Some other features in Bayesian inference

Lazy Propagation uses a secondary structure called the “Junction Tree” to perform the inference.

import pyagrum as gum
import pyagrum.lib.notebook as gnb

bn = gum.loadBN("res/alarm.bgum")
gnb.showJunctionTreeMap(bn);

But this junction tree can be transformed to build different probabilistic queries.

bn = gum.fastBN("A->B->C->D;A->E->D;F->B;C->H")
ie = gum.LazyPropagation(bn)
bn

Evidence impact

Evidence Impact allows the user to analyze the effect of any variables on any other variables

ie.evidenceImpact("B", ["A", "H"])

		B
A	H	0	1
0	0	0.5472	0.4528
	1	0.4726	0.5274
1	0	0.3236	0.6764
	1	0.2619	0.7381

Evidence impact is able to find the minimum set of variables which effectively conditions the analyzed variable

ie.evidenceImpact("E", ["A", "F", "B", "D"])  # {A,D,B} d-separates E and F

			E
A	B	D	0	1
0	0	0	0.3672	0.6328
		1	0.3117	0.6883
	1	0	0.3501	0.6499
		1	0.3342	0.6658
1	0	0	0.6782	0.3218
		1	0.6219	0.3781
	1	0	0.6618	0.3382
		1	0.6458	0.3542

ie.evidenceImpact("E", ["A", "B", "C", "D", "F"])  # {A,C,D} d-separates E and {B,F}

			E
C	A	D	0	1
0	0	0	0.4290	0.5710
		1	0.2396	0.7604
	1	0	0.7318	0.2682
		1	0.5336	0.4664
1	0	0	0.2203	0.7797
		1	0.5601	0.4399
	1	0	0.5064	0.4936
		1	0.8222	0.1778

Evidence Joint Impact

ie.evidenceJointImpact(["A", "F"], ["B", "C", "D", "E", "H"])  # {B,E} d-separates [A,F] and [C,D,H]

			A
E	B	F	0	1
0	0	0	0.0143	0.0756
		1	0.1792	0.7309
	1	0	0.0045	0.0455
		1	0.0823	0.8677
1	0	0	0.0344	0.0501
		1	0.4313	0.4842
	1	0	0.0132	0.0370
		1	0.2434	0.7063