本文整理汇总了Java中cc.mallet.fst.TokenAccuracyEvaluator类的典型用法代码示例。如果您正苦于以下问题：Java TokenAccuracyEvaluator类的具体用法？Java TokenAccuracyEvaluator怎么用？Java TokenAccuracyEvaluator使用的例子？那么恭喜您, 这里精选的类代码示例或许可以为您提供帮助。
TokenAccuracyEvaluator类属于cc.mallet.fst包，在下文中一共展示了TokenAccuracyEvaluator类的9个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于我们的系统推荐出更棒的Java代码示例。
示例1: testTokenAccuracy
import cc.mallet.fst.TokenAccuracyEvaluator; //导入依赖的package包/类
public void testTokenAccuracy() {
Pipe p = makeSpacePredictionPipe();
InstanceList instances = new InstanceList(p);
instances.addThruPipe(new ArrayIterator(data));
InstanceList[] lists = instances.split(new Random(777), new double[] {
.5, .5 });
CRF crf = new CRF(p.getDataAlphabet(), p.getTargetAlphabet());
crf.addFullyConnectedStatesForLabels();
CRFTrainerByLabelLikelihood crft = new CRFTrainerByLabelLikelihood(crf);
crft.setUseSparseWeights(true);
crft.trainIncremental(lists[0]);
TokenAccuracyEvaluator eval = new TokenAccuracyEvaluator(lists,
new String[] { "Train", "Test" });
eval.evaluateInstanceList(crft, lists[1], "Test");
assertEquals(0.9409, eval.getAccuracy("Test"), 0.001);
}
开发者ID:kostagiolasn，项目名称:NucleosomePatternClassifier，代码行数:23，代码来源:TestCRF.java
示例2: train
import cc.mallet.fst.TokenAccuracyEvaluator; //导入依赖的package包/类
public SyllTagModel train(Collection<Alignment> trainInputs, Collection<Alignment> testInputs, boolean eval) {
Pipe pipe = makePipe();
InstanceList trainExamples = makeExamplesFromAlignsWithPipe(trainInputs, pipe);
InstanceList testExamples = null;
if (testInputs != null) {
testExamples = makeExamplesFromAlignsWithPipe(testInputs, pipe);
}
log.info("Training test-time syll aligner on whole data...");
TransducerTrainer trainer = trainOnce(pipe, trainExamples);
if (eval) {
TokenAccuracyEvaluator evaler = new TokenAccuracyEvaluator(trainExamples, "traindata");
evaler.evaluate(trainer);
double trainAcc = evaler.getAccuracy("traindata");
double testAcc = 0.0;
if (testExamples != null) {
TokenAccuracyEvaluator evaler2 = new TokenAccuracyEvaluator(testExamples, "testdata");
evaler2.evaluate(trainer);
testAcc = evaler2.getAccuracy("testdata");
}
log.info("Train data accuracy = " + trainAcc + ", test data accuracy = " + testAcc);
}
return new SyllTagModel((CRF) trainer.getTransducer());
}
开发者ID:steveash，项目名称:jg2p，代码行数:27，代码来源:SyllTagTrainer.java
示例3: ignoretestTokenAccuracy
import cc.mallet.fst.TokenAccuracyEvaluator; //导入依赖的package包/类
public void ignoretestTokenAccuracy() {
Pipe p = makeSpacePredictionPipe();
InstanceList instances = new InstanceList(p);
instances.addThruPipe(new ArrayIterator(data));
InstanceList[] lists = instances.split(new Random(777), new double[] {
.5, .5 });
CRF crf = new CRF(p.getDataAlphabet(), p.getTargetAlphabet());
crf.addFullyConnectedStatesForLabels();
CRFTrainerByLabelLikelihood crft = new CRFTrainerByLabelLikelihood(crf);
crft.setUseSparseWeights(true);
crft.trainIncremental(lists[0]);
TokenAccuracyEvaluator eval = new TokenAccuracyEvaluator(lists,
new String[] { "Train", "Test" });
eval.evaluateInstanceList(crft, lists[1], "Test");
assertEquals(0.9409, eval.getAccuracy("Test"), 0.001);
}
开发者ID:cmoen，项目名称:mallet，代码行数:23，代码来源:TestCRF.java
示例4: train
import cc.mallet.fst.TokenAccuracyEvaluator; //导入依赖的package包/类
public CRF train(InstanceList trainingInstances, InstanceList testingInstances)
throws FileNotFoundException, IOException {
if (this.transducerTrainer == null) {
throw new IllegalStateException("crfTrainer needs to be set via one of the available methods");
}
// trainer.addEvaluator(new PerClassAccuracyEvaluator(trainingInstances,
// "training"));
this.transducerTrainer.addEvaluator(new PerClassAccuracyEvaluator(testingInstances, "testing"));
this.transducerTrainer.addEvaluator(new TokenAccuracyEvaluator(testingInstances, "testing"));
// this.transducerTrainer
// .addEvaluator(new FixedViterbiWriter(new
// File("/home/mkoerner/viterbi.txt"), testingInstances, "test"));
this.transducerTrainer.train(trainingInstances);
return this.crf;
}
开发者ID:exciteproject，项目名称:refext，代码行数:19，代码来源:ReferenceExtractorTrainer.java
示例5: testDualSpaceViewer
import cc.mallet.fst.TokenAccuracyEvaluator; //导入依赖的package包/类
public void testDualSpaceViewer () throws IOException
{
Pipe pipe = TestMEMM.makeSpacePredictionPipe ();
String[] data0 = { TestCRF.data[0] };
String[] data1 = TestCRF.data;
InstanceList training = new InstanceList (pipe);
training.addThruPipe (new ArrayIterator (data0));
InstanceList testing = new InstanceList (pipe);
testing.addThruPipe (new ArrayIterator (data1));
CRF crf = new CRF (pipe, null);
crf.addFullyConnectedStatesForLabels ();
CRFTrainerByLabelLikelihood crft = new CRFTrainerByLabelLikelihood (crf);
TokenAccuracyEvaluator eval = new TokenAccuracyEvaluator (new InstanceList[] {training, testing}, new String[] {"Training", "Testing"});
for (int i = 0; i < 5; i++) {
crft.train (training, 1);
eval.evaluate(crft);
}
CRFExtractor extor = hackCrfExtor (crf);
Extraction e1 = extor.extract (new ArrayIterator (data1));
Pipe pipe2 = TestMEMM.makeSpacePredictionPipe ();
InstanceList training2 = new InstanceList (pipe2);
training2.addThruPipe (new ArrayIterator (data0));
InstanceList testing2 = new InstanceList (pipe2);
testing2.addThruPipe (new ArrayIterator (data1));
MEMM memm = new MEMM (pipe2, null);
memm.addFullyConnectedStatesForLabels ();
MEMMTrainer memmt = new MEMMTrainer (memm);
TransducerEvaluator memmeval = new TokenAccuracyEvaluator (new InstanceList[] {training2, testing2}, new String[] {"Training2", "Testing2"});
memmt.train (training2, 5);
memmeval.evaluate(memmt);
CRFExtractor extor2 = hackCrfExtor (memm);
Extraction e2 = extor2.extract (new ArrayIterator (data1));
if (!htmlDir.exists ()) htmlDir.mkdir ();
LatticeViewer.viewDualResults (htmlDir, e1, extor, e2, extor2);
}
开发者ID:kostagiolasn，项目名称:NucleosomePatternClassifier，代码行数:44，代码来源:TestLatticeViewer.java
示例6: accuracyFor
import cc.mallet.fst.TokenAccuracyEvaluator; //导入依赖的package包/类
private double accuracyFor(InstanceList examples) {
TokenAccuracyEvaluator teval = new TokenAccuracyEvaluator(examples, "train");
teval.evaluate(lastTrainer);
return teval.getAccuracy("train");
}
开发者ID:steveash，项目名称:jg2p，代码行数:6，代码来源:PhonemeCrfTrainer.java
示例7: ignoretestDualSpaceViewer
import cc.mallet.fst.TokenAccuracyEvaluator; //导入依赖的package包/类
public void ignoretestDualSpaceViewer () throws IOException
{
Pipe pipe = TestMEMM.makeSpacePredictionPipe ();
String[] data0 = { TestCRF.data[0] };
String[] data1 = TestCRF.data;
InstanceList training = new InstanceList (pipe);
training.addThruPipe (new ArrayIterator (data0));
InstanceList testing = new InstanceList (pipe);
testing.addThruPipe (new ArrayIterator (data1));
CRF crf = new CRF (pipe, null);
crf.addFullyConnectedStatesForLabels ();
CRFTrainerByLabelLikelihood crft = new CRFTrainerByLabelLikelihood (crf);
TokenAccuracyEvaluator eval = new TokenAccuracyEvaluator (new InstanceList[] {training, testing}, new String[] {"Training", "Testing"});
for (int i = 0; i < 5; i++) {
crft.train (training, 1);
eval.evaluate(crft);
}
CRFExtractor extor = hackCrfExtor (crf);
Extraction e1 = extor.extract (new ArrayIterator (data1));
Pipe pipe2 = TestMEMM.makeSpacePredictionPipe ();
InstanceList training2 = new InstanceList (pipe2);
training2.addThruPipe (new ArrayIterator (data0));
InstanceList testing2 = new InstanceList (pipe2);
testing2.addThruPipe (new ArrayIterator (data1));
MEMM memm = new MEMM (pipe2, null);
memm.addFullyConnectedStatesForLabels ();
MEMMTrainer memmt = new MEMMTrainer (memm);
TransducerEvaluator memmeval = new TokenAccuracyEvaluator (new InstanceList[] {training2, testing2}, new String[] {"Training2", "Testing2"});
memmt.train (training2, 5);
memmeval.evaluate(memmt);
CRFExtractor extor2 = hackCrfExtor (memm);
Extraction e2 = extor2.extract (new ArrayIterator (data1));
if (!htmlDir.exists ()) htmlDir.mkdir ();
LatticeViewer.viewDualResults (htmlDir, e1, extor, e2, extor2);
}
开发者ID:cmoen，项目名称:mallet，代码行数:44，代码来源:TestLatticeViewer.java
示例8: TrainCRF
import cc.mallet.fst.TokenAccuracyEvaluator; //导入依赖的package包/类
public TrainCRF(String trainingFilename, String testingFilename) throws IOException {
ArrayList<Pipe> pipes = new ArrayList<Pipe>();
int[][] conjunctions = new int[2][];
conjunctions[0] = new int[] { -1 };
conjunctions[1] = new int[] { 1 };
pipes.add(new SimpleTaggerSentence2TokenSequence());
pipes.add(new OffsetConjunctions(conjunctions));
//pipes.add(new FeaturesInWindow("PREV-", -1, 1));
pipes.add(new TokenTextCharSuffix("C1=", 1));
pipes.add(new TokenTextCharSuffix("C2=", 2));
pipes.add(new TokenTextCharSuffix("C3=", 3));
pipes.add(new RegexMatches("CAPITALIZED", Pattern.compile("^\\p{Lu}.*")));
pipes.add(new RegexMatches("STARTSNUMBER", Pattern.compile("^[0-9].*")));
pipes.add(new RegexMatches("HYPHENATED", Pattern.compile(".*\\-.*")));
pipes.add(new RegexMatches("DOLLARSIGN", Pattern.compile(".*\\$.*")));
pipes.add(new TokenFirstPosition("FIRSTTOKEN"));
pipes.add(new TokenSequence2FeatureVectorSequence());
Pipe pipe = new SerialPipes(pipes);
InstanceList trainingInstances = new InstanceList(pipe);
InstanceList testingInstances = new InstanceList(pipe);
trainingInstances.addThruPipe(new LineGroupIterator(new BufferedReader(new InputStreamReader(new GZIPInputStream(new FileInputStream(trainingFilename)))), Pattern.compile("^\\s*$"), true));
testingInstances.addThruPipe(new LineGroupIterator(new BufferedReader(new InputStreamReader(new GZIPInputStream(new FileInputStream(testingFilename)))), Pattern.compile("^\\s*$"), true));
CRF crf = new CRF(pipe, null);
//crf.addStatesForLabelsConnectedAsIn(trainingInstances);
crf.addStatesForThreeQuarterLabelsConnectedAsIn(trainingInstances);
crf.addStartState();
CRFTrainerByLabelLikelihood trainer =
new CRFTrainerByLabelLikelihood(crf);
trainer.setGaussianPriorVariance(10.0);
//CRFTrainerByStochasticGradient trainer =
//new CRFTrainerByStochasticGradient(crf, 1.0);
//CRFTrainerByL1LabelLikelihood trainer =
// new CRFTrainerByL1LabelLikelihood(crf, 0.75);
//trainer.addEvaluator(new PerClassAccuracyEvaluator(trainingInstances, "training"));
trainer.addEvaluator(new PerClassAccuracyEvaluator(testingInstances, "testing"));
trainer.addEvaluator(new TokenAccuracyEvaluator(testingInstances, "testing"));
trainer.train(trainingInstances);
}
开发者ID:karahindiba，项目名称:WikiInfoboxExtractor，代码行数:51，代码来源:TrainCRF.java
示例9: TrainWikiCRF
import cc.mallet.fst.TokenAccuracyEvaluator; //导入依赖的package包/类
public TrainWikiCRF(String trainingFilename, String testingFilename) throws IOException {
ArrayList<Pipe> pipes = new ArrayList<Pipe>();
int[][] conjunctions = new int[2][];
conjunctions[0] = new int[] { -1 };
conjunctions[1] = new int[] { 1 };
pipes.add(new SimpleTaggerSentence2TokenSequence());
pipes.add(new OffsetConjunctions(conjunctions));
//pipes.add(new FeaturesInWindow("PREV-", -1, 1));
pipes.add(new TokenTextCharSuffix("C1=", 1));
pipes.add(new TokenTextCharSuffix("C2=", 2));
pipes.add(new TokenTextCharSuffix("C3=", 3));
pipes.add(new RegexMatches("CAPITALIZED", Pattern.compile("^\\p{Lu}.*")));
pipes.add(new RegexMatches("STARTSNUMBER", Pattern.compile("^[0-9].*")));
pipes.add(new RegexMatches("HYPHENATED", Pattern.compile(".*\\-.*")));
pipes.add(new RegexMatches("DOLLARSIGN", Pattern.compile(".*\\$.*")));
pipes.add(new TokenFirstPosition("FIRSTTOKEN"));
pipes.add(new TokenSequence2FeatureVectorSequence());
Pipe pipe = new SerialPipes(pipes);
InstanceList trainingInstances = new InstanceList(pipe);
InstanceList testingInstances = new InstanceList(pipe);
trainingInstances.addThruPipe(new LineGroupIterator(new BufferedReader(new InputStreamReader(new GZIPInputStream(new FileInputStream(trainingFilename)))), Pattern.compile("^\\s*$"), true));
testingInstances.addThruPipe(new LineGroupIterator(new BufferedReader(new InputStreamReader(new GZIPInputStream(new FileInputStream(testingFilename)))), Pattern.compile("^\\s*$"), true));
CRF crf = new CRF(pipe, null);
//crf.addStatesForLabelsConnectedAsIn(trainingInstances);
crf.addStatesForThreeQuarterLabelsConnectedAsIn(trainingInstances);
crf.addStartState();
CRFTrainerByLabelLikelihood trainer =
new CRFTrainerByLabelLikelihood(crf);
trainer.setGaussianPriorVariance(10.0);
//CRFTrainerByStochasticGradient trainer =
//new CRFTrainerByStochasticGradient(crf, 1.0);
//CRFTrainerByL1LabelLikelihood trainer =
// new CRFTrainerByL1LabelLikelihood(crf, 0.75);
//trainer.addEvaluator(new PerClassAccuracyEvaluator(trainingInstances, "training"));
trainer.addEvaluator(new PerClassAccuracyEvaluator(testingInstances, "testing"));
trainer.addEvaluator(new TokenAccuracyEvaluator(testingInstances, "testing"));
trainer.train(trainingInstances);
}
开发者ID:karahindiba，项目名称:WikiInfoboxExtractor，代码行数:51，代码来源:TrainWikiCRF.java
注：本文中的cc.mallet.fst.TokenAccuracyEvaluator类示例整理自Github/MSDocs等源码及文档管理平台，相关代码片段筛选自各路编程大神贡献的开源项目，源码版权归原作者所有，传播和使用请参考对应项目的License；未经允许，请勿转载。 |
客服电话
APP下载
官方微信
请发表评论