Skip to content

heuristics_miner_lossy_counting_budget

An algorithm to mine a Heuristics Net using the Lossy Counting with Budget algorithm.

Parameters

  • model_update_frequency: int default: 10
    How often (in number of events) the model should be returned.

  • budget: int default: 100
    The maximum budget available to the algorithm.

  • dependency_threshold: Float default: 0.5
    The Heuristics Miner's dependency threshold.

  • and_threshold: Float default: 0.8
    The Heuristics Miner's AND threshold.

Returned type

The returned output has type pm4py.objects.heuristics_net.obj.HeuristicsNet. See https://processintelligence.solutions/pm4py/api?page=pm4py.objects.heuristics_net.html%23pm4py.objects.heuristics_net.obj.HeuristicsNet.

Example

from pybeamline.sources import log_source
from pybeamline.algorithms.discovery.heuristics_miner_lossy_counting_budget import heuristics_miner_lossy_counting_budget
from pybeamline.sinks.print_sink import print_sink

log_source(["ABC","ABC","DEF"]).pipe(
    heuristics_miner_lossy_counting_budget(model_update_frequency=3, budget=4)
).subscribe(print_sink())

Output:

{'A': (node:A connections:{B:[0.5]}), 'B': (node:B connections:{C:[0.5]}), 'C': (node:C connections:{})}
{'A': (node:A connections:{B:[0.6666666666666666]}), 'B': (node:B connections:{C:[0.6666666666666666]}), 'C': (node:C connections:{})}
{'E': (node:E connections:{F:[0.5]}), 'F': (node:F connections:{})}

References

The algorithm is described in publications: