cc.mallet.grmm.learning
Class DefaultAcrfTrainer.LogEvaluator

java.lang.Object
  extended by cc.mallet.grmm.learning.ACRFEvaluator
      extended by cc.mallet.grmm.learning.DefaultAcrfTrainer.LogEvaluator
Enclosing class:
DefaultAcrfTrainer

public static class DefaultAcrfTrainer.LogEvaluator
extends ACRFEvaluator


Constructor Summary
DefaultAcrfTrainer.LogEvaluator()
           
 
Method Summary
static DefaultAcrfTrainer.TestResults computeTestResults(InstanceList testList, java.util.List returnedList)
           
 boolean evaluate(ACRF acrf, int iter, InstanceList training, InstanceList validation, InstanceList testing)
          Evalutes the model in the middle of training.
 double getJointAccuracy()
           
 void test(InstanceList testList, java.util.List returnedList, java.lang.String description)
           
 
Methods inherited from class cc.mallet.grmm.learning.ACRFEvaluator
makeOutputFile, setNumIterToSkip, setNumIterToWait, setOutputPrefix, shouldDoEvaluate, test
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Constructor Detail

DefaultAcrfTrainer.LogEvaluator

public DefaultAcrfTrainer.LogEvaluator()
Method Detail

evaluate

public boolean evaluate(ACRF acrf,
                        int iter,
                        InstanceList training,
                        InstanceList validation,
                        InstanceList testing)
Description copied from class: ACRFEvaluator
Evalutes the model in the middle of training.

Specified by:
evaluate in class ACRFEvaluator
Parameters:
acrf - Model tha is being trained.
iter - How many iterations have been completed.
training - Training set.
validation - Validation set; may be null.
testing - Testing set; maybe null.
Returns:
Whether to continue training. If return is false, training should be be stopped.

test

public void test(InstanceList testList,
                 java.util.List returnedList,
                 java.lang.String description)
Specified by:
test in class ACRFEvaluator

computeTestResults

public static DefaultAcrfTrainer.TestResults computeTestResults(InstanceList testList,
                                                                java.util.List returnedList)

getJointAccuracy

public double getJointAccuracy()