depynd.markov_networks._iamb()

depynd.markov_networks._iamb(X, lamb=0.0, **kwargs)

Learn the structure of Markov random field by finding Markov blanket for each variable with Incremental Association Markov Blanket [tsamardinos2003algorithms].

Parameters:
  • X (array, shape (n_samples, n_features)) – Observations of variables.
  • lamb (float) – Threshold for independence test.
  • kwargs (dict, default None) – Optional parameters for MI estimation.
Returns:

adj – Estimated adjacency matrix of an MRF.
Return type:

array, shape (n_features, n_features)

References

[tsamardinos2003algorithms]Tsamardinos, Ioannis, et al. “Algorithms for Large Scale Markov Blanket Discovery.” FLAIRS conference. Vol. 2. 2003.