Aggregators
![]() | ![]() |
Aggregators are special type of nodes that includes a generic CPT for any numbers of parents.
pyAgrum proposes a list of such aggregators. Some of then are used below.
import pyagrum as gumimport pyagrum.lib.notebook as gnbmin_x = 0max_x = 15
bn = gum.BayesNet()l = [bn.add(gum.RangeVariable(item, item, min_x, max_x)) for item in ["a", "b", "c", "d", "e", "f"]]
gum.config["notebook", "histogram_line_threshold"] = 15nmax = bn.addMAX(gum.RangeVariable("MAX", "MAX", min_x, max_x))bn.addArc(l[0], nmax)bn.addArc(l[1], nmax)bn.addArc(l[2], nmax)nmin = bn.addMIN(gum.RangeVariable("MIN", "MIN", min_x, max_x))bn.addArc(l[3], nmin)bn.addArc(l[4], nmin)bn.addArc(l[5], nmin)nampl = bn.addAMPLITUDE(gum.RangeVariable("DELTA", "DELTA", 0, max_x - min_x))bn.addArc(nmax, nampl)bn.addArc(nmin, nampl)nmedian = bn.addMEDIAN(gum.RangeVariable("MEDIAN", "MEDIAN", min_x, max_x))for n in [l[0], l[1], l[2], l[3]]: bn.addArc(n, nmedian)## potential for median has a size : 16^5=2^20 double !nexists = bn.addEXISTS(gum.LabelizedVariable("EXISTS_0", "EXISTS"), 0)bn.addArc(l[0], nexists)bn.addArc(l[1], nexists)bn.addArc(l[2], nexists)nforall = bn.addFORALL(gum.LabelizedVariable("FORALL_1", "FORALL"), 1)bn.addArc(l[3], nforall)bn.addArc(l[4], nforall)bn.addArc(l[5], nforall)ncount = bn.addCOUNT(gum.RangeVariable("COUNT_1", "COUNT_1,", 0, 3), 1)bn.addArc(l[0], ncount)bn.addArc(l[1], ncount)bn.addArc(l[2], ncount)for nod in l: bn.cpt(nod).fillWith(1).normalize()gnb.showInference(bn, size="13")## dot | neato | fdp | sfdp | twopi | circo | osage | patchworkgum.config["notebook", "graphRankDir"] = "LR"gnb.showInference(bn, size="13", evs={"MEDIAN": [0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0]})gum.config.reset()## if the roots do not have uniform but random distributionfor nod in l: bn.generateCPT(nod)
gnb.showInference(bn, size="13")gnb.showInference(bn, size="13", evs={"MEDIAN": [0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0]})Input/Output
Section titled “Input/Output”Aggregator (and ICI model) nodes have no stored CPT — the probability is computed on the fly from the aggregator’s rule. Saving to most BN file formats (BIF, BIFXML, DSL, XDSL, net, UAI, O3PRM) flattens that computed table into a full dense CPT before writing it out. Round-tripping through one of these formats therefore loses the aggregator: reloading the file gives back a plain node with a dense CPT, not an aggregator (bad round trip).
Only aGrUM’s native jgum (JSON) and bgum (binary) formats preserve the aggregator/ICI type exactly. Instead of a flat array of probabilities, the cpt entry for such a node is a small object describing its type and parameters, e.g. {"kind": "aggregator", "name": "forall", "value": 1} for a FORALL node, or {"kind": "ici", "name": "MultiDimNoisyORCompound", ...} for a Noisy-Or node.
import jsonimport osimport tempfile
demo = gum.BayesNet()ps = [demo.add(gum.RangeVariable(f"P{i}", "", 0, 9)) for i in range(4)]for i in range(4): demo.cpt(f"P{i}").randomCPT()nsum = demo.addSUM(gum.RangeVariable("SUM", "", 0, 9))for p in ps: demo.addArc(p, nsum)
with tempfile.TemporaryDirectory() as d: bif_path = os.path.join(d, "demo.bif") jgum_path = os.path.join(d, "demo.jgum") gum.saveBN(demo, bif_path) gum.saveBN(demo, jgum_path) bif_size = os.path.getsize(bif_path) jgum_size = os.path.getsize(jgum_path) with open(jgum_path) as f: jgum_content = json.load(f)
print(f"BIF (dense CPT) : {bif_size:>8} bytes")print(f"jgum (compact aggregator): {jgum_size:>8} bytes")print()print(json.dumps(jgum_content, indent=2))BIF (dense CPT) : 371373 bytesjgum (compact aggregator): 1171 bytes
{ "type": "BN", "GumJsonVersion": "1.0", "nodes": [ "P0[10]", "P1[10]", "P2[10]", "P3[10]", "SUM[10]" ], "parents": { "P0": [], "P1": [], "P2": [], "P3": [], "SUM": [ "P0", "P1", "P2", "P3" ] }, "cpt": { "P0": [ 0.18860514283555507, 0.0795090292393466, 0.020416855453333993, 0.03824350588919484, 0.10504745814658306, 0.13111658958670946, 0.011326512221508489, 0.1377975616708077, 0.21103906303722142, 0.07689828191973935 ], "P1": [ 0.0634957352555945, 0.049148045246097366, 0.0648705243881559, 0.13495263788361228, 0.13544355103284328, 0.024622995538563452, 0.06009240981563374, 0.40306461751096145, 0.04291746971526189, 0.02139201361327614 ], "P2": [ 0.0562652009896491, 0.051640950333211116, 0.007616007881978304, 0.012680539793720191, 0.032331619720787935, 0.44143930456154923, 0.15759123264612973, 0.052057473159765943, 0.14884118695244586, 0.03953648396076259 ], "P3": [ 0.050064576685309635, 0.0018560979311595463, 0.026516337081772937, 0.025556104662755375, 0.06994705218599719, 0.04069927574527202, 0.04736686381954994, 0.1319645815342686, 0.38038672717846306, 0.2256423831754517 ], "SUM": { "kind": "aggregator", "name": "sum" } }, "properties": { "software": "aGrUM 3.3.2", "creation": "2026-10-27 14:22:35.314", "lastModification": "2026-10-27 14:22:35.327" }}Indeed, the cpt for the node SUM should have a size of floats. Instead :
print(json.dumps(jgum_content["cpt"]["SUM"], indent=2)){ "kind": "aggregator", "name": "sum"}
