Package edu.cmu.tetrad.bayes

Interface BayesIm

All Superinterfaces:
Im, Serializable, Simulator, TetradSerializable, VariableSource
All Known Implementing Classes:
DirichletBayesIm, MlBayesIm, MlBayesImObs, UpdatedBayesIm
public interface BayesIm extends VariableSource, Im, Simulator
Interface implemented by Bayes instantiated models. For purposes of clarification, we distinguish a Bayes parametric model from a Bayes instantiated model. The former provides enough information for us to know what the parameters of the Bayes net are, given that we know the graph of the Bayes net--i.e., it tells us how many categories each variable has and what the names of those categories are. It does not, however, tell us what the value of each parameter is; information about the value of each parameter in the Bayes net is provided in the Bayes instantiated model. This information is organized, variable by variable, in conditional probability tables. For each variable, a table is stored representing enough information to recover the conditional probability of each value of each variable given each combination of values of the parents of the variable in the graph. The rows of the table are the combinations of parent values of the variable, and the columns of the table are variable values of the variable. Most of the method in this interface are designed mainly to allow these values to be set and retrieved. A few methods are dedicated to bookkeeping chores, like clearing tables or initializing them randomly. One special method (simulateData) is dedicated to the task of generating randomly simulated data sets consistent with the conditional probabilities implied by the information stored in the conditional probability tables of the Bayes net. See implementations for details.
Author:
josephramsey
See Also:

  • Method Details

    • getBayesPm

      BayesPm getBayesPm()
      Returns:
      the underlying Bayes PM.

    • getDag

      Graph getDag()
      Returns:
      the underlying DAG.

    • getNumNodes

      int getNumNodes()
      Returns:
      the number of nodes in the model.

    • getNode

      Node getNode(int nodeIndex)
      Returns:
      the node corresponding to the given node index.

    • getNode

      Node getNode(String name)
      Parameters:
      name - the name of the node.
      Returns:
      the node with the given name in the associated graph.

    • getNodeIndex

      int getNodeIndex(Node node)
      Parameters:
      node - the given node.
      Returns:
      the index for that node, or -1 if the node is not in the BayesIm.

    • getVariables

      List<Node> getVariables()
      Specified by:
      getVariables in interface VariableSource
      Returns:
      the list of variable for this Bayes net.

    • getVariableNames

      List<String> getVariableNames()
      Specified by:
      getVariableNames in interface VariableSource
      Returns:
      the list of variable names for this Bayes net.

    • getMeasuredNodes

      List<Node> getMeasuredNodes()
      Returns:
      the list of measured variableNodes.

    • getNumColumns

      int getNumColumns(int nodeIndex)
      Returns:
      the number of columns in the table of the given node N with index 'nodeIndex'--that is, the number of possible values that N can take on. That is, if P(N=v0 | P1=v1, P2=v2, ... Pn=vn) is a conditional probability stored in 'probs', then the maximum number of rows in the table for N is #vals(N).
      See Also:

    • getNumRows

      int getNumRows(int nodeIndex)
      Returns:
      the number of rows in the table of the given node, which would be the total number of possible combinations of parent values for a given node. That is, if P(N=v0 | P1=v1, P2=v2, ... Pn=vn) is a conditional probability stored in 'probs', then the maximum number of rows in the table for N is #vals(P1) x #vals(P2) x ... x #vals(Pn).
      See Also:

    • getNumParents

      int getNumParents(int nodeIndex)
      Parameters:
      nodeIndex - the given node.
      Returns:
      the number of parents of the given node.

    • getParent

      int getParent(int nodeIndex, int parentIndex)
      Returns:
      the given parent of the given node.

    • getParentDim

      int getParentDim(int nodeIndex, int parentIndex)
      Returns:
      the dimension of the given parent for the given node.

    • getParentDims

      int[] getParentDims(int nodeIndex)
      Returns:
      (a defensive copy of) the array representing the dimensionality of each parent of a node, that is, the number of values which that node can take on. The order of entries in this array is the same as the order of entries of nodes returned by getParents() for that node.
      See Also:

    • getParents

      int[] getParents(int nodeIndex)
      Returns:
      (a defensive copy of) the array containing all of the parents of a given node in the order in which they are stored internally.
      See Also:

    • getParentValues

      int[] getParentValues(int nodeIndex, int rowIndex)
      Parameters:
      nodeIndex - the index of the node.
      rowIndex - the index of the row in question.
      Returns:
      an array containing the combination of parent values for a given node and given row in the probability table for that node. To get the combination of parent values from the row number, the row number is represented using a variable-base place value system, where the bases for each place value are the dimensions of the parents in the order in which they are given by getParentDims(). For instance, if the row number (base 10) is 103 and the parent dimension array is [3 5 7], we calculate the first value as 103 / 7 = 14 with a remainder of 5. We then divide 14 / 5 = 2 with a remainder of 4. We then divide 2 / 3 = 0 with a remainder of 2. The variable place value representation is [2 4 5], which is the combination of parent values. This is the inverse function of getRowIndex().
      See Also:

    • getParentValue

      int getParentValue(int nodeIndex, int rowIndex, int colIndex)
      Returns:
      the value in the probability table for the given node, at the given row and column.

    • getProbability

      double getProbability(int nodeIndex, int rowIndex, int colIndex)
      Parameters:
      nodeIndex - the index of the node in question.
      rowIndex - the row in the table for this for node which represents the combination of parent values in question.
      colIndex - the column in the table for this node which represents the value of the node in question.
      Returns:
      the probability for the given node at the given row and column in the table for that node. To get the node index, use getNodeIndex(). To get the row index, use getRowIndex(). To get the column index, use getCategoryIndex() from the underlying BayesPm(). The value returned will represent a conditional probability of the form P(N=v0 | P1=v1, P2=v2, ... , Pn=vn), where N is the node referenced by nodeIndex, v0 is the value referenced by colIndex, and the combination of parent values indicated is the combination indicated by rowIndex.
      See Also:

    • getRowIndex

      int getRowIndex(int nodeIndex, int[] values)
      Returns:
      the row in the table at which the given combination of parent values is represented for the given node. The row is calculated as a variable-base place-value number. For instance, if the array of parent dimensions is [3, 5, 7] and the parent value combination is [2, 4, 5], then the row number is (7 * (5 * (3 * 0 + 2) + 4)) + 5 = 103. This is the inverse function to getVariableValues().

      Note: If the node has n values, the length of 'values' must be >= the number of parents. Only the first n values are used.

      See Also:

    • normalizeAll

      void normalizeAll()
      Normalizes all rows in the tables associated with each of node in turn.

    • normalizeNode

      void normalizeNode(int nodeIndex)
      Normalizes all rows in the table associated with a given node.

    • normalizeRow

      void normalizeRow(int nodeIndex, int rowIndex)
      Normalizes the given row.

    • setProbability

      void setProbability(int nodeIndex, int rowIndex, int colIndex, double value)
      Sets the probability for the given node at a given row and column in the table for that node. To get the node index, use getNodeIndex(). To get the row index, use getRowIndex(). To get the column index, use getCategoryIndex() from the underlying BayesPm(). The value returned will represent a conditional probability of the form P(N=v0 | P1=v1, P2=v2, ... , Pn=vn), where N is the node referenced by nodeIndex, v0 is the value referenced by colIndex, and the combination of parent values indicated is the combination indicated by rowIndex.
      Parameters:
      nodeIndex - the index of the node in question.
      rowIndex - the row in the table for this for node which represents the combination of parent values in question.
      colIndex - the column in the table for this node which represents the value of the node in question.
      value - the desired probability to be set.
      See Also:

    • setProbability

      void setProbability(int nodeIndex, double[][] probMatrix)
      Sets the probability for the given node. The matrix row represent row index, the row in the table for this for node which represents the combination of parent values in question. of the CPT. The matrix column represent column index, the column in the table for this node which represents the value of the node in question.
      Parameters:
      nodeIndex - the index of the node in question.
      probMatrix - a matrix containing probabilities of a node along with its parents

    • getCorrespondingNodeIndex

      int getCorrespondingNodeIndex(int nodeIndex, BayesIm otherBayesIm)
      Returns:
      the index of the node with the given name in the specified BayesIm.

    • clearRow

      void clearRow(int nodeIndex, int rowIndex)
      Assigns random probability values to the child values of this row that add to 1.
      Parameters:
      nodeIndex - the node for the table that this row belongs to.
      rowIndex - the index of the row.

    • randomizeRow

      void randomizeRow(int nodeIndex, int rowIndex)
      Assigns random probability values to the child values of this row that add to 1.
      Parameters:
      nodeIndex - the node for the table that this row belongs to.
      rowIndex - the index of the row.

    • randomizeIncompleteRows

      void randomizeIncompleteRows(int nodeIndex)
      Randomizes any row in the table for the given node index that has a Double.NaN value in it.
      Parameters:
      nodeIndex - the node for the table whose incomplete rows are to be randomized.

    • randomizeTable

      void randomizeTable(int nodeIndex)
      Randomizes every row in the table for the given node index.
      Parameters:
      nodeIndex - the node for the table to be randomized.

    • clearTable

      void clearTable(int nodeIndex)
      Randomizes every row in the table for the given node index.
      Parameters:
      nodeIndex - the node for the table to be randomized.

    • isIncomplete

      boolean isIncomplete(int nodeIndex, int rowIndex)
      Returns:
      true iff one of the values in the given row is Double.NaN.

    • isIncomplete

      boolean isIncomplete(int nodeIndex)
      Returns:
      true iff any value in the table for the given node is Double.NaN.

    • simulateData

      DataSet simulateData(int sampleSize, boolean latentDataSaved)
      Simulates a sample with the given sample size.
      Specified by:
      simulateData in interface Simulator
      Parameters:
      sampleSize - the sample size.
      Returns:
      the simulated sample as a DataSet.

    • simulateData

      DataSet simulateData(DataSet dataSet, boolean latentDataSaved)
      Overwrites the given dataSet with a new simulated dataSet, to avoid allocating memory. The given dataSet must have the necessary number of columns.
      Returns:
      the simulated sample as a DataSet.

    • equals

      boolean equals(Object o)
      Overrides:
      equals in class Object
      Returns:
      true iff this bayes net is equal to the given Bayes net. The sense of equality may vary depending on the type of Bayes net.

    • toString

      String toString()
      Overrides:
      toString in class Object
      Returns:
      a string representation for this Bayes net.