cc.mallet.types.InstanceList.split()方法的使用及代码示例
本文整理了Java中cc.mallet.types.InstanceList.split()方法的一些代码示例，展示了InstanceList.split()的具体用法。这些代码示例主要来源于Github/Stackoverflow/Maven等平台，是从一些精选项目中提取出来的代码，具有较强的参考意义，能在一定程度帮忙到你。InstanceList.split()方法的具体详情如下：
包路径：cc.mallet.types.InstanceList
类名称：InstanceList
方法名：split
InstanceList.split介绍
[英]Shuffles the elements of this list among several smaller lists.
[中]在几个较小的列表中洗牌此列表的元素。
代码示例
代码示例来源：origin: cc.mallet/mallet
private InstanceList subsetData (InstanceList data, double pct)
{
InstanceList[] lsts = data.split (r, new double[] { pct, 1 - pct });
return lsts[0];
}代码示例来源：origin: de.julielab/jcore-mallet-2.0.9
private InstanceList subsetData (InstanceList data, double pct)
{
InstanceList[] lsts = data.split (r, new double[] { pct, 1 - pct });
return lsts[0];
}代码示例来源：origin: com.github.steveash.mallet/mallet
private InstanceList subsetData (InstanceList data, double pct)
{
InstanceList[] lsts = data.split (r, new double[] { pct, 1 - pct });
return lsts[0];
}代码示例来源：origin: de.julielab/jcore-mallet-2.0.9
/**
* Constructs a new n-fold cross-validation iterator
*
* @param ilist instance list to split into folds and iterate over
* @param nfolds number of folds to split InstanceList into
* @param r The source of randomness to use in shuffling.
*/
public CrossValidationIterator (InstanceList ilist, int nfolds, java.util.Random r) {
this.nfolds = nfolds;
assert (nfolds > 0) : "nfolds: " + this.nfolds;
this.index = 0;
double fraction = (double) 1 / nfolds;
double[] proportions = new double[nfolds];
for (int i=0; i < nfolds; i++) {
proportions[i] = fraction;
}
this.folds = ilist.split (r, proportions);
}代码示例来源：origin: com.github.steveash.mallet/mallet
/**
* Constructs a new n-fold cross-validation iterator
*
* @param ilist instance list to split into folds and iterate over
* @param nfolds number of folds to split InstanceList into
* @param r The source of randomness to use in shuffling.
*/
public CrossValidationIterator (InstanceList ilist, int nfolds, java.util.Random r) {
assert (nfolds > 0) : "nfolds: " + this.nfolds;
this.nfolds = nfolds;
this.index = 0;
double fraction = (double) 1 / nfolds;
double[] proportions = new double[nfolds];
for (int i=0; i < nfolds; i++) {
proportions[i] = fraction;
}
this.folds = ilist.split (r, proportions);
}代码示例来源：origin: cc.mallet/mallet
/**
* Constructs a new n-fold cross-validation iterator
*
* @param ilist instance list to split into folds and iterate over
* @param nfolds number of folds to split InstanceList into
* @param r The source of randomness to use in shuffling.
*/
public CrossValidationIterator (InstanceList ilist, int nfolds, java.util.Random r) {
this.nfolds = nfolds;
assert (nfolds > 0) : "nfolds: " + this.nfolds;
this.index = 0;
double fraction = (double) 1 / nfolds;
double[] proportions = new double[nfolds];
for (int i=0; i < nfolds; i++) {
proportions[i] = fraction;
}
this.folds = ilist.split (r, proportions);
}代码示例来源：origin: cc.mallet/mallet
/**
@param _nfolds number of folds to split InstanceList into
@param seed seed for random number used to split InstanceList
*/
public CrossValidationIterator (int _nfolds, int seed)
{
assert (_nfolds > 0) : "nfolds: " + nfolds;
this.nfolds = _nfolds;
this.index = 0;
folds = new InstanceList[_nfolds];
double fraction = (double) 1 / _nfolds;
double[] proportions = new double[_nfolds];
for (int i=0; i < _nfolds; i++)
proportions[i] = fraction;
folds = split (new java.util.Random (seed), proportions);
}代码示例来源：origin: de.julielab/jcore-mallet-2.0.9
/**
@param _nfolds number of folds to split InstanceList into
@param seed seed for random number used to split InstanceList
*/
public CrossValidationIterator (int _nfolds, int seed)
{
assert (_nfolds > 0) : "nfolds: " + nfolds;
this.nfolds = _nfolds;
this.index = 0;
folds = new InstanceList[_nfolds];
double fraction = (double) 1 / _nfolds;
double[] proportions = new double[_nfolds];
for (int i=0; i < _nfolds; i++)
proportions[i] = fraction;
folds = split (new java.util.Random (seed), proportions);
}代码示例来源：origin: com.github.steveash.mallet/mallet
/**
@param _nfolds number of folds to split InstanceList into
@param seed seed for random number used to split InstanceList
*/
public CrossValidationIterator (int _nfolds, int seed)
{
assert (_nfolds > 0) : "nfolds: " + nfolds;
this.nfolds = _nfolds;
this.index = 0;
folds = new InstanceList[_nfolds];
double fraction = (double) 1 / _nfolds;
double[] proportions = new double[_nfolds];
for (int i=0; i < _nfolds; i++)
proportions[i] = fraction;
folds = split (new java.util.Random (seed), proportions);
}代码示例来源：origin: cc.mallet/mallet
public InstanceList[] split (double[] proportions) {
return split (new java.util.Random(System.currentTimeMillis()), proportions);
}代码示例来源：origin: de.julielab/jcore-mallet-2.0.9
public InstanceList[] split (double[] proportions) {
return split (new java.util.Random(System.currentTimeMillis()), proportions);
}代码示例来源：origin: com.github.steveash.mallet/mallet
public InstanceList[] split (double[] proportions) {
return split (new java.util.Random(System.currentTimeMillis()), proportions);
}代码示例来源：origin: com.github.steveash.mallet/mallet
public void train (ACRF acrf, InstanceList training, InstanceList validation, InstanceList testing,
ACRFEvaluator eval, double[] proportions, int iterPerProportion)
{
for (int i = 0; i < proportions.length; i++) {
double proportion = proportions[i];
InstanceList[] lists = training.split (r, new double[]{proportion, 1.0});
logger.info ("ACRF trainer: Round " + i + ", training proportion = " + proportion);
train (acrf, lists[0], validation, testing, eval, iterPerProportion);
}
logger.info ("ACRF trainer: Training on full data");
train (acrf, training, validation, testing, eval, 99999);
}代码示例来源：origin: cc.mallet/mallet
public void train (ACRF acrf, InstanceList training, InstanceList validation, InstanceList testing,
ACRFEvaluator eval, double[] proportions, int iterPerProportion)
{
for (int i = 0; i < proportions.length; i++) {
double proportion = proportions[i];
InstanceList[] lists = training.split (r, new double[]{proportion, 1.0});
logger.info ("ACRF trainer: Round " + i + ", training proportion = " + proportion);
train (acrf, lists[0], validation, testing, eval, iterPerProportion);
}
logger.info ("ACRF trainer: Training on full data");
train (acrf, training, validation, testing, eval, 99999);
}代码示例来源：origin: de.julielab/jcore-mallet-2.0.9
public void train (ACRF acrf, InstanceList training, InstanceList validation, InstanceList testing,
ACRFEvaluator eval, double[] proportions, int iterPerProportion)
{
for (int i = 0; i < proportions.length; i++) {
double proportion = proportions[i];
InstanceList[] lists = training.split (r, new double[]{proportion, 1.0});
logger.info ("ACRF trainer: Round " + i + ", training proportion = " + proportion);
train (acrf, lists[0], validation, testing, eval, iterPerProportion);
}
logger.info ("ACRF trainer: Training on full data");
train (acrf, training, validation, testing, eval, 99999);
}代码示例来源：origin: ch.epfl.bbp.nlp/bluima_reference_classifier
public static Trial testTrainSplit(InstanceList instances) {
InstanceList[] instanceLists = instances.split(new Randoms(),
new double[] { 0.9, 0.1, 0.0 });
// LOG.debug("{} training instance, {} testing instances",
// instanceLists[0].size(), instanceLists[1].size());
@SuppressWarnings("rawtypes")
ClassifierTrainer trainer = new MaxEntTrainer();
Classifier classifier = trainer.train(instanceLists[TRAINING]);
return new Trial(classifier, instanceLists[TESTING]);
}代码示例来源：origin: uk.gov.dstl.baleen/baleen-mallet
@Override
protected void execute(JobSettings settings) throws AnalysisEngineProcessException {
Pipe pipe = new ClassifierPipe(stopwords);
InstanceList instances = new InstanceList(pipe);
instances.addThruPipe(getDocumentsFromMongo());
InstanceList training = null;
InstanceList testing = null;
if (forTesting > 0.0) {
InstanceList[] ilists = instances.split(new double[] {1 - forTesting, forTesting});
training = ilists[0];
testing = ilists[1];
} else {
training = instances;
}
processTrainerDefinitions(training, testing);
}代码示例来源：origin: dstl/baleen
@Override
protected void execute(JobSettings settings) throws AnalysisEngineProcessException {
Pipe pipe = new ClassifierPipe(stopwords);
InstanceList instances = new InstanceList(pipe);
instances.addThruPipe(getDocumentsFromMongo());
InstanceList training = null;
InstanceList testing = null;
if (forTesting > 0.0) {
InstanceList[] ilists = instances.split(new double[] {1 - forTesting, forTesting});
training = ilists[0];
testing = ilists[1];
} else {
training = instances;
}
processTrainerDefinitions(training, testing);
}代码示例来源：origin: cc.mallet/mallet
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);
}代码示例来源：origin: com.github.steveash.mallet/mallet
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);
}内容来源于网络，如有侵权，请联系作者删除！
