ConstraintBasedBase<T>
Base Classes · AiDotNet.CausalDiscovery.ConstraintBased
Base class for constraint-based causal discovery algorithms (PC, FCI, MMPC, etc.).
Inheritance: CausalDiscoveryBase<T> → ConstraintBasedBase<T>
Known derived types: CDNODAlgorithm<T>, CPCAlgorithm<T>, FCIAlgorithm<T>, FastIAMBAlgorithm<T>, IAMBAlgorithm<T>, MMPCAlgorithm<T>, MarkovBlanketAlgorithm<T>, PCAlgorithm<T>, RFCIAlgorithm<T>
For Beginners
These algorithms work by asking “Are variables X and Y still related after we account for other variables?” If not, there’s no direct causal link between them. By systematically testing all variable pairs, the algorithm builds a causal graph.
How It Works
Constraint-based methods learn causal structure by performing conditional independence (CI) tests. They start with a complete graph and remove edges between variables that are found to be conditionally independent given some set of other variables.
Properties
| Property | Summary |
|---|---|
CausalDiscoveryCategory Category { get; } |