Examples of statechum.analysis.learning.MarkovModel

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.

  
  /** A bit has been added. u has been seen both in the positive and negative light. */
  @Test
  public void testConstructExtendedGraph7()
  {
    MarkovModel m = new MarkovModel(2,true,true);
    Set<List<Label>> plusStrings = buildSet(new String[][] { new String[]{"a","b"},new String[]{"c","u"} },config,converter), minusStrings = buildSet(new String[][] { new String[]{"a","u"} },config,converter);
    m.createMarkovLearner(plusStrings, minusStrings,false);
    final LearnerGraph graph = FsmParser.buildLearnerGraph("A-a->B / A-c->B-c->Z / T-b->T-u->T","testConstructExtendedGraph7a",config, converter);
    MarkovClassifier cl = new MarkovClassifier(m,graph);
    Map<CmpVertex, Map<Label, MarkovOutcome>> newTransitions = cl.predictTransitions();
    
    Assert.assertEquals(2,newTransitions.size());

View Full Code Here

  
  /** No outgoing from B, hence no inconsistencies. */
  @Test
  public void testCheckFanoutInconsistency1a()
  {
    MarkovModel m = new MarkovModel(2,true,true);
    Set<List<Label>> plusStrings = buildSet(new String[][] { new String[]{"a","b"},new String[]{"c","u"} },config,converter), minusStrings = buildSet(new String[][] { new String[]{"a","u"} },config,converter);
    m.createMarkovLearner(plusStrings, minusStrings,false);
    final LearnerGraph graph = FsmParser.buildLearnerGraph("A-a->B / A-c->B / T-b->T-u->T","testCheckFanoutInconsistency1a",config, converter);
    
    Assert.assertEquals(0,new MarkovClassifier(m,graph).checkFanoutInconsistency(graph.findVertex("B"),new MarkovClassifier.DifferentPredictionsInconsistency()));
  }

View Full Code Here

  
  /** One from B with inconsistent predictions. */
  @Test
  public void testCheckFanoutInconsistency1b1()
  {
    MarkovModel m = new MarkovModel(2,true,true);
    Set<List<Label>> plusStrings = buildSet(new String[][] { new String[]{"a","b"},new String[]{"c","u"} },config,converter), minusStrings = buildSet(new String[][] { new String[]{"a","u"} },config,converter);
    m.createMarkovLearner(plusStrings, minusStrings,false);
    final LearnerGraph graph = FsmParser.buildLearnerGraph("A-a->B / A-c->B / B-u->F / T-b->T-u->T","testCheckFanoutInconsistency1b1",config, converter);
    
    Assert.assertEquals(1,new MarkovClassifier(m,graph).checkFanoutInconsistency(graph.findVertex("B"),new MarkovClassifier.DifferentPredictionsInconsistency()));
  }

View Full Code Here

  
  /** One from B where Markov cannot make up its mind for au+ v.s. au- and c-transition is ignored. Label b from A is not reported by the checker as something to check and hence is ignored. */
  @Test
  public void testCheckFanoutInconsistency1b2()
  {
    MarkovModel m = new MarkovModel(2,true,true);
    Set<List<Label>> plusStrings = buildSet(new String[][] { new String[]{"a","b"},new String[]{"a","u"} },config,converter), minusStrings = buildSet(new String[][] { new String[]{"a","u"} },config,converter);
    m.createMarkovLearner(plusStrings, minusStrings,false);
    final LearnerGraph graph = FsmParser.buildLearnerGraph("A-a->B / A-c->B / B-u->F / T-b->T-u->T","testCheckFanoutInconsistency1b2",config, converter);
    
    Assert.assertEquals(0,new MarkovClassifier(m,graph).checkFanoutInconsistency(graph.findVertex("B"),new MarkovClassifier.DifferentPredictionsInconsistency()));
  }

View Full Code Here

  
  /** One from B where Markov cannot make up its mind for au+ v.s. au- and c-transition is ignored. Label b from A IS reported by the checker as something to check and hence is causes an inconsistency. */
  @Test
  public void testCheckFanoutInconsistency1b3()
  {
    MarkovModel m = new MarkovModel(2,true,true);
    Set<List<Label>> plusStrings = buildSet(new String[][] { new String[]{"a","b"},new String[]{"a","u"} },config,converter), minusStrings = buildSet(new String[][] { new String[]{"a","u"} },config,converter);
    m.createMarkovLearner(plusStrings, minusStrings,false);
    final LearnerGraph graph = FsmParser.buildLearnerGraph("A-a->B / A-c->B / B-u->F / T-b->T-u->T","testCheckFanoutInconsistency1b2",config, converter);
    
    Assert.assertEquals(1,new MarkovClassifier(m,graph).checkFanoutInconsistency(graph.findVertex("B"),new MarkovClassifier.DifferentPredictionsInconsistency()
    {

View Full Code Here

  
  /** Transition d exists as positive but should be present as negative according to Markov. */
  @Test
  public void testCheckFanoutInconsistency1c()
  {
    MarkovModel m = new MarkovModel(2,true,true);
    Set<List<Label>> plusStrings = buildSet(new String[][] { new String[]{"a","b"},new String[]{"c","u"} },config,converter), minusStrings = buildSet(new String[][] { new String[]{"a","u"},new String[]{"a","d"} },config,converter);
    m.createMarkovLearner(plusStrings, minusStrings,false);
    final LearnerGraph graph = FsmParser.buildLearnerGraph("A-a->B / A-c->B / B-d->F / T-b->T-u->T-d->T","testCheckFanoutInconsistency1c",config, converter);
    
    Assert.assertEquals(1,new MarkovClassifier(m,graph).checkFanoutInconsistency(graph.findVertex("B"),new MarkovClassifier.DifferentPredictionsInconsistency()));
  }

View Full Code Here

  
  /** Transition d exists as positive but should be absent according to Markov. */
  @Test
  public void testCheckFanoutInconsistency1d()
  {
    MarkovModel m = new MarkovModel(2,true,true);
    Set<List<Label>> plusStrings = buildSet(new String[][] { new String[]{"a","b"},new String[]{"c","u"} },config,converter), minusStrings = buildSet(new String[][] { new String[]{"a","u"}},config,converter);
    m.createMarkovLearner(plusStrings, minusStrings,false);
    final LearnerGraph graph = FsmParser.buildLearnerGraph("A-a->B / A-c->B / B-d->F / T-b->T-u->T-d->T","testCheckFanoutInconsistency1d",config, converter);
    
    Assert.assertEquals(1,new MarkovClassifier(m,graph).checkFanoutInconsistency(graph.findVertex("B"),new MarkovClassifier.DifferentPredictionsInconsistency()));
  }

View Full Code Here

  
  /** Transition b exists as negative but should be present as positive according to Markov. */
  @Test
  public void testCheckFanoutInconsistency1e()
  {
    MarkovModel m = new MarkovModel(2,true,true);
    Set<List<Label>> plusStrings = buildSet(new String[][] { new String[]{"a","b"},new String[]{"c","u"} },config,converter), minusStrings = buildSet(new String[][] { new String[]{"a","u"}},config,converter);
    m.createMarkovLearner(plusStrings, minusStrings,false);
    final LearnerGraph graph = FsmParser.buildLearnerGraph("A-a->B / A-c->B / B-b-#F / T-b->T-u->T-d->T","testCheckFanoutInconsistency1e",config, converter);
    
    Assert.assertEquals(1,new MarkovClassifier(m,graph).checkFanoutInconsistency(graph.findVertex("B"),new MarkovClassifier.DifferentPredictionsInconsistency()));
  }

View Full Code Here

  
  /** Transition d exists as negative but should be absent according to Markov. */
  @Test
  public void testCheckFanoutInconsistency1f()
  {
    MarkovModel m = new MarkovModel(2,true,true);
    Set<List<Label>> plusStrings = buildSet(new String[][] { new String[]{"a","b"},new String[]{"c","u"} },config,converter), minusStrings = buildSet(new String[][] { new String[]{"a","u"} },config,converter);
    m.createMarkovLearner(plusStrings, minusStrings,false);
    final LearnerGraph graph = FsmParser.buildLearnerGraph("A-a->B / A-c->B / B-d-#F / T-b->T-u->T-d->T","testCheckFanoutInconsistency1f",config, converter);
    
    Assert.assertEquals(1,new MarkovClassifier(m,graph).checkFanoutInconsistency(graph.findVertex("B"),new MarkovClassifier.DifferentPredictionsInconsistency()));
    Assert.assertEquals(4.,MarkovClassifier.computeInconsistency(graph,  m, new MarkovClassifier.DifferentPredictionsInconsistency(),false),Configuration.fpAccuracy);// inconsistencies detected are mostly due to state T
  }

View Full Code Here

  
  /** Two inconsistencies, transition u and transition b which should not exist after c. */
  @Test
  public void testCheckFanoutInconsistency2()
  {
    MarkovModel m = new MarkovModel(2,true,true);
    Set<List<Label>> plusStrings = buildSet(new String[][] { new String[]{"a","b"},new String[]{"c","u"} },config,converter), minusStrings = buildSet(new String[][] { new String[]{"a","u"} },config,converter);
    m.createMarkovLearner(plusStrings, minusStrings,false);
    final LearnerGraph graph = FsmParser.buildLearnerGraph("A-a->B / A-c->B-b->C / B-u->F / T-b->T-u->T","testCheckFanoutInconsistency2",config, converter);
    
    Assert.assertEquals(2,new MarkovClassifier(m,graph).checkFanoutInconsistency(graph.findVertex("B"),new MarkovClassifier.DifferentPredictionsInconsistency()));
  }

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of statechum.analysis.learning.MarkovModel

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.