Examples of statechum.analysis.learning.MarkovModel$MarkovMatrixEngine$PredictionStatePTAAutomaton

statechum.analysis.learning.MarkovModel
Describes a non-probabilistic Markov model, where for every path we know either that,
- the path was never encountered or
- the path was encountered and there is a specific set of elements of alphabet that followed it.
The idea is to use the supplied Markov matrix to predict transitions from a specific state, passed as an argument. The choice of direction is not a choice between predicting transitions leaving a state based on those surrounding that state v.s predicting transitions entering a state based on those surrounding it. It is rather a choice of classifier to make predictions, the one that looks at history and decides what is to follow and the one looking at surrounding transitions and making decisions based on that.
- Where predictForwardOrSideways is true, we are predicting transitions based on paths leading to the state of interest. Parameter Inverse_Graph should be the (non-deterministic) inverse of graph.
- Where predictForwardOrSideways is false, we are predicting transitions based on paths leading from the state of interest (sideways predictions). Parameter Inverse_Graph should be the same as graph and pathBeyondCurrentState should be null because once we predicted one transition, there are no further transitions from that state, hence no further transitions can be predicted sideways.

  
  @Test
  public void testMarkovPerformance1()
  {
    final LearnerGraph trainingGraph = FsmParser.buildLearnerGraph("A-a->B-b->C / B-u-#D / A-c->E-u->F / E-c->G","testUpdateMarkovSideways3",config, converter);
    MarkovModel m = new MarkovModel(2,true,true);
    MarkovClassifier cl=new MarkovClassifier(m,trainingGraph);cl.updateMarkov(false);
    statechum.Pair<Double,Double> pairTraining = cl.evaluateCorrectnessOfMarkov();
    Assert.assertEquals(2./3,pairTraining.firstElem,Configuration.fpAccuracy);// reflects that transitions u and c from G are not present but predicted
    Assert.assertEquals(2./3.,pairTraining.secondElem,Configuration.fpAccuracy);// reflects that transitions a and c are not predicted but present.

View Full Code Here

  
  @Test
  public void testMarkovPerformance2()
  {
    final LearnerGraph trainingGraph = FsmParser.buildLearnerGraph("A-a->B-b->C / B-u-#D / A-c->E-u->F / E-c->G","testUpdateMarkovSideways3",config, converter);
    MarkovModel m = new MarkovModel(2,true,true);
    MarkovClassifier cl=new MarkovClassifier(m,trainingGraph);cl.updateMarkov(false);
    
    MarkovClassifier eval = new MarkovClassifier(m,FsmParser.buildLearnerGraph("A-a->B-u-#D / B-b->G","testMarkovPerformance2",config, converter));
    statechum.Pair<Double,Double> pair = eval.evaluateCorrectnessOfMarkov();
    Assert.assertEquals(1,pair.firstElem,Configuration.fpAccuracy);Assert.assertEquals(2./3,pair.secondElem,Configuration.fpAccuracy);// transition a is not predicted

View Full Code Here

  
  @Test
  public void testMarkovPerformance3()
  {
    final LearnerGraph trainingGraph = FsmParser.buildLearnerGraph("A-a->B-b->C / B-u-#D / A-c->E-u->F / E-c->G","testUpdateMarkovSideways3",config, converter);
    MarkovModel m = new MarkovModel(2,true,true);
    MarkovClassifier cl=new MarkovClassifier(m,trainingGraph);cl.updateMarkov(false);
    
    MarkovClassifier eval = new MarkovClassifier(m,FsmParser.buildLearnerGraph("A-a->B-u-#D / B-b->G / B-e->Z","testMarkovPerformance3",config, converter));
    statechum.Pair<Double,Double> pair = eval.evaluateCorrectnessOfMarkov();
    Assert.assertEquals(1,pair.firstElem,Configuration.fpAccuracy);Assert.assertEquals(0.5,pair.secondElem,Configuration.fpAccuracy);// transition a is not predicted

View Full Code Here

  
  @Test
  public void testMarkovPerformance4()
  {
    final LearnerGraph trainingGraph = FsmParser.buildLearnerGraph("A-a->B-b->C / B-u-#D / A-c->E-u->F / E-c->G","testUpdateMarkovSideways3",config, converter);
    MarkovModel m = new MarkovModel(2,true,true);
    MarkovClassifier cl=new MarkovClassifier(m,trainingGraph);cl.updateMarkov(false);
    
    MarkovClassifier eval = new MarkovClassifier(m,FsmParser.buildLearnerGraph("A-a->B-b->C-c->D-u->E","testMarkovPerformance4",config, converter));
    statechum.Pair<Double,Double> pair = eval.evaluateCorrectnessOfMarkov();
    Assert.assertEquals(3./4,pair.firstElem,Configuration.fpAccuracy);// u is predicted as negative and is indeed missing, b is correctly predicted as a positive; u after c is correctly predicted as positive and c after c is not correctly predicted.

View Full Code Here

  
  @Test
  public void testMarkovPerformance5()
  {
    final LearnerGraph trainingGraph = FsmParser.buildLearnerGraph("A-a->B-b->C / B-u-#D / A-c->E-u->F / E-c->G","testUpdateMarkovSideways3",config, converter);
    MarkovModel m = new MarkovModel(2,true,true);
    MarkovClassifier cl=new MarkovClassifier(m,trainingGraph);cl.updateMarkov(false);
    
    MarkovClassifier eval = new MarkovClassifier(m,FsmParser.buildLearnerGraph("A-a->B-b->G","testMarkovPerformance5",config, converter));
    statechum.Pair<Double,Double> pair = eval.evaluateCorrectnessOfMarkov();
    Assert.assertEquals(1,pair.firstElem,Configuration.fpAccuracy);// u is predicted as negative and is indeed missing, b is correctly predicted as a positive

View Full Code Here

    Helper.checkForCorrectException(new whatToRun() {
      @SuppressWarnings("unused")
      @Override
      public void run() throws NumberFormatException
      {
        new MarkovModel(1,true,true);
      }
    }, IllegalArgumentException.class, "chunkLen");
  }

View Full Code Here

  }
  
  @Test
  public void testCreateMarkovMatrix1()
  {
    MarkovModel m = new MarkovModel(2,true,true);
    Set<List<Label>> plusStrings = buildSet(new String[][] { new String[]{"a","b","c"}, new String[]{"a","b"}, new String[]{"a","d","c"}},config,converter), minusStrings = buildSet(new String[][] { new String[]{"a","b","c","d"}, new String[]{"a","u"} },config,converter);
    Map<Trace, MarkovOutcome> matrix = m.createMarkovLearner(plusStrings, minusStrings,false);
    Assert.assertEquals(11,matrix.size());
    Assert.assertSame(MarkovOutcome.negative, matrix.get(new Trace(Arrays.asList(new Label[]{lblA,lblU}),true)));


    Assert.assertSame(MarkovOutcome.positive, matrix.get(new Trace(Arrays.asList(new Label[]{lblD,lblC}),true)));

View Full Code Here

  }  


  @Test
  public void testCreateMarkovMatrix2()
  {
    MarkovModel m = new MarkovModel(2,true,true);
    Set<List<Label>> plusStrings = buildSet(new String[][] { new String[]{"a","u"} },config,converter), minusStrings = new HashSet<List<Label>>();
    Map<Trace, MarkovOutcome> matrix = m.createMarkovLearner(plusStrings, minusStrings,false);
    Assert.assertEquals(3,matrix.size());
    
    Assert.assertSame(MarkovOutcome.positive, matrix.get(new Trace(Arrays.asList(new Label[]{lblA,lblU}),true)));


    Assert.assertSame(MarkovOutcome.positive, matrix.get(new Trace(Arrays.asList(new Label[]{lblA}),true)));

View Full Code Here

  }
  
  @Test
  public void testCreateMarkovMatrix3a()
  {
    MarkovModel m = new MarkovModel(2,true,true);
    Set<List<Label>> plusStrings = new HashSet<List<Label>>(), minusStrings = buildSet(new String[][] { new String[]{"a","u"} },config,converter);
    Map<Trace, MarkovOutcome> matrix = m.createMarkovLearner(plusStrings, minusStrings,false);
    Assert.assertEquals(3,matrix.size());


    Assert.assertSame(MarkovOutcome.negative, matrix.get(new Trace(Arrays.asList(new Label[]{lblA,lblU}),true)));


    Assert.assertSame(MarkovOutcome.positive, matrix.get(new Trace(Arrays.asList(new Label[]{lblA}),true)));

View Full Code Here

  
  /** Only differs from 3a by the use of chunk_length of 3. The outcome should be the same. */
  @Test
  public void testCreateMarkovMatrix3b()
  {
    MarkovModel m = new MarkovModel(3,true,true);
    Set<List<Label>> plusStrings = new HashSet<List<Label>>(), minusStrings = buildSet(new String[][] { new String[]{"a","u"} },config,converter);
    Map<Trace, MarkovOutcome> matrix = m.createMarkovLearner(plusStrings, minusStrings,false);
    Assert.assertEquals(3,matrix.size());


    Assert.assertSame(MarkovOutcome.negative, matrix.get(new Trace(Arrays.asList(new Label[]{lblA,lblU}),true)));


    Assert.assertSame(MarkovOutcome.positive, matrix.get(new Trace(Arrays.asList(new Label[]{lblA}),true)));

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of statechum.analysis.learning.MarkovModel$MarkovMatrixEngine$PredictionStatePTAAutomaton

statechum.analysis.Erlang.Synapse$StatechumProcess

statechum.analysis.learning.experiments.PairSelection.ASE2014$LearnerRunner

statechum.analysis.learning.experiments.PairSelection.Cav2014$EvaluationOfExisingLearnerRunner

statechum.analysis.learning.experiments.PairSelection.Cav2014$LearnerRunner

statechum.analysis.learning.experiments.PairSelection.CVS$LearnerRunner

statechum.analysis.learning.experiments.PairSelection.CVS_With_Random_traces_Generation$LearnerRunner

statechum.analysis.learning.experiments.PairSelection.LearnFromTracesUsingExperimentalLearners

statechum.analysis.learning.experiments.PairSelection.MarkovLearnerExperimentWithStatisticalAnalysis$LearnerRunner

statechum.analysis.learning.experiments.PairSelection.MarkovPassivePairSelection

statechum.analysis.learning.experiments.PairSelection.MarkovPassivePairSelection$LearnerRunner

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.