Class FaskPool
- All Implemented Interfaces:
Algorithm, MultiDataSetAlgorithm, AcceptsKnowledge, HasParameters, TakesExternalGraph, TakesScoreWrapper, TetradSerializable, Serializable
- Version:
- $Id: $Id
- Author:
- josephramsey
- See Also:
-
Constructor Summary
ConstructorsConstructorDescriptionFaskPool()Constructor for FaskPool.FaskPool(ScoreWrapper score) Constructor for FaskPool. -
Method Summary
Modifier and TypeMethodDescriptiongetComparisonGraph(Graph graph) Returns that graph that the result should be compared to.Returns the data type that the search requires, whether continuous, discrete, or mixed.Returns a short, one-line description of this algorithm.Returns a knowledge object.Returns the list of parameter names that are used.Returns the score wrapper.search(DataModel dataSet, Parameters parameters) Runs the search.search(List<DataModel> dataSets, Parameters parameters) Runs the search.voidsetExternalGraph(Algorithm algorithm) setExternalGraph.voidsetKnowledge(Knowledge knowledge) Sets a knowledge object.voidsetScoreWrapper(ScoreWrapper score) Sets a score wrapper if not null.
-
Constructor Details
-
FaskPool
public FaskPool()Constructor for FaskPool.
-
FaskPool
Constructor for FaskPool.
- Parameters:
score- aScoreWrapperobject
-
-
Method Details
-
search
Runs the search.- Specified by:
searchin interfaceMultiDataSetAlgorithm- Parameters:
dataSets- The data sets.parameters- The parameters.- Returns:
- The graph.
- Throws:
InterruptedException- if any.
-
search
Runs the search.- Specified by:
searchin interfaceAlgorithm- Parameters:
dataSet- The data set to run to the search on.parameters- The paramters of the search.- Returns:
- The result graph.
- Throws:
InterruptedException- if any.
-
getComparisonGraph
Returns that graph that the result should be compared to.- Specified by:
getComparisonGraphin interfaceAlgorithm- Parameters:
graph- The true directed graph, if there is one.- Returns:
- The comparison graph.
-
getDescription
Returns a short, one-line description of this algorithm. This will be printed in the report.- Specified by:
getDescriptionin interfaceAlgorithm- Returns:
- This description.
-
getDataType
Returns the data type that the search requires, whether continuous, discrete, or mixed.- Specified by:
getDataTypein interfaceAlgorithm- Returns:
- This type.
-
getParameters
Returns the list of parameter names that are used. These are looked up in ParamMap, so if they're notReturns the IMaGES parameters, minus OUTPUT_CPDAG: FASK-Pool takes the compelled orientations of the IMaGES CPDAG as evidence whether or not BOSS is asked to output a CPDAG (a DAG is converted to its CPDAG first), so the setting is irrelevant. FASK_POOL_ADJACENCY chooses the adjacency search (1 = IMaGES, 2 = pooled FAS, 3 = MG-FAS, 4 = MG-LiNG, 5 = intersection of 3 and 4); ALPHA and DEPTH govern the FAS-style tests, and THRESHOLD_B with the FastICA parameters governs the LiNG stage. FASK_POOL_ADJACENCY_ORIENTATIONS (default true) makes the IMaGES CPDAG's compelled orientations act as default orientations, overturnable only on strict cross-dataset sign consensus of the left-right statistic; the other adjacency methods produce undirected graphs, for which it has no effect. FASK_POOL_EXTERNAL_ORIENTATIONS (default true) does the same for supplied external graphs, which are estimated one per dataset and combined, and FASK_POOL_EXTERNAL_ADJACENCY_FRACTION (default 0.5) sets how many of them a pair must be adjacent in to enter the composite skeleton. TWO_CYCLE_ALPHA (default 0 = off) enables per-dataset two-cycle tests requiring unanimity across datasets; ORIENTATION_ALPHA (default 0) sets the bootstrap significance gate on orientation decisions, which with a single dataset is the only meaningful gate on the override. No other FASK single-dataset parameters are listed because there is no skew-adjacency stage in this setting.
- Specified by:
getParametersin interfaceHasParameters- Returns:
- Returns the list of parameter names that are used. These are looked up in ParamMap, so if they're not already defined they'll need to be defined there.
-
setExternalGraph
setExternalGraph.
Sets the algorithm supplying the external graphs. It is run separately on each dataset (unless it is itself a multi-dataset algorithm, which is run once on all of them), and the resulting graphs are combined. Null is accepted: external graphs are optional for FASK-Pool, and without them the adjacency search selected by FASK_POOL_ADJACENCY runs as before. Note that a fixed source graph from the interface returns the same graph for every dataset, which is logged, since such a graph carries no cross-dataset evidence.
- Specified by:
setExternalGraphin interfaceTakesExternalGraph- Parameters:
algorithm- aAlgorithmobject
-
getKnowledge
Returns a knowledge object.- Specified by:
getKnowledgein interfaceAcceptsKnowledge- Returns:
- a knowledge object.
-
setKnowledge
Sets a knowledge object.- Specified by:
setKnowledgein interfaceAcceptsKnowledge- Parameters:
knowledge- a knowledge object.
-
getScoreWrapper
Returns the score wrapper.- Specified by:
getScoreWrapperin interfaceTakesScoreWrapper- Returns:
- the score wrapper.
-
setScoreWrapper
Sets a score wrapper if not null.- Specified by:
setScoreWrapperin interfaceMultiDataSetAlgorithm- Specified by:
setScoreWrapperin interfaceTakesScoreWrapper- Parameters:
score- The wrapper
-