math.pow(val - avg, 4);
}
double kurtosis = (nInstances * var4 / Math.pow(var2, 2)) - 3;
double sampleKurtosis =
(kurtosis * (nInstances + 1) + 6)
* (nInstances - 1)
/ ((nInstances - 2) * (nInstances - 3));
mean += sampleKurtosis;
}
}
if (nNumeric > 0) {
mean = mean / nNumeric;
} else {
mean = Double.NaN;
}
this.value = mean;
return value;
}
/** Set the output format. Changes the format of the specified date attribute. */
private void setOutputFormat() {
// Create new attributes
FastVector newAtts = new FastVector(getInputFormat().numAttributes());
for (int j = 0; j < getInputFormat().numAttributes(); j++) {
Attribute att = getInputFormat().attribute(j);
if (j == m_AttIndex.getIndex()) {
newAtts.addElement(new Attribute(att.name(), getDateFormat().toPattern()));
} else {
newAtts.addElement(att.copy());
}
}
// Create new header
Instances newData = new Instances(getInputFormat().relationName(), newAtts, 0);
newData.setClassIndex(getInputFormat().classIndex());
m_OutputAttribute = newData.attribute(m_AttIndex.getIndex());
setOutputFormat(newData);
}
/**
* Returns the test represented by a string in Prolog notation.
*
* @return a string representing the test in Prolog notation
*/
public String toPrologString() {
Attribute att = m_Dataset.attribute(m_AttIndex);
StringBuffer str = new StringBuffer();
String attName = m_Dataset.attribute(m_AttIndex).name();
if (att.isNumeric()) {
str = str.append(attName + " ");
if (m_Not) str = str.append(">= " + Utils.doubleToString(m_Split, 3));
else str = str.append("< " + Utils.doubleToString(m_Split, 3));
} else {
String value = att.value((int) m_Split);
if (value == "false") {
str = str.append("not(" + attName + ")");
} else {
str = str.append(attName);
}
}
return str.toString();
}
/**
* Constructs an instance suitable for passing to the model for scoring
*
* @param incoming the incoming instance
* @return an instance with values mapped to be consistent with what the model is expecting
*/
protected Instance mapIncomingFieldsToModelFields(Instance incoming) {
Instances modelHeader = m_model.getHeader();
double[] vals = new double[modelHeader.numAttributes()];
for (int i = 0; i < modelHeader.numAttributes(); i++) {
if (m_attributeMap[i] < 0) {
// missing or type mismatch
vals[i] = Utils.missingValue();
continue;
}
Attribute modelAtt = modelHeader.attribute(i);
Attribute incomingAtt = incoming.dataset().attribute(m_attributeMap[i]);
if (incoming.isMissing(incomingAtt.index())) {
vals[i] = Utils.missingValue();
continue;
}
if (modelAtt.isNumeric()) {
vals[i] = incoming.value(m_attributeMap[i]);
} else if (modelAtt.isNominal()) {
String incomingVal = incoming.stringValue(m_attributeMap[i]);
int modelIndex = modelAtt.indexOfValue(incomingVal);
if (modelIndex < 0) {
vals[i] = Utils.missingValue();
} else {
vals[i] = modelIndex;
}
} else if (modelAtt.isString()) {
vals[i] = 0;
modelAtt.setStringValue(incoming.stringValue(m_attributeMap[i]));
}
}
if (modelHeader.classIndex() >= 0) {
// set class to missing value
vals[modelHeader.classIndex()] = Utils.missingValue();
}
Instance newInst = null;
if (incoming instanceof SparseInstance) {
newInst = new SparseInstance(incoming.weight(), vals);
} else {
newInst = new DenseInstance(incoming.weight(), vals);
}
newInst.setDataset(modelHeader);
return newInst;
}
/**
* processes the given instance (may change the provided instance) and returns the modified
* version.
*
* @param instance the instance to process
* @return the modified data
* @throws Exception in case the processing goes wrong
*/
protected Instance process(Instance instance) throws Exception {
Instance result;
Attribute att;
double[] values;
int i;
// adjust indices
values = new double[instance.numAttributes()];
for (i = 0; i < instance.numAttributes(); i++) {
att = instance.attribute(i);
if (!att.isNominal() || !m_AttributeIndices.isInRange(i) || instance.isMissing(i))
values[i] = instance.value(i);
else values[i] = m_NewOrder[i][(int) instance.value(i)];
}
// create new instance
result = new DenseInstance(instance.weight(), values);
return result;
}
public String toString() {
if (m_attribute == null) {
return "No model built yet.";
}
StringBuffer text = new StringBuffer();
if (m_attribute == null) {
text.append("Predicting constant " + m_intercept);
} else {
text.append("Linear regression on " + m_attribute.name() + "\n\n");
text.append(Utils.doubleToString(m_slope, 2) + " * " + m_attribute.name());
if (m_intercept > 0) {
text.append(" + " + Utils.doubleToString(m_intercept, 2));
} else {
text.append(" - " + Utils.doubleToString((-m_intercept), 2));
}
}
text.append("\n");
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]);
}
}
}
/**
* Set the output format. Takes the current average class values and m_InputFormat and calls
* setOutputFormat(Instances) appropriately.
*/
private void setOutputFormat() {
Instances newData;
FastVector newAtts, newVals;
// Compute new attributes
newAtts = new FastVector(getInputFormat().numAttributes());
for (int j = 0; j < getInputFormat().numAttributes(); j++) {
Attribute att = getInputFormat().attribute(j);
if (!m_AttIndices.isInRange(j) || !att.isString()) {
// We don't have to copy the attribute because the
// attribute index remains unchanged.
newAtts.addElement(att);
} else {
// Compute list of attribute values
newVals = new FastVector(att.numValues());
for (int i = 0; i < att.numValues(); i++) {
newVals.addElement(att.value(i));
}
newAtts.addElement(new Attribute(att.name(), newVals));
}
}
// Construct new header
newData = new Instances(getInputFormat().relationName(), newAtts, 0);
newData.setClassIndex(getInputFormat().classIndex());
setOutputFormat(newData);
}
/**
* Sets up the structure for the plot instances. Sets m_PlotInstances to null if instances are not
* saved for visualization.
*
* @see #getSaveForVisualization()
*/
protected void determineFormat() {
FastVector hv;
Attribute predictedClass;
Attribute classAt;
FastVector attVals;
int i;
if (!m_SaveForVisualization) {
m_PlotInstances = null;
return;
}
hv = new FastVector();
classAt = m_Instances.attribute(m_ClassIndex);
if (classAt.isNominal()) {
attVals = new FastVector();
for (i = 0; i < classAt.numValues(); i++) attVals.addElement(classAt.value(i));
predictedClass = new Attribute("predicted" + classAt.name(), attVals);
} else {
predictedClass = new Attribute("predicted" + classAt.name());
}
for (i = 0; i < m_Instances.numAttributes(); i++) {
if (i == m_Instances.classIndex()) hv.addElement(predictedClass);
hv.addElement(m_Instances.attribute(i).copy());
}
m_PlotInstances =
new Instances(m_Instances.relationName() + "_predicted", hv, m_Instances.numInstances());
m_PlotInstances.setClassIndex(m_ClassIndex + 1);
}
/**
* Outputs a tree at a certain level.
*
* @param level the level at which the tree is to be printed
* @return the tree as string at the given level
*/
private String toString(int level) {
StringBuffer text = new StringBuffer();
if (m_Attribute == null) {
if (Utils.isMissingValue(m_ClassValue)) {
text.append(": null");
} else {
text.append(": " + m_ClassAttribute.value((int) m_ClassValue));
}
} else {
for (int j = 0; j < m_Attribute.numValues(); j++) {
text.append("\n");
for (int i = 0; i < level; i++) {
text.append("| ");
}
text.append(m_Attribute.name() + " = " + m_Attribute.value(j));
text.append(m_Successors[j].toString(level + 1));
}
}
return text.toString();
}
/**
* Builds a mapping between the header for the incoming data to be scored and the header used to
* train the model. Uses attribute names to match between the two. Also constructs a list of
* missing attributes and a list of type mismatches.
*
* @param modelHeader the header of the data used to train the model
* @param incomingHeader the header of the incoming data
* @throws DistributedWekaException if more than 50% of the attributes expected by the model are
* missing or have a type mismatch with the incoming data
*/
protected void buildAttributeMap(Instances modelHeader, Instances incomingHeader)
throws DistributedWekaException {
m_attributeMap = new int[modelHeader.numAttributes()];
int problemCount = 0;
for (int i = 0; i < modelHeader.numAttributes(); i++) {
Attribute modAtt = modelHeader.attribute(i);
Attribute incomingAtt = incomingHeader.attribute(modAtt.name());
if (incomingAtt == null) {
// missing model attribute
m_attributeMap[i] = -1;
m_missingMismatch.put(modAtt.name(), "missing from incoming data");
problemCount++;
} else if (modAtt.type() != incomingAtt.type()) {
// type mismatch
m_attributeMap[i] = -1;
m_missingMismatch.put(
modAtt.name(),
"type mismatch - "
+ "model: "
+ Attribute.typeToString(modAtt)
+ " != incoming: "
+ Attribute.typeToString(incomingAtt));
problemCount++;
} else {
m_attributeMap[i] = incomingAtt.index();
}
}
// -1 for the class (if set)
int adjustForClass = modelHeader.classIndex() >= 0 ? 1 : 0;
if (problemCount > (modelHeader.numAttributes() - adjustForClass) / 2) {
throw new DistributedWekaException(
"More than 50% of the attributes that the model "
+ "is expecting to see are either missing or have a type mismatch in the "
+ "incoming data.");
}
}
@Override
public void updateNode(Instance inst) throws Exception {
super.updateDistribution(inst);
for (int i = 0; i < inst.numAttributes(); i++) {
Attribute a = inst.attribute(i);
if (i != inst.classIndex()) {
ConditionalSufficientStats stats = m_nodeStats.get(a.name());
if (stats == null) {
if (a.isNumeric()) {
stats = new GaussianConditionalSufficientStats();
} else {
stats = new NominalConditionalSufficientStats();
}
m_nodeStats.put(a.name(), stats);
}
stats.update(
inst.value(a), inst.classAttribute().value((int) inst.classValue()), inst.weight());
}
}
}
