def project(log, groups, activity_key):
# currently not 'noise' proof
# assumes that no empty traces are in the log
logs = list()
for group in groups:
logs.append(
pm4py.filter_log(lambda t: t[0][activity_key] in group, log))
return logs
def split():
ps = process_args(sys.argv[1:])
dpn = DPN(read_pnml_input(ps["model"]))
(log, has_uncertainty) = read_log(ps["log"])
print("number of traces: %d" % len(log))
#naive_part = NaivePartitioning(list(logd.values()))
#interval_part = IntervalPartitioning(dpn, naive_part.representatives())
i = 0
ts = []
for t in log:
tp = preprocess_trace(t, dpn)
if not tp in ts:
log1 = pm4py.filter_log(lambda x: x == t, log)
print(len(log1), i)
xes_exporter.apply(
log1, 'data/hospital_billing/single_traces/' + str(i) + '.xes')
i += 1
ts.append(tp)
def __inductive_miner_internal(log,
dfg,
threshold,
root,
act_key,
use_msd,
remove_noise=False):
alphabet = pm4py.get_event_attribute_values(log, act_key)
if threshold > 0 and remove_noise:
end_activities = get_ends.get_end_activities(
log,
parameters={constants.PARAMETER_CONSTANT_ACTIVITY_KEY: act_key})
dfg = __filter_dfg_on_threshold(dfg, end_activities, threshold)
original_length = len(log)
log = pm4py.filter_log(lambda t: len(t) > 0, log)
# revised EMPTYSTRACES
if original_length - len(log) > original_length * threshold:
return __add_operator_recursive_logs(
pt.ProcessTree(pt.Operator.XOR, root), threshold, act_key,
[EventLog(), log], use_msd)
start_activities = get_starters.get_start_activities(
log, parameters={constants.PARAMETER_CONSTANT_ACTIVITY_KEY: act_key})
end_activities = get_ends.get_end_activities(
log, parameters={constants.PARAMETER_CONSTANT_ACTIVITY_KEY: act_key})
if __is_base_case_act(log, act_key) or __is_base_case_silent(log):
return __apply_base_case(log, root, act_key)
pre, post = dfg_utils.get_transitive_relations(dfg, alphabet)
cut = sequence_cut.detect(alphabet, pre, post)
if cut is not None:
return __add_operator_recursive_logs(
pt.ProcessTree(pt.Operator.SEQUENCE, root), threshold, act_key,
sequence_cut.project(log, cut, act_key), use_msd)
cut = xor_cut.detect(dfg, alphabet)
if cut is not None:
return __add_operator_recursive_logs(
pt.ProcessTree(pt.Operator.XOR, root), threshold, act_key,
xor_cut.project(log, cut, act_key), use_msd)
cut = concurrent_cut.detect(
dfg,
alphabet,
start_activities,
end_activities,
msd=msdw_algo.derive_msd_witnesses(
log,
msd_algo.apply(log,
parameters={
constants.PARAMETER_CONSTANT_ACTIVITY_KEY:
act_key
}),
parameters={constants.PARAMETER_CONSTANT_ACTIVITY_KEY: act_key})
if use_msd else None)
if cut is not None:
return __add_operator_recursive_logs(
pt.ProcessTree(pt.Operator.PARALLEL, root), threshold, act_key,
concurrent_cut.project(log, cut, act_key), use_msd)
cut = loop_cut.detect(dfg, alphabet, start_activities, end_activities)
if cut is not None:
return __add_operator_recursive_logs(
pt.ProcessTree(pt.Operator.LOOP, root), threshold, act_key,
loop_cut.project(log, cut, act_key), use_msd)
aopt = activity_once_per_trace.detect(log, alphabet, act_key)
if aopt is not None:
operator = pt.ProcessTree(operator=pt.Operator.PARALLEL, parent=root)
operator.children.append(
pt.ProcessTree(operator=None, parent=operator, label=aopt))
return __add_operator_recursive_logs(
operator, threshold, act_key,
activity_once_per_trace.project(log, aopt, act_key), use_msd)
act_conc = activity_concurrent.detect(log, alphabet, act_key, use_msd)
if act_conc is not None:
return __add_operator_recursive_logs(
pt.ProcessTree(pt.Operator.PARALLEL, root), threshold, act_key,
activity_concurrent.project(log, act_conc, act_key), use_msd)
stl = strict_tau_loop.detect(log, start_activities, end_activities,
act_key)
if stl is not None:
return __add_operator_recursive_logs(
pt.ProcessTree(pt.Operator.LOOP, root), threshold, act_key,
[stl, EventLog()], use_msd)
tl = tau_loop.detect(log, start_activities, act_key)
if tl is not None:
return __add_operator_recursive_logs(
pt.ProcessTree(pt.Operator.LOOP, root), threshold, act_key,
[tl, EventLog()], use_msd)
if threshold > 0 and not remove_noise:
return __inductive_miner(log,
dfg,
threshold,
root,
act_key,
use_msd,
remove_noise=True)
return __flower(alphabet, root)
def inductive_miner(log, dfg, threshold, root, act_key, use_msd):
alphabet = pm4py.get_attribute_values(log, act_key)
start_activities = get_starters.get_start_activities(
log, parameters={constants.PARAMETER_CONSTANT_ACTIVITY_KEY: act_key})
end_activities = get_ends.get_end_activities(
log, parameters={constants.PARAMETER_CONSTANT_ACTIVITY_KEY: act_key})
empty_traces = pm4py.filter_log(lambda trace: len(trace) == 0, log)
if len(empty_traces) == 0:
if _is_base_case_act(log, act_key) or _is_base_case_silent(log):
return _apply_base_case(log, root, act_key)
pre, post = dfg_utils.get_transitive_relations(dfg, alphabet)
cut = sequence_cut.detect(alphabet, pre, post)
if cut is not None:
return _add_operator_recursive(
pt.ProcessTree(pt.Operator.SEQUENCE, root), threshold, act_key,
sequence_cut.project(log, cut, act_key), use_msd)
cut = xor_cut.detect(dfg, alphabet)
if cut is not None:
return _add_operator_recursive(
pt.ProcessTree(pt.Operator.XOR, root), threshold, act_key,
xor_cut.project(log, cut, act_key), use_msd)
cut = concurrent_cut.detect(
dfg,
alphabet,
start_activities,
end_activities,
msd=msdw_algo.derive_msd_witnesses(
log,
msd_algo.apply(log,
parameters={
constants.PARAMETER_CONSTANT_ACTIVITY_KEY:
act_key
}),
parameters={
constants.PARAMETER_CONSTANT_ACTIVITY_KEY: act_key
}) if use_msd else None)
if cut is not None:
return _add_operator_recursive(
pt.ProcessTree(pt.Operator.PARALLEL, root), threshold, act_key,
concurrent_cut.project(log, cut, act_key), use_msd)
cut = loop_cut.detect(dfg, alphabet, start_activities, end_activities)
if cut is not None:
return _add_operator_recursive(
pt.ProcessTree(pt.Operator.LOOP, root), threshold, act_key,
loop_cut.project(log, cut, act_key), use_msd)
if len(empty_traces) > 0:
nempty = pm4py.filter_log(lambda t: len(t) > 0, log)
return _add_operator_recursive(pt.ProcessTree(pt.Operator.XOR,
root), threshold,
act_key, [EventLog(), nempty], use_msd)
aopt = activity_once_per_trace.detect(log, alphabet, act_key)
if aopt is not None:
operator = pt.ProcessTree(operator=pt.Operator.PARALLEL, parent=root)
operator.children.append(
pt.ProcessTree(operator=None, parent=operator, label=aopt))
return _add_operator_recursive(
operator, threshold, act_key,
activity_once_per_trace.project(log, aopt, act_key), use_msd)
act_conc = activity_concurrent.detect(log, alphabet, act_key, use_msd)
if act_conc is not None:
return _add_operator_recursive(
pt.ProcessTree(pt.Operator.PARALLEL, root), threshold, act_key,
activity_concurrent.project(log, act_conc, act_key), use_msd)
stl = strict_tau_loop.detect(log, start_activities, end_activities,
act_key)
if stl is not None:
return _add_operator_recursive(pt.ProcessTree(pt.Operator.LOOP,
root), threshold,
act_key, [stl, EventLog()], use_msd)
tl = tau_loop.detect(log, start_activities, act_key)
if tl is not None:
return _add_operator_recursive(pt.ProcessTree(pt.Operator.LOOP,
root), threshold,
act_key, [tl, EventLog()], use_msd)
return _flower(alphabet, root)