def test_csv(self):
df = pd.read_csv("input_data/running-example.csv")
df = pm4py.format_dataframe(df, case_id="case:concept:name", activity_key="concept:name",
timestamp_key="time:timestamp")
log2 = pm4py.convert_to_event_log(df)
stream1 = pm4py.convert_to_event_stream(log2)
df2 = pm4py.convert_to_dataframe(log2)
pm4py.write_xes(log2, "test_output_data/log.xes")
os.remove("test_output_data/log.xes")
def renameTasks(self, names, datapath):
if names != {}:
try:
for ic, case in enumerate(self.log):
for ie, event in enumerate(case):
if event['cluster'] in names:
self.log[ic][ie]['concept:name'] = names[
event['cluster']]
pm.write_xes(self.log,
os.path.join(datapath, self.name + ".xes"))
except:
def exportSubP(self, y_pred, center, name, encoding, alg):
path = os.pardir + '/outputLog/' + encoding + '/' + alg
try:
os.makedirs(path, exist_ok=True)
except OSError:
print("Creation of the directory %s failed" % path)
else:
print("Successfully created the directory %s " % path)
frames = [[] for i in range(max(y_pred) + 1)]
for i, s in enumerate(self.sessions):
frames[y_pred[i]].extend(s.export(self.attrNames, i))
for i in range(max(y_pred) + 1):
ind = list(
np.flip(np.argsort(centers[i][:len(self.distinct)])[-1:]))
subP = concatName(self.distinct, ind)
newFile = name + str(i) + subP + '.xes'
log = pd.concat(frames[i], ignore_index=True)
log = pm.format_dataframe(log,
case_id='case',
activity_key='concept:name',
timestamp_key='time:timestamp')
log = pm.convert_to_event_log(log)
pm.write_xes(log, os.path.join(path, newFile))
print("Sessions exported")
def convertLog(self,
centers,
y_pred,
name,
encoding,
alg,
datapath,
exportSes=False):
start = time.time()
frames = []
log = pd.DataFrame()
for i, s in enumerate(self.sessions):
abstracted = s.convertSession(centers[y_pred[i]], y_pred[i],
self.distinct, self.attrNames)
frames.append(abstracted)
log = pd.concat(frames, ignore_index=True)
log = pm.format_dataframe(log,
case_id='case',
activity_key='concept:name',
timestamp_key='time:timestamp')
num = math.ceil(len(log) * 0.7)
log1 = log[:num]
log2 = log[num:]
log = pm.convert_to_event_log(log)
log1 = pm.convert_to_event_log(log1)
log2 = pm.convert_to_event_log(log2)
pm.write_xes(log1, os.path.join(datapath, name + "train.xes"))
pm.write_xes(log2, os.path.join(datapath, name + "test.xes"))
pm.write_xes(log, os.path.join(datapath, name + ".xes"))
if exportSes:
self.exportSubP(y_pred, centers, name, encoding, alg)
print("Convertion Time:", time.time() - start)
def execute_script():
ENABLE_VISUALIZATION = True
# reads a XES into an event log
log1 = pm4py.read_xes("../tests/input_data/running-example.xes")
# reads a CSV into a dataframe
df = pd.read_csv("../tests/input_data/running-example.csv")
# formats the dataframe with the mandatory columns for process mining purposes
df = pm4py.format_dataframe(df,
case_id="case:concept:name",
activity_key="concept:name",
timestamp_key="time:timestamp")
# converts the dataframe to an event log
log2 = pm4py.convert_to_event_log(df)
# converts the log read from XES into a stream and dataframe respectively
stream1 = pm4py.convert_to_event_stream(log1)
df2 = pm4py.convert_to_dataframe(log1)
# writes the log1 to a XES file
pm4py.write_xes(log1, "ru1.xes")
dfg, dfg_sa, dfg_ea = pm4py.discover_dfg(log1)
petri_alpha, im_alpha, fm_alpha = pm4py.discover_petri_net_alpha(log1)
petri_inductive, im_inductive, fm_inductive = pm4py.discover_petri_net_inductive(
log1)
petri_heuristics, im_heuristics, fm_heuristics = pm4py.discover_petri_net_heuristics(
log1)
tree_inductive = pm4py.discover_tree_inductive(log1)
heu_net = pm4py.discover_heuristics_net(log1)
pm4py.write_dfg(dfg, dfg_sa, dfg_ea, "ru_dfg.dfg")
pm4py.write_petri_net(petri_alpha, im_alpha, fm_alpha, "ru_alpha.pnml")
pm4py.write_petri_net(petri_inductive, im_inductive, fm_inductive,
"ru_inductive.pnml")
pm4py.write_petri_net(petri_heuristics, im_heuristics, fm_heuristics,
"ru_heuristics.pnml")
pm4py.write_process_tree(tree_inductive, "ru_inductive.ptml")
dfg, dfg_sa, dfg_ea = pm4py.read_dfg("ru_dfg.dfg")
petri_alpha, im_alpha, fm_alpha = pm4py.read_petri_net("ru_alpha.pnml")
petri_inductive, im_inductive, fm_inductive = pm4py.read_petri_net(
"ru_inductive.pnml")
petri_heuristics, im_heuristics, fm_heuristics = pm4py.read_petri_net(
"ru_heuristics.pnml")
tree_inductive = pm4py.read_process_tree("ru_inductive.ptml")
pm4py.save_vis_petri_net(petri_alpha, im_alpha, fm_alpha, "ru_alpha.png")
pm4py.save_vis_petri_net(petri_inductive, im_inductive, fm_inductive,
"ru_inductive.png")
pm4py.save_vis_petri_net(petri_heuristics, im_heuristics, fm_heuristics,
"ru_heuristics.png")
pm4py.save_vis_process_tree(tree_inductive, "ru_inductive_tree.png")
pm4py.save_vis_heuristics_net(heu_net, "ru_heunet.png")
pm4py.save_vis_dfg(dfg, dfg_sa, dfg_ea, "ru_dfg.png")
if ENABLE_VISUALIZATION:
pm4py.view_petri_net(petri_alpha, im_alpha, fm_alpha, format="svg")
pm4py.view_petri_net(petri_inductive,
im_inductive,
fm_inductive,
format="svg")
pm4py.view_petri_net(petri_heuristics,
im_heuristics,
fm_heuristics,
format="svg")
pm4py.view_process_tree(tree_inductive, format="svg")
pm4py.view_heuristics_net(heu_net, format="svg")
pm4py.view_dfg(dfg, dfg_sa, dfg_ea, format="svg")
aligned_traces = pm4py.conformance_alignments(log1, petri_inductive,
im_inductive, fm_inductive)
replayed_traces = pm4py.conformance_tbr(log1, petri_inductive,
im_inductive, fm_inductive)
fitness_tbr = pm4py.evaluate_fitness_tbr(log1, petri_inductive,
im_inductive, fm_inductive)
print("fitness_tbr", fitness_tbr)
fitness_align = pm4py.evaluate_fitness_alignments(log1, petri_inductive,
im_inductive,
fm_inductive)
print("fitness_align", fitness_align)
precision_tbr = pm4py.evaluate_precision_tbr(log1, petri_inductive,
im_inductive, fm_inductive)
print("precision_tbr", precision_tbr)
precision_align = pm4py.evaluate_precision_alignments(
log1, petri_inductive, im_inductive, fm_inductive)
print("precision_align", precision_align)
print("log start activities = ", pm4py.get_start_activities(log2))
print("df start activities = ", pm4py.get_start_activities(df2))
print("log end activities = ", pm4py.get_end_activities(log2))
print("df end activities = ", pm4py.get_end_activities(df2))
print("log attributes = ", pm4py.get_attributes(log2))
print("df attributes = ", pm4py.get_attributes(df2))
print("log org:resource values = ",
pm4py.get_attribute_values(log2, "org:resource"))
print("df org:resource values = ",
pm4py.get_attribute_values(df2, "org:resource"))
print("start_activities len(filt_log) = ",
len(pm4py.filter_start_activities(log2, ["register request"])))
print("start_activities len(filt_df) = ",
len(pm4py.filter_start_activities(df2, ["register request"])))
print("end_activities len(filt_log) = ",
len(pm4py.filter_end_activities(log2, ["pay compensation"])))
print("end_activities len(filt_df) = ",
len(pm4py.filter_end_activities(df2, ["pay compensation"])))
print(
"attributes org:resource len(filt_log) (cases) cases = ",
len(
pm4py.filter_attribute_values(log2,
"org:resource", ["Ellen"],
level="case")))
print(
"attributes org:resource len(filt_log) (cases) events = ",
len(
pm4py.filter_attribute_values(log2,
"org:resource", ["Ellen"],
level="event")))
print(
"attributes org:resource len(filt_df) (events) cases = ",
len(
pm4py.filter_attribute_values(df2,
"org:resource", ["Ellen"],
level="case")))
print(
"attributes org:resource len(filt_df) (events) events = ",
len(
pm4py.filter_attribute_values(df2,
"org:resource", ["Ellen"],
level="event")))
print(
"attributes org:resource len(filt_df) (events) events notpositive = ",
len(
pm4py.filter_attribute_values(df2,
"org:resource", ["Ellen"],
level="event",
retain=False)))
print("variants log = ", pm4py.get_variants(log2))
print("variants df = ", pm4py.get_variants(df2))
print(
"variants filter log = ",
len(
pm4py.filter_variants(log2, [[
"register request", "examine thoroughly", "check ticket",
"decide", "reject request"
]])))
print(
"variants filter df = ",
len(
pm4py.filter_variants(df2, [[
"register request", "examine thoroughly", "check ticket",
"decide", "reject request"
]])))
print("variants filter percentage = ",
len(pm4py.filter_variants_percentage(log2, threshold=0.8)))
print(
"paths filter log len = ",
len(
pm4py.filter_directly_follows_relation(
log2, [("register request", "examine casually")])))
print(
"paths filter dataframe len = ",
len(
pm4py.filter_directly_follows_relation(
df2, [("register request", "examine casually")])))
print(
"timeframe filter log events len = ",
len(
pm4py.filter_time_range(log2,
"2011-01-01 00:00:00",
"2011-02-01 00:00:00",
mode="events")))
print(
"timeframe filter log traces_contained len = ",
len(
pm4py.filter_time_range(log2,
"2011-01-01 00:00:00",
"2011-02-01 00:00:00",
mode="traces_contained")))
print(
"timeframe filter log traces_intersecting len = ",
len(
pm4py.filter_time_range(log2,
"2011-01-01 00:00:00",
"2011-02-01 00:00:00",
mode="traces_intersecting")))
print(
"timeframe filter df events len = ",
len(
pm4py.filter_time_range(df2,
"2011-01-01 00:00:00",
"2011-02-01 00:00:00",
mode="events")))
print(
"timeframe filter df traces_contained len = ",
len(
pm4py.filter_time_range(df2,
"2011-01-01 00:00:00",
"2011-02-01 00:00:00",
mode="traces_contained")))
print(
"timeframe filter df traces_intersecting len = ",
len(
pm4py.filter_time_range(df2,
"2011-01-01 00:00:00",
"2011-02-01 00:00:00",
mode="traces_intersecting")))
# remove the temporary files
os.remove("ru1.xes")
os.remove("ru_dfg.dfg")
os.remove("ru_alpha.pnml")
os.remove("ru_inductive.pnml")
os.remove("ru_heuristics.pnml")
os.remove("ru_inductive.ptml")
os.remove("ru_alpha.png")
os.remove("ru_inductive.png")
os.remove("ru_heuristics.png")
os.remove("ru_inductive_tree.png")
os.remove("ru_heunet.png")
os.remove("ru_dfg.png")
os.environ['PATH'] += os.pathsep + '/usr/local/bin'
##1
# Preparing the log
event_log = pd.read_csv('running-exampleNew.csv', sep=';')
event_log = pm4py.format_dataframe(event_log,
case_id='case_id',
activity_key='activity',
timestamp_key='timestamp')
start_activities = pm4py.get_start_activities(event_log)
end_activities = pm4py.get_end_activities(event_log)
print("Start activities: {}\nEnd activities: {}".format(
start_activities, end_activities))
# Convert from CSV to XES
pm4py.write_xes(event_log, 'running-example-exported.xes')
# Algorithm alpha
log = pm4py.read_xes('running-example-exported.xes')
net, initial_marking, final_marking = pm4py.algo.discovery.alpha.algorithm.apply(
log)
pm4py.view_petri_net(net, initial_marking, final_marking)
##2
# Preparing the log --- Resource
event_log = pd.read_csv('running-exampleNew.csv', sep=';')
event_log = pm4py.format_dataframe(event_log,
case_id='case_id',
activity_key='resource',
timestamp_key='timestamp')
start_activities = pm4py.get_start_activities(event_log)
