def start_activities(log):
log_start = start_activities_filter.get_start_activities(log)
n_unique_start_activities = len(log_start)
start_activities_occurrences = list(log_start.values())
start_activities_min = np.min(start_activities_occurrences)
start_activities_max = np.max(start_activities_occurrences)
start_activities_mean = np.mean(start_activities_occurrences)
start_activities_median = np.median(start_activities_occurrences)
start_activities_std = np.std(start_activities_occurrences)
start_activities_variance = np.var(start_activities_occurrences)
start_activities_q1 = np.percentile(start_activities_occurrences, 25)
start_activities_q3 = np.percentile(start_activities_occurrences, 75)
start_activities_iqr = stats.iqr(start_activities_occurrences)
start_activities_skewness = stats.skew(start_activities_occurrences)
start_activities_kurtosis = stats.kurtosis(start_activities_occurrences)
return [
n_unique_start_activities,
start_activities_min,
start_activities_max,
start_activities_mean,
start_activities_median,
start_activities_std,
start_activities_variance,
start_activities_q1,
start_activities_q3,
start_activities_iqr,
start_activities_skewness,
start_activities_kurtosis,
]
def test_17(self):
from pm4py.algo.filtering.pandas.start_activities import start_activities_filter
dataframe = self.load_running_example_df()
log_start = start_activities_filter.get_start_activities(dataframe)
df_start_activities = start_activities_filter.apply(dataframe, ["register request"],
parameters={
start_activities_filter.Parameters.CASE_ID_KEY: "case:concept:name",
start_activities_filter.Parameters.ACTIVITY_KEY: "concept:name"})
def apply(log, parameters):
"""
Apply the IMDF algorithm to a log obtaining a Petri net along with an initial and final marking
Parameters
-----------
log
Log
parameters
Parameters of the algorithm, including:
pmutil.constants.PARAMETER_CONSTANT_ACTIVITY_KEY -> attribute of the log to use as activity name
(default concept:name)
Returns
-----------
net
Petri net
initial_marking
Initial marking
final_marking
Final marking
"""
if parameters is None:
parameters = {}
if pmutil.constants.PARAMETER_CONSTANT_ACTIVITY_KEY not in parameters:
parameters[pmutil.constants.PARAMETER_CONSTANT_ACTIVITY_KEY] = xes_util.DEFAULT_NAME_KEY
if pmutil.constants.PARAMETER_CONSTANT_ATTRIBUTE_KEY not in parameters:
parameters[pmutil.constants.PARAMETER_CONSTANT_ATTRIBUTE_KEY] = parameters[
pmutil.constants.PARAMETER_CONSTANT_ACTIVITY_KEY]
activity_key = parameters[pmutil.constants.PARAMETER_CONSTANT_ACTIVITY_KEY]
# get the DFG
dfg = [(k, v) for k, v in dfg_inst.apply(log, parameters={
pmutil.constants.PARAMETER_CONSTANT_ACTIVITY_KEY: activity_key}).items() if v > 0]
# get the activities in the log
activities = attributes_filter.get_attribute_values(log, activity_key)
# gets the start activities from the log
start_activities = list(start_activities_filter.get_start_activities(log, parameters=parameters).keys())
# gets the end activities from the log
end_activities = list(end_activities_filter.get_end_activities(log, parameters=parameters).keys())
# check if the log contains empty traces
contains_empty_traces = False
traces_length = [len(trace) for trace in log]
if traces_length:
contains_empty_traces = min([len(trace) for trace in log]) == 0
net, initial_marking, final_marking = apply_dfg(dfg, parameters=parameters, activities=activities,
contains_empty_traces=contains_empty_traces,
start_activities=start_activities, end_activities=end_activities)
return net, initial_marking, final_marking
def apply(log, parameters=None):
"""
Gets the performance HNet
Parameters
------------
log
Log
parameters
Parameters of the algorithm
Returns
------------
base64
Base64 of an SVG representing the model
model
Text representation of the model
format
Format of the model
"""
if parameters is None:
parameters = {}
decreasingFactor = parameters[
"decreasingFactor"] if "decreasingFactor" in parameters else constants.DEFAULT_DEC_FACTOR
activity_key = parameters[pm4_constants.PARAMETER_CONSTANT_ACTIVITY_KEY] if pm4_constants.PARAMETER_CONSTANT_ACTIVITY_KEY in parameters else xes.DEFAULT_NAME_KEY
log = attributes_filter.filter_log_on_max_no_activities(log, max_no_activities=constants.MAX_NO_ACTIVITIES,
parameters=parameters)
filtered_log = auto_filter.apply_auto_filter(log, parameters=parameters)
activities_count = attributes_filter.get_attribute_values(filtered_log, activity_key)
start_activities_count = start_activities_filter.get_start_activities(filtered_log, parameters=parameters)
end_activities_count = end_activities_filter.get_end_activities(filtered_log, parameters=parameters)
activities = list(activities_count.keys())
start_activities = list(start_activities_count.keys())
end_activities = list(end_activities_count.keys())
dfg_freq = dfg_factory.apply(filtered_log, parameters=parameters)
dfg_perf = dfg_factory.apply(filtered_log, variant="performance", parameters=parameters)
heu_net = HeuristicsNet(dfg_freq, performance_dfg=dfg_perf, activities=activities, start_activities=start_activities, end_activities=end_activities, activities_occurrences=activities_count)
heu_net.calculate(dfg_pre_cleaning_noise_thresh=constants.DEFAULT_DFG_CLEAN_MULTIPLIER * decreasingFactor)
vis = heu_vis_factory.apply(heu_net, parameters={"format": "svg"})
vis2 = heu_vis_factory.apply(heu_net, parameters={"format": "dot"})
gviz_base64 = get_base64_from_file(vis2.name)
return get_base64_from_file(vis.name), None, "", "xes", activities, start_activities, end_activities, gviz_base64, [], "heuristics", "perf", None, "", activity_key
def get_start_activities(self, parameters=None):
"""
Gets the start activities from the log
Returns
------------
start_activities_dict
Dictionary of start activities
"""
if parameters is None:
parameters = {}
parameters[constants.PARAMETER_CONSTANT_ACTIVITY_KEY] = self.activity_key
parameters[constants.PARAMETER_CONSTANT_ATTRIBUTE_KEY] = self.activity_key
return start_activities_filter.get_start_activities(self.log, parameters=parameters)
def apply_heu(log, parameters=None):
"""
Discovers an Heuristics Net using Heuristics Miner
Parameters
------------
log
Event log
parameters
Possible parameters of the algorithm,
including: activity_key, case_id_glue, timestamp_key,
dependency_thresh, and_measure_thresh, min_act_count, min_dfg_occurrences, dfg_pre_cleaning_noise_thresh,
loops_length_two_thresh
Returns
------------
heu
Heuristics Net
"""
if parameters is None:
parameters = {}
activity_key = parameters[
constants.
PARAMETER_CONSTANT_ACTIVITY_KEY] if constants.PARAMETER_CONSTANT_ACTIVITY_KEY in parameters else xes.DEFAULT_NAME_KEY
start_activities = log_sa_filter.get_start_activities(
log, parameters=parameters)
end_activities = log_ea_filter.get_end_activities(log,
parameters=parameters)
activities_occurrences = log_attributes.get_attribute_values(
log, activity_key, parameters=parameters)
activities = list(activities_occurrences.keys())
dfg = dfg_factory.apply(log, parameters=parameters)
parameters_w2 = deepcopy(parameters)
parameters_w2["window"] = 2
dfg_window_2 = dfg_factory.apply(log, parameters=parameters_w2)
freq_triples = dfg_factory.apply(log,
parameters=parameters,
variant="freq_triples")
return apply_heu_dfg(dfg,
activities=activities,
activities_occurrences=activities_occurrences,
start_activities=start_activities,
end_activities=end_activities,
dfg_window_2=dfg_window_2,
freq_triples=freq_triples,
parameters=parameters)
def apply_tree(log, parameters):
"""
Apply the IMDF algorithm to a log obtaining a process tree
Parameters
----------
log
Log
parameters
Parameters of the algorithm, including:
pmutil.constants.PARAMETER_CONSTANT_ACTIVITY_KEY -> attribute of the log to use as activity name
(default concept:name)
Returns
----------
tree
Process tree
"""
if parameters is None:
parameters = {}
if pmutil.constants.PARAMETER_CONSTANT_ACTIVITY_KEY not in parameters:
parameters[pmutil.constants.PARAMETER_CONSTANT_ACTIVITY_KEY] = xes_util.DEFAULT_NAME_KEY
activity_key = parameters[pmutil.constants.PARAMETER_CONSTANT_ACTIVITY_KEY]
# get the DFG
dfg = [(k, v) for k, v in dfg_inst.apply(log, parameters={
pmutil.constants.PARAMETER_CONSTANT_ACTIVITY_KEY: activity_key}).items() if v > 0]
# gets the start activities from the log
start_activities = start_activities_filter.get_start_activities(log, parameters=parameters)
# gets the end activities from the log
end_activities = end_activities_filter.get_end_activities(log, parameters=parameters)
# get the activities in the log
activities = attributes_filter.get_attribute_values(log, activity_key)
# check if the log contains empty traces
contains_empty_traces = False
traces_length = [len(trace) for trace in log]
if traces_length:
contains_empty_traces = min([len(trace) for trace in log]) == 0
return apply_tree_dfg(dfg, parameters, activities=activities, contains_empty_traces=contains_empty_traces,
start_activities=start_activities, end_activities=end_activities)
def read_xes(data_dir, dataset, aggregate_type, mode="pruning"):
prune_parameter_freq = 350
prune_parameter_time = -1 #keep all
#read the xes file
if dataset in "BPIC14":
# log = csv_importer.import_event_stream(os.path.join(data_dir, dataset + ".csv"))
data = csv_import_adapter.import_dataframe_from_path(os.path.join(
data_dir, dataset + ".csv"),
sep=";")
data['case:concept:name'] = data['Incident ID']
data['time:timestamp'] = data['DateStamp']
data['concept:name'] = data['IncidentActivity_Type']
log = conversion_factory.apply(data)
elif dataset == "Unrineweginfectie":
data = csv_import_adapter.import_dataframe_from_path(os.path.join(
data_dir, dataset + ".csv"),
sep=",")
data['case:concept:name'] = data['Patientnummer']
data['time:timestamp'] = data['Starttijd']
data['concept:name'] = data['Aciviteit']
log = conversion_factory.apply(data)
else:
log = xes_import_factory.apply(os.path.join(data_dir,
dataset + ".xes"))
data = get_dataframe_from_event_stream(log)
# dataframe = log_converter.apply(log, variant=log_converter.Variants.TO_DATA_FRAME)
# dfg_freq = dfg_factory.apply(log,variant="frequency")
# dfg_time =get_dfg_time(data,aggregate_type,dataset)
if aggregate_type == AggregateType.FREQ:
dfg = dfg_factory.apply(log, variant="frequency")
else:
dfg = get_dfg_time(data, aggregate_type, dataset)
"""Getting Start and End activities"""
# log = xes_importer.import_log(xes_file)
log_start = start_activities_filter.get_start_activities(log)
log_end = end_activities_filter.get_end_activities(log)
# return dfg_freq,dfg_time
return dfg
def apply(log, parameters=None):
"""
Gets the process tree using Inductive Miner Directly-Follows
Parameters
------------
log
Log
parameters
Parameters of the algorithm
Returns
------------
base64
Base64 of an SVG representing the model
model
Text representation of the model
format
Format of the model
"""
if parameters is None:
parameters = {}
decreasingFactor = parameters[
"decreasingFactor"] if "decreasingFactor" in parameters else constants.DEFAULT_DEC_FACTOR
activity_key = parameters[
pm4_constants.
PARAMETER_CONSTANT_ACTIVITY_KEY] if pm4_constants.PARAMETER_CONSTANT_ACTIVITY_KEY in parameters else xes.DEFAULT_NAME_KEY
log = attributes_filter.filter_log_on_max_no_activities(
log,
max_no_activities=constants.MAX_NO_ACTIVITIES,
parameters=parameters)
filtered_log = auto_filter.apply_auto_filter(log, parameters=parameters)
activities_count = attributes_filter.get_attribute_values(
filtered_log, activity_key)
activities = list(activities_count.keys())
start_activities = list(
start_activities_filter.get_start_activities(
filtered_log, parameters=parameters).keys())
end_activities = list(
end_activities_filter.get_end_activities(filtered_log,
parameters=parameters).keys())
dfg = dfg_factory.apply(filtered_log, parameters=parameters)
dfg = clean_dfg_based_on_noise_thresh(
dfg,
activities,
decreasingFactor * constants.DEFAULT_DFG_CLEAN_MULTIPLIER,
parameters=parameters)
tree = inductive_miner.apply_tree_dfg(dfg,
parameters=parameters,
activities=activities,
start_activities=start_activities,
end_activities=end_activities)
parameters["format"] = "svg"
gviz = pt_vis_factory.apply(tree, parameters=parameters)
gviz_base64 = base64.b64encode(str(gviz).encode('utf-8'))
return get_base64_from_gviz(gviz), None, "", "xes", activities, start_activities, end_activities, gviz_base64, [], "tree", "freq", None, "", activity_key
def apply(log, net, marking, final_marking, parameters=None):
"""
Get Align-ET Conformance precision
Parameters
----------
log
Trace log
net
Petri net
marking
Initial marking
final_marking
Final marking
parameters
Parameters of the algorithm, including:
pm4py.util.constants.PARAMETER_CONSTANT_ACTIVITY_KEY -> Activity key
"""
if parameters is None:
parameters = {}
debug_level = parameters[
"debug_level"] if "debug_level" in parameters else 0
activity_key = parameters[
PARAM_ACTIVITY_KEY] if PARAM_ACTIVITY_KEY in parameters else log_lib.util.xes.DEFAULT_NAME_KEY
# default value for precision, when no activated transitions (not even by looking at the initial marking) are found
precision = 1.0
sum_ee = 0
sum_at = 0
unfit = 0
if not petri.check_soundness.check_relaxed_soundness_net_in_fin_marking(
net, marking, final_marking):
raise Exception(
"trying to apply Align-ETConformance on a Petri net that is not a relaxed sound net!!"
)
prefixes, prefix_count = precision_utils.get_log_prefixes(
log, activity_key=activity_key)
prefixes_keys = list(prefixes.keys())
fake_log = precision_utils.form_fake_log(prefixes_keys,
activity_key=activity_key)
align_stop_marking = align_fake_log_stop_marking(fake_log,
net,
marking,
final_marking,
parameters=parameters)
all_markings = transform_markings_from_sync_to_original_net(
align_stop_marking, net, parameters=parameters)
for i in range(len(prefixes)):
markings = all_markings[i]
if markings is not None:
log_transitions = set(prefixes[prefixes_keys[i]])
activated_transitions_labels = set()
for m in markings:
# add to the set of activated transitions in the model the activated transitions
# for each prefix
activated_transitions_labels = activated_transitions_labels.union(
x.label for x in utils.
get_visible_transitions_eventually_enabled_by_marking(
net, m) if x.label is not None)
escaping_edges = activated_transitions_labels.difference(
log_transitions)
sum_at += len(activated_transitions_labels) * prefix_count[
prefixes_keys[i]]
sum_ee += len(escaping_edges) * prefix_count[prefixes_keys[i]]
if debug_level > 1:
print("")
print("prefix=", prefixes_keys[i])
print("log_transitions=", log_transitions)
print("activated_transitions=", activated_transitions_labels)
print("escaping_edges=", escaping_edges)
else:
unfit += prefix_count[prefixes_keys[i]]
if debug_level > 0:
print("\n")
print("overall unfit", unfit)
print("overall activated transitions", sum_at)
print("overall escaping edges", sum_ee)
# fix: also the empty prefix should be counted!
start_activities = set(
start_activities_filter.get_start_activities(log,
parameters=parameters))
trans_en_ini_marking = set([
x.label for x in get_visible_transitions_eventually_enabled_by_marking(
net, marking)
])
diff = trans_en_ini_marking.difference(start_activities)
sum_at += len(log) * len(trans_en_ini_marking)
sum_ee += len(log) * len(diff)
# end fix
if sum_at > 0:
precision = 1 - float(sum_ee) / float(sum_at)
return precision
parameters={
"sort": True,
"sort_field":
"time:timestamp"
})
log = conversion_factory.apply(event_stream,
parameters={"timestamp_sort": True})
####### Filter the event log
## Start activities
from pm4py.algo.filtering.log.start_activities import start_activities_filter
log_start = start_activities_filter.get_start_activities(log)
log = start_activities_filter.apply_auto_filter(
log, parameters={"decreasingFactor": 0.6})
print(start_activities_filter.get_start_activities(log))
## End activities
from pm4py.algo.filtering.log.end_activities import end_activities_filter
log_end = end_activities_filter.get_end_activities(log)
log_af_ea = end_activities_filter.apply_auto_filter(
log, parameters={"decreasingFactor": 0.6})
print(end_activities_filter.get_end_activities(log_af_ea))
def test_16(self):
from pm4py.algo.filtering.log.start_activities import start_activities_filter
log = self.load_running_example_xes()
log_start = start_activities_filter.get_start_activities(log)
filtered_log = start_activities_filter.apply(log,
["register request"])
# print(rr)
# print(df)
# print(type(df['org:resource'][5]))
# df = pd.read_csv("not_so_good_data.csv")
# df['org:resource'] = df['org:resource'].astype(str)
from pm4py.objects.conversion.log import factory as log_conv_factory
conv_log = log_conv_factory.apply(df)
print(len(conv_log))
print(conv_log)
from pm4py.objects.log.util import sorting
sorted_log = sorting.sort_lambda(conv_log,
lambda x: x.attributes["concept:name"],
reverse=False)
from pm4py.algo.filtering.log.start_activities import start_activities_filter
log_start = start_activities_filter.get_start_activities(sorted_log)
filtered_log = start_activities_filter.apply(sorted_log, ["A"])
# print(rrr)
# from pm4py.algo.discovery.simple.model.log import factory as simple_algorithm
# net, initial_marking, final_marking = simple_algorithm.apply(conv_log, classic_output=True, parameters={"max_no_variants": 20})
# gviz = pn_vis_factory.apply(net, im, fm)
# pn_vis_factory.view(gviz)
# print(ooo)
from pm4py.algo.discovery.alpha import factory as alpha_miner
# the same exact discovery technique can be applied directly to Pandas dataframes! :)
from pm4py.algo.discovery.inductive import factory as inductive_miner
# discovers an accepting Petri net
net, im, fm = inductive_miner.apply(filtered_log)
tree = inductive_miner.apply_tree(filtered_log)
def detect_cut(self, second_iteration=False, parameters=None):
if pkgutil.find_loader("networkx"):
import networkx as nx
if parameters is None:
parameters = {}
activity_key = exec_utils.get_param_value(
Parameters.ACTIVITY_KEY, parameters,
pmutil.xes_constants.DEFAULT_NAME_KEY)
# check base cases:
empty_log = base_case.empty_log(self.log)
single_activity = base_case.single_activity(self.log, activity_key)
if empty_log:
self.detected_cut = 'empty_log'
elif single_activity:
self.detected_cut = 'single_activity'
# if no base cases are found, search for a cut:
else:
conn_components = detection_utils.get_connected_components(
self.ingoing, self.outgoing, self.activities)
this_nx_graph = transform_dfg_to_directed_nx_graph(
self.dfg, activities=self.activities)
strongly_connected_components = [
list(x)
for x in nx.strongly_connected_components(this_nx_graph)
]
xor_cut = self.detect_xor(conn_components)
# the following part searches for a cut in the current log_skeleton
# if a cut is found, the log_skeleton is split according to the cut, the resulting logs are saved in new_logs
# recursion is used on all the logs in new_logs
if xor_cut[0]:
logging.debug("xor_cut")
self.detected_cut = 'concurrent'
new_logs = split.split_xor(xor_cut[1], self.log,
activity_key)
for i in range(len(new_logs)):
new_logs[
i] = filtering_utils.keep_one_trace_per_variant(
new_logs[i], parameters=parameters)
for l in new_logs:
new_dfg = [(k, v) for k, v in dfg_inst.apply(
l, parameters=parameters).items() if v > 0]
activities = attributes_filter.get_attribute_values(
l, activity_key)
start_activities = list(
start_activities_filter.get_start_activities(
l, parameters=parameters).keys())
end_activities = list(
end_activities_filter.get_end_activities(
l, parameters=parameters).keys())
self.children.append(
SubtreePlain(l,
new_dfg,
self.master_dfg,
self.initial_dfg,
activities,
self.counts,
self.rec_depth + 1,
noise_threshold=self.noise_threshold,
start_activities=start_activities,
end_activities=end_activities,
initial_start_activities=self.
initial_start_activities,
initial_end_activities=self.
initial_end_activities,
parameters=parameters))
else:
sequence_cut = cut_detection.detect_sequential_cut(
self, self.dfg, strongly_connected_components)
if sequence_cut[0]:
logging.debug("sequence_cut")
new_logs = split.split_sequence(
sequence_cut[1], self.log, activity_key)
for i in range(len(new_logs)):
new_logs[
i] = filtering_utils.keep_one_trace_per_variant(
new_logs[i], parameters=parameters)
self.detected_cut = "sequential"
for l in new_logs:
new_dfg = [(k, v) for k, v in dfg_inst.apply(
l, parameters=parameters).items() if v > 0]
activities = attributes_filter.get_attribute_values(
l, activity_key)
start_activities = list(
start_activities_filter.get_start_activities(
l, parameters=parameters).keys())
end_activities = list(
end_activities_filter.get_end_activities(
l, parameters=parameters).keys())
self.children.append(
SubtreePlain(
l,
new_dfg,
self.master_dfg,
self.initial_dfg,
activities,
self.counts,
self.rec_depth + 1,
noise_threshold=self.noise_threshold,
start_activities=start_activities,
end_activities=end_activities,
initial_start_activities=self.
initial_start_activities,
initial_end_activities=self.
initial_end_activities,
parameters=parameters))
else:
parallel_cut = self.detect_concurrent()
if parallel_cut[0]:
logging.debug("parallel_cut")
new_logs = split.split_parallel(
parallel_cut[1], self.log, activity_key)
for i in range(len(new_logs)):
new_logs[
i] = filtering_utils.keep_one_trace_per_variant(
new_logs[i], parameters=parameters)
self.detected_cut = "parallel"
for l in new_logs:
new_dfg = [(k, v) for k, v in dfg_inst.apply(
l, parameters=parameters).items() if v > 0]
activities = attributes_filter.get_attribute_values(
l, activity_key)
start_activities = list(
start_activities_filter.
get_start_activities(
l, parameters=parameters).keys())
end_activities = list(
end_activities_filter.get_end_activities(
l, parameters=parameters).keys())
self.children.append(
SubtreePlain(
l,
new_dfg,
self.master_dfg,
self.initial_dfg,
activities,
self.counts,
self.rec_depth + 1,
noise_threshold=self.noise_threshold,
start_activities=start_activities,
end_activities=end_activities,
initial_start_activities=self.
initial_start_activities,
initial_end_activities=self.
initial_end_activities,
parameters=parameters))
else:
loop_cut = self.detect_loop()
if loop_cut[0]:
logging.debug("loop_cut")
new_logs = split.split_loop(
loop_cut[1], self.log, activity_key)
for i in range(len(new_logs)):
new_logs[
i] = filtering_utils.keep_one_trace_per_variant(
new_logs[i], parameters=parameters)
self.detected_cut = "loopCut"
for l in new_logs:
new_dfg = [
(k, v) for k, v in dfg_inst.apply(
l, parameters=parameters).items()
if v > 0
]
activities = attributes_filter.get_attribute_values(
l, activity_key)
start_activities = list(
start_activities_filter.
get_start_activities(
l, parameters=parameters).keys())
end_activities = list(
end_activities_filter.
get_end_activities(
l, parameters=parameters).keys())
self.children.append(
SubtreePlain(
l,
new_dfg,
self.master_dfg,
self.initial_dfg,
activities,
self.counts,
self.rec_depth + 1,
noise_threshold=self.
noise_threshold,
start_activities=start_activities,
end_activities=end_activities,
initial_start_activities=self.
initial_start_activities,
initial_end_activities=self.
initial_end_activities,
parameters=parameters))
# if the code gets to this point, there is no base_case and no cut found in the log_skeleton
# therefore, we now apply fall through:
else:
self.apply_fall_through(parameters)
else:
msg = "networkx is not available. inductive miner cannot be used!"
logging.error(msg)
raise Exception(msg)
def apply(log, parameters=None, classic_output=False):
"""
Gets a simple model out of a log
Parameters
-------------
log
Trace log
parameters
Parameters of the algorithm, including:
maximum_number_activities -> Maximum number of activities to keep
discovery_algorithm -> Discovery algorithm to use (alpha, inductive)
desidered_output -> Desidered output of the algorithm (default: Petri)
include_filtered_log -> Include the filtered log in the output
include_dfg_frequency -> Include the DFG of frequencies in the output
include_dfg_performance -> Include the DFG of performance in the output
include_filtered_dfg_frequency -> Include the filtered DFG of frequencies in the output
include_filtered_dfg_performance -> Include the filtered DFG of performance in the output
classic_output
Determine if the output shall contains directly the objects (e.g. net, initial_marking, final_marking)
or can return a more detailed dictionary
"""
if parameters is None:
parameters = {}
returned_dictionary = {}
net = None
initial_marking = None
final_marking = None
bpmn_graph = None
dfg_frequency = None
dfg_performance = None
filtered_dfg_frequency = None
filtered_dfg_performance = None
maximum_number_activities = parameters[
"maximum_number_activities"] if "maximum_number_activities" in parameters else 20
discovery_algorithm = parameters["discovery_algorithm"] if "discovery_algorithm" in parameters else "alpha"
desidered_output = parameters["desidered_output"] if "desidered_output" in parameters else "petri"
include_filtered_log = parameters["include_filtered_log"] if "include_filtered_log" in parameters else True
include_dfg_frequency = parameters["include_dfg_frequency"] if "include_dfg_frequency" in parameters else True
include_dfg_performance = parameters[
"include_dfg_performance"] if "include_dfg_performance" in parameters else False
include_filtered_dfg_frequency = parameters[
"include_filtered_dfg_frequency"] if "include_filtered_dfg_frequency" in parameters else True
include_filtered_dfg_performance = parameters[
"include_filtered_dfg_performance"] if "include_filtered_dfg_performance" in parameters else False
if PARAMETER_CONSTANT_ATTRIBUTE_KEY in parameters:
activity_key = parameters[
PARAMETER_CONSTANT_ATTRIBUTE_KEY] if PARAMETER_CONSTANT_ATTRIBUTE_KEY in parameters else DEFAULT_NAME_KEY
parameters[PARAMETER_CONSTANT_ATTRIBUTE_KEY] = activity_key
else:
log, activity_key = insert_classifier.search_act_class_attr(log)
if activity_key is None:
activity_key = DEFAULT_NAME_KEY
parameters[PARAMETER_CONSTANT_ATTRIBUTE_KEY] = activity_key
if PARAMETER_CONSTANT_ACTIVITY_KEY not in parameters:
parameters[PARAMETER_CONSTANT_ACTIVITY_KEY] = parameters[PARAMETER_CONSTANT_ATTRIBUTE_KEY]
activities_count_dictio = attributes_filter.get_attribute_values(log, activity_key)
activities_count_list = []
for activity in activities_count_dictio:
activities_count_list.append([activity, activities_count_dictio[activity]])
activities_count_list = sorted(activities_count_list, key=lambda x: x[1], reverse=True)
activities_count_list = activities_count_list[:min(len(activities_count_list), maximum_number_activities)]
activities_keep_list = [x[0] for x in activities_count_list]
log = attributes_filter.apply(log, activities_keep_list, parameters=parameters)
filtered_log = None
if "alpha" in discovery_algorithm:
# parameters_sa = deepcopy(parameters)
# parameters_sa["decreasingFactor"] = 1.0
filtered_log = start_activities_filter.apply_auto_filter(log, parameters=parameters)
filtered_log = end_activities_filter.apply_auto_filter(filtered_log, parameters=parameters)
filtered_log = filter_topvariants_soundmodel.apply(filtered_log, parameters=parameters)
elif "dfg_mining" in discovery_algorithm:
filtered_log = start_activities_filter.apply_auto_filter(log, parameters=parameters)
filtered_log = end_activities_filter.apply_auto_filter(filtered_log, parameters=parameters)
filtered_log = auto_filter.apply_auto_filter(filtered_log, parameters=parameters)
if include_dfg_frequency or "dfg_mining" in discovery_algorithm:
dfg_frequency = dfg_factory.apply(log, parameters=parameters, variant="frequency")
if include_dfg_performance:
dfg_performance = dfg_factory.apply(log, parameters=parameters, variant="performance")
if include_filtered_dfg_frequency:
filtered_dfg_frequency = dfg_factory.apply(filtered_log, parameters=parameters, variant="frequency")
if include_filtered_dfg_performance:
filtered_dfg_performance = dfg_factory.apply(filtered_log, parameters=parameters, variant="performance")
if "alpha" in discovery_algorithm:
net, initial_marking, final_marking = alpha_miner.apply(filtered_log, parameters=parameters)
elif "dfg_mining" in discovery_algorithm:
start_activities = start_activities_filter.get_start_activities(filtered_log, parameters=parameters)
end_activities = end_activities_filter.get_end_activities(filtered_log, parameters=parameters)
parameters_conv = {}
parameters_conv["start_activities"] = start_activities
parameters_conv["end_activities"] = end_activities
net, initial_marking, final_marking = dfg_conv_factory.apply(dfg_frequency, parameters=parameters_conv)
if filtered_log is not None and include_filtered_log:
returned_dictionary["filtered_log"] = filtered_log
if net is not None and desidered_output == "petri":
returned_dictionary["net"] = net
if initial_marking is not None and desidered_output == "petri":
returned_dictionary["initial_marking"] = initial_marking
if final_marking is not None and desidered_output == "petri":
returned_dictionary["final_marking"] = final_marking
if bpmn_graph is not None and desidered_output == "bpmn":
returned_dictionary["bpmn_graph"] = bpmn_graph
if dfg_frequency is not None and include_dfg_frequency:
returned_dictionary["dfg_frequency"] = dfg_frequency
if dfg_performance is not None and include_dfg_performance:
returned_dictionary["dfg_performance"] = dfg_performance
if filtered_dfg_frequency is not None and include_filtered_dfg_frequency:
returned_dictionary["filtered_dfg_frequency"] = filtered_dfg_frequency
if filtered_dfg_performance is not None and include_filtered_dfg_performance:
returned_dictionary["filtered_dfg_performance"] = filtered_dfg_performance
if classic_output:
if net is not None and desidered_output == "petri":
return net, initial_marking, final_marking
return returned_dictionary
log_tree_num = 0
sum_tree_num = 0
print(tree)
tree_avg_tel = 0
tree_avg_log = 0
tree_avg_sum = 0
for sam in range(1, 11):
print(sam)
path = os.path.join("input_data", "df_complete_logs",
"%d_1000_%d.xes" % (tree, sam))
log = xes_importer.apply(path)
tel = xes_importer.apply(path)
xes_utils.set_enabled(tel)
dfg_100 = dfg_factory.apply(log)
start_act = set(get_start_activities(log).keys())
end_act = set(get_end_activities(log).keys())
result_norm = []
result_tel = []
num = len(dfg_100.keys())
score_tel = 0
score_log = 0
score_sum = 0
su_tel = 0
su_log = 0
su_sum = 0
for k in range(10):
found_tel = False
found_log = False
def apply_tree(log, parameters):
"""
Apply the IM_FF algorithm to a log obtaining a process tree
Parameters
----------
log
Log
parameters
Parameters of the algorithm, including:
Parameters.ACTIVITY_KEY -> attribute of the log to use as activity name
(default concept:name)
Returns
----------
process_tree
Process tree
"""
if parameters is None:
parameters = {}
if type(log) is pd.DataFrame:
vars = variants_get.get_variants_count(log, parameters=parameters)
return apply_tree_variants(vars, parameters=parameters)
else:
activity_key = exec_utils.get_param_value(
Parameters.ACTIVITY_KEY, parameters,
pmutil.xes_constants.DEFAULT_NAME_KEY)
log = converter.apply(log, parameters=parameters)
# keep only the activity attribute (since the others are not used)
log = filtering_utils.keep_only_one_attribute_per_event(
log, activity_key)
noise_threshold = exec_utils.get_param_value(
Parameters.NOISE_THRESHOLD, parameters,
shared_constants.NOISE_THRESHOLD_IMF)
dfg = [(k, v)
for k, v in dfg_inst.apply(log, parameters=parameters).items()
if v > 0]
c = Counts()
activities = attributes_filter.get_attribute_values(log, activity_key)
start_activities = list(
start_activities_filter.get_start_activities(
log, parameters=parameters).keys())
end_activities = list(
end_activities_filter.get_end_activities(
log, parameters=parameters).keys())
contains_empty_traces = False
traces_length = [len(trace) for trace in log]
if traces_length:
contains_empty_traces = min([len(trace) for trace in log]) == 0
# set the threshold parameter based on f and the max value in the dfg:
max_value = 0
for key, value in dfg:
if value > max_value:
max_value = value
threshold = noise_threshold * max_value
recursion_depth = 0
sub = subtree.make_tree(log,
dfg,
dfg,
dfg,
activities,
c,
recursion_depth,
noise_threshold,
threshold,
start_activities,
end_activities,
start_activities,
end_activities,
parameters=parameters)
process_tree = get_tree_repr_implain.get_repr(
sub, 0, contains_empty_traces=contains_empty_traces)
# Ensures consistency to the parent pointers in the process tree
tree_consistency.fix_parent_pointers(process_tree)
# Fixes a 1 child XOR that is added when single-activities flowers are found
tree_consistency.fix_one_child_xor_flower(process_tree)
# folds the process tree (to simplify it in case fallthroughs/filtering is applied)
process_tree = util.fold(process_tree)
return process_tree
def apply(log, net, marking, final_marking, parameters=None):
"""
Get Align-ET Conformance precision
Parameters
----------
log
Trace log
net
Petri net
marking
Initial marking
final_marking
Final marking
parameters
Parameters of the algorithm, including:
pm4py.util.constants.PARAMETER_CONSTANT_ACTIVITY_KEY -> Activity key
"""
if parameters is None:
parameters = {}
activity_key = parameters[
PARAM_ACTIVITY_KEY] if PARAM_ACTIVITY_KEY in parameters else log_lib.util.xes.DEFAULT_NAME_KEY
# default value for precision, when no activated transitions (not even by looking at the initial marking) are found
precision = 1.0
sum_ee = 0
sum_at = 0
if not (petri.check_soundness.check_wfnet(net) and
petri.check_soundness.check_relaxed_soundness_net_in_fin_marking(
net, marking, final_marking)):
raise Exception(
"trying to apply Align-ETConformance on a Petri net that is not a relaxed sound workflow net!!"
)
prefixes, prefix_count = precision_utils.get_log_prefixes(
log, activity_key=activity_key)
prefixes_keys = list(prefixes.keys())
fake_log = precision_utils.form_fake_log(prefixes_keys,
activity_key=activity_key)
align_stop_marking = align_fake_log_stop_marking(fake_log,
net,
marking,
final_marking,
parameters=parameters)
all_markings = transform_markings_from_sync_to_original_net(
align_stop_marking, net, parameters=parameters)
for i in range(len(all_markings)):
atm = all_markings[i]
log_transitions = set(prefixes[prefixes_keys[i]])
activated_transitions_labels = set(
x.label for x in utils.
get_visible_transitions_eventually_enabled_by_marking(net, atm)
if x.label is not None)
sum_at += len(activated_transitions_labels) * prefix_count[
prefixes_keys[i]]
escaping_edges = activated_transitions_labels.difference(
log_transitions)
sum_ee += len(escaping_edges) * prefix_count[prefixes_keys[i]]
# fix: also the empty prefix should be counted!
start_activities = set(
start_activities_filter.get_start_activities(log,
parameters=parameters))
trans_en_ini_marking = set([
x.label for x in get_visible_transitions_eventually_enabled_by_marking(
net, marking)
])
diff = trans_en_ini_marking.difference(start_activities)
sum_at += len(log) * len(trans_en_ini_marking)
sum_ee += len(log) * len(diff)
# end fix
if sum_at > 0:
precision = 1 - float(sum_ee) / float(sum_at)
return precision
def apply(log, net, marking, final_marking, parameters=None):
"""
Get ET Conformance precision
Parameters
----------
log
Trace log
net
Petri net
marking
Initial marking
final_marking
Final marking
parameters
Parameters of the algorithm, including:
pm4py.util.constants.PARAMETER_CONSTANT_ACTIVITY_KEY -> Activity key
"""
if parameters is None:
parameters = {}
cleaning_token_flood = parameters[
"cleaning_token_flood"] if "cleaning_token_flood" in parameters else False
activity_key = parameters[
PARAM_ACTIVITY_KEY] if PARAM_ACTIVITY_KEY in parameters else log_lib.util.xes.DEFAULT_NAME_KEY
# default value for precision, when no activated transitions (not even by looking at the initial marking) are found
precision = 1.0
sum_ee = 0
sum_at = 0
parameters_tr = {
"consider_remaining_in_fitness": False,
"try_to_reach_final_marking_through_hidden": False,
"stop_immediately_unfit": True,
"walk_through_hidden_trans": True,
"cleaning_token_flood": cleaning_token_flood,
PARAM_ACTIVITY_KEY: activity_key
}
prefixes, prefix_count = precision_utils.get_log_prefixes(
log, activity_key=activity_key)
prefixes_keys = list(prefixes.keys())
fake_log = precision_utils.form_fake_log(prefixes_keys,
activity_key=activity_key)
aligned_traces = token_replay.apply(fake_log,
net,
marking,
final_marking,
parameters=parameters_tr)
# fix: also the empty prefix should be counted!
start_activities = set(
start_activities_filter.get_start_activities(log,
parameters=parameters))
trans_en_ini_marking = set([
x.label for x in get_visible_transitions_eventually_enabled_by_marking(
net, marking)
])
diff = trans_en_ini_marking.difference(start_activities)
sum_at += len(log) * len(trans_en_ini_marking)
sum_ee += len(log) * len(diff)
# end fix
for i in range(len(aligned_traces)):
if aligned_traces[i]["trace_is_fit"]:
log_transitions = set(prefixes[prefixes_keys[i]])
activated_transitions_labels = set([
x.label
for x in aligned_traces[i]["enabled_transitions_in_marking"]
if x.label is not None
])
sum_at += len(activated_transitions_labels) * prefix_count[
prefixes_keys[i]]
escaping_edges = activated_transitions_labels.difference(
log_transitions)
sum_ee += len(escaping_edges) * prefix_count[prefixes_keys[i]]
if sum_at > 0:
precision = 1 - float(sum_ee) / float(sum_at)
return precision
def apply(log, parameters=None):
"""
Gets the Petri net through Inductive Miner, decorated by frequency metric
Parameters
------------
log
Log
parameters
Parameters of the algorithm
Returns
------------
base64
Base64 of an SVG representing the model
model
Text representation of the model
format
Format of the model
"""
if parameters is None:
parameters = {}
decreasingFactor = parameters[
"decreasingFactor"] if "decreasingFactor" in parameters else constants.DEFAULT_DEC_FACTOR
activity_key = parameters[
pm4_constants.
PARAMETER_CONSTANT_ACTIVITY_KEY] if pm4_constants.PARAMETER_CONSTANT_ACTIVITY_KEY in parameters else xes.DEFAULT_NAME_KEY
# reduce the depth of the search done by token-based replay
token_replay.MAX_REC_DEPTH = 1
token_replay.MAX_IT_FINAL1 = 1
token_replay.MAX_IT_FINAL2 = 1
token_replay.MAX_REC_DEPTH_HIDTRANSENABL = 1
log = attributes_filter.filter_log_on_max_no_activities(
log,
max_no_activities=constants.MAX_NO_ACTIVITIES,
parameters=parameters)
filtered_log = auto_filter.apply_auto_filter(log, parameters=parameters)
activities_count = attributes_filter.get_attribute_values(
filtered_log, activity_key)
activities = list(activities_count.keys())
start_activities = list(
start_activities_filter.get_start_activities(
filtered_log, parameters=parameters).keys())
end_activities = list(
end_activities_filter.get_end_activities(filtered_log,
parameters=parameters).keys())
dfg = dfg_factory.apply(filtered_log, parameters=parameters)
dfg = clean_dfg_based_on_noise_thresh(
dfg,
activities,
decreasingFactor * constants.DEFAULT_DFG_CLEAN_MULTIPLIER,
parameters=parameters)
net, im, fm = inductive_miner.apply_dfg(dfg,
parameters=parameters,
activities=activities,
start_activities=start_activities,
end_activities=end_activities)
parameters["format"] = "svg"
gviz = pn_vis_factory.apply(net,
im,
fm,
log=filtered_log,
variant="frequency",
parameters=parameters)
svg = get_base64_from_gviz(gviz)
gviz_base64 = base64.b64encode(str(gviz).encode('utf-8'))
ret_graph = get_graph.get_graph_from_petri(net, im, fm)
return svg, export_petri_as_string(
net, im, fm
), ".pnml", "xes", activities, start_activities, end_activities, gviz_base64, ret_graph, "inductive", "freq", None, "", activity_key
alpha_num = []
for tree in range(1, 11):
tel_tree_num = 0
log_tree_num = 0
print(tree)
tree_avg_tel = 0
tree_avg_log = 0
for sam in range(1, 11):
print(sam)
path = os.path.join("input_data", "df_complete_logs",
"%d_1000_%d.xes" % (tree, sam))
log = xes_importer.apply(path)
dfg_org = dfg_factory.apply(log)
start_act = set(get_start_activities(log).keys())
end_act = set(get_end_activities(log).keys())
alpha_path = os.path.join("input_data", "df_complete_logs",
"df_complete_alpha",
"%d_alpha_%d.xes" % (tree, sam))
alpha_log = xes_importer.apply(alpha_path)
num = len(dfg_org.keys())
score_tel = 0
su_tel = 0
for k in range(10):
for n in range(1, 1000):
sampled_log = sampling.sample_log(alpha_log, no_traces=n)
dfg_log = dfg_factory.apply(sampled_log)
def detect_loop(self):
# p0 is part of return value, it contains the partition of activities
# write all start and end activities in p1
if self.contains_empty_trace():
return [False, []]
start_activities = list(
start_activities_filter.get_start_activities(
self.log, parameters=self.parameters).keys())
end_activities = list(
end_activities_filter.get_end_activities(
self.log, parameters=self.parameters).keys())
p1 = []
for act in start_activities:
if act not in p1:
p1.append(act)
for act in end_activities:
if act not in p1:
p1.append(act)
# create new dfg without the transitions to start and end activities
new_dfg = copy(self.dfg)
copy_dfg = copy(new_dfg)
for ele in copy_dfg:
if ele[0][0] in p1 or ele[0][1] in p1:
new_dfg.remove(ele)
# get connected components of this new dfg
new_ingoing = get_ingoing_edges(new_dfg)
new_outgoing = get_outgoing_edges(new_dfg)
# it was a pain in the *** to get a working directory of the current_activities, as we can't iterate ove the dfg
current_activities = {}
for element in self.activities:
if element not in p1:
current_activities.update({element: 1})
p0 = detection_utils.get_connected_components(new_ingoing,
new_outgoing,
current_activities)
p0.insert(0, p1)
iterable_dfg = []
for i in range(0, len(self.dfg)):
iterable_dfg.append(self.dfg[i][0])
# p0 is like P1,P2,...,Pn in line 3 on page 190 of the IM Thesis
# check for subsets in p0 that have connections to and end or from a start activity
p0_copy = []
for int_el in p0:
p0_copy.append(int_el)
for element in p0_copy: # for every set in p0
removed = False
if element in p0 and element != p0[0]:
for act in element: # for every activity in this set
for e in end_activities: # for every end activity
if e not in start_activities:
if (act, e) in iterable_dfg: # check if connected
# is there an element in dfg pointing from any act in a subset of p0 to an end activity
for activ in element:
if activ not in p0[0]:
p0[0].append(activ)
if element in p0:
p0.remove(
element
) # remove subsets that are connected to an end activity
removed = True
break
if removed:
break
for s in start_activities:
if s not in end_activities:
if not removed:
if (s, act) in iterable_dfg:
for acti in element:
if acti not in p0[0]:
p0[0].append(acti)
if element in p0:
p0.remove(
element
) # remove subsets that are connected to an end activity
removed = True
break
else:
break
if removed:
break
iterable_dfg = []
for i in range(0, len(self.dfg)):
iterable_dfg.append(self.dfg[i][0])
p0_copy = []
for int_el in p0:
p0_copy.append(int_el)
for element in p0_copy:
if element in p0 and element != p0[0]:
for act in element:
for e in self.end_activities:
if (
e, act
) in iterable_dfg: # get those act, that are connected from an end activity
for e2 in self.end_activities: # check, if the act is connected from all end activities
if (e2, act) not in iterable_dfg:
for acti in element:
if acti not in p0[0]:
p0[0].append(acti)
if element in p0:
p0.remove(
element
) # remove subsets that are connected to an end activity
break
for s in self.start_activities:
if (
act, s
) in iterable_dfg: # same as above (in this case for activities connected to
# a start activity)
for s2 in self.start_activities:
if (act, s2) not in iterable_dfg:
for acti in element:
if acti not in p0[0]:
p0[0].append(acti)
if element in p0:
p0.remove(
element
) # remove subsets that are connected to an end activity
break
if len(p0) > 1:
return [True, p0]
else:
return [False, []]
def apply_cut_im_plain(self, type_of_cut, cut, activity_key):
# dfg_viz = dfg_factory.apply(self.log)
# gviz = dfg_vis_factory.apply(dfg_viz, log=self.log, variant="frequency", parameters={"format": "PDF"})
# dfg_vis_factory.view(gviz)
if type_of_cut == 'concurrent':
self.detected_cut = 'concurrent'
new_logs = split.split_xor(cut[1], self.log, activity_key)
for l in new_logs:
new_dfg = [(k, v) for k, v in dfg_inst.apply(
l, parameters=self.parameters).items() if v > 0]
activities = attributes_filter.get_attribute_values(
l, activity_key)
start_activities = list(
start_activities_filter.get_start_activities(
l, parameters=self.parameters).keys())
end_activities = list(
end_activities_filter.get_end_activities(
l, parameters=self.parameters).keys())
self.children.append(
SubtreeInfrequent(
l,
new_dfg,
self.master_dfg,
self.initial_dfg,
activities,
self.counts,
self.rec_depth + 1,
self.f,
noise_threshold=self.noise_threshold,
start_activities=start_activities,
end_activities=end_activities,
initial_start_activities=self.initial_start_activities,
initial_end_activities=self.initial_end_activities,
parameters=self.parameters))
elif type_of_cut == 'sequential':
new_logs = split.split_sequence(cut[1], self.log, activity_key)
self.detected_cut = "sequential"
for l in new_logs:
new_dfg = [(k, v) for k, v in dfg_inst.apply(
l, parameters=self.parameters).items() if v > 0]
activities = attributes_filter.get_attribute_values(
l, activity_key)
start_activities = list(
start_activities_filter.get_start_activities(
l, parameters=self.parameters).keys())
end_activities = list(
end_activities_filter.get_end_activities(
l, parameters=self.parameters).keys())
self.children.append(
SubtreeInfrequent(
l,
new_dfg,
self.master_dfg,
self.initial_dfg,
activities,
self.counts,
self.rec_depth + 1,
self.f,
noise_threshold=self.noise_threshold,
start_activities=start_activities,
end_activities=end_activities,
initial_start_activities=self.initial_start_activities,
initial_end_activities=self.initial_end_activities,
parameters=self.parameters))
elif type_of_cut == 'parallel':
new_logs = split.split_parallel(cut[1], self.log, activity_key)
self.detected_cut = "parallel"
for l in new_logs:
new_dfg = [(k, v) for k, v in dfg_inst.apply(
l, parameters=self.parameters).items() if v > 0]
activities = attributes_filter.get_attribute_values(
l, activity_key)
start_activities = list(
start_activities_filter.get_start_activities(
l, parameters=self.parameters).keys())
end_activities = list(
end_activities_filter.get_end_activities(
l, parameters=self.parameters).keys())
self.children.append(
SubtreeInfrequent(
l,
new_dfg,
self.master_dfg,
self.initial_dfg,
activities,
self.counts,
self.rec_depth + 1,
self.f,
noise_threshold=self.noise_threshold,
start_activities=start_activities,
end_activities=end_activities,
initial_start_activities=self.initial_start_activities,
initial_end_activities=self.initial_end_activities,
parameters=self.parameters))
elif type_of_cut == 'loopCut':
new_logs = split.split_loop(cut[1], self.log, activity_key)
self.detected_cut = "loopCut"
for l in new_logs:
new_dfg = [(k, v) for k, v in dfg_inst.apply(
l, parameters=self.parameters).items() if v > 0]
activities = attributes_filter.get_attribute_values(
l, activity_key)
start_activities = list(
start_activities_filter.get_start_activities(
l, parameters=self.parameters).keys())
end_activities = list(
end_activities_filter.get_end_activities(
l, parameters=self.parameters).keys())
self.children.append(
SubtreeInfrequent(
l,
new_dfg,
self.master_dfg,
self.initial_dfg,
activities,
self.counts,
self.rec_depth + 1,
self.f,
noise_threshold=self.noise_threshold,
start_activities=start_activities,
end_activities=end_activities,
initial_start_activities=self.initial_start_activities,
initial_end_activities=self.initial_end_activities,
parameters=self.parameters))
def detect_cut_if(self, second_iteration=False, parameters=None):
# dfg_viz = dfg_factory.apply(self.log)
# gviz = dfg_vis_factory.apply(dfg_viz, log=self.log, variant="frequency", parameters={"format": "PDF"})
# dfg_vis_factory.view(gviz)
if parameters is None:
parameters = {}
activity_key = exec_utils.get_param_value(
Parameters.ACTIVITY_KEY, self.parameters,
pmutil.xes_constants.DEFAULT_NAME_KEY)
# check base cases:
empty_log = base_case.empty_log(self.log)
single_activity = base_case.single_activity(self.log, activity_key)
if empty_log:
self.detected_cut = 'empty_log'
elif single_activity:
self.detected_cut = 'single_activity'
# if no base cases are found, search for a cut:
# use the cutting and splitting functions of im_plain:
else:
found_plain_cut, type_of_cut, cut = self.check_cut_im_plain()
if found_plain_cut:
self.apply_cut_im_plain(type_of_cut, cut, activity_key)
# if im_plain does not find a cut, we filter on our threshold and then again apply the im_cut detection
# but this time, we have to use different splitting functions:
else:
self.filter_dfg_on_threshold()
"""
dfg_viz = dfg_factory.apply(self.log)
gviz = dfg_vis_factory.apply(dfg_viz, log=self.log, variant="frequency", parameters={"format": "PDF"})
dfg_vis_factory.view(gviz)
"""
found_plain_cut, type_of_cut, cut = self.check_cut_im_plain()
if found_plain_cut:
if type_of_cut == 'concurrent':
logging.debug("concurrent_cut_if")
self.detected_cut = 'concurrent'
new_logs = splitting_infrequent.split_xor_infrequent(
cut[1], self.log, activity_key)
for l in new_logs:
new_dfg = [(k, v) for k, v in dfg_inst.apply(
l, parameters=parameters).items() if v > 0]
activities = attributes_filter.get_attribute_values(
l, activity_key)
start_activities = list(
start_activities_filter.get_start_activities(
l, parameters=parameters).keys())
end_activities = list(
end_activities_filter.get_end_activities(
l, parameters=parameters).keys())
self.children.append(
SubtreeInfrequent(
l,
new_dfg,
self.master_dfg,
self.initial_dfg,
activities,
self.counts,
self.rec_depth + 1,
self.f,
noise_threshold=self.noise_threshold,
start_activities=start_activities,
end_activities=end_activities,
initial_start_activities=self.
initial_start_activities,
initial_end_activities=self.
initial_end_activities,
parameters=parameters))
elif type_of_cut == 'sequential':
logging.debug("sequential_if")
new_logs = splitting_infrequent.split_sequence_infrequent(
cut[1], self.log, activity_key)
self.detected_cut = "sequential"
for l in new_logs:
new_dfg = [(k, v) for k, v in dfg_inst.apply(
l, parameters=parameters).items() if v > 0]
activities = attributes_filter.get_attribute_values(
l, activity_key)
start_activities = list(
start_activities_filter.get_start_activities(
l, parameters=parameters).keys())
end_activities = list(
end_activities_filter.get_end_activities(
l, parameters=parameters).keys())
self.children.append(
SubtreeInfrequent(
l,
new_dfg,
self.master_dfg,
self.initial_dfg,
activities,
self.counts,
self.rec_depth + 1,
self.f,
noise_threshold=self.noise_threshold,
start_activities=start_activities,
end_activities=end_activities,
initial_start_activities=self.
initial_start_activities,
initial_end_activities=self.
initial_end_activities,
parameters=parameters))
elif type_of_cut == 'parallel':
logging.debug("parallel_if")
new_logs = split.split_parallel(
cut[1], self.log, activity_key)
self.detected_cut = "parallel"
for l in new_logs:
new_dfg = [(k, v) for k, v in dfg_inst.apply(
l, parameters=parameters).items() if v > 0]
activities = attributes_filter.get_attribute_values(
l, activity_key)
start_activities = list(
start_activities_filter.get_start_activities(
l, parameters=parameters).keys())
end_activities = list(
end_activities_filter.get_end_activities(
l, parameters=parameters).keys())
self.children.append(
SubtreeInfrequent(
l,
new_dfg,
self.master_dfg,
self.initial_dfg,
activities,
self.counts,
self.rec_depth + 1,
self.f,
noise_threshold=self.noise_threshold,
start_activities=start_activities,
end_activities=end_activities,
initial_start_activities=self.
initial_start_activities,
initial_end_activities=self.
initial_end_activities,
parameters=parameters))
elif type_of_cut == 'loopCut':
logging.debug("loopCut_if")
new_logs = splitting_infrequent.split_loop_infrequent(
cut[1], self.log, activity_key)
self.detected_cut = "loopCut"
for l in new_logs:
new_dfg = [(k, v) for k, v in dfg_inst.apply(
l, parameters=parameters).items() if v > 0]
activities = attributes_filter.get_attribute_values(
l, activity_key)
start_activities = list(
start_activities_filter.get_start_activities(
l, parameters=parameters).keys())
end_activities = list(
end_activities_filter.get_end_activities(
l, parameters=parameters).keys())
self.children.append(
SubtreeInfrequent(
l,
new_dfg,
self.master_dfg,
self.initial_dfg,
activities,
self.counts,
self.rec_depth + 1,
self.f,
noise_threshold=self.noise_threshold,
start_activities=start_activities,
end_activities=end_activities,
initial_start_activities=self.
initial_start_activities,
initial_end_activities=self.
initial_end_activities,
parameters=parameters))
else:
self.apply_fall_through_infrequent(parameters)
def apply_tree(log, parameters=None):
"""
Apply the IM algorithm to a log_skeleton obtaining a process tree
Parameters
----------
log
Log
parameters
Parameters of the algorithm, including:
Parameters.ACTIVITY_KEY -> attribute of the log_skeleton to use as activity name
(default concept:name)
Returns
----------
process_tree
Process tree
"""
if parameters is None:
parameters = {}
if pkgutil.find_loader("pandas"):
import pandas as pd
from pm4py.statistics.variants.pandas import get as variants_get
if type(log) is pd.DataFrame:
vars = variants_get.get_variants_count(log, parameters=parameters)
return apply_tree_variants(vars, parameters=parameters)
activity_key = exec_utils.get_param_value(
Parameters.ACTIVITY_KEY, parameters,
pmutil.xes_constants.DEFAULT_NAME_KEY)
log = converter.apply(log, parameters=parameters)
# since basic IM is influenced once per variant, it makes sense to keep one trace per variant
log = filtering_utils.keep_one_trace_per_variant(log,
parameters=parameters)
# keep only the activity attribute (since the others are not used)
log = filtering_utils.keep_only_one_attribute_per_event(log, activity_key)
dfg = [(k, v)
for k, v in dfg_inst.apply(log, parameters=parameters).items()
if v > 0]
c = Counts()
activities = attributes_filter.get_attribute_values(log, activity_key)
start_activities = list(
start_activities_filter.get_start_activities(
log, parameters=parameters).keys())
end_activities = list(
end_activities_filter.get_end_activities(log,
parameters=parameters).keys())
contains_empty_traces = False
traces_length = [len(trace) for trace in log]
if traces_length:
contains_empty_traces = min([len(trace) for trace in log]) == 0
recursion_depth = 0
sub = subtree.make_tree(log, dfg, dfg, dfg, activities, c, recursion_depth,
0.0, start_activities, end_activities,
start_activities, end_activities, parameters)
process_tree = get_tree_repr_implain.get_repr(
sub, 0, contains_empty_traces=contains_empty_traces)
# Ensures consistency to the parent pointers in the process tree
tree_consistency.fix_parent_pointers(process_tree)
# Fixes a 1 child XOR that is added when single-activities flowers are found
tree_consistency.fix_one_child_xor_flower(process_tree)
# folds the process tree (to simplify it in case fallthroughs/filtering is applied)
process_tree = util.fold(process_tree)
return process_tree
def apply_fall_through_infrequent(self, parameters=None):
if parameters is None:
parameters = {}
activity_key = exec_utils.get_param_value(
Parameters.ACTIVITY_KEY, self.parameters,
pmutil.xes_constants.DEFAULT_NAME_KEY)
# set flags for fall_throughs, base case is True (enabled)
use_empty_trace = (Parameters.EMPTY_TRACE_KEY not in parameters
) or parameters[Parameters.EMPTY_TRACE_KEY]
use_act_once_per_trace = (
Parameters.ONCE_PER_TRACE_KEY
not in parameters) or parameters[Parameters.ONCE_PER_TRACE_KEY]
use_act_concurrent = (Parameters.CONCURRENT_KEY not in parameters
) or parameters[Parameters.CONCURRENT_KEY]
use_strict_tau_loop = (Parameters.STRICT_TAU_LOOP_KEY not in parameters
) or parameters[Parameters.STRICT_TAU_LOOP_KEY]
use_tau_loop = (Parameters.TAU_LOOP_KEY not in parameters
) or parameters[Parameters.TAU_LOOP_KEY]
if use_empty_trace:
empty_traces_present, enough_traces, new_log = fall_through_infrequent.empty_trace_filtering(
self.log, self.f)
self.log = new_log
else:
empty_traces_present = False
enough_traces = False
# if an empty trace is found, the empty trace fallthrough applies
if empty_traces_present and enough_traces:
logging.debug("empty_trace_if")
self.detected_cut = 'empty_trace'
new_dfg = [(k, v) for k, v in dfg_inst.apply(
new_log, parameters=self.parameters).items() if v > 0]
activities = attributes_filter.get_attribute_values(
new_log, activity_key)
start_activities = list(
start_activities_filter.get_start_activities(
new_log, parameters=parameters).keys())
end_activities = list(
end_activities_filter.get_end_activities(
new_log, parameters=parameters).keys())
self.children.append(
SubtreeInfrequent(
new_log,
new_dfg,
self.master_dfg,
self.initial_dfg,
activities,
self.counts,
self.rec_depth + 1,
self.f,
noise_threshold=self.noise_threshold,
start_activities=start_activities,
end_activities=end_activities,
initial_start_activities=self.initial_start_activities,
initial_end_activities=self.initial_end_activities,
parameters=parameters))
elif empty_traces_present and not enough_traces:
# no node is added to the PT, instead we just use recursion on the log without the empty traces
self.detect_cut_if()
else:
if use_act_once_per_trace:
activity_once, new_log, small_log = fall_through.act_once_per_trace(
self.log, self.activities, activity_key)
else:
activity_once = False
if activity_once:
self.detected_cut = 'parallel'
# create two new dfgs as we need them to append to self.children later
new_dfg = [(k, v) for k, v in dfg_inst.apply(
new_log, parameters=parameters).items() if v > 0]
activities = attributes_filter.get_attribute_values(
new_log, activity_key)
small_dfg = [(k, v) for k, v in dfg_inst.apply(
small_log, parameters=parameters).items() if v > 0]
small_activities = attributes_filter.get_attribute_values(
small_log, activity_key)
start_activities = list(
start_activities_filter.get_start_activities(
new_log, parameters=parameters).keys())
end_activities = list(
end_activities_filter.get_end_activities(
new_log, parameters=parameters).keys())
# append the chosen activity as leaf:
self.children.append(
SubtreeInfrequent(
small_log,
small_dfg,
self.master_dfg,
self.initial_dfg,
small_activities,
self.counts,
self.rec_depth + 1,
self.f,
noise_threshold=self.noise_threshold,
initial_start_activities=self.initial_start_activities,
initial_end_activities=self.initial_end_activities,
parameters=parameters))
# continue with the recursion on the new log
self.children.append(
SubtreeInfrequent(
new_log,
new_dfg,
self.master_dfg,
self.initial_dfg,
activities,
self.counts,
self.rec_depth + 1,
self.f,
noise_threshold=self.noise_threshold,
start_activities=start_activities,
end_activities=end_activities,
initial_start_activities=self.initial_start_activities,
initial_end_activities=self.initial_end_activities,
parameters=parameters))
else:
if use_act_concurrent:
activity_concurrent, new_log, small_log, key = fall_through.activity_concurrent(
self,
self.log,
self.activities,
activity_key,
parameters=parameters)
else:
activity_concurrent = False
if activity_concurrent:
self.detected_cut = 'parallel'
# create two new dfgs on to append later
new_dfg = [(k, v) for k, v in dfg_inst.apply(
new_log, parameters=parameters).items() if v > 0]
activities = attributes_filter.get_attribute_values(
new_log, activity_key)
small_dfg = [(k, v) for k, v in dfg_inst.apply(
small_log, parameters=parameters).items() if v > 0]
small_activities = attributes_filter.get_attribute_values(
small_log, activity_key)
start_activities = list(
start_activities_filter.get_start_activities(
new_log, parameters=parameters).keys())
end_activities = list(
end_activities_filter.get_end_activities(
new_log, parameters=parameters).keys())
# append the concurrent activity as leaf:
self.children.append(
SubtreeInfrequent(
small_log,
small_dfg,
self.master_dfg,
self.initial_dfg,
small_activities,
self.counts,
self.rec_depth + 1,
self.f,
noise_threshold=self.noise_threshold,
initial_start_activities=self.
initial_start_activities,
initial_end_activities=self.initial_end_activities,
parameters=parameters))
# continue with the recursion on the new log:
self.children.append(
SubtreeInfrequent(
new_log,
new_dfg,
self.master_dfg,
self.initial_dfg,
activities,
self.counts,
self.rec_depth + 1,
self.f,
noise_threshold=self.noise_threshold,
start_activities=start_activities,
end_activities=end_activities,
initial_start_activities=self.
initial_start_activities,
initial_end_activities=self.initial_end_activities,
parameters=parameters))
else:
if use_strict_tau_loop:
strict_tau_loop, new_log = fall_through.strict_tau_loop(
self.log, self.start_activities,
self.end_activities, activity_key)
else:
strict_tau_loop = False
if strict_tau_loop:
self.detected_cut = 'strict_tau_loop'
new_dfg = [(k, v) for k, v in dfg_inst.apply(
new_log, parameters=parameters).items() if v > 0]
activities = attributes_filter.get_attribute_values(
new_log, activity_key)
start_activities = list(
start_activities_filter.get_start_activities(
new_log, parameters=parameters).keys())
end_activities = list(
end_activities_filter.get_end_activities(
new_log, parameters=parameters).keys())
self.children.append(
SubtreeInfrequent(
new_log,
new_dfg,
self.master_dfg,
self.initial_dfg,
activities,
self.counts,
self.rec_depth + 1,
self.f,
noise_threshold=self.noise_threshold,
start_activities=start_activities,
end_activities=end_activities,
initial_start_activities=self.
initial_start_activities,
initial_end_activities=self.
initial_end_activities,
parameters=parameters))
else:
if use_tau_loop:
tau_loop, new_log = fall_through.tau_loop(
self.log, self.start_activities, activity_key)
else:
tau_loop = False
if tau_loop:
self.detected_cut = 'tau_loop'
new_dfg = [(k, v) for k, v in dfg_inst.apply(
new_log, parameters=parameters).items()
if v > 0]
activities = attributes_filter.get_attribute_values(
new_log, activity_key)
start_activities = list(
start_activities_filter.get_start_activities(
new_log, parameters=parameters).keys())
end_activities = list(
end_activities_filter.get_end_activities(
new_log, parameters=parameters).keys())
self.children.append(
SubtreeInfrequent(
new_log,
new_dfg,
self.master_dfg,
self.initial_dfg,
activities,
self.counts,
self.rec_depth + 1,
self.f,
noise_threshold=self.noise_threshold,
start_activities=start_activities,
end_activities=end_activities,
initial_start_activities=self.
initial_start_activities,
initial_end_activities=self.
initial_end_activities,
parameters=parameters))
else:
logging.debug("flower_if")
self.detected_cut = 'flower'
def apply(log, parameters=None):
"""
Gets the frequency DFG
Parameters
------------
log
Log
parameters
Parameters of the algorithm
Returns
------------
base64
Base64 of an SVG representing the model
model
Text representation of the model
format
Format of the model
"""
if parameters is None:
parameters = {}
decreasingFactor = parameters[
"decreasingFactor"] if "decreasingFactor" in parameters else constants.DEFAULT_DEC_FACTOR
activity_key = parameters[
pm4_constants.
PARAMETER_CONSTANT_ACTIVITY_KEY] if pm4_constants.PARAMETER_CONSTANT_ACTIVITY_KEY in parameters else xes.DEFAULT_NAME_KEY
log = attributes_filter.filter_log_on_max_no_activities(
log,
max_no_activities=constants.MAX_NO_ACTIVITIES,
parameters=parameters)
filtered_log = auto_filter.apply_auto_filter(log, parameters=parameters)
activities_count = attributes_filter.get_attribute_values(
filtered_log, activity_key)
activities = list(activities_count.keys())
start_activities = list(
start_activities_filter.get_start_activities(
filtered_log, parameters=parameters).keys())
end_activities = list(
end_activities_filter.get_end_activities(filtered_log,
parameters=parameters).keys())
dfg = dfg_factory.apply(filtered_log, parameters=parameters)
dfg = clean_dfg_based_on_noise_thresh(
dfg,
activities,
decreasingFactor * constants.DEFAULT_DFG_CLEAN_MULTIPLIER,
parameters=parameters)
parameters["format"] = "svg"
parameters["start_activities"] = start_activities
parameters["end_activities"] = end_activities
gviz = dfg_vis_factory.apply(dfg,
log=filtered_log,
variant="frequency",
parameters=parameters)
gviz_base64 = base64.b64encode(str(gviz).encode('utf-8'))
ret_graph = get_graph.get_graph_from_dfg(dfg, start_activities,
end_activities)
net, im, fm = dfg_conv_factory.apply(dfg,
parameters={
"start_activities":
start_activities,
"end_activities": end_activities
})
return get_base64_from_gviz(gviz), export_petri_as_string(
net, im, fm
), ".pnml", "xes", activities, start_activities, end_activities, gviz_base64, ret_graph, "dfg", "freq", None, "", activity_key
def apply(log, parameters):
"""
Apply the IMDF algorithm to a log obtaining a Petri net along with an initial and final marking
Parameters
-----------
log
Log
parameters
Parameters of the algorithm, including:
pmutil.constants.PARAMETER_CONSTANT_ACTIVITY_KEY -> attribute of the log to use as activity name
(default concept:name)
Returns
-----------
net
Petri net
initial_marking
Initial marking
final_marking
Final marking
"""
if parameters is None:
parameters = {}
if pmutil.constants.PARAMETER_CONSTANT_ACTIVITY_KEY not in parameters:
parameters[pmutil.constants.
PARAMETER_CONSTANT_ACTIVITY_KEY] = xes_util.DEFAULT_NAME_KEY
if pmutil.constants.PARAMETER_CONSTANT_ATTRIBUTE_KEY not in parameters:
parameters[
pmutil.constants.PARAMETER_CONSTANT_ATTRIBUTE_KEY] = parameters[
pmutil.constants.PARAMETER_CONSTANT_ACTIVITY_KEY]
activity_key = parameters[pmutil.constants.PARAMETER_CONSTANT_ACTIVITY_KEY]
# apply the reduction by default only on very small logs
enable_reduction = parameters[
"enable_reduction"] if "enable_reduction" in parameters else True
# get the DFG
if isinstance(log[0][0], tel.Event):
dfg = [(k, v) for k, v in inductive_revise.get_dfg_graph_trans(
log,
parameters={
pmutil.constants.PARAMETER_CONSTANT_ACTIVITY_KEY: activity_key
}).items() if v > 0]
else:
dfg = [(k, v) for k, v in dfg_inst.apply(
log,
parameters={
pmutil.constants.PARAMETER_CONSTANT_ACTIVITY_KEY: activity_key
}).items() if v > 0]
# get the activities in the log
activities = attributes_filter.get_attribute_values(log, activity_key)
# gets the start activities from the log
start_activities = list(
start_activities_filter.get_start_activities(
log, parameters=parameters).keys())
# gets the end activities from the log
end_activities = list(
end_activities_filter.get_end_activities(log,
parameters=parameters).keys())
# check if the log contains empty traces
contains_empty_traces = False
traces_length = [len(trace) for trace in log]
if traces_length:
contains_empty_traces = min([len(trace) for trace in log]) == 0
net, initial_marking, final_marking = apply_dfg(
dfg,
parameters=parameters,
activities=activities,
contains_empty_traces=contains_empty_traces,
start_activities=start_activities,
end_activities=end_activities)
"""if enable_reduction:
vis_trans = [x for x in net.transitions if x.label]
hid_trans = [x for x in net.transitions if x.label is None]
if vis_trans:
ratio = len(hid_trans) / len(vis_trans)
if ratio < 2.0:
# avoid reducting too much complicated processes
reduction_parameters = copy(parameters)
if "is_reduction" not in reduction_parameters:
reduction_parameters["is_reduction"] = True
if "thread_maximum_ex_time" not in reduction_parameters:
reduction_parameters["thread_maximum_ex_time"] = shared_constants.RED_MAX_THR_EX_TIME
# do the replay
aligned_traces = token_replay.apply(log, net, initial_marking, final_marking,
parameters=reduction_parameters)
# apply petri_reduction technique in order to simplify the Petri net
net = petri_cleaning.petri_reduction_treplay(net, parameters={"aligned_traces": aligned_traces})"""
return net, initial_marking, final_marking
def apply_fall_through(self, parameters=None):
if parameters is None:
parameters = {}
activity_key = exec_utils.get_param_value(
Parameters.ACTIVITY_KEY, parameters,
pmutil.xes_constants.DEFAULT_NAME_KEY)
# set flags for fall_throughs, base case is True (enabled)
use_empty_trace = (Parameters.EMPTY_TRACE_KEY not in parameters
) or parameters[Parameters.EMPTY_TRACE_KEY]
use_act_once_per_trace = (
Parameters.ONCE_PER_TRACE_KEY
not in parameters) or parameters[Parameters.ONCE_PER_TRACE_KEY]
use_act_concurrent = (Parameters.CONCURRENT_KEY not in parameters
) or parameters[Parameters.CONCURRENT_KEY]
use_strict_tau_loop = (Parameters.STRICT_TAU_LOOP_KEY not in parameters
) or parameters[Parameters.STRICT_TAU_LOOP_KEY]
use_tau_loop = (Parameters.TAU_LOOP_KEY not in parameters
) or parameters[Parameters.TAU_LOOP_KEY]
if use_empty_trace:
empty_trace, new_log = fall_through.empty_trace(self.log)
# if an empty trace is found, the empty trace fallthrough applies
#
else:
empty_trace = False
if empty_trace:
logging.debug("empty_trace")
activites_left = []
for trace in new_log:
for act in trace:
if act[activity_key] not in activites_left:
activites_left.append(act[activity_key])
self.detected_cut = 'empty_trace'
new_dfg = [(k, v) for k, v in dfg_inst.apply(
new_log, parameters=parameters).items() if v > 0]
activities = attributes_filter.get_attribute_values(
new_log, activity_key)
start_activities = list(
start_activities_filter.get_start_activities(
new_log, parameters=self.parameters).keys())
end_activities = list(
end_activities_filter.get_end_activities(
new_log, parameters=self.parameters).keys())
self.children.append(
SubtreePlain(
new_log,
new_dfg,
self.master_dfg,
self.initial_dfg,
activities,
self.counts,
self.rec_depth + 1,
noise_threshold=self.noise_threshold,
start_activities=start_activities,
end_activities=end_activities,
initial_start_activities=self.initial_start_activities,
initial_end_activities=self.initial_end_activities,
parameters=parameters))
else:
if use_act_once_per_trace:
activity_once, new_log, small_log = fall_through.act_once_per_trace(
self.log, self.activities, activity_key)
small_log = filtering_utils.keep_one_trace_per_variant(
small_log, parameters=parameters)
else:
activity_once = False
if use_act_once_per_trace and activity_once:
self.detected_cut = 'parallel'
# create two new dfgs as we need them to append to self.children later
new_dfg = [(k, v) for k, v in dfg_inst.apply(
new_log, parameters=parameters).items() if v > 0]
activities = attributes_filter.get_attribute_values(
new_log, activity_key)
small_dfg = [(k, v) for k, v in dfg_inst.apply(
small_log, parameters=parameters).items() if v > 0]
small_activities = attributes_filter.get_attribute_values(
small_log, activity_key)
self.children.append(
SubtreePlain(
small_log,
small_dfg,
self.master_dfg,
self.initial_dfg,
small_activities,
self.counts,
self.rec_depth + 1,
noise_threshold=self.noise_threshold,
initial_start_activities=self.initial_start_activities,
initial_end_activities=self.initial_end_activities,
parameters=parameters))
# continue with the recursion on the new log_skeleton
start_activities = list(
start_activities_filter.get_start_activities(
new_log, parameters=self.parameters).keys())
end_activities = list(
end_activities_filter.get_end_activities(
new_log, parameters=self.parameters).keys())
self.children.append(
SubtreePlain(
new_log,
new_dfg,
self.master_dfg,
self.initial_dfg,
activities,
self.counts,
self.rec_depth + 1,
noise_threshold=self.noise_threshold,
start_activities=start_activities,
end_activities=end_activities,
initial_start_activities=self.initial_start_activities,
initial_end_activities=self.initial_end_activities,
parameters=parameters))
else:
if use_act_concurrent:
activity_concurrent, new_log, small_log, activity_left_out = fall_through.activity_concurrent(
self,
self.log,
self.activities,
activity_key,
parameters=parameters)
small_log = filtering_utils.keep_one_trace_per_variant(
small_log, parameters=parameters)
else:
activity_concurrent = False
if use_act_concurrent and activity_concurrent:
self.detected_cut = 'parallel'
# create two new dfgs on to append later
new_dfg = [(k, v) for k, v in dfg_inst.apply(
new_log, parameters=parameters).items() if v > 0]
activities = attributes_filter.get_attribute_values(
new_log, activity_key)
small_dfg = [(k, v) for k, v in dfg_inst.apply(
small_log, parameters=parameters).items() if v > 0]
small_activities = attributes_filter.get_attribute_values(
small_log, activity_key)
# append the concurrent activity as leaf:
self.children.append(
SubtreePlain(
small_log,
small_dfg,
self.master_dfg,
self.initial_dfg,
small_activities,
self.counts,
self.rec_depth + 1,
noise_threshold=self.noise_threshold,
initial_start_activities=self.
initial_start_activities,
initial_end_activities=self.initial_end_activities,
parameters=parameters))
# continue with the recursion on the new log_skeleton:
start_activities = list(
start_activities_filter.get_start_activities(
new_log, parameters=self.parameters).keys())
end_activities = list(
end_activities_filter.get_end_activities(
new_log, parameters=self.parameters).keys())
self.children.append(
SubtreePlain(
new_log,
new_dfg,
self.master_dfg,
self.initial_dfg,
activities,
self.counts,
self.rec_depth + 1,
noise_threshold=self.noise_threshold,
start_activities=start_activities,
end_activities=end_activities,
initial_start_activities=self.
initial_start_activities,
initial_end_activities=self.initial_end_activities,
parameters=parameters))
else:
if use_strict_tau_loop:
strict_tau_loop, new_log = fall_through.strict_tau_loop(
self.log, self.start_activities,
self.end_activities, activity_key)
new_log = filtering_utils.keep_one_trace_per_variant(
new_log, parameters=parameters)
else:
strict_tau_loop = False
if use_strict_tau_loop and strict_tau_loop:
activites_left = []
for trace in new_log:
for act in trace:
if act[activity_key] not in activites_left:
activites_left.append(act[activity_key])
self.detected_cut = 'strict_tau_loop'
new_dfg = [(k, v) for k, v in dfg_inst.apply(
new_log, parameters=parameters).items() if v > 0]
activities = attributes_filter.get_attribute_values(
new_log, activity_key)
start_activities = list(
start_activities_filter.get_start_activities(
new_log, parameters=self.parameters).keys())
end_activities = list(
end_activities_filter.get_end_activities(
new_log, parameters=self.parameters).keys())
self.children.append(
SubtreePlain(new_log,
new_dfg,
self.master_dfg,
self.initial_dfg,
activities,
self.counts,
self.rec_depth + 1,
noise_threshold=self.noise_threshold,
start_activities=start_activities,
end_activities=end_activities,
initial_start_activities=self.
initial_start_activities,
initial_end_activities=self.
initial_end_activities,
parameters=parameters))
else:
if use_tau_loop:
tau_loop, new_log = fall_through.tau_loop(
self.log, self.start_activities, activity_key)
new_log = filtering_utils.keep_one_trace_per_variant(
new_log, parameters=parameters)
else:
tau_loop = False
if use_tau_loop and tau_loop:
activites_left = []
for trace in new_log:
for act in trace:
if act[activity_key] not in activites_left:
activites_left.append(
act[activity_key])
self.detected_cut = 'tau_loop'
new_dfg = [(k, v) for k, v in dfg_inst.apply(
new_log, parameters=parameters).items()
if v > 0]
activities = attributes_filter.get_attribute_values(
new_log, activity_key)
start_activities = list(
start_activities_filter.get_start_activities(
new_log,
parameters=self.parameters).keys())
end_activities = list(
end_activities_filter.get_end_activities(
new_log,
parameters=self.parameters).keys())
self.children.append(
SubtreePlain(
new_log,
new_dfg,
self.master_dfg,
self.initial_dfg,
activities,
self.counts,
self.rec_depth + 1,
noise_threshold=self.noise_threshold,
start_activities=start_activities,
end_activities=end_activities,
initial_start_activities=self.
initial_start_activities,
initial_end_activities=self.
initial_end_activities,
parameters=parameters))
else:
logging.debug("flower model")
activites_left = []
for trace in self.log:
for act in trace:
if act[activity_key] not in activites_left:
activites_left.append(
act[activity_key])
self.detected_cut = 'flower'
result_avg = []
result_num = []
print(model)
tree = 5
tree_num = 0
tree_avg = 0
print(tree)
for sam in range(1, 11):
print(sam)
input_file_path = os.path.join("input_data", "df_complete_logs",
"%d_1000_%d.xes" % (tree, sam))
log = xes_importer.apply(input_file_path)
dfg_org = dfg_factory.apply(log)
start_act = set(get_start_activities(log).keys())
end_act = set(get_end_activities(log).keys())
#make petri net for simulation
net, im, fm = heu_factory.apply(log)
num = len(dfg_org.keys())
sim_log = sim_factory.apply(net,
im,
parameters={
'maxTraceLength': 20,
'noTraces': 1000
})
dfg_algo = dfg_factory.apply(log)
start_act_algo = set(get_start_activities(sim_log).keys())
end_act_algo = set(get_end_activities(sim_log).keys())
