def test_class_nb(self):
job = create_test_job(
predictive_model=create_test_predictive_model(
prediction_method=ClassificationMethods.
MULTINOMIAL_NAIVE_BAYES.value),
labelling=create_test_labelling(
label_type=LabelTypes.ATTRIBUTE_STRING.value,
attribute_name='concept:name'),
clustering=create_test_clustering(
clustering_type=ClusteringMethods.NO_CLUSTER.value))
result, _ = calculate(job)
del result['elapsed_time']
self.assertDictEqual(
result, {
'f1score': 0.0,
'acc': 0.0,
'precision': 0.0,
'recall': 0.0,
'true_positive': 0,
'true_negative': 0,
'false_negative': 2,
'false_positive': 0,
'auc': 0.0
})
def test_next_activity(self):
labelling = create_test_labelling(
label_type=LabelTypes.NEXT_ACTIVITY.value)
encoding = create_test_encoding(
value_encoding=ValueEncodings.BOOLEAN.value,
prefix_length=3,
task_generation_type=TaskGenerationTypes.ONLY_THIS.value)
_, df = encode_label_logs(
self.test_log, self.test_log,
create_test_job(
encoding=encoding,
labelling=labelling,
predictive_model=create_test_predictive_model(
predictive_model=PredictiveModels.CLASSIFICATION.value)))
self.assertEqual(df.shape, (2, 9))
trace_5 = df[df.trace_id == '5'].iloc[0].values.tolist()
self.assertListEqual(
trace_5,
['5', True, True, True, False, False, False, False, 'decide'])
trace_4 = df[df.trace_id == '4'].iloc[0].values.tolist()
self.assertListEqual(
trace_4,
['4', True, False, True, False, False, False, True, 'decide'])
def test_explain(self):
split = create_test_split(
split_type=SplitTypes.SPLIT_DOUBLE.value,
split_ordering_method=SplitOrderingMethods.SPLIT_SEQUENTIAL.value,
test_size=0.2,
original_log=None,
train_log=create_test_log(
log_name='train_explainability.xes',
log_path='cache/log_cache/test_logs/train_explainability.xes'),
test_log=create_test_log(
log_name='test_explainability.xes',
log_path='cache/log_cache/test_logs/test_explainability.xes'))
predictive_model = create_test_predictive_model(
predictive_model=PredictiveModels.CLASSIFICATION.value,
prediction_method=ClassificationMethods.DECISION_TREE.value)
job = create_test_job(
split=split,
encoding=create_test_encoding(
prefix_length=4,
padding=True,
value_encoding=ValueEncodings.SIMPLE_INDEX.value),
labelling=create_test_labelling(
label_type=LabelTypes.ATTRIBUTE_STRING.value,
attribute_name='label'),
clustering=None,
create_models=True,
predictive_model=predictive_model,
job_type=JobTypes.PREDICTION.value,
hyperparameter_optimizer=None,
incremental_train=None)
prediction_task(job.id, do_publish_result=False)
job.refresh_from_db()
exp = Explanation.objects.get_or_create(
type=ExplanationTypes.ICE.value,
split=split,
predictive_model=predictive_model,
job=job,
results={})[0]
training_df_old, test_df_old = get_encoded_logs(job)
explanation_target = 'prefix_2'
explanation = explain(exp,
training_df_old,
test_df_old,
explanation_target,
prefix_target=None)
expected = [{
'value': 'Contact Hospital',
'label': 1.2962962962962963,
'count': 351
}, {
'value': 'Create Questionnaire',
'label': 1.5526992287917738,
'count': 1167
}, {
'value': 'High Insurance Check',
'label': 1.2667660208643816,
'count': 671
}]
self.assertEqual(expected, explanation)
def test_prefix1_no_label(self):
labelling = create_test_labelling(label_type=LabelTypes.NO_LABEL.value)
df = frequency(self.log, self.event_names, labelling, self.encoding)
self.assertEqual(df.shape, (2, 8))
self.assertNotIn('label', df.columns.values.tolist())
def test_remaining_time(self):
job = self.get_job()
job.labelling = create_test_labelling(label_type=LabelTypes.REMAINING_TIME.value)
job.save()
result, _ = calculate(job)
self.assertEqual(result, {'true': 529, 'false': 354})