Struct BayesianNetwork 

pub struct BayesianNetwork { /* private fields */ }

Bayesian Network builder.

Provides a convenient API for constructing directed acyclic graphical models with conditional probability distributions.

Implementations

impl BayesianNetwork

pub fn new() -> Self

Create a new Bayesian Network.

pub fn add_variable(&mut self, name: String, cardinality: usize) -> &mut Self

Add a variable node to the network.

pub fn add_cpd( &mut self, child: String, parents: Vec<String>, cpd: ArrayD<f64>, ) -> Result<&mut Self>

Add a conditional probability distribution P(child | parents).

Arguments

• child - The dependent variable
• parents - Parent variables that child depends on
• cpd - Conditional probability table (dimensions: [parent1_card, …, child_card])

pub fn add_prior( &mut self, variable: String, prior: ArrayD<f64>, ) -> Result<&mut Self>

Add a prior probability P(variable) for a root node.

pub fn graph(&self) -> &FactorGraph

Get the underlying factor graph.

pub fn is_acyclic(&self) -> bool

Check if the network is acyclic (DAG property).

pub fn topological_order(&self) -> Result<Vec<String>>

Get topological ordering of variables (ancestors before descendants).

Trait Implementations

impl Default for BayesianNetwork

fn default() -> Self

Returns the “default value” for a type.