Package edu.cmu.tetrad.search
package edu.cmu.tetrad.search
-
ClassDescriptionConstructs and AD leaf tree on the fly.Stores AD trees for data sets for reuse.This class contains a method classify which uses an instantiated Bayes net (BayesIm) provided in the constructor.Implements the BOSS DC Experimental algorithm.Calculates the BDe score.Calculates the BDeu score.Implements the continuous BIC score for FGES.Implements the backward equivalence search of FGES.J.M.Does BOSS + retain unshielded colliders + final FCI orientation rulesDoes an FCI-style latent variable search using permutation-based reasoning.Implements the BOSS (Best Order Permutation Search) algorithm.Implements the GRASP algorithms, with various execution flags.Implements the GRASP algorithms, with various execution flags.Implements the BOSS algorithm.An enumeration of the test types for BuildPureClusters, and Purify.Implements a really simple idea for building pure clusters, just using the Purify algorithm.GesSearch is an implementation of the GES algorithm, as specified in Chickering (2002) "Optimal structure identification with greedy search" Journal of Machine Learning Research.GesSearch is an implementation of the GES algorithm, as specified in Chickering (2002) "Optimal structure identification with greedy search" Journal of Machine Learning Research.Implementation of the experimental BRIDGES algorithmBuildPureClusters is an implementation of the automated clustering and purification methods described on the report "Learning Measurement Models" CMU-CALD-03-100.This class provides the data structures and methods for carrying out the Cyclic Causal Discovery algorithm (CCD) described by Thomas Richardson and Peter Spirtes in Chapter 7 of Computation, Causation, and Discovery by Glymour and Cooper eds.This is an optimization of the CCD (Cyclic Causal Discovery) algorithm by Thomas Richardson.Searches for a CPDAG representing all of the Markov blankets for a given target T consistent with the given independence information.Extends Erin Korber's implementation of the Fast Causal Inference algorithm (found in FCI.java) with Jiji Zhang's Augmented FCI rules (found in sec.Calculates marginal chi square test results for a discrete dataset.Simple class to store the parameters of the result returned by the G Square test.Some methods to check significance of clusters for clustering algroithms.Some general utilities for dealing with clustering input and output.Checks conditional independence of variable in a continuous data set using Daudin's method.Checks conditional independence of variable in a continuous data set using Daudin's method.Implements a conditional Gaussian likelihood.A return value for a likelihood--returns a likelihood value and the degrees of freedom for it.Implements a conditional Gaussian likelihood.A return value for a likelihood--returns a likelihood value and the degrees of freedom for it.Implements a conditional Gaussian BIC score for FGS.Implements a conditional Gaussian BIC score for FGS.Implements different tests of tetrad constraints: using Wishart's test (CPS, Wishart 1928); Bollen's test (Bollen, 1990) or a more computationally intensive test that fits one/two factor Gaussian models.Implements a convervative version of PC, in which the Markov condition is assumed but faithfulness is tested locally.Reorients edges in the getModel graph as CPC would orient them.Implements a convervative version of PC, in which the Markov condition is assumed but faithfulness is tested locally.An adaptation of the CStaR algorithm (Steckoven et al., 2012).Given a pattern, lists all of the DAGs in that pattern.Given a graph, lists all DAGs that result from directing the undirected edges in that graph every possible way.Determines sepsets, collider, and noncolliders by examining d-separation facts in a DAG.Extends Erin Korber's implementation of the Fast Causal Inference algorithm (found in FCI.java) with Jiji Zhang's Augmented FCI rules (found in sec.Implements the DCI (Distributed Causal Inference) algorithm for learning causal structure over a set of variable from multiple datasets that each may only measure proper overlapping subsets subsets of that sets, or datasets with some variables in common and others not.Implements a degenerate Gaussian BIC score for FGES.Deprecated.Use DegenerateGaussianScoreImplements a test for simultaneously zero sextads in the style of Bollen, K.Implements a test for simultaneously zero tetrads in Bollen, K.Calculates the BDeu score.Calculates the discrete BIC score.Interface implemented by classes that do discrete classification.Implements a conditional Gaussian likelihood.A return value for a likelihood--returns a likelihood value and the degrees of freedom for it.Implements a conditional Gaussian BIC score for FGS.Implementation of a test of tetrad constraints with discrete variables.Implements the DM search.Implements the extended BIC score (Chen and Chen)..Estimates the rank of a matrix.Useful references: "Factor Analysis of Data Matrices" - Paul Horst (1965) This work has good specifications and explanations of factor analysis algorithm and methods of communality estimation.Implements the "fast adjacency search" used in several causal algorithm in this package.Implements the "fast adjacency search" used in several causal algorithm in this package.Implements a modified version of the the "fast adjacency search" for use in the Distributed Causal Inference (DCI) algorithm.Implements the "fast adjacency search" used in several causal algorithm in this package.Implements the "fast adjacency search" used in several causal algorithm in this package.Runs the FASK (Fast Adjacency Skewness) algorithm.Fast adjacency search followed by robust skew orientation.Implements the "fast adjacency search" used in several causal algorithm in this package.A Java implementation of FastIca following the R package fastICA.A list containing the following componentsImplements the "fast adjacency search" used in several causal algorithm in this package.Extends Erin Korber's implementation of the Fast Causal Inference algorithm (found in FCI.java) with Jiji Zhang's Augmented FCI rules (found in sec.Extends Erin Korber's implementation of the Fast Causal Inference algorithm (found in FCI.java) with Jiji Zhang's Augmented FCI rules (found in sec.Extends Erin Korber's implementation of the Fast Causal Inference algorithm (found in FCI.java) with Jiji Zhang's Augmented FCI rules (found in sec.GesSearch is an implementation of the GES algorithm, as specified in Chickering (2002) "Optimal structure identification with greedy search" Journal of Machine Learning Research.GesSearch is an implementation of the GES algorithm, as specified in Chickering (2002) "Optimal structure identification with greedy search" Journal of Machine Learning Research.GesSearch is an implementation of the GES algorithm, as specified in Chickering (2002) "Optimal structure identification with greedy search" Journal of Machine Learning Research.Implements FindOneFactorCluster by Erich Kummerfeld (adaptation of a two factor quartet algorithm to a one factor tetrad algorithm).Implements FindOneFactorCluster by Erich Kummerfeld (adaptation of a two factor sextet algorithm to a one factor IntSextad algorithm).J.M.A translation from Tibshirani's 2008 Fortran implementation of glasso.Return value of the algorithm.**************************************************************************************Checks the graphoid axioms for a set of Independence Model statements.Implements Chickering and Meek's (2002) locally consistent score criterion.Interface for a method that scores a DAG.Interface for a search method that returns a graph.Dag plus edge weights.Implements the GRASP algorithms, with various execution flags.J.M.Implements the GRASP algorithms, with various execution flags.Implements the Grow-Shrink algorithm of Margaritis and Thrun.Performs conditional independence tests of discrete data using the G Square method.Simple class to store the parameters of the result returned by the G Square test.The purpose of this class is to store evaluation results.Loss function for PC: * for adjacency errors, 1 pt (i.e.Best Fit Finder using a beam search.Interface for Bff (Best Fit Finder) algorithm.Best Fit Finder using the GES algorithm.The Hungarian algorithm for solving the N-Queens problem.Created by jdramsey on 2/21/16.Implements the IDA algorithm, Maathuis, Marloes H., Markus Kalisch, and Peter Bühlmann.A list of nodes and corresponding minimum effects.An interface for fast adjacency searches (i.e.Implements a score to average results over multiple scores.Adds any orientations implied by the given orientation.Interface implemented by classes that do conditional independence testing.Checks the conditional independence X _||_ Y | S, where S is a set of discrete variable, and X and Y are discrete variable not in S, by applying a conditional Chi Square test.Checks conditional independence of variable in a continuous data set using Fisher's Z test.Checks conditional independence of variable in a continuous data set using a conditional correlation test for the nonlinear nonGaussian case.Checks conditional independence of variable in a continuous data set using a conditional correlation test for the nonlinear nonGaussian case.Performs a test of conditional independence X _||_ Y | Z1...Zn where all searchVariables are either continuous or discrete.Checks conditional independence for continuous variables using Cramer's T-test formula (Cramer, Mathematical Methods of Statistics (1951), page 413).A return value for a likelihood--returns a likelihood value and the degrees of freedom for it.Checks independence facts for variables associated with the nodes in a given graph by checking d-separation facts on the underlying nodes.Checks conditional independence of variable in a continuous data set using Fisher's Z test.Calculates independence from pooled residuals.Calculates independence from pooled residuals.Checks independence of X _||_ Y | Z for variables X and Y and list Z of variables.Calculates independence from pooled residuals.Checks conditional independence of variable in a continuous data set using Fisher's Z test.Checks the conditional independence X _||_ Y | S, where S is a set of discrete variable, and X and Y are discrete variable not in S, by applying a conditional G Square test.Checks the conditional independence X _||_ Y | S, where S is a set of continuous variable, and X and Y are discrete variable not in S, using the Hilbert-Schmidth Independence Criterion (HSIC), a kernel based nonparametric test for conditional independence.Checks conditional independence against a list of conditional independence facts, manually entered.Performs a test of conditional independence X _||_ Y | Z1...Zn where all searchVariables are either continuous or discrete.Performs a test of conditional independence X _||_ Y | Z1...Zn where all searchVariables are either continuous or discrete.Pools together a set of independence tests using a specified methodsPerforms a test of conditional independence X _||_ Y | Z1...Zn where all searchVariables are either continuous or discrete.Performs a test of conditional independence X _||_ Y | Z1...Zn where all searchVariables are either continuous or discrete.Checks conditional independence of variable in a continuous data set using Fisher's Z test.Uses BCInference by Cooper and Bui to calculate probabilistic conditional independence judgments.Checks independence of X _||_ Y | Z for variables X and Y and list Z of variables.Interface implemented by classes that do conditional independence testing.Checks independence facts for variables associated associated with a sepset by simply querying the sepsetChecks d-separations in structural model using t-separations over indicators.A typesafe enumeration of the types of independence tests that are used for basic search algorithm in this package.Returns edges whose entries in the precision matrix exceed a certain threshold.Implements the ION (Integration of Overlapping Networks) algorithm for distributed causal inference.Implements the ION (Integration of Overlapping Networks) algorithm for distributed causal inference.**************************************************************************An interface for Purify algorithm.Created by jdramsey on 2/21/16.Kernal Independence Test (KCI).Implements the continuous BIC score for FGES.Kernelized PC algorithm.Determines whether nodes indexed as (n1, center, n2) form a legal pair of edges in a graph for purposes of some algorithm that uses this information.The code used within this class is largely Gustave Lacerda's, which corresponds to his essay, Discovering Cyclic Causal Models by Independent Components Analysis.This small class is used to store graph permutations.Implements the LiNGAM algorithm in Shimizu, Hoyer, Hyvarinen, and Kerminen, A linear nongaussian acyclic model for causal discovery, JMLR 7 (2006).Implements the Lingam CPDAG algorithm as specified in Hoyer et al., "Causal discovery of linear acyclic models with arbitrary distributions," UAI 2008.Implements the Lingam CPDAG algorithm as specified in Hoyer et al., "Causal discovery of linear acyclic models with arbitrary distributions," UAI 2008.Created by IntelliJ IDEA.LOFS = Ling Orientation Fixed Structure.LOFS = Ling Orientation Fixed Structure.Implements the backward equivalence search of FGES.Performs a Bayesian classification of a test set based on a given training set.An interface for Markov blanket searches.Some useful utilities for dealing with Markov blankets and Markov blanket DAGs.Implements Meek's complete orientation rule set for PC (Chris Meek (1995), "Causal inference and causal explanation with background knowledge"), modified for Conservative PC to check noncolliders against recorded noncolliders before orienting.Implements Meek's complete orientation rule set for PC (Chris Meek (1995), "Causal inference and causal explanation with background Knowledge"), modified for Conservative PC to check noncolliders against recorded noncolliders before orienting.Implements Meek's complete orientation rule set for PC (Chris Meek (1995), "Causal inference and causal explanation with background knowledge"), modified for Conservative PC to check noncolliders against recorded noncolliders before orienting.An implemetation of Mimbuild based on the Fgsl score.An implemetation of Mimbuild based on the treks and ranks.Holds some utility methods for Purify, Build Clusters, and Mimbuild.Calculates Mixed Variables Polynomial likelihood.Implements a mixed variable polynomial BIC score for fGES.Created by user on 3/29/18.Calculates Mixed Variables Polynomial likelihood.Implements a mixed variable polynomial BIC score for fGES.This is an optimization of the CCD (Cyclic Causal Discovery) algorithm by Thomas Richardson.Implements various permutation algorithms, including BOSS and GASP.This class contains methods which can be used to determine whether a directed graph is in the equivalence class determined by the given PAG.Implements the PC ("Peter/Clark") algorithm, as specified in Chapter 6 of Spirtes, Glymour, and Scheines, "Causation, Prediction, and Search," 2nd edition, with a modified rule set in step D due to Chris Meek.Implements a convervative version of PC, in which the Markov condition is assumed but faithfulness is tested locally.Implements the PC ("Peter/Clark") algorithm, as specified in Chapter 6 of Spirtes, Glymour, and Scheines, "Causation, Prediction, and Search," 2nd edition, with a modified rule set in step D due to Chris Meek.Implements the PC Local algorithm.Implements the PC ("Peter/Clark") algorithm, as specified in Chapter 6 of Spirtes, Glymour, and Scheines, "Causation, Prediction, and Search," 2nd edition, with a modified rule set in step D due to Chris Meek.Searches for a CPDAG representing all the Markov blankets for a given target T consistent with the given independence information.Implements the PC ("Peter/Clark") algorithm, as specified in Chapter 6 of Spirtes, Glymour, and Scheines, "Causation, Prediction, and Search," 2nd edition, with a modified rule set in step D due to Chris Meek.Implements a modification of the the PC ("Peter/Clark") algorithm, as specified in Chapter 6 of Spirtes, Glymour, and Scheines, Causation, Prediction, and Search, 2nd edition, using the rule set in step D due to Chris Meek.Implements permutation search.Implements Poisson prior score (Bryan).Implements a test of tetrad constraints in a known correlation matrix.Finds possible d-connecting undirectedPaths for the IonSearch.This class implements the Possible-D-Sep search step of Spirtes, et al's (1993) FCI algorithm (pp 144-145).Uses BCInference by Cooper and Bui to calculate probabilistic conditional independence judgments.Purify is a implementation of the automated purification methods described on CPS and the report "Learning Measurement Models" CMU-CALD-03-100.Created by IntelliJ IDEA.A clean-up of Ricardo's IntSextad-based purify.A clean-up of Ricardo's tetrad-based purify.A clean-up of Ricardo's tetrad-based purify.Created by josephramsey on 4/13/14.Reorients all or part of the given graph.Utilities for resolving inconsistencies that arise between sepsets learned for overlapping datasets.Extends Erin Korber's implementation of the Fast Causal Inference algorithm (found in FCI.java) with Jiji Zhang's Augmented FCI rules (found in sec.Implements a conservative version of PC, in which the Markov condition is assumed but faithfulness is tested locally.Implements a conservative version of PC, in which the Markov condition is assumed but faithfulness is tested locally.Interface for a score suitable for FGESStores a graph with a score.Implements Chickering and Meek's (2002) locally consistent score criterion.Graph utilities for search algorithm.Contains utilities for logging search steps.Implements the continuous BIC score for FGES.Implements the continuous BIC score for FGES.Implements the continuous BIC score for FGES.Implements the continuous BIC score for FGES.Stores a map from pairs of nodes to separating sets--that is, for each unordered pair of nodes {node1, node2} in a graph, stores a set of nodes conditional on which node1 and node2 are independent (where the nodes are considered as variables) or stores null if the pair was not judged to be independent.This is the same as the usual SepsetMap described below, but also keeps up with the individual sets of conditioning nodes for d-separation relations for use with the Distributed Causal Inference (DCI) algorithm.Created by josephramsey on 3/24/15.Selects the first sepset it comes to from among the extra sepsets or the adjacents of i or k, or null if none is found.Selects the first sepset it comes to from among the extra sepsets or the adjacents of i or k, or null if none is found.Created by josephramsey on 3/24/15.Represents a sextad of variables.Tries to find a good shifting of variables to minimize average BICImplements the SP (Sparsest Permutation) algorithm.J.M.Extends Erin Korber's implementation of the Fast Causal Inference algorithm (found in FCI.java) with Jiji Zhang's Augmented FCI rules (found in sec.Extends Erin Korber's implementation of the Fast Causal Inference algorithm (found in FCI.java) with Jiji Zhang's Augmented FCI rules (found in sec.Replaces the FAS search in the previous version with GES followed by PC adjacency removals for more accuracy.Implements a conditional Gaussian BIC score for FGES.An enumeration of the test types for BuildPureClusters, and Purify.Represents a tetrad of variables.Interface implemented by classes that test tetrad constraints.Implements a scorer extending Teyssier, M., and Koller, D.Implements a scorer extending Teyssier, M., and Koller, D.Implements a scorer extending Teyssier, M., and Koller, D.Implements a scorer extending Teyssier, M., and Koller, D.Implements a convervative version of PC, in which the Markov condition is assumed but faithfulness is tested locally.Contains some utilities for doing autoregression.Extends Erin Korber's implementation of the Fast Causal Inference algorithm (found in FCI.java) with Jiji Zhang's Augmented FCI rules (found in sec.GesSearch is an implementation of the GES algorithm, as specified in Chickering (2002) "Optimal structure identification with greedy search" Journal of Machine Learning Research.Implements the "fast adjacency search" used in several causal algorithm in this package.Implements a convervative version of PC, in which the Markov condition is assumed but faithfulness is tested locally.Implements a convervative version of PC, in which the Markov condition is assumed but faithfulness is tested locally.Implements a convervative version of PC, in which the Markov condition is assumed but faithfulness is tested locally.Implements the Washdown algorithm,This class takes an xml element representing a bayes im and converts it to a BayesIMImplements the Zhang-Shen bound score.Implements the continuous BIC score for FGES.