def initialize_tree(self,
dfg,
log,
initial_dfg,
activities,
second_iteration=False,
end_call=True,
parameters=None):
"""
Initialize the tree
Parameters
-----------
dfg
Directly follows graph of this subtree
log
the event log_skeleton
initial_dfg
Referral directly follows graph that should be taken in account adding hidden/loop transitions
activities
Activities of this subtree
second_iteration
Boolean that indicates if we are executing this method for the second time
"""
self.second_iteration = second_iteration
if activities is None:
self.activities = get_activities_from_dfg(dfg)
else:
self.activities = copy(activities)
if second_iteration:
self.dfg = clean_dfg_based_on_noise_thresh(self.dfg,
self.activities,
self.noise_threshold)
else:
self.dfg = copy(dfg)
self.initial_dfg = initial_dfg
self.outgoing = get_outgoing_edges(self.dfg)
self.ingoing = get_ingoing_edges(self.dfg)
self.self_loop_activities = get_activities_self_loop(self.dfg)
self.initial_outgoing = get_outgoing_edges(self.initial_dfg)
self.initial_ingoing = get_ingoing_edges(self.initial_dfg)
self.negated_dfg = negate(self.dfg)
self.negated_activities = get_activities_from_dfg(self.negated_dfg)
self.negated_outgoing = get_outgoing_edges(self.negated_dfg)
self.negated_ingoing = get_ingoing_edges(self.negated_dfg)
self.detected_cut = None
self.children = []
self.log = log
self.original_log = log
self.parameters = parameters
self.detect_cut(second_iteration=False, parameters=parameters)
def apply(dfg, parameters=None):
"""
Clean Directly-Follows graph based on noise threshold
Parameters
-----------
dfg
Directly-Follows graph
parameters
Possible parameters of the algorithm, including:
noiseThreshold -> Threshold of noise in the algorithm
Returns
----------
newDfg
Cleaned dfg based on noise threshold
"""
if parameters is None:
parameters = {}
noise_threshold = parameters[
"noiseThreshold"] if "noiseThreshold" in parameters else filtering_constants.DEFAULT_NOISE_THRESH_DF
activities = get_activities_from_dfg(dfg)
return clean_dfg_based_on_noise_thresh(dfg, activities, noise_threshold)
def apply(dfg,
log=None,
parameters=None,
activities_count=None,
measure="frequency"):
if parameters is None:
parameters = {}
activity_key = parameters[
PARAMETER_CONSTANT_ACTIVITY_KEY] if PARAMETER_CONSTANT_ACTIVITY_KEY in parameters else xes.DEFAULT_NAME_KEY
image_format = "png"
max_no_of_edges_in_diagram = 75
if "format" in parameters:
image_format = parameters["format"]
if "maxNoOfEdgesInDiagram" in parameters:
max_no_of_edges_in_diagram = parameters["maxNoOfEdgesInDiagram"]
if activities_count is None:
if log is not None:
activities_count = attributes_filter.get_attribute_values(
log, activity_key, parameters=parameters)
else:
activities = dfg_utils.get_activities_from_dfg(dfg)
activities_count = {key: 1 for key in activities}
return graphviz_visualization(
activities_count,
dfg,
image_format=image_format,
measure=measure,
max_no_of_edges_in_diagram=max_no_of_edges_in_diagram)
def apply(dfg, parameters=None):
"""
Applies the DFG mining on a given object (if it is a Pandas dataframe or a log, the DFG is calculated)
Parameters
-------------
dfg
Object (DFG) (if it is a Pandas dataframe or a log, the DFG is calculated)
parameters
Parameters
"""
if parameters is None:
parameters = {}
dfg = dfg
start_activities = parameters[
PARAM_KEY_START_ACTIVITIES] if PARAM_KEY_START_ACTIVITIES in parameters else dfg_utils.infer_start_activities(
dfg)
end_activities = parameters[
PARAM_KEY_END_ACTIVITIES] if PARAM_KEY_END_ACTIVITIES in parameters else dfg_utils.infer_end_activities(
dfg)
activities = dfg_utils.get_activities_from_dfg(dfg)
net = PetriNet("")
im = Marking()
fm = Marking()
source = PetriNet.Place("source")
net.places.add(source)
im[source] = 1
sink = PetriNet.Place("sink")
net.places.add(sink)
fm[sink] = 1
places_corr = {}
index = 0
for act in activities:
places_corr[act] = PetriNet.Place(act)
net.places.add(places_corr[act])
for act in start_activities:
if act in places_corr:
index = index + 1
trans = PetriNet.Transition(act + "_" + str(index), act)
net.transitions.add(trans)
add_arc_from_to(source, trans, net)
add_arc_from_to(trans, places_corr[act], net)
for act in end_activities:
if act in places_corr:
index = index + 1
inv_trans = PetriNet.Transition(act + "_" + str(index), None)
net.transitions.add(inv_trans)
add_arc_from_to(places_corr[act], inv_trans, net)
add_arc_from_to(inv_trans, sink, net)
for el in dfg.keys():
act1 = el[0]
act2 = el[1]
index = index + 1
trans = PetriNet.Transition(act2 + "_" + str(index), act2)
net.transitions.add(trans)
add_arc_from_to(places_corr[act1], trans, net)
add_arc_from_to(trans, places_corr[act2], net)
return net, im, fm
def __init__(self,
frequency_dfg,
activities=None,
start_activities=None,
end_activities=None,
activities_occurrences=None,
default_edges_color="#000000",
performance_dfg=None,
net_name=DEFAULT_NET_NAME):
"""
Initialize an Hueristics Net
The implementation is based on the original paper on Heuristics Miner, namely:
Weijters, A. J. M. M., Wil MP van Der Aalst, and AK Alves De Medeiros.
"Process mining with the heuristics miner-algorithm."
Technische Universiteit Eindhoven, Tech. Rep. WP 166 (2006): 1-34.
and it manages to calculate the dependency matrix, the loops of length one and two, and
the AND measure
Parameters
-------------
frequency_dfg
Directly-Follows graph (frequency)
activities
Activities
start_activities
Start activities
end_activities
End activities
activities_occurrences
Activities occurrences
default_edges_color
(If provided) Default edges color
performance_dfg
Performance DFG
net_name
(If provided) name of the heuristics net
"""
self.net_name = [net_name]
self.nodes = {}
self.dependency_matrix = {}
self.dfg_matrix = {}
self.dfg = frequency_dfg
self.performance_dfg = performance_dfg
self.node_type = "frequency" if self.performance_dfg is None else "performance"
self.activities = activities
if self.activities is None:
self.activities = dfg_utils.get_activities_from_dfg(frequency_dfg)
if start_activities is None:
self.start_activities = [
dfg_utils.infer_start_activities(frequency_dfg)
]
else:
self.start_activities = [start_activities]
if end_activities is None:
self.end_activities = [
dfg_utils.infer_end_activities(frequency_dfg)
]
else:
self.end_activities = [end_activities]
self.activities_occurrences = activities_occurrences
if self.activities_occurrences is None:
self.activities_occurrences = {}
for act in self.activities:
self.activities_occurrences[
act] = dfg_utils.sum_activities_count(
frequency_dfg, [act])
self.default_edges_color = [default_edges_color]
