/**
* 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.");
}
}
public MappingInfo(Instances dataSet, MiningSchema miningSchema, Logger log) throws Exception {
m_log = log;
// miningSchema.convertStringAttsToNominal();
Instances fieldsI = miningSchema.getMiningSchemaAsInstances();
m_fieldsMap = new int[fieldsI.numAttributes()];
m_nominalValueMaps = new int[fieldsI.numAttributes()][];
for (int i = 0; i < fieldsI.numAttributes(); i++) {
String schemaAttName = fieldsI.attribute(i).name();
boolean found = false;
for (int j = 0; j < dataSet.numAttributes(); j++) {
if (dataSet.attribute(j).name().equals(schemaAttName)) {
Attribute miningSchemaAtt = fieldsI.attribute(i);
Attribute incomingAtt = dataSet.attribute(j);
// check type match
if (miningSchemaAtt.type() != incomingAtt.type()) {
throw new Exception(
"[MappingInfo] type mismatch for field "
+ schemaAttName
+ ". Mining schema type "
+ miningSchemaAtt.toString()
+ ". Incoming type "
+ incomingAtt.toString()
+ ".");
}
// check nominal values (number, names...)
if (miningSchemaAtt.numValues() != incomingAtt.numValues()) {
String warningString =
"[MappingInfo] WARNING: incoming nominal attribute "
+ incomingAtt.name()
+ " does not have the same "
+ "number of values as the corresponding mining "
+ "schema attribute.";
if (m_log != null) {
m_log.logMessage(warningString);
} else {
System.err.println(warningString);
}
}
if (miningSchemaAtt.isNominal() || miningSchemaAtt.isString()) {
int[] valuesMap = new int[incomingAtt.numValues()];
for (int k = 0; k < incomingAtt.numValues(); k++) {
String incomingNomVal = incomingAtt.value(k);
int indexInSchema = miningSchemaAtt.indexOfValue(incomingNomVal);
if (indexInSchema < 0) {
String warningString =
"[MappingInfo] WARNING: incoming nominal attribute "
+ incomingAtt.name()
+ " has value "
+ incomingNomVal
+ " that doesn't occur in the mining schema.";
if (m_log != null) {
m_log.logMessage(warningString);
} else {
System.err.println(warningString);
}
valuesMap[k] = UNKNOWN_NOMINAL_VALUE;
} else {
valuesMap[k] = indexInSchema;
}
}
m_nominalValueMaps[i] = valuesMap;
}
/*if (miningSchemaAtt.isNominal()) {
for (int k = 0; k < miningSchemaAtt.numValues(); k++) {
if (!miningSchemaAtt.value(k).equals(incomingAtt.value(k))) {
throw new Exception("[PMMLUtils] value " + k + " (" +
miningSchemaAtt.value(k) + ") does not match " +
"incoming value (" + incomingAtt.value(k) +
") for attribute " + miningSchemaAtt.name() +
".");
}
}
}*/
found = true;
m_fieldsMap[i] = j;
}
}
if (!found) {
throw new Exception(
"[MappingInfo] Unable to find a match for mining schema "
+ "attribute "
+ schemaAttName
+ " in the "
+ "incoming instances!");
}
}
// check class attribute (if set)
if (fieldsI.classIndex() >= 0) {
if (dataSet.classIndex() < 0) {
// first see if we can find a matching class
String className = fieldsI.classAttribute().name();
Attribute classMatch = dataSet.attribute(className);
if (classMatch == null) {
throw new Exception(
"[MappingInfo] Can't find match for target field "
+ className
+ "in incoming instances!");
}
dataSet.setClass(classMatch);
} else if (!fieldsI.classAttribute().name().equals(dataSet.classAttribute().name())) {
throw new Exception(
"[MappingInfo] class attribute in mining schema does not match "
+ "class attribute in incoming instances!");
}
}
// Set up the textual description of the mapping
fieldsMappingString(fieldsI, dataSet);
}
