本文整理汇总了Java中cc.mallet.types.InstanceList.split方法的典型用法代码示例。如果您正苦于以下问题：Java InstanceList.split方法的具体用法？Java InstanceList.split怎么用？Java InstanceList.split使用的例子？那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类cc.mallet.types.InstanceList的用法示例。
在下文中一共展示了InstanceList.split方法的5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，您的评价将有助于系统推荐出更棒的Java代码示例。
示例1: testTokenAccuracy
import cc.mallet.types.InstanceList; //导入方法依赖的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);
}
示例2: testTrainStochasticGradient
import cc.mallet.types.InstanceList; //导入方法依赖的package包/类
public void testTrainStochasticGradient() {
Pipe p = makeSpacePredictionPipe();
Pipe p2 = new TestCRF2String();
InstanceList instances = new InstanceList(p);
instances.addThruPipe(new ArrayIterator(data));
InstanceList[] lists = instances.split(new double[] { .5, .5 });
CRF crf = new CRF(p, p2);
crf.addFullyConnectedStatesForLabels();
crf.setWeightsDimensionAsIn(lists[0], false);
CRFTrainerByStochasticGradient crft = new CRFTrainerByStochasticGradient(
crf, 0.0001);
System.out.println("Training Accuracy before training = "
+ crf.averageTokenAccuracy(lists[0]));
System.out.println("Testing Accuracy before training = "
+ crf.averageTokenAccuracy(lists[1]));
System.out.println("Training...");
// either fixed learning rate or selected on a sample
crft.setLearningRateByLikelihood(lists[0]);
// crft.setLearningRate(0.01);
crft.train(lists[0], 100);
crf.print();
System.out.println("Training Accuracy after training = "
+ crf.averageTokenAccuracy(lists[0]));
System.out.println("Testing Accuracy after training = "
+ crf.averageTokenAccuracy(lists[1]));
}
示例3: subsetData
import cc.mallet.types.InstanceList; //导入方法依赖的package包/类
private InstanceList subsetData (InstanceList data, double pct)
{
InstanceList[] lsts = data.split (r, new double[] { pct, 1 - pct });
return lsts[0];
}
示例4: testAddOrderNStates
import cc.mallet.types.InstanceList; //导入方法依赖的package包/类
public void testAddOrderNStates() {
Pipe p = makeSpacePredictionPipe();
InstanceList instances = new InstanceList(p);
instances.addThruPipe(new ArrayIterator(data));
InstanceList[] lists = instances.split(new java.util.Random(678),
new double[] { .5, .5 });
// Compare 3 CRFs trained with addOrderNStates, and make sure
// that having more features leads to a higher likelihood
CRF crf1 = new CRF(p.getDataAlphabet(), p.getTargetAlphabet());
crf1.addOrderNStates(lists[0], new int[] { 1, },
new boolean[] { false, }, "START", null, null, false);
new CRFTrainerByLabelLikelihood(crf1).trainIncremental(lists[0]);
CRF crf2 = new CRF(p.getDataAlphabet(), p.getTargetAlphabet());
crf2.addOrderNStates(lists[0], new int[] { 1, 2, }, new boolean[] {
false, true }, "START", null, null, false);
new CRFTrainerByLabelLikelihood(crf2).trainIncremental(lists[0]);
CRF crf3 = new CRF(p.getDataAlphabet(), p.getTargetAlphabet());
crf3.addOrderNStates(lists[0], new int[] { 1, 2, }, new boolean[] {
false, false }, "START", null, null, false);
new CRFTrainerByLabelLikelihood(crf3).trainIncremental(lists[0]);
// Prevent cached values
double lik1 = getLikelihood(crf1, lists[0]);
double lik2 = getLikelihood(crf2, lists[0]);
double lik3 = getLikelihood(crf3, lists[0]);
System.out.println("CRF1 likelihood " + lik1);
assertTrue("Final zero-order likelihood <" + lik1
+ "> greater than first-order <" + lik2 + ">", lik1 < lik2);
assertTrue("Final defaults-only likelihood <" + lik2
+ "> greater than full first-order <" + lik3 + ">", lik2 < lik3);
assertEquals(-167.2234457483949, lik1, 0.0001);
assertEquals(-165.81326484466342, lik2, 0.0001);
assertEquals(-90.37680146432787, lik3, 0.0001);
}
示例5: disabledtestAddOrderNStates
import cc.mallet.types.InstanceList; //导入方法依赖的package包/类
public void disabledtestAddOrderNStates ()
{
Pipe p = makeSpacePredictionPipe ();
InstanceList instances = new InstanceList (p);
instances.addThruPipe (new ArrayIterator(data));
InstanceList[] lists = instances.split (new java.util.Random (678), new double[]{.5, .5});
// Compare 3 CRFs trained with addOrderNStates, and make sure
// that having more features leads to a higher likelihood
MEMM crf1 = new MEMM(p.getDataAlphabet(), p.getTargetAlphabet());
crf1.addOrderNStates (lists [0],
new int[] { 1, },
new boolean[] { false, },
"START",
null,
null,
false);
crf1.setWeightsDimensionAsIn(lists[0]);
MEMMTrainer memmt1 = new MEMMTrainer (crf1);
memmt1.train(lists [0]);
MEMM crf2 = new MEMM(p.getDataAlphabet(), p.getTargetAlphabet());
crf2.addOrderNStates (lists [0],
new int[] { 1, 2, },
new boolean[] { false, true },
"START",
null,
null,
false);
crf2.setWeightsDimensionAsIn(lists[0]);
MEMMTrainer memmt2 = new MEMMTrainer (crf2);
memmt2.train(lists [0]);
MEMM crf3 = new MEMM(p.getDataAlphabet(), p.getTargetAlphabet());
crf3.addOrderNStates (lists [0],
new int[] { 1, 2, },
new boolean[] { false, false },
"START",
null,
null,
false);
crf3.setWeightsDimensionAsIn(lists[0]);
MEMMTrainer memmt3 = new MEMMTrainer (crf3);
memmt3.train(lists [0]);
// Prevent cached values
double lik1 = getLikelihood (memmt1, lists[0]);
double lik2 = getLikelihood (memmt2, lists[0]);
double lik3 = getLikelihood (memmt3, lists[0]);
System.out.println("CRF1 likelihood "+lik1);
assertTrue ("Final zero-order likelihood <"+lik1+"> greater than first-order <"+lik2+">",
lik1 < lik2);
assertTrue ("Final defaults-only likelihood <"+lik2+"> greater than full first-order <"+lik3+">",
lik2 < lik3);
assertEquals (-167.335971702, lik1, 0.0001);
assertEquals (-166.212235389, lik2, 0.0001);
assertEquals ( -90.386005741, lik3, 0.0001);
}