Java tutorial
package moa.tasks; /* * EvaluateInterleavedSeed.java * Copyright (C) 2013 Federal University of Minas Gerais, Belo Horizonte, Brazil * @author Roberto L. Oliveira Junior (robertolojr at dcc dot ufmg dot br) * * 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 <http://www.gnu.org/licenses/>. * */ import java.io.File; import java.io.FileOutputStream; import java.io.PrintStream; import moa.classifiers.Classifier; import moa.core.Measurement; import moa.core.ObjectRepository; import moa.core.TimingUtils; import moa.evaluation.ClassificationPerformanceEvaluator; import moa.evaluation.LearningCurve; import moa.evaluation.LearningEvaluation; import moa.options.ClassOption; import moa.options.FileOption; import moa.options.IntOption; import moa.streams.InstanceStream; import moa.tasks.MainTask; import weka.core.Instance; /** * Task for evaluating a classifier on a stream by testing then training with each example in sequence. * This class implements a easy way in order to provide training seed to classifier. * * @author Roberto L. de Oliveira Junior (robertolojr at dcc dot ufmg dot br) * @version $Revision: 1 $ */ public class EvaluateInterleavedSeed extends MainTask { @Override public String getPurposeString() { return "Evaluates a classifier on a stream by testing then training with each example in sequence."; } private static final long serialVersionUID = 1L; public ClassOption learnerOption = new ClassOption("learner", 'l', "Classifier to train.", Classifier.class, "rules.IncrementalLac"); public ClassOption streamOption = new ClassOption("stream", 's', "Stream to learn from.", InstanceStream.class, "generators.RandomTreeGenerator"); public ClassOption evaluatorOption = new ClassOption("evaluator", 'e', "Classification performance evaluation method.", ClassificationPerformanceEvaluator.class, "BasicClassificationScoringEvaluator"); public IntOption instanceLimitOption = new IntOption("instanceLimit", 'i', "Maximum number of instances to test/train on (-1 = no limit).", 100000000, -1, Integer.MAX_VALUE); public IntOption timeLimitOption = new IntOption("timeLimit", 't', "Maximum number of seconds to test/train for (-1 = no limit).", -1, -1, Integer.MAX_VALUE); public IntOption sampleFrequencyOption = new IntOption("sampleFrequency", 'f', "How many instances between samples of the learning performance.", 100000, 0, Integer.MAX_VALUE); public IntOption seedOption = new IntOption("trainingSeed", 'g', "How many instances are used to be initial training set.", 1, 1, Integer.MAX_VALUE); public IntOption memCheckFrequencyOption = new IntOption("memCheckFrequency", 'q', "How many instances between memory bound checks.", 100000, 0, Integer.MAX_VALUE); public FileOption dumpFileOption = new FileOption("dumpFile", 'd', "File to append intermediate csv reslts to.", null, "csv", true); @Override public Class<?> getTaskResultType() { return LearningCurve.class; } @Override protected Object doMainTask(TaskMonitor monitor, ObjectRepository repository) { Classifier learner = (Classifier) getPreparedClassOption(this.learnerOption); InstanceStream stream = (InstanceStream) getPreparedClassOption(this.streamOption); ClassificationPerformanceEvaluator evaluator = (ClassificationPerformanceEvaluator) getPreparedClassOption( this.evaluatorOption); learner.setModelContext(stream.getHeader()); int maxInstances = this.instanceLimitOption.getValue(); long instancesProcessed = 0; int maxSeconds = this.timeLimitOption.getValue(); int secondsElapsed = 0; monitor.setCurrentActivity("Evaluating learner...", -1.0); LearningCurve learningCurve = new LearningCurve("learning evaluation instances"); File dumpFile = this.dumpFileOption.getFile(); PrintStream immediateResultStream = null; if (dumpFile != null) { try { if (dumpFile.exists()) { immediateResultStream = new PrintStream(new FileOutputStream(dumpFile, true), true); } else { immediateResultStream = new PrintStream(new FileOutputStream(dumpFile), true); } } catch (Exception ex) { throw new RuntimeException("Unable to open immediate result file: " + dumpFile, ex); } } boolean firstDump = true; boolean preciseCPUTiming = TimingUtils.enablePreciseTiming(); long evaluateStartTime = TimingUtils.getNanoCPUTimeOfCurrentThread(); long lastEvaluateStartTime = evaluateStartTime; double RAMHours = 0.0; //Creating training Seed for (int i = 0; i < seedOption.getValue() && stream.hasMoreInstances(); i++) { Instance trainInst = stream.nextInstance(); learner.trainOnInstance(trainInst); } while (stream.hasMoreInstances() && ((maxInstances < 0) || (instancesProcessed < maxInstances)) && ((maxSeconds < 0) || (secondsElapsed < maxSeconds))) { Instance trainInst = stream.nextInstance(); Instance testInst = (Instance) trainInst.copy(); //testInst.setClassMissing(); double[] prediction = learner.getVotesForInstance(testInst); //evaluator.addClassificationAttempt(trueClass, prediction, testInst // .weight()); evaluator.addResult(testInst, prediction); learner.trainOnInstance(trainInst); instancesProcessed++; if (instancesProcessed % this.sampleFrequencyOption.getValue() == 0 || stream.hasMoreInstances() == false) { long evaluateTime = TimingUtils.getNanoCPUTimeOfCurrentThread(); double time = TimingUtils.nanoTimeToSeconds(evaluateTime - evaluateStartTime); double timeIncrement = TimingUtils.nanoTimeToSeconds(evaluateTime - lastEvaluateStartTime); double RAMHoursIncrement = learner.measureByteSize() / (1024.0 * 1024.0 * 1024.0); //GBs RAMHoursIncrement *= (timeIncrement / 3600.0); //Hours RAMHours += RAMHoursIncrement; lastEvaluateStartTime = evaluateTime; learningCurve.insertEntry(new LearningEvaluation( new Measurement[] { new Measurement("learning evaluation instances", instancesProcessed), new Measurement("evaluation time (" + (preciseCPUTiming ? "cpu " : "") + "seconds)", time), new Measurement("model cost (RAM-Hours)", RAMHours) }, evaluator, learner)); if (immediateResultStream != null) { if (firstDump) { immediateResultStream.println(learningCurve.headerToString()); firstDump = false; } immediateResultStream.println(learningCurve.entryToString(learningCurve.numEntries() - 1)); immediateResultStream.flush(); } } if (instancesProcessed % INSTANCES_BETWEEN_MONITOR_UPDATES == 0) { if (monitor.taskShouldAbort()) { return null; } long estimatedRemainingInstances = stream.estimatedRemainingInstances(); if (maxInstances > 0) { long maxRemaining = maxInstances - instancesProcessed; if ((estimatedRemainingInstances < 0) || (maxRemaining < estimatedRemainingInstances)) { estimatedRemainingInstances = maxRemaining; } } monitor.setCurrentActivityFractionComplete(estimatedRemainingInstances < 0 ? -1.0 : (double) instancesProcessed / (double) (instancesProcessed + estimatedRemainingInstances)); if (monitor.resultPreviewRequested()) { monitor.setLatestResultPreview(learningCurve.copy()); } secondsElapsed = (int) TimingUtils .nanoTimeToSeconds(TimingUtils.getNanoCPUTimeOfCurrentThread() - evaluateStartTime); } } if (immediateResultStream != null) { immediateResultStream.close(); } return learningCurve; } }