Models

Public model classes for probabilistic, causal, and structural-equation workflows.

Directed Probabilistic Models

DiscreteBayesianNetwork(*args[, backend])	Initializes a Discrete Bayesian Network.
LinearGaussianBayesianNetwork(*args[, backend])	Class to represent Linear Gaussian Bayesian Networks (LGBN).
FunctionalBayesianNetwork(*args[, backend])	Class for representing Functional Bayesian Network.
DynamicBayesianNetwork(*args[, backend])	Base class for Dynamic Bayesian Network
NaiveBayes(*args[, backend])	Class to represent Naive Bayes.

Structural Equation Models

SEMGraph([ebunch, latents, err_corr, err_var])	Base class for graphical representation of Structural Equation Models(SEMs).
SEMAlg([eta, B, zeta, wedge_y, fixed_values])	Base class for algebraic representation of Structural Equation Models(SEMs).
SEM(syntax, **kwargs)	Class for representing Structural Equation Models.

Undirected and Derived Models

DiscreteMarkovNetwork(*args[, backend])	Base class for Markov Model.
MarkovChain([variables, card, start_state])	Class to represent a Markov Chain with multiple kernels for factored state space, along with methods to simulate a run.
FactorGraph(*args[, backend])	Class for representing factor graph.
JunctionTree(*args[, backend])	Class for representing Junction Tree.
ClusterGraph(*args[, backend])	Base class for representing Cluster Graph.

Note

Deprecated compatibility aliases such as BayesianNetwork and MarkovNetwork are omitted here. Use DiscreteBayesianNetwork and DiscreteMarkovNetwork instead.