weka.filters.unsupervised.attribute.Center Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of weka-dev Show documentation
Show all versions of weka-dev Show documentation
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 .
*/
/*
* Center.java
* Copyright (C) 2006-2012 University of Waikato, Hamilton, New Zealand
*
*/
package weka.filters.unsupervised.attribute;
import weka.core.Capabilities;
import weka.core.Capabilities.Capability;
import weka.core.DenseInstance;
import weka.core.Instance;
import weka.core.Instances;
import weka.core.RevisionUtils;
import weka.core.SparseInstance;
import weka.core.Utils;
import weka.filters.Sourcable;
import weka.filters.UnsupervisedFilter;
/**
* Centers all numeric attributes in the given dataset to have zero mean (apart from the class attribute, if set).
*
*
* Valid options are:
*
* -unset-class-temporarily
* Unsets the class index temporarily before the filter is
* applied to the data.
* (default: no)
*
*
* @author Eibe Frank ([email protected])
* @author FracPete (fracpete at waikato dot ac dot nz)
* @version $Revision: 8034 $
*/
public class Center
extends PotentialClassIgnorer
implements UnsupervisedFilter, Sourcable {
/** for serialization */
private static final long serialVersionUID = -9101338448900581023L;
/** The means */
private double[] m_Means;
/**
* Returns a string describing this filter
*
* @return a description of the filter suitable for
* displaying in the explorer/experimenter gui
*/
public String globalInfo() {
return "Centers all numeric attributes in the given dataset "
+ "to have zero mean (apart from the class attribute, if set).";
}
/**
* Returns the Capabilities of this filter.
*
* @return the capabilities of this object
* @see Capabilities
*/
public Capabilities getCapabilities() {
Capabilities result = super.getCapabilities();
result.disableAll();
// attributes
result.enableAllAttributes();
result.enable(Capability.MISSING_VALUES);
// class
result.enableAllClasses();
result.enable(Capability.MISSING_CLASS_VALUES);
result.enable(Capability.NO_CLASS);
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
*/
public boolean setInputFormat(Instances instanceInfo) throws Exception {
super.setInputFormat(instanceInfo);
setOutputFormat(instanceInfo);
m_Means = null;
return true;
}
/**
* 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.
*/
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_Means == null) {
bufferInput(instance);
return false;
}
else {
convertInstance(instance);
return true;
}
}
/**
* 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
*/
public boolean batchFinished() {
if (getInputFormat() == null)
throw new IllegalStateException("No input instance format defined");
if (m_Means == null) {
Instances input = getInputFormat();
m_Means = new double[input.numAttributes()];
for (int i = 0; i < input.numAttributes(); i++) {
if (input.attribute(i).isNumeric() &&
(input.classIndex() != i)) {
m_Means[i] = input.meanOrMode(i);
}
}
// Convert pending input instances
for (int i = 0; i < input.numInstances(); i++)
convertInstance(input.instance(i));
}
// Free memory
flushInput();
m_NewBatch = true;
return (numPendingOutput() != 0);
}
/**
* Convert a single instance over. The converted instance is
* added to the end of the output queue.
*
* @param instance the instance to convert
*/
private void convertInstance(Instance instance) {
Instance inst = null;
if (instance instanceof SparseInstance) {
double[] newVals = new double[instance.numAttributes()];
int[] newIndices = new int[instance.numAttributes()];
double[] vals = instance.toDoubleArray();
int ind = 0;
for (int j = 0; j < instance.numAttributes(); j++) {
double value;
if (instance.attribute(j).isNumeric() &&
(!Utils.isMissingValue(vals[j])) &&
(getInputFormat().classIndex() != j)) {
value = vals[j] - m_Means[j];
if (value != 0.0) {
newVals[ind] = value;
newIndices[ind] = j;
ind++;
}
} else {
value = vals[j];
if (value != 0.0) {
newVals[ind] = value;
newIndices[ind] = j;
ind++;
}
}
}
double[] tempVals = new double[ind];
int[] tempInd = new int[ind];
System.arraycopy(newVals, 0, tempVals, 0, ind);
System.arraycopy(newIndices, 0, tempInd, 0, ind);
inst = new SparseInstance(instance.weight(), tempVals, tempInd,
instance.numAttributes());
}
else {
double[] vals = instance.toDoubleArray();
for (int j = 0; j < getInputFormat().numAttributes(); j++) {
if (instance.attribute(j).isNumeric() &&
(!Utils.isMissingValue(vals[j])) &&
(getInputFormat().classIndex() != j)) {
vals[j] = (vals[j] - m_Means[j]);
}
}
inst = new DenseInstance(instance.weight(), vals);
}
inst.setDataset(instance.dataset());
push(inst);
}
/**
* Returns a string that describes the filter as source. The
* filter will be contained in a class with the given name (there may
* be auxiliary classes),
* and will contain two methods with these signatures:
*
* // converts one row
* public static Object[] filter(Object[] i);
* // converts a full dataset (first dimension is row index)
* public static Object[][] filter(Object[][] i);
*
* where the array i
contains elements that are either
* Double, String, with missing values represented as null. The generated
* code is public domain and comes with no warranty.
*
* @param className the name that should be given to the source class.
* @param data the dataset used for initializing the filter
* @return the object source described by a string
* @throws Exception if the source can't be computed
*/
public String toSource(String className, Instances data) throws Exception {
StringBuffer result;
boolean[] process;
int i;
result = new StringBuffer();
// determine what attributes were processed
process = new boolean[data.numAttributes()];
for (i = 0; i < data.numAttributes(); i++) {
process[i] = (data.attribute(i).isNumeric() && (i != data.classIndex()));
}
result.append("class " + className + " {\n");
result.append("\n");
result.append(" /** lists which attributes will be processed */\n");
result.append(" protected final static boolean[] PROCESS = new boolean[]{" + Utils.arrayToString(process) + "};\n");
result.append("\n");
result.append(" /** the computed means */\n");
result.append(" protected final static double[] MEANS = new double[]{" + Utils.arrayToString(m_Means) + "};\n");
result.append("\n");
result.append(" /**\n");
result.append(" * filters a single row\n");
result.append(" * \n");
result.append(" * @param i the row to process\n");
result.append(" * @return the processed row\n");
result.append(" */\n");
result.append(" public static Object[] filter(Object[] i) {\n");
result.append(" Object[] result;\n");
result.append("\n");
result.append(" result = new Object[i.length];\n");
result.append(" for (int n = 0; n < i.length; n++) {\n");
result.append(" if (PROCESS[n] && (i[n] != null))\n");
result.append(" result[n] = ((Double) i[n]) - MEANS[n];\n");
result.append(" else\n");
result.append(" result[n] = i[n];\n");
result.append(" }\n");
result.append("\n");
result.append(" return result;\n");
result.append(" }\n");
result.append("\n");
result.append(" /**\n");
result.append(" * filters multiple rows\n");
result.append(" * \n");
result.append(" * @param i the rows to process\n");
result.append(" * @return the processed rows\n");
result.append(" */\n");
result.append(" public static Object[][] filter(Object[][] i) {\n");
result.append(" Object[][] result;\n");
result.append("\n");
result.append(" result = new Object[i.length][];\n");
result.append(" for (int n = 0; n < i.length; n++) {\n");
result.append(" result[n] = filter(i[n]);\n");
result.append(" }\n");
result.append("\n");
result.append(" return result;\n");
result.append(" }\n");
result.append("}\n");
return result.toString();
}
/**
* Returns the revision string.
*
* @return the revision
*/
public String getRevision() {
return RevisionUtils.extract("$Revision: 8034 $");
}
/**
* Main method for running this filter.
*
* @param args should contain arguments to the filter: use -h for help
*/
public static void main(String [] args) {
runFilter(new Center(), args);
}
}