Examples of statechum.Configuration

statechum.Configuration
Represents a configuration for a learner. The purpose is a possibility of a global customisation of all objects used by a learner in the course of learning by the same object.
When you add to this class, please add the corresponding entries to hashCode and equals.
This class is using the built-in clone method, hence all attributes have to be either primitives or immutable (such as String).

   * @param args trace file to load.
     * @throws IOException 
   */
  public static void generateHugeArff(final int ifDepth, @SuppressWarnings("unused") String[] args) throws Exception 
  {
    final Configuration learnerConfig = Configuration.getDefaultConfiguration().copy();learnerConfig.setGeneralisationThreshold(0);learnerConfig.setGdFailOnDuplicateNames(false);
        learnerConfig.setGdLowToHighRatio(0.75);learnerConfig.setGdKeyPairThreshold(0.5);learnerConfig.setTransitionMatrixImplType(STATETREE.STATETREE_ARRAY);
        learnerConfig.setAskQuestions(false);
        
       final InitialConfigurationAndData initialConfigAndData = PairQualityLearner.loadInitialAndPopulateInitialConfiguration(PairQualityLearner.largePTAFileName, learnerConfig, new Transform.InternStringLabel());


    LearnerGraph referenceGraph = new LearnerGraph(initialConfigAndData.initial.graph.config);AbstractPersistence.loadGraph("resources/largePTA/outcome_correct", referenceGraph, initialConfigAndData.learnerInitConfiguration.getLabelConverter());
      WekaDataCollector dataCollector = PairQualityLearner.createDataCollector(ifDepth);

View Full Code Here

      else
      {// only create a top-level element if writing pure XML.
        outputStream=outStream;
        topElement = doc.createElement(ELEM_KINDS.ELEM_STATECHUM_TESTTRACE.name());doc.appendChild(topElement);topElement.appendChild(Transform322.endl(doc));
      }
      Configuration seriesConfiguration = config.copy();seriesConfiguration.setGdMaxNumberOfStatesInCrossProduct(0);
    }
    catch(ParserConfigurationException e)
    {
      statechum.Helper.throwUnchecked("failed to construct DOM document",e);
    }

View Full Code Here

   * @param gr the graph to save and then load.
   * @throws IOException
   */
  public void checkLoading(LearnerGraph gr) throws IOException
  {
    final Configuration config = Configuration.getDefaultConfiguration();
    StringWriter writer = new StringWriter();gr.transform322.writeGraphML(writer);
    LearnerGraph loaded = LearnerGraph.loadGraph(new StringReader(writer.toString()),config);


    Assert.assertTrue(!gr.wmethod.checkUnreachableStates());Assert.assertTrue(!loaded.wmethod.checkUnreachableStates());
    Assert.assertNull(checkM(gr,loaded));

View Full Code Here

  }


  /** Checks if simply creating vertices we may get an ID with existing number. */
  protected static final boolean ids_are_valid(LearnerGraph gr)
  {
    final Configuration config = gr.config.copy();config.setLearnerCloneGraph(false);
    LearnerGraph graph = gr.copy(config);
    
    // Now we check that we can create lots of vertices and none of their numbers 
    // will be included 
    {

View Full Code Here

    /** Maps states to a function associating labels to a sum of probabilities from a Markov matrix. Such a sum is supposed to predict the likelyhood of a transition with this label from every state. */
    Map<CmpVertex,Map<Label,UpdatablePairInteger>> state_outgoing_occurence=new HashMap<CmpVertex,Map<Label,UpdatablePairInteger>>();
    /** Maps states to a function associating labels to a probability of a transition with the label of interest from a state of interest. Computed from {@link MarkovUniversalLearner#state_outgoing_occurence}. */
    Map<CmpVertex,Map<Label,UpdatablePairDouble>> state_outgoing=new HashMap<CmpVertex,Map<Label,UpdatablePairDouble>>();


    final Configuration shallowCopy = tentativeAutomaton.config.copy();shallowCopy.setLearnerCloneGraph(false);
    Extension_Graph= new LearnerGraph(shallowCopy);
    LearnerGraph.copyGraphs(tentativeAutomaton, Extension_Graph);
    Set<Label> allElementsOfAlphabet = tentativeAutomaton.learnerCache.getAlphabet(); 
    List<Label> pathToNewState=new LinkedList<Label>();
    // mapping map to store all paths leave each state in different length

View Full Code Here

   * @param predictForwardOrSideways whether to update a forward or a sideways Markov matrix.
   * @param onlyLongest if set, only add traces of <i>chunkLen</i> to Markov matrix. Where false, all prefixes are added as well.
   */
  public void updateMarkov(LearnerGraph tentativeAutomaton, boolean predictForwardOrSideways, boolean onlyLongest)
  {
    final Configuration shallowCopy = tentativeAutomaton.config.copy();shallowCopy.setLearnerCloneGraph(false);
    Set<Label> alphabet = tentativeAutomaton.learnerCache.getAlphabet();
    Map<Trace, MarkovOutcome> MarkovMatrix = getMarkov(predictForwardOrSideways);
    Map<Trace, UpdatablePairInteger> occurrenceMatrix = getOccurrence(predictForwardOrSideways);
    @SuppressWarnings("rawtypes")
    AbstractLearnerGraph Inverse_Graph = computeInverseGraph(tentativeAutomaton, predictForwardOrSideways);

View Full Code Here

  public static AbstractLearnerGraph computeInverseGraph(LearnerGraph graph,boolean predictForward)
  {
    AbstractLearnerGraph Inverse_Graph = null;
    if (predictForward)
    {
      Configuration shallowCopy = graph.config.copy();shallowCopy.setLearnerCloneGraph(false);
      LearnerGraphND Inverse = new LearnerGraphND(shallowCopy);Inverse.initEmpty();
      AbstractPathRoutines.buildInverse(graph,LearnerGraphND.ignoreNone,Inverse);  // do the inverse to the tentative graph
      Inverse_Graph = Inverse;
    }
    else

View Full Code Here

  public Map<CmpVertex, Map<Label, MarkovOutcome>> predictTransitions(LearnerGraph tentativeAutomaton, boolean predictForwardOrSideways)
  {
    /** Maps states to a function associating labels to a probability of a transition with the label of interest from a state of interest. Computed from {@link MarkovUniversalLearner#state_outgoing_occurence}. */
    Map<CmpVertex,Map<Label,MarkovOutcome>> state_outgoing=new HashMap<CmpVertex,Map<Label,MarkovOutcome>>();


    final Configuration shallowCopy = tentativeAutomaton.config.copy();shallowCopy.setLearnerCloneGraph(false);
    Set<Label> alphabet = tentativeAutomaton.learnerCache.getAlphabet(); 
    Map<Trace, MarkovOutcome> MarkovMatrix = getMarkov(predictForwardOrSideways);
    // mapping map to store all paths leave each state in different length
    @SuppressWarnings("rawtypes")
    AbstractLearnerGraph Inverse_Graph = computeInverseGraph(tentativeAutomaton, predictForwardOrSideways);

View Full Code Here

  public Map<CmpVertex, Map<Label, MarkovOutcome>> constructMarkovTentative(LearnerGraph tentativeAutomaton, boolean predictForwardOrSideways)
  {
    /** Maps states to a function associating labels to a probability of a transition with the label of interest from a state of interest. Computed from {@link MarkovUniversalLearner#state_outgoing_occurence}. */
    Map<CmpVertex,Map<Label,MarkovOutcome>> state_outgoing=predictTransitions(tentativeAutomaton,predictForwardOrSideways);


    final Configuration shallowCopy = tentativeAutomaton.config.copy();shallowCopy.setLearnerCloneGraph(false);
    Extension_Graph= new LearnerGraph(shallowCopy);
    LearnerGraph.copyGraphs(tentativeAutomaton, Extension_Graph);


    // in this part the tree is extended depend on their outgoing transition probabilities
     for(Entry<CmpVertex, Map<Label, MarkovOutcome>> outgoing:state_outgoing.entrySet())

View Full Code Here

    assert original.transitionMatrix.containsKey(pair.firstElem);
    assert original.transitionMatrix.containsKey(pair.secondElem);
    Map<CmpVertex,List<CmpVertex>> mergedVertices = original.config.getTransitionMatrixImplType() == STATETREE.STATETREE_ARRAY?
        new ArrayMapWithSearch<CmpVertex,List<CmpVertex>>(original.getStateNumber()):
        new HashMapWithSearch<CmpVertex,List<CmpVertex>>(original.getStateNumber());
    Configuration shallowCopy = original.config.copy();shallowCopy.setLearnerCloneGraph(false);
    LearnerGraph result = new LearnerGraph(original,shallowCopy);
    assert result.transitionMatrix.containsKey(pair.firstElem);
    assert result.transitionMatrix.containsKey(pair.secondElem);


    long pairScore = original.pairscores.computePairCompatibilityScore_internal(pair,mergedVertices);

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of statechum.Configuration

statechum.analysis.Erlang.ErlangAppReader

statechum.analysis.Erlang.ErlangModule

statechum.analysis.Erlang.Signatures.TestTypes

statechum.analysis.Erlang.Synapse$StatechumProcess

statechum.analysis.Erlang.TestErlangGraphs

statechum.analysis.Erlang.TestErlangModule

statechum.analysis.Erlang.TestSynapseAuxiliaryFunctions

statechum.analysis.learning.experiments.Benchmarklinear

statechum.analysis.learning.experiments.ExperimentRunner$GeneratorConfiguration

statechum.analysis.learning.experiments.ExperimentRunner$LearnerEvaluator

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.