/*
* RapidMiner
*
* Copyright (C) 2001-2008 by Rapid-I and the contributors
*
* Complete list of developers available at our web site:
*
* http://rapid-i.com
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero 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 Affero General Public License for more details.
*
* You should have received a copy of the GNU Affero General Public License
* along with this program. If not, see http://www.gnu.org/licenses/.
*/
package com.rapidminer.operator.preprocessing.sampling;
import java.util.Arrays;
import java.util.Iterator;
import java.util.LinkedList;
import java.util.List;
import com.rapidminer.example.Attribute;
import com.rapidminer.example.AttributeRole;
import com.rapidminer.example.Example;
import com.rapidminer.example.ExampleSet;
import com.rapidminer.example.set.SimpleExampleSet;
import com.rapidminer.example.table.DataRow;
import com.rapidminer.example.table.ExampleTable;
import com.rapidminer.example.table.ListDataRowReader;
import com.rapidminer.example.table.MemoryExampleTable;
import com.rapidminer.operator.IOObject;
import com.rapidminer.operator.Operator;
import com.rapidminer.operator.OperatorDescription;
import com.rapidminer.operator.OperatorException;
import com.rapidminer.parameter.ParameterType;
import com.rapidminer.parameter.ParameterTypeDouble;
import com.rapidminer.parameter.ParameterTypeInt;
import com.rapidminer.parameter.UndefinedParameterError;
import com.rapidminer.tools.RandomGenerator;
/**
* Simple sampling operator. This operator performs a random sampling of a given
* fraction. For example, if the input example set contains 5000 examples and
* the sample ratio is set to 0.1, the result will have approximately 500
* examples.
*
* @author Ingo Mierswa
* @version $Id: SimpleSampling.java,v 1.5 2008/07/07 07:06:47 ingomierswa Exp $
*/
public class SimpleSampling extends Operator {
/** The parameter name for "The fraction of examples which should be sampled" */
public static final String PARAMETER_SAMPLE_RATIO = "sample_ratio";
/** The parameter name for "Use the given random seed instead of global random numbers (-1: use global)." */
public static final String PARAMETER_LOCAL_RANDOM_SEED = "local_random_seed";
private double fraction = 0.1d;
public SimpleSampling(OperatorDescription description) {
super(description);
}
public IOObject[] apply() throws OperatorException {
ExampleSet exampleSet = getInput(ExampleSet.class);
this.fraction = getParameterAsDouble(PARAMETER_SAMPLE_RATIO);
// fill new table
List<DataRow> dataList = new LinkedList<DataRow>();
Iterator<Example> reader = exampleSet.iterator();
while (reader.hasNext()) {
Example example = reader.next();
if (accept(example)) {
dataList.add(example.getDataRow());
}
checkForStop();
}
List<Attribute> attributes = Arrays.asList(exampleSet.getExampleTable().getAttributes());
ExampleTable exampleTable = new MemoryExampleTable(attributes, new ListDataRowReader(dataList.iterator()));
// regular attributes
List<Attribute> regularAttributes = new LinkedList<Attribute>();
for (Attribute attribute : exampleSet.getAttributes()) {
regularAttributes.add(attribute);
}
// special attributes
ExampleSet result = new SimpleExampleSet(exampleTable, regularAttributes);
Iterator<AttributeRole> special = exampleSet.getAttributes().specialAttributes();
while (special.hasNext()) {
AttributeRole role = special.next();
result.getAttributes().setSpecialAttribute(role.getAttribute(), role.getSpecialName());
}
return new IOObject[] { result };
}
protected boolean accept(Example example) throws UndefinedParameterError {
return RandomGenerator.getRandomGenerator(getParameterAsInt(PARAMETER_LOCAL_RANDOM_SEED)).nextDouble() < fraction;
}
public Class<?>[] getInputClasses() {
return new Class[] { ExampleSet.class };
}
public Class<?>[] getOutputClasses() {
return new Class[] { ExampleSet.class };
}
public List<ParameterType> getParameterTypes() {
List<ParameterType> types = super.getParameterTypes();
ParameterType type = new ParameterTypeDouble(PARAMETER_SAMPLE_RATIO, "The fraction of examples which should be sampled", 0.0d, 1.0d, 0.1d);
type.setExpert(false);
types.add(type);
types.add(new ParameterTypeInt(PARAMETER_LOCAL_RANDOM_SEED, "Use the given random seed instead of global random numbers (-1: use global).", -1, Integer.MAX_VALUE, -1));
return types;
}
}