Struct BayesianNetwork 

pub struct BayesianNetwork {
    pub nodes: Vec<BnNode>,
}

A Bayesian Network: directed acyclic graph with conditional probability tables.

Supports exact inference via variable elimination on small networks and loopy belief propagation on larger ones.

Fields

nodes: Vec<BnNode>

Nodes in topological order.

Implementations

impl BayesianNetwork

pub fn new() -> Self

Creates a new empty BayesianNetwork.

pub fn add_node(&mut self, node: BnNode) -> usize

Adds a node and returns its index.

pub fn joint_probability(&self, assignment: &[usize]) -> f64

Computes the joint probability of a complete assignment.

assignment[i] is the state of node i.

pub fn marginal(&self, target: usize, target_state: usize) -> f64

Computes the marginal probability of node target being in state by summing over all other assignments (exact, exponential complexity).

pub fn marginal_all(&self, target: usize) -> Vec<f64>

Returns marginal probabilities for all states of node target.

pub fn conditional( &self, target: usize, target_state: usize, evidence: &[(usize, usize)], ) -> f64

Computes conditional probability P(target=state | evidence).

evidence is a list of (node_idx, state) observations.

pub fn validate(&self) -> bool

Checks that all CPTs are valid (non-negative, rows sum to 1).

Trait Implementations

impl Clone for BayesianNetwork

fn clone(&self) -> BayesianNetwork

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for BayesianNetwork

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for BayesianNetwork

fn default() -> Self

Returns the “default value” for a type.