Class PCStructuralLearningOptions

    • Constructor Detail

      • PCStructuralLearningOptions

        public PCStructuralLearningOptions()
        Initializes a new instance of the com.bayesserver.learning.structure.pc.PCStructuralLearningOptions class.
    • Method Detail

      • getStopping

        public Stop getStopping()
        Gets the instance implementing Stop used for early stopping. Stopping is different to cancellation, as stopping will still complete the learning process, albeit having not run to completion.
        Specified by:
        getStopping in interface StructuralLearningOptions
        Returns:
        The instance used for stopping.
      • setStopping

        public void setStopping​(Stop value)
        Sets the instance implementing Stop used for early stopping. Stopping is different to cancellation, as stopping will still complete the learning process, albeit having not run to completion.
        Specified by:
        setStopping in interface StructuralLearningOptions
        Parameters:
        value - The instance used for stopping.
      • getMaximumBatchSize

        public long getMaximumBatchSize()
        Gets the maximum number of tests that are buffered in memory for processing in a single iteration of the data. When large numbers of tests are required, instead of exhausting available memory, the tests are performed in batches. This value limits the number of tests that need to be stored in memory.
      • setMaximumBatchSize

        public void setMaximumBatchSize​(long value)
        Sets the maximum number of tests that are buffered in memory for processing in a single iteration of the data. When large numbers of tests are required, instead of exhausting available memory, the tests are performed in batches. This value limits the number of tests that need to be stored in memory.
      • getMaximumTemporalOrder

        public int getMaximumTemporalOrder()
        Gets the maximum order of temporal links that are considered during learning. When learning Bayesian networks with temporal nodes (time series or sequence nodes) this value tells the algorithm the maximum order or links (sometimes referred to as the lag).
      • setMaximumTemporalOrder

        public void setMaximumTemporalOrder​(int value)
        Sets the maximum order of temporal links that are considered during learning. When learning Bayesian networks with temporal nodes (time series or sequence nodes) this value tells the algorithm the maximum order or links (sometimes referred to as the lag).
      • getIndependence

        public IndependenceOptions getIndependence()
        Gets options controlling how the independence tests are carried out.
      • getMaximumConditional

        public int getMaximumConditional()
        Gets the maximum number of conditional variables to consider during independence testing.
        Returns:
        The maximum number of conditional variables considered.

        Typically a value of 3 is used.

        A value of 0 means that only marginal independence tests will be performed.

      • setMaximumConditional

        public void setMaximumConditional​(int value)
        Sets the maximum number of conditional variables to consider during independence testing.
        Parameters:
        value - The maximum number of conditional variables considered.

        Typically a value of 3 is used.

        A value of 0 means that only marginal independence tests will be performed.