weka.core.pmml.MappingInfo Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of weka-stable Show documentation
Show all versions of weka-stable Show documentation
The Waikato Environment for Knowledge Analysis (WEKA), a machine
learning workbench. This is the stable version. Apart from bugfixes, this version
does not receive any other updates.
/*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program. If not, see Instance to an array of values that matches the
* format of the mining schema. First maps raw attribute values and then
* applies rules for missing values, outliers etc.
*
* @param inst the Instance to convert
* @param miningSchema the mining schema incoming instance attributes
* @return an array of doubles that are values from the incoming Instances,
* correspond to the format of the mining schema and have had missing
* values, outliers etc. dealt with.
* @throws Exception if something goes wrong
*/
public double[] instanceToSchema(Instance inst, MiningSchema miningSchema)
throws Exception {
Instances miningSchemaI = miningSchema.getMiningSchemaAsInstances();
// allocate enough space for both mining schema fields and any derived
// fields
double[] result = new double[miningSchema.getFieldsAsInstances()
.numAttributes()];
// Copy over the values
for (int i = 0; i < miningSchemaI.numAttributes(); i++) {
// if (miningSchemaI.attribute(i).isNumeric()) {
result[i] = inst.value(m_fieldsMap[i]);
if (miningSchemaI.attribute(i).isNominal()
|| miningSchemaI.attribute(i).isString()) {
// If not missing, look up the index of this incoming categorical value
// in
// the mining schema
if (!Utils.isMissingValue(inst.value(m_fieldsMap[i]))) {
int[] valueMap = m_nominalValueMaps[i];
int index = valueMap[(int) inst.value(m_fieldsMap[i])];
String incomingAttValue = inst.attribute(m_fieldsMap[i]).value(
(int) inst.value(m_fieldsMap[i]));
/*
* int index =
* miningSchemaI.attribute(i).indexOfValue(incomingAttValue);
*/
if (index >= 0) {
result[i] = index;
} else {
// set this to "unknown" (-1) for nominal valued attributes
result[i] = UNKNOWN_NOMINAL_VALUE;
String warningString = "[MappingInfo] WARNING: Can't match nominal value "
+ incomingAttValue;
if (m_log != null) {
m_log.logMessage(warningString);
} else {
System.err.println(warningString);
}
}
}
}
}
// Now deal with missing values and outliers...
miningSchema.applyMissingAndOutlierTreatments(result);
// printInst(result);
// now fill in any derived values
ArrayList derivedFields = miningSchema
.getDerivedFields();
for (int i = 0; i < derivedFields.size(); i++) {
DerivedFieldMetaInfo temp = derivedFields.get(i);
// System.err.println("Applying : " + temp);
double r = temp.getDerivedValue(result);
result[i + miningSchemaI.numAttributes()] = r;
}
/*
* System.err.print("==> "); for (int i = 0; i < result.length; i++) {
* System.err.print(" " + result[i]); } System.err.println();
*/
return result;
}
/**
* Get a textual description of them mapping between mining schema fields and
* incoming data fields.
*
* @return a description of the fields mapping as a String
*/
public String getFieldsMappingString() {
if (m_fieldsMappingText == null) {
return "No fields mapping constructed!";
}
return m_fieldsMappingText;
}
}