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	0.3347	0.6653
	1	0.2379	0.7621
1	0	0.2680	0.7320
	1	0.1852	0.8148

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	0.9995	0.0005
		1	0.9995	0.0005
	1	0	0.9992	0.0008
		1	0.9996	0.0004
1	0	0	0.2079	0.7921
		1	0.2048	0.7952
	1	0	0.1419	0.8581
		1	0.2690	0.7310

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	0.9996	0.0004
		1	0.9992	0.0008
	1	0	0.2616	0.7384
		1	0.1463	0.8537
1	0	0	0.9991	0.0009
		1	0.9997	0.0003
	1	0	0.1273	0.8727
		1	0.2821	0.7179

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	0.3270	0.0026
		1	0.6323	0.0380
	1	0	0.4284	0.0288
		1	0.5166	0.0262
1	0	0	0.0011	0.0648
		1	0.0021	0.9320
	1	0	0.0011	0.5227
		1	0.0013	0.4750