Dynamic Bayesian Network Action Set

Computes evolution of beliefs in hidden variables over time by using Dynamic Bayesian Networks

dynBnet Action

Dynamic Bayesian Network Action.

CASL Syntax

dynamicBayesianNetwork.dynBnet <result=results> <status=rc> /

cliques={

data={

caslib="string"

computedOnDemand=TRUE | FALSE

computedVars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

computedVarsProgram="string"

dataSourceOptions={key-1=any-list-or-data-type-1 <, key-2=any-list-or-data-type-2, ...>}

groupBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

groupByMode="NOSORT" | "REDISTRIBUTE"

importOptions={fileType="ANY" | "AUDIO" | "AUTO" | "BASESAS" | "CSV" | "DELIMITED" | "DOCUMENT" | "DTA" | "ESP" | "EXCEL" | "FMT" | "HDAT" | "IMAGE" | "JMP" | "LASR" | "PARQUET" | "SOUND" | "SPSS" | "VIDEO" | "XLS", fileType-specific-parameters}

name="table-name"

onDemand=TRUE | FALSE

orderBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

singlePass=TRUE | FALSE

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

whereTable={

casLib="string"

dataSourceOptions={adls_noreq-parameters | bigquery-parameters | cas_noreq-parameters | clouddex-parameters | db2-parameters | dnfs-parameters | esp-parameters | fedsvr-parameters | gcs_noreq-parameters | hadoop-parameters | hana-parameters | impala-parameters | jdbc-parameters | mongodb-parameters | mysql-parameters | odbc-parameters | oracle-parameters | path-parameters | postgres-parameters | redshift-parameters | s3-parameters | sforce-parameters | snowflake-parameters | spark-parameters | spde-parameters | sqlserver-parameters | teradata-parameters | vertica-parameters | yellowbrick-parameters}

name="table-name"

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

}

id="string",

stage="string",

toid="string",

type="string",

varname="string"

initialBeliefs={

data={

caslib="string"

computedOnDemand=TRUE | FALSE

computedVars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

computedVarsProgram="string"

dataSourceOptions={key-1=any-list-or-data-type-1 <, key-2=any-list-or-data-type-2, ...>}

groupBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

groupByMode="NOSORT" | "REDISTRIBUTE"

name="table-name"

onDemand=TRUE | FALSE

orderBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

singlePass=TRUE | FALSE

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

whereTable={

casLib="string"

name="table-name"

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

}

intervalvar="string",

mean="string",

nominalvar="string",

sdev="string",

varlevel="string"

linearApproximationType="EXTENDED" | "UNSCENTED",

links={

child="string",

data={

caslib="string"

computedOnDemand=TRUE | FALSE

computedVars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

computedVarsProgram="string"

dataSourceOptions={key-1=any-list-or-data-type-1 <, key-2=any-list-or-data-type-2, ...>}

groupBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

groupByMode="NOSORT" | "REDISTRIBUTE"

name="table-name"

onDemand=TRUE | FALSE

orderBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

singlePass=TRUE | FALSE

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

whereTable={

casLib="string"

name="table-name"

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

}

parent="string",

stage="string"

odeApproximationType="ALL" | "GRADIENT" | "NONE",

output={

data={

caslib="string"

compress=TRUE | FALSE

indexVars={"variable-name-1" <, "variable-name-2", ...>}

label="string"

lifetime=64-bit-integer

maxMemSize=64-bit-integer

memoryFormat="DVR" | "INHERIT" | "STANDARD"

name="table-name"

onDemand=TRUE | FALSE

promote=TRUE | FALSE

replace=TRUE | FALSE

replication=integer

threadBlockSize=64-bit-integer

timeStamp="string"

where={"string-1" <, "string-2", ...>}

}

outputCliques={

data={

caslib="string"

compress=TRUE | FALSE

indexVars={"variable-name-1" <, "variable-name-2", ...>}

label="string"

lifetime=64-bit-integer

maxMemSize=64-bit-integer

memoryFormat="DVR" | "INHERIT" | "STANDARD"

name="table-name"

onDemand=TRUE | FALSE

promote=TRUE | FALSE

replace=TRUE | FALSE

replication=integer

threadBlockSize=64-bit-integer

timeStamp="string"

where={"string-1" <, "string-2", ...>}

id="string",

stage="string",

toid="string",

type="string",

varname="string"

outputDetails={

data={

caslib="string"

compress=TRUE | FALSE

indexVars={"variable-name-1" <, "variable-name-2", ...>}

label="string"

lifetime=64-bit-integer

maxMemSize=64-bit-integer

memoryFormat="DVR" | "INHERIT" | "STANDARD"

name="table-name"

onDemand=TRUE | FALSE

promote=TRUE | FALSE

replace=TRUE | FALSE

replication=integer

threadBlockSize=64-bit-integer

timeStamp="string"

where={"string-1" <, "string-2", ...>}

intervalvar="string",

mean="string",

nominalvar="string",

sdev="string",

varlevel="string"

syncThreshold=double,

table={

data={

caslib="string"

computedOnDemand=TRUE | FALSE

computedVars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

computedVarsProgram="string"

dataSourceOptions={key-1=any-list-or-data-type-1 <, key-2=any-list-or-data-type-2, ...>}

groupBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

groupByMode="NOSORT" | "REDISTRIBUTE"

name="table-name"

onDemand=TRUE | FALSE

orderBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

singlePass=TRUE | FALSE

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

whereTable={

casLib="string"

name="table-name"

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

}

variableLevels={

data={

caslib="string"

computedOnDemand=TRUE | FALSE

computedVars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

computedVarsProgram="string"

dataSourceOptions={key-1=any-list-or-data-type-1 <, key-2=any-list-or-data-type-2, ...>}

groupBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

groupByMode="NOSORT" | "REDISTRIBUTE"

name="table-name"

onDemand=TRUE | FALSE

orderBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

singlePass=TRUE | FALSE

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

whereTable={

casLib="string"

name="table-name"

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

}

varlevel="string",

varname="string"

variableOdes={

data={

caslib="string"

computedOnDemand=TRUE | FALSE

computedVars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

computedVarsProgram="string"

dataSourceOptions={key-1=any-list-or-data-type-1 <, key-2=any-list-or-data-type-2, ...>}

groupBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

groupByMode="NOSORT" | "REDISTRIBUTE"

name="table-name"

onDemand=TRUE | FALSE

orderBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

singlePass=TRUE | FALSE

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

whereTable={

casLib="string"

name="table-name"

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

}

system="string",

varname="string"

variableRoles={

data={

caslib="string"

computedOnDemand=TRUE | FALSE

computedVars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

computedVarsProgram="string"

dataSourceOptions={key-1=any-list-or-data-type-1 <, key-2=any-list-or-data-type-2, ...>}

groupBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

groupByMode="NOSORT" | "REDISTRIBUTE"

name="table-name"

onDemand=TRUE | FALSE

orderBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

singlePass=TRUE | FALSE

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

whereTable={

casLib="string"

name="table-name"

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

}

varname="string",

varrole="string"

variableSyncParms={

data={

caslib="string"

computedOnDemand=TRUE | FALSE

computedVars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

computedVarsProgram="string"

dataSourceOptions={key-1=any-list-or-data-type-1 <, key-2=any-list-or-data-type-2, ...>}

groupBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

groupByMode="NOSORT" | "REDISTRIBUTE"

name="table-name"

onDemand=TRUE | FALSE

orderBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

singlePass=TRUE | FALSE

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

whereTable={

casLib="string"

name="table-name"

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

}

intervalvar="string",

mean="string",

nominalvar="string",

sdev="string",

varlevel="string"

}

;

Summary: Input and Output Tables

If a row includes a subparameter, you can specify the name, caslib, and so on in the subparameter. Otherwise, you can specify the name, caslib, and so on in the parameter.

Parameters for Reading Input Tables
Parameter	Subparameter	Description
cliques	data	specifies the table of the factors and the cliques that form the clique tree obtained by processing the Bayesian network of variables. A clique tree permits an exact two-pass belief propagation over the tree. If cliques are not supplied using this table, then the network is processed to form cliques, and output cliques are saved in this table for use in subsequent runs of the filter.
initialBeliefs	required parameterdata	specifies the table of incoming beliefs in hidden variables from the previous run of the filter.
links	required parameterdata	specifies the table of parent-child relationships among variables in a two-time-period network.
table	required parameterdata	specifies the input table that contains observations by time.
variableLevels	data	specifies the table of valid levels of nominal variables.
variableOdes	data	specifies the table of variables by systems of ordinary differential equations (ODEs). Each system has a unique group number.
variableRoles	required parameterdata	specifies the table of variables and their properties: TIMEID, CONTROL, HIDDEN, or OBSERVED.
variableSyncParms	data	specifies the table of parameters that are used in synchronizing beliefs of hidden interval variables for different values of hidden nominal variables.

Parameters for Creating Output Tables
Parameter	Subparameter	Description
output	data	specifies the table that contains the outgoing beliefs of hidden variables. Beliefs of interval variables differ by levels of nominal variables. This table provides the interval variable beliefs for the most probable levels of the nominal variables.
outputCliques	data	specifies the table that contains the cliques in the clique tree obtained by processing the Bayesian network.
outputDetails	data	specifies the table that contains the outgoing beliefs of hidden variables specific to the branches (values) of hidden nominal variables. Thus, this table provides beliefs of interval variables over less probable values of nominal variables as well.

Parameter Descriptions

cliques={_cliques}

specifies the table of the factors and the cliques that form the clique tree obtained by processing the Bayesian network of variables. A clique tree permits an exact two-pass belief propagation over the tree. If cliques are not supplied using this table, then the network is processed to form cliques, and output cliques are saved in this table for use in subsequent runs of the filter.

The _cliques value can be one or more of the following:

data={castable}

specifies the name of the cliques data table.

For more information about specifying the data parameter, see the common castable parameter (Appendix A: Common Parameters).

id="string"

specifies the name of the ID column in the cliques data table, where the ID corresponds to a clique ID or the ID of a factor in the clique. The model of the clique is obtained from the models of the factors that form a clique.

Default	"id"

stage="string"

specifies the name of the stage column in the cliques data table, where the value of the stage parameter is 1 for a variable in the current time period and 2 for a variable in the previous time period.

Default	"stage"

toid="string"

specifies the name of the column that contains the ID of the clique that receives the message.

Default	"toid"

type="string"

specifies the name of the type column in the cliques data table, where the type parameter determines whether the ID parameter value corresponds to a clique or a factor.

Default	"type"

varname="string"

specifies the name of the variable column in the cliques data table, which is specified when the ID parameter value corresponds to a belief factor for a variable.

Default	"varname"

initialBeliefs={_initbeliefs}

specifies the table of incoming beliefs in hidden variables from the previous run of the filter.

Alias	initBeliefs

The _initbeliefs value can be one or more of the following:

* data={castable}

specifies the name of the initial beliefs data table.

For more information about specifying the data parameter, see the common castable parameter (Appendix A: Common Parameters).

intervalvar="string"

specifies the name of the interval variable column in the initial beliefs data table.

Default	"intervalvar"

mean="string"

specifies the name of the mean column of the interval variable or the probability of the nominal variable in the initial beliefs data table.

Default	"mean"

nominalvar="string"

specifies the name of the nominal variable column in the initial beliefs data table. The belief in the interval variable varies by levels of the nominal variables.

Default	"nominalvar"

sdev="string"

specifies the name of the standard deviation column of the interval variable in the initial beliefs data table.

Default	"sdev"

varlevel="string"

specifies the name of the level column of the nominal variable in the initial beliefs data table.

Default	"varlevel"

linearApproximationType="EXTENDED" | "UNSCENTED"

specifies the technique that is used to generate a linear approximation of the nonlinear relationships.

Alias	linApprox
Default	EXTENDED

EXTENDED

uses the extended method of linear approximation.

UNSCENTED

uses the unscented method of linear approximation.

links={_links}

specifies the table of parent-child relationships among variables in a two-time-period network.

The _links value can be one or more of the following:

child="string"

specifies the name of the child variable column in the links data table.

Default	"child"

* data={castable}

specifies the name of the links data table.

For more information about specifying the data parameter, see the common castable parameter (Appendix A: Common Parameters).

parent="string"

specifies the name of the parent variable column in the links data table.

Default	"parent"

stage="string"

specifies the name of the stage column in the links data table, where the value of the stage parameter is 1 for the current time period or 2 for the previous time period.

Default	"stage"

odeApproximationType="ALL" | "GRADIENT" | "NONE"

specifies which type of ordinary differential equation (ODE) approximation to use.

Alias	odeApprox
Default	GRADIENT

ALL

approximately solves the ODEs that are used in the mean and gradient calculations used in linearization.

GRADIENT

approximately solves the ODEs that are used in the gradient calculations used in linearization.

NONE

does not use any approximation to solve the ODEs that are used in the mean and gradient calculations used in linearization.

output={_output}

specifies the table that contains the outgoing beliefs of hidden variables. Beliefs of interval variables differ by levels of nominal variables. This table provides the interval variable beliefs for the most probable levels of the nominal variables.

Alias	out

data={casouttable}

specifies the name of the output data table.

For more information about specifying the data parameter, see the common casouttable parameter (Appendix A: Common Parameters).

outputCliques={_outcliques}

specifies the table that contains the cliques in the clique tree obtained by processing the Bayesian network.

Alias	outcliques

The _outcliques value can be one or more of the following:

data={casouttable}

specifies the name of the cliques data table.

For more information about specifying the data parameter, see the common casouttable parameter (Appendix A: Common Parameters).

id="string"

Default	"id"

stage="string"

Default	"stage"

toid="string"

specifies the name of the column that contains the ID of the clique that receives the message.

Default	"toid"

type="string"

specifies the name of the type column in the cliques data table, where the type parameter determines whether the ID parameter value corresponds to a clique or a factor.

Default	"type"

varname="string"

specifies the name of the variable column in the cliques data table, which is specified when the ID parameter value corresponds to a belief factor for a variable.

Default	"varname"

outputDetails={_outdetails}

specifies the table that contains the outgoing beliefs of hidden variables specific to the branches (values) of hidden nominal variables. Thus, this table provides beliefs of interval variables over less probable values of nominal variables as well.

Alias	outdetails

The _outdetails value can be one or more of the following:

data={casouttable}

specifies the name of the output details data table.

For more information about specifying the data parameter, see the common casouttable parameter (Appendix A: Common Parameters).

intervalvar="string"

specifies the name of the interval variable column in the output details data table.

Default	"intervalvar"

mean="string"

specifies the name of the mean column of the beliefs for the interval variable on this branch in the output details data table.

Default	"mean"

nominalvar="string"

specifies the name of the nominal variable column in the output details data table.

Default	"nominalvar"

sdev="string"

specifies the name of the standard deviation column of the beliefs for the interval variable on this branch in the output details data table.

Default	"sdev"

varlevel="string"

specifies the name of the variable level column in the output details data table.

Default	"varlevel"

syncThreshold=double

specifies the synchronization threshold. Probabilities over the levels of a nominal variable define a point in the probability space at each time. Euclidean distance (L2-norm) between two points that specify probabilities at the beginning and end of a time period is calculated and compared to the synchronization threshold. If the distance exceeds this threshold, then the beliefs in interval variables at all levels of the nominal variable are synchronized over the branches that correspond to the values of nominal variables.

Alias	threshold
Default	0.005
Range	0.001–1

table={_data}

specifies the input table that contains observations by time.

* data={castable}

specifies the name of the data table that contains observations.

For more information about specifying the data parameter, see the common castable parameter (Appendix A: Common Parameters).

variableLevels={_varlevels}

specifies the table of valid levels of nominal variables.

Alias	varLevels

The _varlevels value can be one or more of the following:

data={castable}

specifies the name of the levels data table.

For more information about specifying the data parameter, see the common castable parameter (Appendix A: Common Parameters).

varlevel="string"

specifies the name of the level column in the levels data table.

Default	"varlevel"

varname="string"

specifies the name of the variable column in the levels data table.

Default	"varname"

variableOdes={_varodes}

specifies the table of variables by systems of ordinary differential equations (ODEs). Each system has a unique group number.

Alias	varOdes

The _varodes value can be one or more of the following:

data={castable}

specifies the name of the data table of variables in ODE systems.

For more information about specifying the data parameter, see the common castable parameter (Appendix A: Common Parameters).

system="string"

specifies the name of the ODE system column of variables in the ODE systems data table.

Default	"system"

varname="string"

specifies the name of the variable column in the ODE systems data table.

Default	"varname"

variableRoles={_variables}

specifies the table of variables and their properties: TIMEID, CONTROL, HIDDEN, or OBSERVED.

Alias	varRoles

The _variables value can be one or more of the following:

* data={castable}

specifies the name of the variables data table.

For more information about specifying the data parameter, see the common castable parameter (Appendix A: Common Parameters).

varname="string"

specifies the name of the variable column in the variables data table.

Default	"varname"

varrole="string"

specifies the name of the role column in the variables data table.

Default	"varrole"

variableSyncParms={_varsyncs}

specifies the table of parameters that are used in synchronizing beliefs of hidden interval variables for different values of hidden nominal variables.

Alias	varSyncs

The _varsyncs value can be one or more of the following:

data={castable}

specifies the name of the variable synchronization data table.

For more information about specifying the data parameter, see the common castable parameter (Appendix A: Common Parameters).

intervalvar="string"

specifies the name of the interval variable column in the variable synchronization data table.

Default	"intervalvar"

mean="string"

specifies the name of the mean column for synchronization of the interval variable or the probability of the nominal variable in the variable synchronization data table.

Default	"mean"

nominalvar="string"

specifies the name of the nominal variable column in the variable synchronization data table. The synchronization value of the interval variable can vary by levels of the nominal variables.

Default	"nominalvar"

sdev="string"

specifies the name of the standard deviation column for synchronization of the interval variable in the variable synchronization data table.

Default	"sdev"

varlevel="string"

specifies the name of the level column of the nominal variable in the variable synchronization data table.

Default	"varlevel"

dynBnet Action

Dynamic Bayesian Network Action.

Lua Syntax

results, info = s:dynamicBayesianNetwork_dynBnet{

cliques={

data={

caslib="string"

computedOnDemand=true | false

computedVars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

computedVarsProgram="string"

dataSourceOptions={key-1=any-list-or-data-type-1 <, key-2=any-list-or-data-type-2, ...>}

groupBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

groupByMode="NOSORT" | "REDISTRIBUTE"

name="table-name"

onDemand=true | false

orderBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

singlePass=true | false

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

whereTable={

casLib="string"

name="table-name"

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

}

id="string",

stage="string",

toid="string",

type="string",

varname="string"

initialBeliefs={

data={

caslib="string"

computedOnDemand=true | false

computedVars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

computedVarsProgram="string"

dataSourceOptions={key-1=any-list-or-data-type-1 <, key-2=any-list-or-data-type-2, ...>}

groupBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

groupByMode="NOSORT" | "REDISTRIBUTE"

name="table-name"

onDemand=true | false

orderBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

singlePass=true | false

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

whereTable={

casLib="string"

name="table-name"

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

}

intervalvar="string",

mean="string",

nominalvar="string",

sdev="string",

varlevel="string"

linearApproximationType="EXTENDED" | "UNSCENTED",

links={

child="string",

data={

caslib="string"

computedOnDemand=true | false

computedVars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

computedVarsProgram="string"

dataSourceOptions={key-1=any-list-or-data-type-1 <, key-2=any-list-or-data-type-2, ...>}

groupBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

groupByMode="NOSORT" | "REDISTRIBUTE"

name="table-name"

onDemand=true | false

orderBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

singlePass=true | false

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

whereTable={

casLib="string"

name="table-name"

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

}

parent="string",

stage="string"

odeApproximationType="ALL" | "GRADIENT" | "NONE",

output={

data={

caslib="string"

compress=true | false

indexVars={"variable-name-1" <, "variable-name-2", ...>}

label="string"

lifetime=64-bit-integer

maxMemSize=64-bit-integer

memoryFormat="DVR" | "INHERIT" | "STANDARD"

name="table-name"

onDemand=true | false

promote=true | false

replace=true | false

replication=integer

threadBlockSize=64-bit-integer

timeStamp="string"

where={"string-1" <, "string-2", ...>}

}

outputCliques={

data={

caslib="string"

compress=true | false

indexVars={"variable-name-1" <, "variable-name-2", ...>}

label="string"

lifetime=64-bit-integer

maxMemSize=64-bit-integer

memoryFormat="DVR" | "INHERIT" | "STANDARD"

name="table-name"

onDemand=true | false

promote=true | false

replace=true | false

replication=integer

threadBlockSize=64-bit-integer

timeStamp="string"

where={"string-1" <, "string-2", ...>}

id="string",

stage="string",

toid="string",

type="string",

varname="string"

outputDetails={

data={

caslib="string"

compress=true | false

indexVars={"variable-name-1" <, "variable-name-2", ...>}

label="string"

lifetime=64-bit-integer

maxMemSize=64-bit-integer

memoryFormat="DVR" | "INHERIT" | "STANDARD"

name="table-name"

onDemand=true | false

promote=true | false

replace=true | false

replication=integer

threadBlockSize=64-bit-integer

timeStamp="string"

where={"string-1" <, "string-2", ...>}

intervalvar="string",

mean="string",

nominalvar="string",

sdev="string",

varlevel="string"

syncThreshold=double,

table={

data={

caslib="string"

computedOnDemand=true | false

computedVars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

computedVarsProgram="string"

dataSourceOptions={key-1=any-list-or-data-type-1 <, key-2=any-list-or-data-type-2, ...>}

groupBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

groupByMode="NOSORT" | "REDISTRIBUTE"

name="table-name"

onDemand=true | false

orderBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

singlePass=true | false

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

whereTable={

casLib="string"

name="table-name"

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

}

variableLevels={

data={

caslib="string"

computedOnDemand=true | false

computedVars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

computedVarsProgram="string"

dataSourceOptions={key-1=any-list-or-data-type-1 <, key-2=any-list-or-data-type-2, ...>}

groupBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

groupByMode="NOSORT" | "REDISTRIBUTE"

name="table-name"

onDemand=true | false

orderBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

singlePass=true | false

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

whereTable={

casLib="string"

name="table-name"

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

}

varlevel="string",

varname="string"

variableOdes={

data={

caslib="string"

computedOnDemand=true | false

computedVars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

computedVarsProgram="string"

dataSourceOptions={key-1=any-list-or-data-type-1 <, key-2=any-list-or-data-type-2, ...>}

groupBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

groupByMode="NOSORT" | "REDISTRIBUTE"

name="table-name"

onDemand=true | false

orderBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

singlePass=true | false

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

whereTable={

casLib="string"

name="table-name"

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

}

system="string",

varname="string"

variableRoles={

data={

caslib="string"

computedOnDemand=true | false

computedVars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

computedVarsProgram="string"

dataSourceOptions={key-1=any-list-or-data-type-1 <, key-2=any-list-or-data-type-2, ...>}

groupBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

groupByMode="NOSORT" | "REDISTRIBUTE"

name="table-name"

onDemand=true | false

orderBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

singlePass=true | false

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

whereTable={

casLib="string"

name="table-name"

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

}

varname="string",

varrole="string"

variableSyncParms={

data={

caslib="string"

computedOnDemand=true | false

computedVars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

computedVarsProgram="string"

dataSourceOptions={key-1=any-list-or-data-type-1 <, key-2=any-list-or-data-type-2, ...>}

groupBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

groupByMode="NOSORT" | "REDISTRIBUTE"

name="table-name"

onDemand=true | false

orderBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

singlePass=true | false

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

whereTable={

casLib="string"

name="table-name"

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

}

intervalvar="string",

mean="string",

nominalvar="string",

sdev="string",

varlevel="string"

}

Summary: Input and Output Tables

If a row includes a subparameter, you can specify the name, caslib, and so on in the subparameter. Otherwise, you can specify the name, caslib, and so on in the parameter.

Parameters for Reading Input Tables
Parameter	Subparameter	Description
cliques	data	specifies the table of the factors and the cliques that form the clique tree obtained by processing the Bayesian network of variables. A clique tree permits an exact two-pass belief propagation over the tree. If cliques are not supplied using this table, then the network is processed to form cliques, and output cliques are saved in this table for use in subsequent runs of the filter.
initialBeliefs	required parameterdata	specifies the table of incoming beliefs in hidden variables from the previous run of the filter.
links	required parameterdata	specifies the table of parent-child relationships among variables in a two-time-period network.
table	required parameterdata	specifies the input table that contains observations by time.
variableLevels	data	specifies the table of valid levels of nominal variables.
variableOdes	data	specifies the table of variables by systems of ordinary differential equations (ODEs). Each system has a unique group number.
variableRoles	required parameterdata	specifies the table of variables and their properties: TIMEID, CONTROL, HIDDEN, or OBSERVED.
variableSyncParms	data	specifies the table of parameters that are used in synchronizing beliefs of hidden interval variables for different values of hidden nominal variables.

Parameters for Creating Output Tables
Parameter	Subparameter	Description
output	data	specifies the table that contains the outgoing beliefs of hidden variables. Beliefs of interval variables differ by levels of nominal variables. This table provides the interval variable beliefs for the most probable levels of the nominal variables.
outputCliques	data	specifies the table that contains the cliques in the clique tree obtained by processing the Bayesian network.
outputDetails	data	specifies the table that contains the outgoing beliefs of hidden variables specific to the branches (values) of hidden nominal variables. Thus, this table provides beliefs of interval variables over less probable values of nominal variables as well.

Parameter Descriptions

cliques={_cliques}

The _cliques value can be one or more of the following:

data={castable}

specifies the name of the cliques data table.

For more information about specifying the data parameter, see the common castable parameter (Appendix A: Common Parameters).

id="string"

Default	"id"

stage="string"

Default	"stage"

toid="string"

specifies the name of the column that contains the ID of the clique that receives the message.

Default	"toid"

type="string"

specifies the name of the type column in the cliques data table, where the type parameter determines whether the ID parameter value corresponds to a clique or a factor.

Default	"type"

varname="string"

specifies the name of the variable column in the cliques data table, which is specified when the ID parameter value corresponds to a belief factor for a variable.

Default	"varname"

initialBeliefs={_initbeliefs}

specifies the table of incoming beliefs in hidden variables from the previous run of the filter.

Alias	initBeliefs

The _initbeliefs value can be one or more of the following:

* data={castable}

specifies the name of the initial beliefs data table.

For more information about specifying the data parameter, see the common castable parameter (Appendix A: Common Parameters).

intervalvar="string"

specifies the name of the interval variable column in the initial beliefs data table.

Default	"intervalvar"

mean="string"

specifies the name of the mean column of the interval variable or the probability of the nominal variable in the initial beliefs data table.

Default	"mean"

nominalvar="string"

specifies the name of the nominal variable column in the initial beliefs data table. The belief in the interval variable varies by levels of the nominal variables.

Default	"nominalvar"

sdev="string"

specifies the name of the standard deviation column of the interval variable in the initial beliefs data table.

Default	"sdev"

varlevel="string"

specifies the name of the level column of the nominal variable in the initial beliefs data table.

Default	"varlevel"

linearApproximationType="EXTENDED" | "UNSCENTED"

specifies the technique that is used to generate a linear approximation of the nonlinear relationships.

Alias	linApprox
Default	EXTENDED

EXTENDED

uses the extended method of linear approximation.

UNSCENTED

uses the unscented method of linear approximation.

links={_links}

specifies the table of parent-child relationships among variables in a two-time-period network.

The _links value can be one or more of the following:

child="string"

specifies the name of the child variable column in the links data table.

Default	"child"

* data={castable}

specifies the name of the links data table.

For more information about specifying the data parameter, see the common castable parameter (Appendix A: Common Parameters).

parent="string"

specifies the name of the parent variable column in the links data table.

Default	"parent"

stage="string"

specifies the name of the stage column in the links data table, where the value of the stage parameter is 1 for the current time period or 2 for the previous time period.

Default	"stage"

odeApproximationType="ALL" | "GRADIENT" | "NONE"

specifies which type of ordinary differential equation (ODE) approximation to use.

Alias	odeApprox
Default	GRADIENT

ALL

approximately solves the ODEs that are used in the mean and gradient calculations used in linearization.

GRADIENT

approximately solves the ODEs that are used in the gradient calculations used in linearization.

NONE

does not use any approximation to solve the ODEs that are used in the mean and gradient calculations used in linearization.

output={_output}

Alias	out

data={casouttable}

specifies the name of the output data table.

For more information about specifying the data parameter, see the common casouttable parameter (Appendix A: Common Parameters).

outputCliques={_outcliques}

specifies the table that contains the cliques in the clique tree obtained by processing the Bayesian network.

Alias	outcliques

The _outcliques value can be one or more of the following:

data={casouttable}

specifies the name of the cliques data table.

For more information about specifying the data parameter, see the common casouttable parameter (Appendix A: Common Parameters).

id="string"

Default	"id"

stage="string"

Default	"stage"

toid="string"

specifies the name of the column that contains the ID of the clique that receives the message.

Default	"toid"

type="string"

specifies the name of the type column in the cliques data table, where the type parameter determines whether the ID parameter value corresponds to a clique or a factor.

Default	"type"

varname="string"

specifies the name of the variable column in the cliques data table, which is specified when the ID parameter value corresponds to a belief factor for a variable.

Default	"varname"

outputDetails={_outdetails}

Alias	outdetails

The _outdetails value can be one or more of the following:

data={casouttable}

specifies the name of the output details data table.

For more information about specifying the data parameter, see the common casouttable parameter (Appendix A: Common Parameters).

intervalvar="string"

specifies the name of the interval variable column in the output details data table.

Default	"intervalvar"

mean="string"

specifies the name of the mean column of the beliefs for the interval variable on this branch in the output details data table.

Default	"mean"

nominalvar="string"

specifies the name of the nominal variable column in the output details data table.

Default	"nominalvar"

sdev="string"

specifies the name of the standard deviation column of the beliefs for the interval variable on this branch in the output details data table.

Default	"sdev"

varlevel="string"

specifies the name of the variable level column in the output details data table.

Default	"varlevel"

syncThreshold=double

Alias	threshold
Default	0.005
Range	0.001–1

table={_data}

specifies the input table that contains observations by time.

* data={castable}

specifies the name of the data table that contains observations.

For more information about specifying the data parameter, see the common castable parameter (Appendix A: Common Parameters).

variableLevels={_varlevels}

specifies the table of valid levels of nominal variables.

Alias	varLevels

The _varlevels value can be one or more of the following:

data={castable}

specifies the name of the levels data table.

For more information about specifying the data parameter, see the common castable parameter (Appendix A: Common Parameters).

varlevel="string"

specifies the name of the level column in the levels data table.

Default	"varlevel"

varname="string"

specifies the name of the variable column in the levels data table.

Default	"varname"

variableOdes={_varodes}

specifies the table of variables by systems of ordinary differential equations (ODEs). Each system has a unique group number.

Alias	varOdes

The _varodes value can be one or more of the following:

data={castable}

specifies the name of the data table of variables in ODE systems.

For more information about specifying the data parameter, see the common castable parameter (Appendix A: Common Parameters).

system="string"

specifies the name of the ODE system column of variables in the ODE systems data table.

Default	"system"

varname="string"

specifies the name of the variable column in the ODE systems data table.

Default	"varname"

variableRoles={_variables}

specifies the table of variables and their properties: TIMEID, CONTROL, HIDDEN, or OBSERVED.

Alias	varRoles

The _variables value can be one or more of the following:

* data={castable}

specifies the name of the variables data table.

For more information about specifying the data parameter, see the common castable parameter (Appendix A: Common Parameters).

varname="string"

specifies the name of the variable column in the variables data table.

Default	"varname"

varrole="string"

specifies the name of the role column in the variables data table.

Default	"varrole"

variableSyncParms={_varsyncs}

specifies the table of parameters that are used in synchronizing beliefs of hidden interval variables for different values of hidden nominal variables.

Alias	varSyncs

The _varsyncs value can be one or more of the following:

data={castable}

specifies the name of the variable synchronization data table.

For more information about specifying the data parameter, see the common castable parameter (Appendix A: Common Parameters).

intervalvar="string"

specifies the name of the interval variable column in the variable synchronization data table.

Default	"intervalvar"

mean="string"

specifies the name of the mean column for synchronization of the interval variable or the probability of the nominal variable in the variable synchronization data table.

Default	"mean"

nominalvar="string"

specifies the name of the nominal variable column in the variable synchronization data table. The synchronization value of the interval variable can vary by levels of the nominal variables.

Default	"nominalvar"

sdev="string"

specifies the name of the standard deviation column for synchronization of the interval variable in the variable synchronization data table.

Default	"sdev"

varlevel="string"

specifies the name of the level column of the nominal variable in the variable synchronization data table.

Default	"varlevel"

dynBnet Action

Dynamic Bayesian Network Action.

Python Syntax

results= s.dynamicBayesianNetwork.dynBnet(

cliques={

"data":{

"caslib":"string"

"computedOnDemand"=True | False

"computedVars"=[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"computedVarsProgram"="string"

"dataSourceOptions":{"key-1":{any-list-or-data-type-1} <, "key-2":{any-list-or-data-type-2}, ...>}

"groupBy"=[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"groupByMode"="NOSORT" | "REDISTRIBUTE"

"importOptions":{"fileType":"ANY" | "AUDIO" | "AUTO" | "BASESAS" | "CSV" | "DELIMITED" | "DOCUMENT" | "DTA" | "ESP" | "EXCEL" | "FMT" | "HDAT" | "IMAGE" | "JMP" | "LASR" | "PARQUET" | "SOUND" | "SPSS" | "VIDEO" | "XLS", fileType-specific-parameters}

"name":"table-name"

"onDemand":True | False

"orderBy":[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"singlePass":True | False

"vars":[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"where":"where-expression"

"whereTable":{

"casLib":"string"

"dataSourceOptions":{adls_noreq-parameters | bigquery-parameters | cas_noreq-parameters | clouddex-parameters | db2-parameters | dnfs-parameters | esp-parameters | fedsvr-parameters | gcs_noreq-parameters | hadoop-parameters | hana-parameters | impala-parameters | jdbc-parameters | mongodb-parameters | mysql-parameters | odbc-parameters | oracle-parameters | path-parameters | postgres-parameters | redshift-parameters | s3-parameters | sforce-parameters | snowflake-parameters | spark-parameters | spde-parameters | sqlserver-parameters | teradata-parameters | vertica-parameters | yellowbrick-parameters}

"name":"table-name"

"vars":[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"where":"where-expression"

}

"id":"string",

"stage":"string",

"toid":"string",

"type":"string",

"varname":"string"

initialBeliefs={

"data":{

"caslib":"string"

"computedOnDemand"=True | False

"computedVars"=[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"computedVarsProgram"="string"

"dataSourceOptions":{"key-1":{any-list-or-data-type-1} <, "key-2":{any-list-or-data-type-2}, ...>}

"groupBy"=[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"groupByMode"="NOSORT" | "REDISTRIBUTE"

"name":"table-name"

"onDemand":True | False

"orderBy":[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"singlePass":True | False

"vars":[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"where":"where-expression"

"whereTable":{

"casLib":"string"

"name":"table-name"

"vars":[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"where":"where-expression"

}

"intervalvar":"string",

"mean":"string",

"nominalvar":"string",

"sdev":"string",

"varlevel":"string"

linearApproximationType="EXTENDED" | "UNSCENTED",

links={

"child":"string",

"data":{

"caslib":"string"

"computedOnDemand"=True | False

"computedVars"=[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"computedVarsProgram"="string"

"dataSourceOptions":{"key-1":{any-list-or-data-type-1} <, "key-2":{any-list-or-data-type-2}, ...>}

"groupBy"=[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"groupByMode"="NOSORT" | "REDISTRIBUTE"

"name":"table-name"

"onDemand":True | False

"orderBy":[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"singlePass":True | False

"vars":[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"where":"where-expression"

"whereTable":{

"casLib":"string"

"name":"table-name"

"vars":[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"where":"where-expression"

}

"parent":"string",

"stage":"string"

odeApproximationType="ALL" | "GRADIENT" | "NONE",

output={

"data":{

"caslib":"string"

"compress":True | False

"indexVars":["variable-name-1" <, "variable-name-2", ...>]

"label":"string"

"lifetime":64-bit-integer

"maxMemSize":64-bit-integer

"memoryFormat":"DVR" | "INHERIT" | "STANDARD"

"name":"table-name"

"onDemand":True | False

"promote":True | False

"replace":True | False

"replication":integer

"threadBlockSize":64-bit-integer

"timeStamp":"string"

"where":["string-1" <, "string-2", ...>]

}

outputCliques={

"data":{

"caslib":"string"

"compress":True | False

"indexVars":["variable-name-1" <, "variable-name-2", ...>]

"label":"string"

"lifetime":64-bit-integer

"maxMemSize":64-bit-integer

"memoryFormat":"DVR" | "INHERIT" | "STANDARD"

"name":"table-name"

"onDemand":True | False

"promote":True | False

"replace":True | False

"replication":integer

"threadBlockSize":64-bit-integer

"timeStamp":"string"

"where":["string-1" <, "string-2", ...>]

"id":"string",

"stage":"string",

"toid":"string",

"type":"string",

"varname":"string"

outputDetails={

"data":{

"caslib":"string"

"compress":True | False

"indexVars":["variable-name-1" <, "variable-name-2", ...>]

"label":"string"

"lifetime":64-bit-integer

"maxMemSize":64-bit-integer

"memoryFormat":"DVR" | "INHERIT" | "STANDARD"

"name":"table-name"

"onDemand":True | False

"promote":True | False

"replace":True | False

"replication":integer

"threadBlockSize":64-bit-integer

"timeStamp":"string"

"where":["string-1" <, "string-2", ...>]

"intervalvar":"string",

"mean":"string",

"nominalvar":"string",

"sdev":"string",

"varlevel":"string"

syncThreshold=double,

table={

"data":{

"caslib":"string"

"computedOnDemand"=True | False

"computedVars"=[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"computedVarsProgram"="string"

"dataSourceOptions":{"key-1":{any-list-or-data-type-1} <, "key-2":{any-list-or-data-type-2}, ...>}

"groupBy"=[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"groupByMode"="NOSORT" | "REDISTRIBUTE"

"name":"table-name"

"onDemand":True | False

"orderBy":[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"singlePass":True | False

"vars":[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"where":"where-expression"

"whereTable":{

"casLib":"string"

"name":"table-name"

"vars":[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"where":"where-expression"

}

variableLevels={

"data":{

"caslib":"string"

"computedOnDemand"=True | False

"computedVars"=[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"computedVarsProgram"="string"

"dataSourceOptions":{"key-1":{any-list-or-data-type-1} <, "key-2":{any-list-or-data-type-2}, ...>}

"groupBy"=[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"groupByMode"="NOSORT" | "REDISTRIBUTE"

"name":"table-name"

"onDemand":True | False

"orderBy":[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"singlePass":True | False

"vars":[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"where":"where-expression"

"whereTable":{

"casLib":"string"

"name":"table-name"

"vars":[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"where":"where-expression"

}

"varlevel":"string",

"varname":"string"

variableOdes={

"data":{

"caslib":"string"

"computedOnDemand"=True | False

"computedVars"=[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"computedVarsProgram"="string"

"dataSourceOptions":{"key-1":{any-list-or-data-type-1} <, "key-2":{any-list-or-data-type-2}, ...>}

"groupBy"=[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"groupByMode"="NOSORT" | "REDISTRIBUTE"

"name":"table-name"

"onDemand":True | False

"orderBy":[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"singlePass":True | False

"vars":[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"where":"where-expression"

"whereTable":{

"casLib":"string"

"name":"table-name"

"vars":[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"where":"where-expression"

}

"system":"string",

"varname":"string"

variableRoles={

"data":{

"caslib":"string"

"computedOnDemand"=True | False

"computedVars"=[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"computedVarsProgram"="string"

"dataSourceOptions":{"key-1":{any-list-or-data-type-1} <, "key-2":{any-list-or-data-type-2}, ...>}

"groupBy"=[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"groupByMode"="NOSORT" | "REDISTRIBUTE"

"name":"table-name"

"onDemand":True | False

"orderBy":[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"singlePass":True | False

"vars":[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"where":"where-expression"

"whereTable":{

"casLib":"string"

"name":"table-name"

"vars":[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"where":"where-expression"

}

"varname":"string",

"varrole":"string"

variableSyncParms={

"data":{

"caslib":"string"

"computedOnDemand"=True | False

"computedVars"=[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"computedVarsProgram"="string"

"dataSourceOptions":{"key-1":{any-list-or-data-type-1} <, "key-2":{any-list-or-data-type-2}, ...>}

"groupBy"=[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"groupByMode"="NOSORT" | "REDISTRIBUTE"

"name":"table-name"

"onDemand":True | False

"orderBy":[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"singlePass":True | False

"vars":[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"where":"where-expression"

"whereTable":{

"casLib":"string"

"name":"table-name"

"vars":[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"where":"where-expression"

}

"intervalvar":"string",

"mean":"string",

"nominalvar":"string",

"sdev":"string",

"varlevel":"string"

}

)

Summary: Input and Output Tables

If a row includes a subparameter, you can specify the name, caslib, and so on in the subparameter. Otherwise, you can specify the name, caslib, and so on in the parameter.

Parameters for Reading Input Tables
Parameter	Subparameter	Description
cliques	data	specifies the table of the factors and the cliques that form the clique tree obtained by processing the Bayesian network of variables. A clique tree permits an exact two-pass belief propagation over the tree. If cliques are not supplied using this table, then the network is processed to form cliques, and output cliques are saved in this table for use in subsequent runs of the filter.
initialBeliefs	required parameterdata	specifies the table of incoming beliefs in hidden variables from the previous run of the filter.
links	required parameterdata	specifies the table of parent-child relationships among variables in a two-time-period network.
table	required parameterdata	specifies the input table that contains observations by time.
variableLevels	data	specifies the table of valid levels of nominal variables.
variableOdes	data	specifies the table of variables by systems of ordinary differential equations (ODEs). Each system has a unique group number.
variableRoles	required parameterdata	specifies the table of variables and their properties: TIMEID, CONTROL, HIDDEN, or OBSERVED.
variableSyncParms	data	specifies the table of parameters that are used in synchronizing beliefs of hidden interval variables for different values of hidden nominal variables.

Parameters for Creating Output Tables
Parameter	Subparameter	Description
output	data	specifies the table that contains the outgoing beliefs of hidden variables. Beliefs of interval variables differ by levels of nominal variables. This table provides the interval variable beliefs for the most probable levels of the nominal variables.
outputCliques	data	specifies the table that contains the cliques in the clique tree obtained by processing the Bayesian network.
outputDetails	data	specifies the table that contains the outgoing beliefs of hidden variables specific to the branches (values) of hidden nominal variables. Thus, this table provides beliefs of interval variables over less probable values of nominal variables as well.

Parameter Descriptions

cliques={_cliques}

The _cliques value can be one or more of the following:

"data":{castable}

specifies the name of the cliques data table.

For more information about specifying the data parameter, see the common castable parameter (Appendix A: Common Parameters).

"id":"string"

Default	"id"

"stage":"string"

Default	"stage"

"toid":"string"

specifies the name of the column that contains the ID of the clique that receives the message.

Default	"toid"

"type":"string"

specifies the name of the type column in the cliques data table, where the type parameter determines whether the ID parameter value corresponds to a clique or a factor.

Default	"type"

"varname":"string"

specifies the name of the variable column in the cliques data table, which is specified when the ID parameter value corresponds to a belief factor for a variable.

Default	"varname"

initialBeliefs={_initbeliefs}

specifies the table of incoming beliefs in hidden variables from the previous run of the filter.

Alias	initBeliefs

The _initbeliefs value can be one or more of the following:

* "data":{castable}

specifies the name of the initial beliefs data table.

For more information about specifying the data parameter, see the common castable parameter (Appendix A: Common Parameters).

"intervalvar":"string"

specifies the name of the interval variable column in the initial beliefs data table.

Default	"intervalvar"

"mean":"string"

specifies the name of the mean column of the interval variable or the probability of the nominal variable in the initial beliefs data table.

Default	"mean"

"nominalvar":"string"

specifies the name of the nominal variable column in the initial beliefs data table. The belief in the interval variable varies by levels of the nominal variables.

Default	"nominalvar"

"sdev":"string"

specifies the name of the standard deviation column of the interval variable in the initial beliefs data table.

Default	"sdev"

"varlevel":"string"

specifies the name of the level column of the nominal variable in the initial beliefs data table.

Default	"varlevel"

linearApproximationType="EXTENDED" | "UNSCENTED"

specifies the technique that is used to generate a linear approximation of the nonlinear relationships.

Alias	linApprox
Default	EXTENDED

EXTENDED

uses the extended method of linear approximation.

UNSCENTED

uses the unscented method of linear approximation.

links={_links}

specifies the table of parent-child relationships among variables in a two-time-period network.

The _links value can be one or more of the following:

"child":"string"

specifies the name of the child variable column in the links data table.

Default	"child"

* "data":{castable}

specifies the name of the links data table.

For more information about specifying the data parameter, see the common castable parameter (Appendix A: Common Parameters).

"parent":"string"

specifies the name of the parent variable column in the links data table.

Default	"parent"

"stage":"string"

specifies the name of the stage column in the links data table, where the value of the stage parameter is 1 for the current time period or 2 for the previous time period.

Default	"stage"

odeApproximationType="ALL" | "GRADIENT" | "NONE"

specifies which type of ordinary differential equation (ODE) approximation to use.

Alias	odeApprox
Default	GRADIENT

ALL

approximately solves the ODEs that are used in the mean and gradient calculations used in linearization.

GRADIENT

approximately solves the ODEs that are used in the gradient calculations used in linearization.

NONE

does not use any approximation to solve the ODEs that are used in the mean and gradient calculations used in linearization.

output={_output}

Alias	out

"data":{casouttable}

specifies the name of the output data table.

For more information about specifying the data parameter, see the common casouttable parameter (Appendix A: Common Parameters).

outputCliques={_outcliques}

specifies the table that contains the cliques in the clique tree obtained by processing the Bayesian network.

Alias	outcliques

The _outcliques value can be one or more of the following:

"data":{casouttable}

specifies the name of the cliques data table.

For more information about specifying the data parameter, see the common casouttable parameter (Appendix A: Common Parameters).

"id":"string"

Default	"id"

"stage":"string"

Default	"stage"

"toid":"string"

specifies the name of the column that contains the ID of the clique that receives the message.

Default	"toid"

"type":"string"

specifies the name of the type column in the cliques data table, where the type parameter determines whether the ID parameter value corresponds to a clique or a factor.

Default	"type"

"varname":"string"

specifies the name of the variable column in the cliques data table, which is specified when the ID parameter value corresponds to a belief factor for a variable.

Default	"varname"

outputDetails={_outdetails}

Alias	outdetails

The _outdetails value can be one or more of the following:

"data":{casouttable}

specifies the name of the output details data table.

For more information about specifying the data parameter, see the common casouttable parameter (Appendix A: Common Parameters).

"intervalvar":"string"

specifies the name of the interval variable column in the output details data table.

Default	"intervalvar"

"mean":"string"

specifies the name of the mean column of the beliefs for the interval variable on this branch in the output details data table.

Default	"mean"

"nominalvar":"string"

specifies the name of the nominal variable column in the output details data table.

Default	"nominalvar"

"sdev":"string"

specifies the name of the standard deviation column of the beliefs for the interval variable on this branch in the output details data table.

Default	"sdev"

"varlevel":"string"

specifies the name of the variable level column in the output details data table.

Default	"varlevel"

syncThreshold=double

Alias	threshold
Default	0.005
Range	0.001–1

table={_data}

specifies the input table that contains observations by time.

* "data":{castable}

specifies the name of the data table that contains observations.

For more information about specifying the data parameter, see the common castable parameter (Appendix A: Common Parameters).

variableLevels={_varlevels}

specifies the table of valid levels of nominal variables.

Alias	varLevels

The _varlevels value can be one or more of the following:

"data":{castable}

specifies the name of the levels data table.

For more information about specifying the data parameter, see the common castable parameter (Appendix A: Common Parameters).

"varlevel":"string"

specifies the name of the level column in the levels data table.

Default	"varlevel"

"varname":"string"

specifies the name of the variable column in the levels data table.

Default	"varname"

variableOdes={_varodes}

specifies the table of variables by systems of ordinary differential equations (ODEs). Each system has a unique group number.

Alias	varOdes

The _varodes value can be one or more of the following:

"data":{castable}

specifies the name of the data table of variables in ODE systems.

For more information about specifying the data parameter, see the common castable parameter (Appendix A: Common Parameters).

"system":"string"

specifies the name of the ODE system column of variables in the ODE systems data table.

Default	"system"

"varname":"string"

specifies the name of the variable column in the ODE systems data table.

Default	"varname"

variableRoles={_variables}

specifies the table of variables and their properties: TIMEID, CONTROL, HIDDEN, or OBSERVED.

Alias	varRoles

The _variables value can be one or more of the following:

* "data":{castable}

specifies the name of the variables data table.

For more information about specifying the data parameter, see the common castable parameter (Appendix A: Common Parameters).

"varname":"string"

specifies the name of the variable column in the variables data table.

Default	"varname"

"varrole":"string"

specifies the name of the role column in the variables data table.

Default	"varrole"

variableSyncParms={_varsyncs}

specifies the table of parameters that are used in synchronizing beliefs of hidden interval variables for different values of hidden nominal variables.

Alias	varSyncs

The _varsyncs value can be one or more of the following:

"data":{castable}

specifies the name of the variable synchronization data table.

For more information about specifying the data parameter, see the common castable parameter (Appendix A: Common Parameters).

"intervalvar":"string"

specifies the name of the interval variable column in the variable synchronization data table.

Default	"intervalvar"

"mean":"string"

specifies the name of the mean column for synchronization of the interval variable or the probability of the nominal variable in the variable synchronization data table.

Default	"mean"

"nominalvar":"string"

specifies the name of the nominal variable column in the variable synchronization data table. The synchronization value of the interval variable can vary by levels of the nominal variables.

Default	"nominalvar"

"sdev":"string"

specifies the name of the standard deviation column for synchronization of the interval variable in the variable synchronization data table.

Default	"sdev"

"varlevel":"string"

specifies the name of the level column of the nominal variable in the variable synchronization data table.

Default	"varlevel"

dynBnet Action

Dynamic Bayesian Network Action.

R Syntax

results <– cas.dynamicBayesianNetwork.dynBnet(s,

cliques=list(

data=list(

caslib="string"

computedOnDemand=TRUE | FALSE

computedVars=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

computedVarsProgram="string"

dataSourceOptions=list(key-1=list(any-list-or-data-type-1) <, key-2=list(any-list-or-data-type-2), ...>)

groupBy=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

groupByMode="NOSORT" | "REDISTRIBUTE"

name="table-name"

onDemand=TRUE | FALSE

orderBy=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

singlePass=TRUE | FALSE

vars=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

where="where-expression"

whereTable=list(

casLib="string"

name="table-name"

vars=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

where="where-expression"

)

id="string",

stage="string",

toid="string",

type="string",

varname="string"

initialBeliefs=list(

data=list(

caslib="string"

computedOnDemand=TRUE | FALSE

computedVars=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

computedVarsProgram="string"

dataSourceOptions=list(key-1=list(any-list-or-data-type-1) <, key-2=list(any-list-or-data-type-2), ...>)

groupBy=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

groupByMode="NOSORT" | "REDISTRIBUTE"

name="table-name"

onDemand=TRUE | FALSE

orderBy=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

singlePass=TRUE | FALSE

vars=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

where="where-expression"

whereTable=list(

casLib="string"

name="table-name"

vars=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

where="where-expression"

)

intervalvar="string",

mean="string",

nominalvar="string",

sdev="string",

varlevel="string"

linearApproximationType="EXTENDED" | "UNSCENTED",

links=list(

child="string",

data=list(

caslib="string"

computedOnDemand=TRUE | FALSE

computedVars=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

computedVarsProgram="string"

dataSourceOptions=list(key-1=list(any-list-or-data-type-1) <, key-2=list(any-list-or-data-type-2), ...>)

groupBy=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

groupByMode="NOSORT" | "REDISTRIBUTE"

name="table-name"

onDemand=TRUE | FALSE

orderBy=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

singlePass=TRUE | FALSE

vars=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

where="where-expression"

whereTable=list(

casLib="string"

name="table-name"

vars=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

where="where-expression"

)

parent="string",

stage="string"

odeApproximationType="ALL" | "GRADIENT" | "NONE",

output=list(

data=list(

caslib="string"

compress=TRUE | FALSE

indexVars=list("variable-name-1" <, "variable-name-2", ...>)

label="string"

lifetime=64-bit-integer

maxMemSize=64-bit-integer

memoryFormat="DVR" | "INHERIT" | "STANDARD"

name="table-name"

onDemand=TRUE | FALSE

promote=TRUE | FALSE

replace=TRUE | FALSE

replication=integer

threadBlockSize=64-bit-integer

timeStamp="string"

where=list("string-1" <, "string-2", ...>)

)

outputCliques=list(

data=list(

caslib="string"

compress=TRUE | FALSE

indexVars=list("variable-name-1" <, "variable-name-2", ...>)

label="string"

lifetime=64-bit-integer

maxMemSize=64-bit-integer

memoryFormat="DVR" | "INHERIT" | "STANDARD"

name="table-name"

onDemand=TRUE | FALSE

promote=TRUE | FALSE

replace=TRUE | FALSE

replication=integer

threadBlockSize=64-bit-integer

timeStamp="string"

where=list("string-1" <, "string-2", ...>)

id="string",

stage="string",

toid="string",

type="string",

varname="string"

outputDetails=list(

data=list(

caslib="string"

compress=TRUE | FALSE

indexVars=list("variable-name-1" <, "variable-name-2", ...>)

label="string"

lifetime=64-bit-integer

maxMemSize=64-bit-integer

memoryFormat="DVR" | "INHERIT" | "STANDARD"

name="table-name"

onDemand=TRUE | FALSE

promote=TRUE | FALSE

replace=TRUE | FALSE

replication=integer

threadBlockSize=64-bit-integer

timeStamp="string"

where=list("string-1" <, "string-2", ...>)

intervalvar="string",

mean="string",

nominalvar="string",

sdev="string",

varlevel="string"

syncThreshold=double,

table=list(

data=list(

caslib="string"

computedOnDemand=TRUE | FALSE

computedVars=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

computedVarsProgram="string"

dataSourceOptions=list(key-1=list(any-list-or-data-type-1) <, key-2=list(any-list-or-data-type-2), ...>)

groupBy=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

groupByMode="NOSORT" | "REDISTRIBUTE"

name="table-name"

onDemand=TRUE | FALSE

orderBy=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

singlePass=TRUE | FALSE

vars=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

where="where-expression"

whereTable=list(

casLib="string"

name="table-name"

vars=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

where="where-expression"

)

variableLevels=list(

data=list(

caslib="string"

computedOnDemand=TRUE | FALSE

computedVars=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

computedVarsProgram="string"

dataSourceOptions=list(key-1=list(any-list-or-data-type-1) <, key-2=list(any-list-or-data-type-2), ...>)

groupBy=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

groupByMode="NOSORT" | "REDISTRIBUTE"

name="table-name"

onDemand=TRUE | FALSE

orderBy=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

singlePass=TRUE | FALSE

vars=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

where="where-expression"

whereTable=list(

casLib="string"

name="table-name"

vars=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

where="where-expression"

)

varlevel="string",

varname="string"

variableOdes=list(

data=list(

caslib="string"

computedOnDemand=TRUE | FALSE

computedVars=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

computedVarsProgram="string"

dataSourceOptions=list(key-1=list(any-list-or-data-type-1) <, key-2=list(any-list-or-data-type-2), ...>)

groupBy=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

groupByMode="NOSORT" | "REDISTRIBUTE"

name="table-name"

onDemand=TRUE | FALSE

orderBy=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

singlePass=TRUE | FALSE

vars=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

where="where-expression"

whereTable=list(

casLib="string"

name="table-name"

vars=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

where="where-expression"

)

system="string",

varname="string"

variableRoles=list(

data=list(

caslib="string"

computedOnDemand=TRUE | FALSE

computedVars=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

computedVarsProgram="string"

dataSourceOptions=list(key-1=list(any-list-or-data-type-1) <, key-2=list(any-list-or-data-type-2), ...>)

groupBy=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

groupByMode="NOSORT" | "REDISTRIBUTE"

name="table-name"

onDemand=TRUE | FALSE

orderBy=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

singlePass=TRUE | FALSE

vars=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

where="where-expression"

whereTable=list(

casLib="string"

name="table-name"

vars=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

where="where-expression"

)

varname="string",

varrole="string"

variableSyncParms=list(

data=list(

caslib="string"

computedOnDemand=TRUE | FALSE

computedVars=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

computedVarsProgram="string"

dataSourceOptions=list(key-1=list(any-list-or-data-type-1) <, key-2=list(any-list-or-data-type-2), ...>)

groupBy=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

groupByMode="NOSORT" | "REDISTRIBUTE"

name="table-name"

onDemand=TRUE | FALSE

orderBy=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

singlePass=TRUE | FALSE

vars=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

where="where-expression"

whereTable=list(

casLib="string"

name="table-name"

vars=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

where="where-expression"

)

intervalvar="string",

mean="string",

nominalvar="string",

sdev="string",

varlevel="string"

)

Summary: Input and Output Tables

If a row includes a subparameter, you can specify the name, caslib, and so on in the subparameter. Otherwise, you can specify the name, caslib, and so on in the parameter.

Parameters for Reading Input Tables
Parameter	Subparameter	Description
cliques	data	specifies the table of the factors and the cliques that form the clique tree obtained by processing the Bayesian network of variables. A clique tree permits an exact two-pass belief propagation over the tree. If cliques are not supplied using this table, then the network is processed to form cliques, and output cliques are saved in this table for use in subsequent runs of the filter.
initialBeliefs	required parameterdata	specifies the table of incoming beliefs in hidden variables from the previous run of the filter.
links	required parameterdata	specifies the table of parent-child relationships among variables in a two-time-period network.
table	required parameterdata	specifies the input table that contains observations by time.
variableLevels	data	specifies the table of valid levels of nominal variables.
variableOdes	data	specifies the table of variables by systems of ordinary differential equations (ODEs). Each system has a unique group number.
variableRoles	required parameterdata	specifies the table of variables and their properties: TIMEID, CONTROL, HIDDEN, or OBSERVED.
variableSyncParms	data	specifies the table of parameters that are used in synchronizing beliefs of hidden interval variables for different values of hidden nominal variables.

Parameters for Creating Output Tables
Parameter	Subparameter	Description
output	data	specifies the table that contains the outgoing beliefs of hidden variables. Beliefs of interval variables differ by levels of nominal variables. This table provides the interval variable beliefs for the most probable levels of the nominal variables.
outputCliques	data	specifies the table that contains the cliques in the clique tree obtained by processing the Bayesian network.
outputDetails	data	specifies the table that contains the outgoing beliefs of hidden variables specific to the branches (values) of hidden nominal variables. Thus, this table provides beliefs of interval variables over less probable values of nominal variables as well.

Parameter Descriptions

cliques=list(_cliques)

The _cliques value can be one or more of the following:

data=list(castable)

specifies the name of the cliques data table.

For more information about specifying the data parameter, see the common castable parameter (Appendix A: Common Parameters).

id="string"

Default	"id"

stage="string"

Default	"stage"

toid="string"

specifies the name of the column that contains the ID of the clique that receives the message.

Default	"toid"

type="string"

specifies the name of the type column in the cliques data table, where the type parameter determines whether the ID parameter value corresponds to a clique or a factor.

Default	"type"

varname="string"

specifies the name of the variable column in the cliques data table, which is specified when the ID parameter value corresponds to a belief factor for a variable.

Default	"varname"

initialBeliefs=list(_initbeliefs)

specifies the table of incoming beliefs in hidden variables from the previous run of the filter.

Alias	initBeliefs

The _initbeliefs value can be one or more of the following:

* data=list(castable)

specifies the name of the initial beliefs data table.

For more information about specifying the data parameter, see the common castable parameter (Appendix A: Common Parameters).

intervalvar="string"

specifies the name of the interval variable column in the initial beliefs data table.

Default	"intervalvar"

mean="string"

specifies the name of the mean column of the interval variable or the probability of the nominal variable in the initial beliefs data table.

Default	"mean"

nominalvar="string"

specifies the name of the nominal variable column in the initial beliefs data table. The belief in the interval variable varies by levels of the nominal variables.

Default	"nominalvar"

sdev="string"

specifies the name of the standard deviation column of the interval variable in the initial beliefs data table.

Default	"sdev"

varlevel="string"

specifies the name of the level column of the nominal variable in the initial beliefs data table.

Default	"varlevel"

linearApproximationType="EXTENDED" | "UNSCENTED"

specifies the technique that is used to generate a linear approximation of the nonlinear relationships.

Alias	linApprox
Default	EXTENDED

EXTENDED

uses the extended method of linear approximation.

UNSCENTED

uses the unscented method of linear approximation.

links=list(_links)

specifies the table of parent-child relationships among variables in a two-time-period network.

The _links value can be one or more of the following:

child="string"

specifies the name of the child variable column in the links data table.

Default	"child"

* data=list(castable)

specifies the name of the links data table.

For more information about specifying the data parameter, see the common castable parameter (Appendix A: Common Parameters).

parent="string"

specifies the name of the parent variable column in the links data table.

Default	"parent"

stage="string"

specifies the name of the stage column in the links data table, where the value of the stage parameter is 1 for the current time period or 2 for the previous time period.

Default	"stage"

odeApproximationType="ALL" | "GRADIENT" | "NONE"

specifies which type of ordinary differential equation (ODE) approximation to use.

Alias	odeApprox
Default	GRADIENT

ALL

approximately solves the ODEs that are used in the mean and gradient calculations used in linearization.

GRADIENT

approximately solves the ODEs that are used in the gradient calculations used in linearization.

NONE

does not use any approximation to solve the ODEs that are used in the mean and gradient calculations used in linearization.

output=list(_output)

Alias	out

data=list(casouttable)

specifies the name of the output data table.

For more information about specifying the data parameter, see the common casouttable parameter (Appendix A: Common Parameters).

outputCliques=list(_outcliques)

specifies the table that contains the cliques in the clique tree obtained by processing the Bayesian network.

Alias	outcliques

The _outcliques value can be one or more of the following:

data=list(casouttable)

specifies the name of the cliques data table.

For more information about specifying the data parameter, see the common casouttable parameter (Appendix A: Common Parameters).

id="string"

Default	"id"

stage="string"

Default	"stage"

toid="string"

specifies the name of the column that contains the ID of the clique that receives the message.

Default	"toid"

type="string"

specifies the name of the type column in the cliques data table, where the type parameter determines whether the ID parameter value corresponds to a clique or a factor.

Default	"type"

varname="string"

specifies the name of the variable column in the cliques data table, which is specified when the ID parameter value corresponds to a belief factor for a variable.

Default	"varname"

outputDetails=list(_outdetails)

Alias	outdetails

The _outdetails value can be one or more of the following:

data=list(casouttable)

specifies the name of the output details data table.

For more information about specifying the data parameter, see the common casouttable parameter (Appendix A: Common Parameters).

intervalvar="string"

specifies the name of the interval variable column in the output details data table.

Default	"intervalvar"

mean="string"

specifies the name of the mean column of the beliefs for the interval variable on this branch in the output details data table.

Default	"mean"

nominalvar="string"

specifies the name of the nominal variable column in the output details data table.

Default	"nominalvar"

sdev="string"

specifies the name of the standard deviation column of the beliefs for the interval variable on this branch in the output details data table.

Default	"sdev"

varlevel="string"

specifies the name of the variable level column in the output details data table.

Default	"varlevel"

syncThreshold=double

Alias	threshold
Default	0.005
Range	0.001–1

table=list(_data)

specifies the input table that contains observations by time.

* data=list(castable)

specifies the name of the data table that contains observations.

For more information about specifying the data parameter, see the common castable parameter (Appendix A: Common Parameters).

variableLevels=list(_varlevels)

specifies the table of valid levels of nominal variables.

Alias	varLevels

The _varlevels value can be one or more of the following:

data=list(castable)

specifies the name of the levels data table.

For more information about specifying the data parameter, see the common castable parameter (Appendix A: Common Parameters).

varlevel="string"

specifies the name of the level column in the levels data table.

Default	"varlevel"

varname="string"

specifies the name of the variable column in the levels data table.

Default	"varname"

variableOdes=list(_varodes)

specifies the table of variables by systems of ordinary differential equations (ODEs). Each system has a unique group number.

Alias	varOdes

The _varodes value can be one or more of the following:

data=list(castable)

specifies the name of the data table of variables in ODE systems.

For more information about specifying the data parameter, see the common castable parameter (Appendix A: Common Parameters).

system="string"

specifies the name of the ODE system column of variables in the ODE systems data table.

Default	"system"

varname="string"

specifies the name of the variable column in the ODE systems data table.

Default	"varname"

variableRoles=list(_variables)

specifies the table of variables and their properties: TIMEID, CONTROL, HIDDEN, or OBSERVED.

Alias	varRoles

The _variables value can be one or more of the following:

* data=list(castable)

specifies the name of the variables data table.

For more information about specifying the data parameter, see the common castable parameter (Appendix A: Common Parameters).

varname="string"

specifies the name of the variable column in the variables data table.

Default	"varname"

varrole="string"

specifies the name of the role column in the variables data table.

Default	"varrole"

variableSyncParms=list(_varsyncs)

specifies the table of parameters that are used in synchronizing beliefs of hidden interval variables for different values of hidden nominal variables.

Alias	varSyncs

The _varsyncs value can be one or more of the following:

data=list(castable)

specifies the name of the variable synchronization data table.

For more information about specifying the data parameter, see the common castable parameter (Appendix A: Common Parameters).

intervalvar="string"

specifies the name of the interval variable column in the variable synchronization data table.

Default	"intervalvar"

mean="string"

specifies the name of the mean column for synchronization of the interval variable or the probability of the nominal variable in the variable synchronization data table.

Default	"mean"

nominalvar="string"

specifies the name of the nominal variable column in the variable synchronization data table. The synchronization value of the interval variable can vary by levels of the nominal variables.

Default	"nominalvar"

sdev="string"

specifies the name of the standard deviation column for synchronization of the interval variable in the variable synchronization data table.

Default	"sdev"

varlevel="string"

specifies the name of the level column of the nominal variable in the variable synchronization data table.

Default	"varlevel"

Last updated: September 15, 2022