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.dsl")
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	0.0841	0.9159
	1	0.1104	0.8896
1	0	0.5675	0.4325
	1	0.6396	0.3604

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	0.5582	0.4418
		1	0.2303	0.7697
	1	0	0.5830	0.4170
		1	0.1880	0.8120
1	0	0	0.8034	0.1966
		1	0.4918	0.5082
	1	0	0.8189	0.1811
		1	0.4282	0.5718

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	0.6455	0.3545
		1	0.0600	0.9400
	1	0	0.8548	0.1452
		1	0.1711	0.8289
1	0	0	0.4814	0.5186
		1	0.3389	0.6611
	1	0	0.7502	0.2498
		1	0.6238	0.3762

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	0.0974	0.7268
		1	0.1018	0.0740
	1	0	0.7291	0.1911
		1	0.0514	0.0283
1	0	0	0.2180	0.5029
		1	0.2279	0.0512
	1	0	0.8594	0.0696
		1	0.0606	0.0103