def save_vis_performance_dfg(dfg: dict,
start_activities: dict,
end_activities: dict,
file_path: str,
aggregation_measure="mean"):
"""
Saves the visualization of a performance DFG
Parameters
----------------
dfg
DFG object
start_activities
Start activities
end_activities
End activities
file_path
Destination path
aggregation_measure
Aggregation measure (default: mean): mean, median, min, max, sum, stdev
"""
format = os.path.splitext(file_path)[1][1:]
from pm4py.visualization.dfg import visualizer as dfg_visualizer
from pm4py.visualization.dfg.variants import performance as dfg_perf_visualizer
dfg_parameters = dfg_perf_visualizer.Parameters
parameters = {}
parameters[dfg_parameters.FORMAT] = format
parameters[dfg_parameters.START_ACTIVITIES] = start_activities
parameters[dfg_parameters.END_ACTIVITIES] = end_activities
parameters[dfg_parameters.AGGREGATION_MEASURE] = aggregation_measure
gviz = dfg_perf_visualizer.apply(dfg, parameters=parameters)
dfg_visualizer.save(gviz, file_path)
def execute_script():
log_input_directory = "xesinput"
all_logs_names = os.listdir(log_input_directory)
all_logs_names = [log for log in all_logs_names if ".xe" in log]
for logName in all_logs_names:
# logPath = os.path.join("..", "tests", "inputData", logName)
log_path = log_input_directory + "\\" + logName
log = xes_importer.apply(log_path)
print("\n\n")
print("log loaded")
print("Number of traces - ", len(log))
event_log = log_conversion.apply(
log, variant=log_conversion.TO_EVENT_STREAM)
print("Number of events - ", len(event_log))
print("Classifiers ", log.classifiers)
exp_log_name = "xescert_exportlogs" + "\\" + "exp_" + logName
print("exporting log", exp_log_name)
xes_exporter.apply(log, exp_log_name)
print("exported log", exp_log_name)
log, classifier_attr_key = insert_classifier.search_act_class_attr(log)
classifiers = list(log.classifiers.keys())
if classifier_attr_key is None and classifiers:
try:
print(classifiers)
log, classifier_attr_key = insert_classifier.insert_activity_classifier_attribute(
log, classifiers[0])
print(classifier_attr_key)
except:
print("exception in handling classifier")
if classifier_attr_key is None:
classifier_attr_key = "concept:name"
if len(event_log) > 0 and classifier_attr_key in event_log[0]:
parameters = {
constants.PARAMETER_CONSTANT_ACTIVITY_KEY: classifier_attr_key
}
dfg = dfg_algorithm.apply(log, parameters=parameters)
gviz = dfg_vis.apply(dfg,
log=log,
variant="frequency",
parameters=parameters)
# dfg_vis.view(gviz)
dfg_vis.save(gviz,
"xescert_images\\" + logName.replace("xes", "png"))
print("Reimporting log file just exported - ", exp_log_name)
log = xes_importer.apply(exp_log_name)
print("log loaded", exp_log_name)
print("Number of traces - ", len(log))
event_log = log_conversion.apply(
log, variant=log_conversion.TO_EVENT_STREAM)
print("Number of events - ", len(event_log))
print("Classifiers ", log.classifiers)
def save_vis_dfg(dfg, start_activities, end_activities, file_path, log=None):
"""
Saves a DFG visualization to a file
Parameters
--------------
dfg
DFG object
start_activities
Start activities
end_activities
End activities
file_path
Destination path
"""
format = file_path[file_path.index(".") + 1:].lower()
from pm4py.visualization.dfg import visualizer as dfg_visualizer
parameters = dfg_visualizer.Variants.FREQUENCY.value.Parameters
gviz = dfg_visualizer.apply(dfg,
log=log,
variant=dfg_visualizer.Variants.FREQUENCY,
parameters={
parameters.FORMAT: format,
parameters.START_ACTIVITIES:
start_activities,
parameters.END_ACTIVITIES: end_activities
})
dfg_visualizer.save(gviz, file_path)
def save_directly_follows_graph(graph, path):
"""
Saves a directly-follows graph to the specified path.
:param graph: the directly-follows graph
:param path: the path
"""
log.info('saving directly follows graph %s to path %s', graph, path)
dfg_vis.save(graph, path)
def test_45(self):
import os
from pm4py.objects.log.importer.xes import importer as xes_importer
log = xes_importer.apply(os.path.join("input_data", "running-example.xes"))
from pm4py.algo.discovery.dfg import algorithm as dfg_discovery
from pm4py.visualization.dfg import visualizer as dfg_visualization
dfg = dfg_discovery.apply(log, variant=dfg_discovery.Variants.PERFORMANCE)
parameters = {dfg_visualization.Variants.PERFORMANCE.value.Parameters.FORMAT: "svg"}
gviz = dfg_visualization.apply(dfg, log=log, variant=dfg_visualization.Variants.PERFORMANCE,
parameters=parameters)
dfg_visualization.save(gviz, os.path.join("test_output_data", "dfg.svg"))
os.remove(os.path.join("test_output_data", "dfg.svg"))
def save_full_dfg(log):
dfg = dfg_discovery.apply(log)
gviz = dfg_visualization.apply(
dfg, log=log, variant=dfg_visualization.Variants.FREQUENCY)
dfg_visualization.view(gviz)
parameters = {
dfg_visualization.Variants.PERFORMANCE.value.Parameters.FORMAT: "svg"
}
gviz = dfg_visualization.apply(
dfg,
log=log,
variant=dfg_visualization.Variants.FREQUENCY,
parameters=parameters)
dfg_visualization.save(gviz, "dfg_full.svg")
print('Full DFG saves as "dfg_full.svg"')
return gviz
def save_graph_file(type, gviz, path):
if type == "alpha":
pn_visualizer.save(gviz, path)
elif type == "heuristic-heu-net":
hn_visualizer.save(gviz, path)
elif type == "heuristic-pet-net":
pn_visualizer.save(gviz, path)
elif type == "dfg-discovery-frequency":
dfg_visualization.save(gviz, path)
elif type == "dfg-discovery-active-time":
dfg_visualization.save(gviz, path)
elif type == "dfg-discovery-pet-net":
pt_visualizer.save(gviz, path)
elif type == "inductive-miner-tree":
pt_visualizer.save(gviz, path)
elif type == "inductive-miner-petri":
pn_visualizer.save(gviz, path)
def create_directly_follows_graph(frame: DataFrame, output_format='svg'):
"""
Creates a Directly Follows Graph from the supplied DataFrame.
:param frame: the DataFrame
:param output_format: desired output format
:return: object representing the created graph
"""
event_log = _convert_data_frame_to_event_log(frame)
dfg = dfg_alg.apply(log=event_log, variant=DfgAlgVariants.FREQUENCY)
apply = dfg_vis.apply(
dfg,
log=event_log,
variant=DfgVisVariants.FREQUENCY,
parameters={VisualisationParams.FORMAT: output_format})
saved_dfg = tempfile.NamedTemporaryFile(prefix='pm_',
suffix=f'.{output_format}',
delete=False)
dfg_vis.save(apply, saved_dfg.name)
# close here and delete after final use to work around access issues on
# in case anybody tries to run this on windows
saved_dfg.close()
return saved_dfg
def save_vis_dfg(dfg: dict,
start_activities: dict,
end_activities: dict,
file_path: str,
log: Optional[EventLog] = None):
"""
Saves a DFG visualization to a file
Parameters
--------------
dfg
DFG object
start_activities
Start activities
end_activities
End activities
file_path
Destination path
"""
if log is not None:
if type(log) not in [pd.DataFrame, EventLog, EventStream]:
raise Exception(
"the method can be applied only to a traditional event log!")
format = os.path.splitext(file_path)[1][1:]
from pm4py.visualization.dfg import visualizer as dfg_visualizer
dfg_parameters = dfg_visualizer.Variants.FREQUENCY.value.Parameters
parameters = get_properties(log)
parameters[dfg_parameters.FORMAT] = format
parameters[dfg_parameters.START_ACTIVITIES] = start_activities
parameters[dfg_parameters.END_ACTIVITIES] = end_activities
gviz = dfg_visualizer.apply(dfg,
log=log,
variant=dfg_visualizer.Variants.FREQUENCY,
parameters=parameters)
dfg_visualizer.save(gviz, file_path)
def api_gerar_modelo_pm():
ramojustica = request.args.get('ramojustica')
codtribunal = request.args.get('codtribunal')
atuacao = request.args.get('atuacao')
cluster = request.args.get('cluster')
grau = request.args.get('grau')
codorgaoj = request.args.get('codorgaoj')
natureza = request.args.get('natureza')
codclasse = request.args.get('codclasse')
dtinicio = request.args.get('dtinicio')
dtfim = request.args.get('dtfim')
baixado = request.args.get('baixado')
sensibilidade = request.args.get('sensibilidade')
metrica = request.args.get('metrica')
formato = request.args.get('formato')
if ramojustica is None:
abort(400, description="ramojustica nao informado")
if atuacao is None:
abort(400, description="atuacao nao informado")
if codtribunal is None and cluster is None:
abort(400, description="codtribunal ou cluster deve ser informado")
gviz = gerar_view_dfg_model_from_params(ramojustica, codtribunal, atuacao, cluster, grau, codorgaoj, natureza, codclasse, \
dtinicio, dtfim, baixado=baixado, sensibility=sensibilidade, metric_type=metrica, image_format=formato)
if gviz != None:
file_remover = FileRemover()
tempdir = tempfile.mkdtemp()
path = tempdir + "/model_mp." + str(formato).lower()
dfg_visualization.save(gviz, path)
resp = send_file(path, as_attachment=False)
file_remover.cleanup_once_done(resp, path)
return resp
else:
print("sem dados")
abort(404, description="Nao encontrado")
def filter_for_periods(detect_result, event_counts):
start_element1 = 0 if CHOSEN_PERIOD1 == 1 else detect_result[CHOSEN_PERIOD1
- 2]
end_element1 = detect_result[CHOSEN_PERIOD1 - 1]
start_element2 = 0 if CHOSEN_PERIOD2 == 1 else detect_result[CHOSEN_PERIOD2
- 2]
end_element2 = detect_result[CHOSEN_PERIOD2 - 1]
days = list(event_counts.keys())
#print(days[start_element1])
start_day1 = days[start_element1]
end_day1 = days[end_element1 - 1]
days_count1 = end_element1 - start_element1
start_day2 = days[start_element2]
end_day2 = days[end_element2 - 1]
days_count2 = end_element2 - start_element2
# Traces that are FULLY CONTAINED in the given timeframe
period_1_log = timestamp_filter.filter_traces_contained(
log, start_day1 + " 00:00:00", end_day1 + " 23:59:59")
period_2_log = timestamp_filter.filter_traces_contained(
log, start_day2 + " 00:00:00", end_day2 + " 23:59:59")
# Traces that INTERSECT with the given timeframe
# period_1_log = timestamp_filter.filter_traces_intersecting(log, start_day+" 00:00:00", end_day+" 23:59:59")
dfg1 = dfg_discovery.apply(period_1_log)
dfg2 = dfg_discovery.apply(period_2_log)
gviz1 = dfg_visualization.apply(
dfg1, log=period_1_log, variant=dfg_visualization.Variants.FREQUENCY)
dfg_visualization.view(gviz1)
# Saving the DFG
parameters = {
dfg_visualization.Variants.PERFORMANCE.value.Parameters.FORMAT: "svg"
}
gviz1 = dfg_visualization.apply(
dfg1,
log=period_1_log,
variant=dfg_visualization.Variants.FREQUENCY,
parameters=parameters)
dfg_visualization.save(gviz1, "dfg1.svg")
nodes_period1, edges_period1 = dot_to_df(gviz1)
gviz2 = dfg_visualization.apply(
dfg2, log=period_2_log, variant=dfg_visualization.Variants.FREQUENCY)
dfg_visualization.view(gviz2)
# Saving the DFG
parameters = {
dfg_visualization.Variants.PERFORMANCE.value.Parameters.FORMAT: "svg"
}
gviz2 = dfg_visualization.apply(
dfg2,
log=period_2_log,
variant=dfg_visualization.Variants.FREQUENCY,
parameters=parameters)
dfg_visualization.save(gviz2, "dfg2.svg")
return days_count1, days_count2, period_1_log, period_2_log, gviz1, gviz2
def apply_filter(req):
sessions[req.session["id"]] = datetime.now()
filters = {
"time": True,
"variants": True,
"performance": True,
"activities": True,
"attribute": True
}
req.session.set_expiry(7200)
#print(str(req.body))
o = json.loads(req.body)
print(str(o))
custom_time_range = []
for pair in o["filter1"]:
#custom_time_range.append((dateutil.parser.parse(pair[0]),dateutil.parser.parse(pair[1])))
custom_time_range.append((pair[0],pair[1]))
if o["filter1"] == []:
filters["time"] = False
#print(o["filter1"][0])
#print(custom_time_range[0][0])
#print(custom_time_range)
custom_path_range = []
for pair in o["filter2"]:
custom_path_range.append((float(pair[0]),float(pair[1])))
if o["filter2"] == []:
filters["variants"] = False
#custom_path_range = [(0,1)] #filter2
custom_performance_range = []
for pair in o["filter3"]:
custom_performance_range.append((float(pair[0]),float(pair[1])))
if o["filter3"] == []:
filters["performance"] = False
custom_activitiy_range = []
for pair in o["filter4"]:
custom_activitiy_range.append((float(pair[0]),float(pair[1])))
if o["filter4"] == []:
filters["activities"] = False
#custom_activitiy_range = [(0,1)] #filter3
custom_attribute_range = []
for pair in o["filter5"]:
custom_attribute_range.append((float(pair[0]),float(pair[1])))
if o["filter5"] == [] or o["filter5attribute"] == "Empty":
filters["attribute"] = False
additional_attribute = o["filter5attribute"]
selected_viz = o["visualization"]
calc_lev = o["distance"]
#input_file = os.path.join("webapp","static", req.session["id"] + "_l0.xes")
input_file = os.path.join("webapp","static", "sepsis.xes")
input_log = xes_importer.apply(input_file)
not_filtered_logs = {}
flatten = lambda l: [item for sublist in l for item in sublist]
time_timestamp_started = datetime.now()
if filters["time"]:
#TODO check overlapping for filter
custom_time_range = sorted(custom_time_range, reverse=False)
for i in range(0,len(custom_time_range)-1):
if(custom_time_range[i][1] > custom_time_range[i+1][0]):
response = HttpResponse(json.dumps({'error': "Wrong intervals for time filter"}))
response.status_code = 200
return response
#raise ValueError("Overlapping time ranges")
logs = []
for (x,y) in custom_time_range:
logs.append(timestamp_filter.filter_traces_contained(input_log, x, y))
#log = timestamp_filter.filter_traces_contained(input_log, custom_time_range[0][0], custom_time_range[0][1])
log = pm4py.objects.log.log.EventLog()
for timeslice in logs:
for trace in timeslice:
log.append(trace)
print(len(input_log))
print(len(log))
#l2
not_filtered_logs["timestamp_filter"] = pm4py.objects.log.log.EventLog()
for trace in input_log:
if trace not in log:
not_filtered_logs["timestamp_filter"].append(trace)
print(len(not_filtered_logs["timestamp_filter"]))
else:
log = input_log
time_variants_started = datetime.now() # where should I start?
if filters["variants"]:
variants = variants_filter.get_variants(log)
variants_count = case_statistics.get_variant_statistics(log)
variants_count = sorted(variants_count, key=lambda x: x['count'], reverse=False)
custom_path_range = sorted(custom_path_range, reverse=False)
# check overlapping
for i in range(0,len(custom_path_range)-1):
if(custom_path_range[i][1] > custom_path_range[i+1][0]):
response = HttpResponse(json.dumps({'error': "Wrong intervals for variants filter"}))
response.status_code = 200
return response
#raise ValueError("Overlapping variants ranges")
nr_variants = len(variants_count)
custom_path_range * nr_variants
idx = [(math.floor(x*nr_variants), math.ceil(y*nr_variants)) for (x,y) in custom_path_range]
variants_subset = [variants_count[x:y+1] for (x,y) in idx]
variants_subset = flatten(variants_subset)
filtered_variants = {k:v for k,v in variants.items() if k in [x["variant"] for x in variants_subset]}
#l2
not_filtered_variants = {k:v for k,v in variants.items() if k not in [x["variant"] for x in variants_subset]}
filtered_log = variants_filter.apply(log, filtered_variants)
#l2
not_filtered_logs["variant_filter"] = variants_filter.apply(log, not_filtered_variants)
else:
filtered_log = log
time_variants_finished = datetime.now() # note: incl log2 generation
if filters["performance"]:
custom_performance_range = sorted(custom_performance_range, reverse=False)
# check overlapping
for i in range(0,len(custom_performance_range)-1):
if(custom_performance_range[i][1] > custom_performance_range[i+1][0]):
response = HttpResponse(json.dumps({'error': "Wrong intervals for performance filter"}))
response.status_code = 200
return response
#raise ValueError("Overlapping performance ranges")
#all_case_durations = case_statistics.get_all_casedurations(log, parameters={case_statistics.Parameters.TIMESTAMP_KEY: "time:timestamp"})
#case_filter.filter_case_performance(log, 86400, 864000)
performances = []
for i in range(len(filtered_log)):
filtered_log[i].attributes["throughput"] = (max([event["time:timestamp"]for event in filtered_log[i]])-min([event["time:timestamp"] for event in filtered_log[i]])).total_seconds()
performances.append(filtered_log[i].attributes["throughput"])
nr_cases = len(filtered_log)
performances = sorted(performances, reverse=False)
idx = [(math.floor(x*nr_cases), math.ceil(y*nr_cases)) for (x,y) in custom_performance_range]
perf_subset = [performances[x:y+1] for (x,y) in idx]
perf_subset = flatten(perf_subset)
performance_log = pm4py.objects.log.log.EventLog([trace for trace in filtered_log if trace.attributes["throughput"] in perf_subset])
#l2
not_filtered_logs["performance_filter"] = pm4py.objects.log.log.EventLog([trace for trace in filtered_log if trace.attributes["throughput"] not in perf_subset])
#print(str(len(not_filtered_logs["performance_filter"])))
else:
performance_log = filtered_log
time_performance_finished = datetime.now()
if filters["activities"]:
variants = variants_filter.get_variants(performance_log)
variants_count = case_statistics.get_variant_statistics(performance_log)
variants_count = sorted(variants_count, key=lambda x: x['count'], reverse=False)
activities = dict()
for variant in variants_count:
for activity in variant["variant"].split(","):
if (activity not in activities.keys()):
activities[activity] = variant["count"]
else:
activities[activity] += variant["count"]
sorted_activities = {k: v for k, v in sorted(activities.items(), key=lambda item: item[1])}
activities_sorted_list = list(sorted_activities)
custom_activitiy_range = sorted(custom_activitiy_range, reverse=False)
# check overlapping
for i in range(0,len(custom_activitiy_range)-1):
if(custom_activitiy_range[i][1] > custom_activitiy_range[i+1][0]):
response = HttpResponse(json.dumps({'error': "Wrong intervals for activities filter"}))
response.status_code = 200
return response
#raise ValueError("Overlapping activities ranges")
nr_activities = len(activities_sorted_list)
idx = [(math.floor(x*nr_activities), math.ceil(y*nr_activities)) for (x,y) in custom_activitiy_range]
activities_to_keep = [activities_sorted_list[x:y+1] for (x,y) in idx]
activities_to_keep = flatten(activities_to_keep)
variants_idx = []
for i in range(len(variants_count)):
for activity in activities_to_keep:
if (activity in variants_count[i]["variant"].split(",") and (i not in variants_idx)):
variants_idx.append(i)
variants_subset = [variants_count[i] for i in variants_idx]
filtered_variants = {k:v for k,v in variants.items() if k in [x["variant"] for x in variants_subset]}
#l2
not_filtered_variants = {k:v for k,v in variants.items() if k not in [x["variant"] for x in variants_subset]}
filtered_log = variants_filter.apply(performance_log, filtered_variants)
#l2
not_filtered_logs["activities_filter"] = variants_filter.apply(performance_log, not_filtered_variants)
new_log = pm4py.objects.log.log.EventLog()
#not_filtered_logs["activities_filter_traces"] = pm4py.objects.log.log.EventLog()
for trace in filtered_log:
new_trace = pm4py.objects.log.log.Trace()
not_new_trace = pm4py.objects.log.log.Trace()
for event in trace:
if(event['concept:name'] in activities_to_keep):
new_trace.append(event)
else:
not_new_trace.append(event)
if(len(new_trace)>0):
new_log.append(new_trace)
if(len(not_new_trace)>0):
not_filtered_logs["activities_filter"].append(not_new_trace)
else:
new_log = performance_log
time_activities_finished = datetime.now()
if filters["attribute"]:
custom_attribute_range = sorted(custom_attribute_range, reverse=False)
# check overlapping
for i in range(0,len(custom_attribute_range)-1):
if(custom_attribute_range[i][1] > custom_attribute_range[i+1][0]):
response = HttpResponse(json.dumps({'error': "Wrong intervals for additional attribute filter"}))
response.status_code = 200
return response
newest_log = pm4py.objects.log.log.EventLog()
not_filtered_logs["additional_filter"] = pm4py.objects.log.log.EventLog()
traces_with_attr = []
not_traces_with_attr = []
for trace in new_log:
if additional_attribute in trace.attributes.keys():
traces_with_attr.append(trace)
else:
not_traces_with_attr.append(trace)
#check if trace attribute
if len(traces_with_attr)>0:
#check if numeric
if type(traces_with_attr[0].attributes[additional_attribute]) in [int, float]:
for trace in traces_with_attr:
if any([trace.attributes[additional_attribute] >= x and trace.attributes[additional_attribute] <= y for (x,y) in custom_attribute_range]):
newest_log.append(trace)
else:
not_filtered_logs["additional_filter"].append(trace)
for trace in not_traces_with_attr:
not_filtered_logs["additional_filter"].append(trace)
else: #string
attribute_frequencies = dict()
for trace in traces_with_attr:
if trace.attributes[additional_attribute] not in attribute_frequencies.keys():
attribute_frequencies[trace.attributes[additional_attribute]] = 0
attribute_frequencies[trace.attributes[additional_attribute]] += 1
sorted_frequencies = {k: v for k, v in sorted(attribute_frequencies.items(), key=lambda item: item[1])}
frequencies_sorted_list = list(sorted_frequencies)
nr_values = len(frequencies_sorted_list)
idx = [(math.floor(x*nr_values), math.ceil(y*nr_values)) for (x,y) in custom_attribute_range]
values_to_keep = [frequencies_sorted_list[x:y+1] for (x,y) in idx]
values_to_keep = flatten(values_to_keep)
for trace in traces_with_attr:
if trace.attributes[additional_attribute] in values_to_keep:
newest_log.append(trace)
else:
not_filtered_logs["additional_filter"].append(trace)
for trace in not_traces_with_attr:
not_filtered_logs["additional_filter"].append(trace)
else: #event attribute
if [type(event[additional_attribute]) for trace in new_log for event in trace if additional_attribute in event.keys()][0] in [int, float]:
for trace in new_log:
new_trace = pm4py.objects.log.log.Trace()
not_new_trace = pm4py.objects.log.log.Trace()
for event in trace:
if(additional_attribute in event.keys() and any([event[additional_attribute] >= x and event[additional_attribute] <= y for (x,y) in custom_attribute_range ])):
new_trace.append(event)
else:
not_new_trace.append(event)
if(len(new_trace)>0):
newest_log.append(new_trace)
if(len(not_new_trace)>0):
not_filtered_logs["additional_filter"].append(not_new_trace)
else: #string
attribute_frequencies = dict()
for trace in new_log:
for event in trace:
if additional_attribute in event.keys():
if event[additional_attribute] not in attribute_frequencies.keys():
attribute_frequencies[event[additional_attribute]] = 0
attribute_frequencies[event[additional_attribute]] += 1
sorted_frequencies = {k: v for k, v in sorted(attribute_frequencies.items(), key=lambda item: item[1])}
frequencies_sorted_list = list(sorted_frequencies)
nr_values = len(frequencies_sorted_list)
idx = [(math.floor(x*nr_values), math.ceil(y*nr_values)) for (x,y) in custom_attribute_range]
values_to_keep = [frequencies_sorted_list[x:y+1] for (x,y) in idx]
values_to_keep = flatten(values_to_keep)
for trace in new_log:
new_trace = pm4py.objects.log.log.Trace()
not_new_trace = pm4py.objects.log.log.Trace()
for event in trace:
if(additional_attribute in event.keys() and event[additional_attribute] in values_to_keep):
new_trace.append(event)
else:
not_new_trace.append(event)
if(len(new_trace)>0):
newest_log.append(new_trace)
if(len(not_new_trace)>0):
not_filtered_logs["additional_filter"].append(not_new_trace)
else:
newest_log = new_log
time_attribute_finished = datetime.now()
if(selected_viz=="dfgf"):
dfg = dfg_discovery.apply(newest_log)
gviz = dfg_visualization.apply(dfg, log=newest_log, variant=dfg_visualization.Variants.FREQUENCY)
dfg_visualization.save(gviz, os.path.join("webapp","static", req.session["id"] + "_l1.png"))
elif(selected_viz=="dfgp"):
dfg = dfg_discovery.apply(newest_log)
gviz = dfg_visualization.apply(dfg, log=newest_log, variant=dfg_visualization.Variants.PERFORMANCE)
dfg_visualization.save(gviz, os.path.join("webapp","static", req.session["id"] + "_l1.png"))
else:
heu_net = heuristics_miner.apply_heu(newest_log, parameters={"dependency_thresh": 0.99})
gviz = hn_vis_factory.apply(heu_net)
hn_vis_factory.save(gviz, os.path.join("webapp","static", req.session["id"] + "_l1.png"))
xes_exporter.apply(newest_log, os.path.join("webapp","static", req.session["id"] + "_l1.xes"))
#l2
not_filtered_log = pm4py.objects.log.log.EventLog()
for part in not_filtered_logs.keys():
for trace in not_filtered_logs[part]:
not_filtered_log.append(trace)
if(selected_viz=="dfgf"):
dfg = dfg_discovery.apply(not_filtered_log)
gviz = dfg_visualization.apply(dfg, log=not_filtered_log, variant=dfg_visualization.Variants.FREQUENCY)
dfg_visualization.save(gviz, os.path.join("webapp","static", req.session["id"] + "_l2.png"))
elif(selected_viz=="dfgp"):
dfg = dfg_discovery.apply(not_filtered_log)
gviz = dfg_visualization.apply(dfg, log=not_filtered_log, variant=dfg_visualization.Variants.PERFORMANCE)
dfg_visualization.save(gviz, os.path.join("webapp","static", req.session["id"] + "_l2.png"))
else:
heu_net = heuristics_miner.apply_heu(not_filtered_log, parameters={"dependency_thresh": 0.99})
gviz = hn_vis_factory.apply(heu_net)
hn_vis_factory.save(gviz, os.path.join("webapp","static", req.session["id"] + "_l2.png"))
xes_exporter.apply(not_filtered_log, os.path.join("webapp","static", req.session["id"] + "_l2.xes"))
if(calc_lev):
lev_new = [0]*len(newest_log)
for i in range(len(newest_log)):
lev_new[i] = [hash(event['concept:name']) for event in newest_log[i]]
lev_not = [0]*len(not_filtered_log)
for i in range(len(not_filtered_log)):
lev_not[i] = [hash(event['concept:name']) for event in not_filtered_log[i]]
distances = []
for i in range(len(lev_new)):
for j in range(len(lev_not)):
distances.append(lev_dist(lev_new[i], lev_not[j]))
lev_d = sum(distances)/len(distances)
print("Levenshtein's distance: "+str(lev_d))
else:
lev_d = "null"
used_paths = 0
for lower, higher in custom_path_range:
used_paths += round((higher-lower)*100)
print(f"Using {used_paths}% of paths. {100-used_paths}% of paths are discarded.")
print("Timestamp filter: {} seconds. \nVariants filter: {} seconds. \nPerformance filter: {} seconds. \nActivities filter: {} seconds. \nAttribute filter: {} seconds.".format((time_variants_started - time_timestamp_started).total_seconds(), (time_variants_finished - time_variants_started).total_seconds(), (time_performance_finished - time_variants_finished).total_seconds(), (time_activities_finished - time_performance_finished).total_seconds(), (time_attribute_finished - time_activities_finished).total_seconds()))
response = HttpResponse(json.dumps({'time':(time_variants_started - time_timestamp_started).total_seconds(), 'variants':(time_variants_finished - time_variants_started).total_seconds(),'performance':(time_performance_finished - time_variants_finished).total_seconds(), 'activities':(time_activities_finished - time_performance_finished).total_seconds(), 'attribute':(time_attribute_finished - time_activities_finished).total_seconds(), 'traces':[len(newest_log), len(not_filtered_log)], 'distance':lev_d}))
response.status_code = 200
return response
def discover_process_models(log_path, log_name):
custom_print('Importando log')
log_complete = xes_importer.apply(log_path)
log = variants_filter.filter_log_variants_percentage(log_complete, 0.9)
#A_ACTIVATED, A_DECLINED, A_CANCELLED
#log = attributes_filter.apply(log_complete, ["A_ACTIVATED"], parameters={attributes_filter.Parameters.ATTRIBUTE_KEY: "concept:name", attributes_filter.Parameters.POSITIVE: True})
custom_print('Log importado')
if (1 == 2):
#Inductive Miner
custom_print('Iniciando Inductive Miner')
parameters = {
inductive_miner.Variants.IM.value.Parameters.CASE_ID_KEY:
'case:concept:name',
inductive_miner.Variants.IM.value.Parameters.TIMESTAMP_KEY:
'time:timestamp'
}
variant = inductive_miner.Variants.IM
petrinet = inductive_miner.apply(log,
parameters=parameters,
variant=variant)
print_statistics(petrinet[0], 'IM')
custom_print('Inductive Miner finalizado\n')
if (1 == 2):
#Inductive Miner Infrequent 0.2
custom_print('Iniciando Inductive Miner Infrequent 0.2')
parameters = {
inductive_miner.Variants.IMf.value.Parameters.NOISE_THRESHOLD:
0.2,
inductive_miner.Variants.IMf.value.Parameters.CASE_ID_KEY:
'case:concept:name',
inductive_miner.Variants.IMf.value.Parameters.TIMESTAMP_KEY:
'time:timestamp'
}
variant = inductive_miner.Variants.IMf
petrinet = inductive_miner.apply(log,
parameters=parameters,
variant=variant)
print_statistics(petrinet[0], 'IMf0.2')
custom_print('Inductive Miner Infrequent 0.2 finalizado\n')
if (1 == 1):
#Inductive Miner Infrequent 0.5
custom_print('Iniciando Inductive Miner Infrequent 0.5')
parameters = {
inductive_miner.Variants.IMf.value.Parameters.NOISE_THRESHOLD:
0.5,
inductive_miner.Variants.IMf.value.Parameters.CASE_ID_KEY:
'case:concept:name',
inductive_miner.Variants.IMf.value.Parameters.TIMESTAMP_KEY:
'time:timestamp'
}
variant = inductive_miner.Variants.IMf
petrinet, initial_marking, final_marking = inductive_miner.apply(
log, parameters=parameters, variant=variant)
print_statistics(petrinet, 'IMf0.5')
custom_print('Inductive Miner Infrequent 0.5 finalizado\n')
ts = reachability_graph.construct_reachability_graph(
petrinet, initial_marking)
gviz = ts_visualizer.apply(
ts,
parameters={
ts_visualizer.Variants.VIEW_BASED.value.Parameters.FORMAT:
"png"
})
gviz.render('petrinets/simple-reach', cleanup=True)
pnml_exporter.apply(petrinet, initial_marking,
"petrinets/simple-petri.pnml")
if (1 == 2):
#Inductive Miner Infrequent 0.8
custom_print('Iniciando Inductive Miner Infrequent 0.8')
parameters = {
inductive_miner.Variants.IMf.value.Parameters.NOISE_THRESHOLD:
0.8,
inductive_miner.Variants.IMf.value.Parameters.CASE_ID_KEY:
'case:concept:name',
inductive_miner.Variants.IMf.value.Parameters.TIMESTAMP_KEY:
'time:timestamp'
}
variant = inductive_miner.Variants.IMf
petrinet = inductive_miner.apply(log,
parameters=parameters,
variant=variant)
print_statistics(petrinet[0], 'IMf0.8')
custom_print('Inductive Miner Infrequent 0.8 finalizado\n')
if (1 == 2):
#Inductive Miner Directly-Follows
custom_print('Iniciando Inductive Miner Directly-Follows')
parameters = {
inductive_miner.Variants.IMd.value.Parameters.CASE_ID_KEY:
'case:concept:name',
inductive_miner.Variants.IMd.value.Parameters.TIMESTAMP_KEY:
'time:timestamp'
}
variant = inductive_miner.Variants.IMd
petrinet = inductive_miner.apply(log,
parameters=parameters,
variant=variant)
print_statistics(petrinet[0], 'IMd')
custom_print('Inductive Miner Infrequent Directly-Follows\n')
if (1 == 2):
#Alpha Miner
custom_print('Iniciando Alpha Miner')
parameters = {}
variant = alpha_miner.Variants.ALPHA_VERSION_CLASSIC
petrinet = alpha_miner.apply(log,
parameters=parameters,
variant=variant)
print_statistics(petrinet[0], 'Alpha')
custom_print('Alpha Miner finalizado\n')
if (1 == 2):
#Heuristic Miner 0.5
custom_print('Iniciando Heuristic Miner 0.5')
parameters = {
heuristics_miner.Variants.CLASSIC.value.Parameters.DEPENDENCY_THRESH:
0.5
}
petrinet = heuristics_miner.apply(log, parameters=parameters)
print_statistics(petrinet[0], 'HM0.5')
custom_print('Heuristic Miner 0.5 finalizado\n')
if (1 == 2):
#Heuristic Miner 0.99
custom_print('Iniciando Heuristic Miner 0.99')
parameters = {
heuristics_miner.Variants.CLASSIC.value.Parameters.DEPENDENCY_THRESH:
0.99
}
petrinet = heuristics_miner.apply(log, parameters=parameters)
print_statistics(petrinet[0], 'HM0.99')
custom_print('Heuristic Miner 0.99 finalizado\n')
if (1 == 2):
#Heuristic Miner 0.1
custom_print('Iniciando Heuristic Miner 0.1')
parameters = {
heuristics_miner.Variants.CLASSIC.value.Parameters.DEPENDENCY_THRESH:
0.1
}
petrinet = heuristics_miner.apply(log, parameters=parameters)
print_statistics(petrinet[0], 'HM0.1')
custom_print('Heuristic Miner 0.1 finalizado\n')
if (1 == 2):
#Heuristic Miner 1.0
custom_print('Iniciando Heuristic Miner 1.0')
parameters = {
heuristics_miner.Variants.CLASSIC.value.Parameters.DEPENDENCY_THRESH:
1.0
}
petrinet = heuristics_miner.apply(log, parameters=parameters)
print_statistics(petrinet[0], 'HM1.0')
custom_print('Heuristic Miner 1.0 finalizado\n')
if (1 == 2):
#DFG
custom_print('Iniciando DFG')
dfg = dfg_discovery.apply(log)
parameters = {
dfg_visualization.Variants.FREQUENCY.value.Parameters.FORMAT: 'png'
}
gviz = dfg_visualization.apply(
dfg,
log=log,
variant=dfg_visualization.Variants.FREQUENCY,
parameters=parameters)
dfg_visualization.save(gviz, 'petrinets/simple-DFG.png')
custom_print('DFG finalizado\n')
#with performance
from pm4py.algo.discovery.dfg import algorithm as dfg_discovery
from pm4py.visualization.dfg import visualizer as dfg_visualization
dfg = dfg_discovery.apply(log, variant=dfg_discovery.Variants.PERFORMANCE)
gviz = dfg_visualization.apply(dfg, log=log, variant=dfg_visualization.Variants.PERFORMANCE)
dfg_visualization.view(gviz)
#svg format
from pm4py.algo.discovery.dfg import algorithm as dfg_discovery
from pm4py.visualization.dfg import visualizer as dfg_visualization
dfg = dfg_discovery.apply(log, variant=dfg_discovery.Variants.PERFORMANCE)
parameters = {dfg_visualization.Variants.PERFORMANCE.value.Parameters.FORMAT: "svg"}
gviz = dfg_visualization.apply(dfg, log=log, variant=dfg_visualization.Variants.PERFORMANCE, parameters=parameters)
dfg_visualization.save(gviz, "dfg.svg")
#Conver DF graph to a workflow net
from pm4py.objects.log.importer.xes import importer as xes_importer
import os
filepath = os.path.join('E:/data/pm/running-example.xes')
log = xes_importer.apply(filepath)
from pm4py.algo.discovery.dfg import algorithm as dfg_discovery
dfg = dfg_discovery.apply(log)
from pm4py.objects.conversion.dfg import converter as dfg_mining
net, im, fm = dfg_mining.apply(dfg)
net
def create_process_models(output_case_traces_cluster, path_data_sources,
dir_runtime_files, dir_dfg_cluster_files,
filename_dfg_cluster, rel_proportion_dfg_threshold,
logging_level):
"""
Creates directly follows graphs out of a event log.
:param output_case_traces_cluster: traces that are visualised
:param path_data_sources: path of sources and outputs
:param dir_runtime_files: folder containing files read and written during runtime
:param dir_dfg_cluster_files: folder containing dfg png files
:param filename_dfg_cluster: filename of dfg file (per cluster)
:param rel_proportion_dfg_threshold: threshold for filtering out sensors in dfg relative to max occurrences of a sensor
:param logging_level: level of logging
:return:
"""
# keep only needed columns
output_case_traces_cluster = output_case_traces_cluster.reindex(
columns={'Case', 'LC_Activity', 'Timestamp', 'Cluster'})
output_case_traces_cluster = output_case_traces_cluster.rename(
columns={
'Case': 'case:concept:name',
'LC_Activity': 'concept:name',
'Timestamp': 'time:timestamp'
})
# create directory for dfg pngs
os.mkdir(path_data_sources + dir_runtime_files + dir_dfg_cluster_files)
# create dfg for each cluster
clusters = output_case_traces_cluster.Cluster.unique()
for cluster in clusters:
log = output_case_traces_cluster.loc[output_case_traces_cluster.Cluster
== cluster]
log = log.astype(str)
# convert pandas data frame to pm4py event log for further processing
log = log_converter.apply(log)
# keep only activities with more than certain number of occurrences
activities = attributes_get.get_attribute_values(log, 'concept:name')
# determine that number relative to the max number of occurrences of a sensor in a cluster. (the result is
# the threshold at which an activity/activity strand is kept)
min_number_of_occurrences = round(
(max(activities.values()) * rel_proportion_dfg_threshold), 0)
activities = {
x: y
for x, y in activities.items() if y >= min_number_of_occurrences
}
log = attributes_filter.apply(log, activities)
# create dfg out of event log
dfg = dfg_discovery.apply(log)
# define start and
start_activities = sa_get.get_start_activities(log)
end_activities = ea_get.get_end_activities(log)
# create png of dfg (if the graph does not show a graph, it is possible that the sensors did not trigger often)
gviz = dfg_visualization.apply(
dfg=dfg,
log=log,
variant=dfg_visualization.Variants.FREQUENCY,
parameters={
'start_activities': start_activities,
'end_activities': end_activities
})
dfg_visualization.save(
gviz,
path_data_sources + dir_runtime_files + dir_dfg_cluster_files +
(filename_dfg_cluster.format(cluster=str(cluster))))
# logger
logger = logging.getLogger(inspect.stack()[0][3])
logger.setLevel(logging_level)
logger.info("Saved directly follows graphs into '../%s'.",
path_data_sources + dir_runtime_files + dir_dfg_cluster_files)