Package edu.cmu.tetrad.search.unmix

Class ParentSupersetBuilder

java.lang.Object

edu.cmu.tetrad.search.unmix.ParentSupersetBuilder

public final class ParentSupersetBuilder
extends Object

Builds a parent *superset* per node without assuming a single pooled DAG. Combines fast statistical screening (|corr| or |Kendall τ) with an optional union of parents from several *shallow searches* run on subsamples ("bags").

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	ParentSupersetBuilder.Config	Represents the configuration settings used for statistical screening and optional bagging operations in the parent superset construction process.
static enum	ParentSupersetBuilder.ScoreType	Represents the type of correlation score used for statistical calculations or comparisons.

Method Summary

Modifier and Type	Method	Description
static Map<Node,List<Node>>	build(DataSet data, ParentSupersetBuilder.Config cfg)	Builds a map representing a superset of parent nodes for each variable node in the given data set.

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Method Details

build

public static Map<Node,List<Node>> build(DataSet data,
 ParentSupersetBuilder.Config cfg)

Builds a map representing a superset of parent nodes for each variable node in the given data set. This method performs statistical screening based on provided configurations, and optionally refines the superset using bagged subsamples and a shallow-search procedure.

Parameters:

data - The dataset containing the variables for which the parent superset will be constructed.

cfg - The configuration object that specifies scoring type, top variable selection, bagging preferences, and shallow-search method among other parameters.

Returns:

A map where each key is a target node, and the corresponding value is a list of potential parent nodes. These parent nodes are determined based on the statistical screening and optional bagging operations.