def experiment_outliers():
with open("model_30000", "rb") as fin:
model = pickle.load(fin)
train = LogFile("../Data/bpic2018.csv",
",",
0,
30000,
"startTime",
"case",
activity_attr=None,
integer_input=False,
convert=False)
train.remove_attributes([
"eventid", "identity_id", "event_identity_id", "year", "penalty_",
"amount_applied", "payment_actual", "penalty_amount", "risk_factor",
"cross_compliance", "selected_random", "selected_risk",
"selected_manually", "rejected"
])
train.convert2int()
attr_dicts = []
data = LogFile("../Data/bpic2018.csv",
",",
0,
None,
"startTime",
"case",
convert=False,
values=train.values)
data.filter("self.data.year == 1")
data.remove_attributes([
"event_identity_id", "year", "penalty_", "amount_applied",
"payment_actual", "penalty_amount", "risk_factor", "cross_compliance",
"selected_random", "selected_risk", "selected_manually", "rejected"
])
scores = cd.get_event_scores(data, model)
for s in scores:
if sum(scores[s]) != 0:
score = math.log10(sum(scores[s]) / len(scores[s]))
if score < -12:
for case in attr_dicts[0]:
if attr_dicts[0][case] == s:
print(s, case, score)
def experiment_clusters():
with open("model_30000", "rb") as fin:
model = pickle.load(fin)
train = LogFile("../Data/bpic2018.csv", ",", 0, 30000, "startTime", "case", activity_attr=None, integer_input=False, convert=False)
train.remove_attributes(["eventid", "identity_id", "event_identity_id", "year", "penalty_", "amount_applied", "payment_actual", "penalty_amount", "risk_factor", "cross_compliance", "selected_random", "selected_risk", "selected_manually", "rejected"])
train.convert2int()
data = LogFile("../Data/bpic2018.csv", ",", 0, None, "startTime", "case", convert=False, values=train.values)
data.remove_attributes(["event_identity_id", "year", "penalty_", "amount_applied", "payment_actual",
"penalty_amount", "risk_factor", "cross_compliance", "selected_random",
"selected_risk", "selected_manually", "rejected"])
data.convert2int()
data.filter("self.data.year == 1")
scores = cd.get_event_detailed_scores(data, model)
# First calculate score per trace
attributes = list(scores.keys())
num_traces = len(scores[attributes[0]])
upper = {}
lower = {}
for a in attributes:
upper[a] = []
lower[a] = []
for trace_ix in range(num_traces):
score = 1
for a in scores:
a_score = scores[a][trace_ix]
if a_score == -5:
score = 0
break
score *= a_score
if -8 < score < -10:
for a in scores:
upper[a].append(scores[a][trace_ix])
elif -10 < score < -12:
for a in scores:
lower[a].append(scores[a][trace_ix])
print(attributes)
print(upper)
cd.plot_attribute_graph(upper, attributes)
cd.plot_attribute_graph(lower, attributes)
