Many resources are needed to download a project. Please understand that we have to compensate our server costs. Thank you in advance. Project price only 1 $
You can buy this project and download/modify it how often you want.
The Waikato Environment for Knowledge Analysis (WEKA), a machine
learning workbench. This version represents the developer version, the
"bleeding edge" of development, you could say. New functionality gets added
to this version.
/*
* 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 .
*/
/*
* NominalToBinary.java
* Copyright (C) 1999-2012 University of Waikato, Hamilton, New Zealand
*
*/
package weka.filters.supervised.attribute;
import java.util.ArrayList;
import java.util.Enumeration;
import java.util.Vector;
import weka.core.*;
import weka.core.Capabilities.Capability;
import weka.core.TechnicalInformation.Field;
import weka.core.TechnicalInformation.Type;
import weka.filters.Filter;
import weka.filters.SupervisedFilter;
/**
* Converts all nominal attributes into binary numeric
* attributes. An attribute with k values is transformed into k binary
* attributes if the class is nominal (using the one-attribute-per-value
* approach). Binary attributes are left binary if option '-A' is not given. If
* the class is numeric, k - 1 new binary attributes are generated in the manner
* described in "Classification and Regression Trees" by Breiman et al. (i.e.
* by taking the average class value associated with each attribute value into
* account)
*
* For more information, see:
*
* L. Breiman, J.H. Friedman, R.A. Olshen, C.J. Stone (1984). Classification and
* Regression Trees. Wadsworth Inc.
*
*
*
* BibTeX:
*
*
* @book{Breiman1984,
* author = {L. Breiman and J.H. Friedman and R.A. Olshen and C.J. Stone},
* publisher = {Wadsworth Inc},
* title = {Classification and Regression Trees},
* year = {1984},
* ISBN = {0412048418}
* }
*
*
*
*
* Valid options are:
*
*
*
* -N
* Sets if binary attributes are to be coded as nominal ones.
*
*
*
* -A
* For each nominal value a new attribute is created,
* not only if there are more than 2 values.
*
*
*
-spread-attribute-weight
* When generating binary attributes, spread weight of old
* attribute across new attributes. Do not give each new attribute the old weight.
*
*
*
* @author Eibe Frank ([email protected])
* @version $Revision: 14509 $
*/
public class NominalToBinary extends Filter implements SupervisedFilter,
OptionHandler, TechnicalInformationHandler, WeightedAttributesHandler, WeightedInstancesHandler {
/** for serialization */
static final long serialVersionUID = -5004607029857673950L;
/** The sorted indices of the attribute values. */
private int[][] m_Indices = null;
/** Are the new attributes going to be nominal or numeric ones? */
private boolean m_Numeric = true;
/** Are all values transformed into new attributes? */
private boolean m_TransformAll = false;
/** Whether we need to transform at all */
private boolean m_needToTransform = false;
/** Whether to spread attribute weight when creating binary attributes */
protected boolean m_SpreadAttributeWeight = false;
/**
* Returns a string describing this filter
*
* @return a description of the filter suitable for displaying in the
* explorer/experimenter gui
*/
public String globalInfo() {
return "Converts all nominal attributes into binary numeric attributes. An "
+ "attribute with k values is transformed into k binary attributes if "
+ "the class is nominal (using the one-attribute-per-value approach). "
+ "Binary attributes are left binary if option '-A' is not given. "
+ "If the class is numeric, k - 1 new binary attributes are generated "
+ "in the manner described in \"Classification and Regression "
+ "Trees\" by Breiman et al. (i.e., by taking the average class value associated "
+ "with each attribute value into account).\n\n"
+ "For more information, see:\n\n" + getTechnicalInformation().toString();
}
/**
* Returns an instance of a TechnicalInformation object, containing detailed
* information about the technical background of this class, e.g., paper
* reference or book this class is based on.
*
* @return the technical information about this class
*/
@Override
public TechnicalInformation getTechnicalInformation() {
TechnicalInformation result;
result = new TechnicalInformation(Type.BOOK);
result.setValue(Field.AUTHOR,
"L. Breiman and J.H. Friedman and R.A. Olshen and C.J. Stone");
result.setValue(Field.TITLE, "Classification and Regression Trees");
result.setValue(Field.YEAR, "1984");
result.setValue(Field.PUBLISHER, "Wadsworth Inc");
result.setValue(Field.ISBN, "0412048418");
return result;
}
/**
* Returns the Capabilities of this filter.
*
* @return the capabilities of this object
* @see Capabilities
*/
@Override
public Capabilities getCapabilities() {
Capabilities result = super.getCapabilities();
result.disableAll();
// attributes
result.enableAllAttributes();
result.enable(Capability.MISSING_VALUES);
// class
result.enable(Capability.NUMERIC_CLASS);
result.enable(Capability.DATE_CLASS);
result.enable(Capability.NOMINAL_CLASS);
result.enable(Capability.MISSING_CLASS_VALUES);
return result;
}
/**
* 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 Exception if the input format can't be set successfully
*/
@Override
public boolean setInputFormat(Instances instanceInfo) throws Exception {
super.setInputFormat(instanceInfo);
if (instanceInfo.classIndex() < 0) {
throw new UnassignedClassException(
"No class has been assigned to the instances");
}
setOutputFormat();
m_Indices = null;
if (instanceInfo.classAttribute().isNominal()) {
return true;
} else {
return false;
}
}
/**
* Input an instance for filtering. Filter requires all training instances be
* read before producing output.
*
* @param instance the input instance
* @return true if the filtered instance may now be collected with output().
* @throws IllegalStateException if no input format has been set
*/
@Override
public boolean input(Instance instance) {
if (getInputFormat() == null) {
throw new IllegalStateException("No input instance format defined");
}
if (m_NewBatch) {
resetQueue();
m_NewBatch = false;
}
if ((m_Indices != null) || (getInputFormat().classAttribute().isNominal())) {
convertInstance((Instance)instance.copy());
return true;
}
bufferInput(instance);
return false;
}
/**
* Signify that this batch of input to the filter is finished. If the filter
* requires all instances prior to filtering, output() may now be called to
* retrieve the filtered instances.
*
* @return true if there are instances pending output
* @throws IllegalStateException if no input structure has been defined
*/
@Override
public boolean batchFinished() {
if (getInputFormat() == null) {
throw new IllegalStateException("No input instance format defined");
}
if ((m_Indices == null) && (getInputFormat().classAttribute().isNumeric())) {
computeAverageClassValues();
setOutputFormat();
// Convert pending input instances
for (int i = 0; i < getInputFormat().numInstances(); i++) {
convertInstance(getInputFormat().instance(i));
}
}
flushInput();
m_NewBatch = true;
return (numPendingOutput() != 0);
}
/**
* Returns an enumeration describing the available options.
*
* @return an enumeration of all the available options.
*/
@Override
public Enumeration