def execute_script():
log = pm4py.read_xes(
os.path.join("..", "tests", "input_data", "receipt.xes"))
net, im, fm = inductive_miner.apply(
log, variant=inductive_miner.Variants.IM_CLEAN)
idx = 0
# try to resolve the marking equation to find an heuristics and possible a vector of transitions
# leading from im to fm
sync_net, sync_im, sync_fm = pm4py.construct_synchronous_product_net(
log[idx], net, im, fm)
me_solver = marking_equation.build(sync_net, sync_im, sync_fm)
h, x = me_solver.solve()
firing_sequence, reach_fm1, explained_events = me_solver.get_firing_sequence(
x)
print("for trace at index " + str(idx) + ": marking equation h = ", h)
print("x vector reaches fm = ", reach_fm1)
print("firing sequence = ", firing_sequence)
# it fails and the value of heuristics is low
#
# now let's try with extended marking equation to find the heuristics and the vector!
eme_solver = extended_marking_equation.build(log[idx], sync_net, sync_im,
sync_fm)
h, x = eme_solver.solve()
# the heuristics is much better
firing_sequence, reach_fm2, explained_events = eme_solver.get_firing_sequence(
x)
print(
"for trace at index " + str(idx) + ": extended marking equation h = ",
h)
print("x vector reaches fm = ", reach_fm2)
print("firing sequence = ", firing_sequence)
def solve_marking_equation(petri_net: PetriNet, initial_marking: Marking,
final_marking: Marking, cost_function: Dict[PetriNet.Transition, float] = None) -> float:
"""
Solves the marking equation of a Petri net.
The marking equation is solved as an ILP problem.
An optional transition-based cost function to minimize can be provided as well.
Parameters
---------------
petri_net
Petri net
initial_marking
Initial marking
final_marking
Final marking
cost_function
optional cost function to use when solving the marking equation.
Returns
----------------
h_value
Heuristics value calculated resolving the marking equation
"""
from pm4py.algo.analysis.marking_equation import algorithm as marking_equation
if cost_function is None:
cost_function = dict()
for t in petri_net.transitions:
cost_function[t] = 1
me = marking_equation.build(petri_net, initial_marking, final_marking, parameters={'costs': cost_function})
return marking_equation.get_h_value(me)