def test_next_activity_zero_padding_elapsed_time(self):
labelling = create_test_labelling(
label_type=LabelTypes.NEXT_ACTIVITY.value)
encoding = create_test_encoding(
value_encoding=ValueEncodings.SIMPLE_INDEX.value,
add_elapsed_time=True,
task_generation_type=TaskGenerationTypes.ONLY_THIS.value,
prefix_length=10,
padding=True)
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, 13))
self.assertTrue('elapsed_time' in df.columns.values.tolist())
trace_5 = df[df.trace_id == '5'].iloc[0].values.tolist()
self.assertListEqual(trace_5,
['5', 1, 3, 2, 2, 2, 0, 0, 0, 0, 1296240.0, 2])
trace_4 = df[df.trace_id == '4'].iloc[0].values.tolist()
self.assertListEqual(trace_4, [
'4', 52903968, 32171502, 17803069, 1149821, 72523760, 0, 0, 0, 0,
0, 520920.0, 0
])
def test_label_remaining_time_with_elapsed_time_custom_threshold(self):
encoding = create_test_encoding(
value_encoding=ValueEncodings.SIMPLE_INDEX.value,
add_elapsed_time=True,
add_remaining_time=True,
task_generation_type=TaskGenerationTypes.ONLY_THIS.value,
prefix_length=2)
labelling = create_test_labelling(
label_type=LabelTypes.REMAINING_TIME.value,
threshold_type=ThresholdTypes.THRESHOLD_CUSTOM.value,
threshold=40000)
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, 5))
self.assertListEqual(
df.columns.values.tolist(),
['trace_id', 'prefix_1', 'prefix_2', 'elapsed_time', 'label'])
trace_5 = df[df.trace_id == '5'].iloc[0].values.tolist()
self.assertListEqual(trace_5, ['5', 1, 2, 0, 0])
trace_4 = df[df.trace_id == '4'].iloc[0].values.tolist()
self.assertListEqual(trace_4, ['4', 1, 1, 0, 0])
def test_attribute_number(self):
encoding = create_test_encoding(
value_encoding=ValueEncodings.BOOLEAN.value,
prefix_length=2,
task_generation_type=TaskGenerationTypes.ONLY_THIS.value)
labelling = create_test_labelling(
label_type=LabelTypes.ATTRIBUTE_NUMBER.value,
attribute_name='AMOUNT')
_, 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, False, False, False, False, False, False])
trace_4 = df[df.trace_id == '4'].iloc[0].values.tolist()
self.assertListEqual(
trace_4,
['4', True, False, True, False, False, False, False, True])
def test_hyperopt(self):
job = Job.objects.create(
split=create_test_split(split_type=SplitTypes.SPLIT_SINGLE.value,
original_log=create_test_log(
log_name=general_example_filename,
log_path=general_example_filepath)),
encoding=create_test_encoding(
value_encoding=ValueEncodings.SIMPLE_INDEX.value,
prefix_length=3,
padding=False),
labelling=create_test_labelling(
label_type=LabelTypes.REMAINING_TIME.value),
clustering=create_test_clustering(
clustering_type=ClusteringMethods.KMEANS.value),
predictive_model=create_test_predictive_model(
predictive_model=PredictiveModels.CLASSIFICATION.value,
prediction_method=ClassificationMethods.RANDOM_FOREST.value),
hyperparameter_optimizer=create_test_hyperparameter_optimizer(
hyperoptim_type=HyperparameterOptimizationMethods.HYPEROPT.
value,
performance_metric=HyperOptLosses.ACC.value,
max_evals=2))
prediction_task(job.pk)
job = Job.objects.get(pk=1)
self.assertFalse(classification_random_forest(
) == job.predictive_model.classification.__getattribute__(
ClassificationMethods.RANDOM_FOREST.value.lower()).to_dict())
def test_ValueError_decode(self):
try:
encoder = Encoder(df=self.df, encoding=self.encoding)
encoder.decode(df=self.df,
encoding=create_test_encoding(data_encoding='None'))
except ValueError:
pass
def test_rnn_time_series_predictor_complex_no_exceptions(self):
encoding = create_test_encoding(
value_encoding=ValueEncodings.COMPLEX.value,
prefix_length=5,
padding=True)
labelling = create_test_labelling(
label_type=LabelTypes.DURATION.value,
threshold_type=ThresholdTypes.THRESHOLD_MEAN.value)
train_df = complex(self.train_log, labelling, encoding,
self.train_add_col)
test_df = complex(self.test_log, labelling, encoding,
self.test_add_col)
train_df, targets_df = self._drop_columns_and_split(train_df)
test_df, _ = self._drop_columns_and_split(test_df)
config = self._get_rnn_default_config(
encoding=ValueEncodings.COMPLEX.value)
rnn_time_series_predictor = RNNTimeSeriesPredictor(**config)
# with HidePrints():
rnn_time_series_predictor.fit(train_df)
rnn_time_series_predictor.predict(test_df)
def test_NotImplementedException_init_encoder(self):
try:
Encoder(df=self.df,
encoding=create_test_encoding(
data_encoding=DataEncodings.ONE_HOT_ENCODER.value))
except NotImplementedError:
pass
def test_nn_regressor_complex_no_exceptions(self):
encoding = create_test_encoding(
value_encoding=ValueEncodings.COMPLEX.value,
prefix_length=2,
padding=True)
labelling = create_test_labelling(
label_type=LabelTypes.REMAINING_TIME.value)
train_df = complex(self.train_log, labelling, encoding,
self.train_add_col)
test_df = complex(self.test_log, labelling, encoding,
self.test_add_col)
train_df, targets_df = self._drop_columns_and_split(train_df)
targets_df = targets_df.values.ravel()
test_df, _ = self._drop_columns_and_split(test_df)
config = self._get_nn_default_config(
encoding=ValueEncodings.COMPLEX.value)
nn_regressor = NNRegressor(**config)
# with HidePrints():
nn_regressor.fit(train_df, targets_df)
nn_regressor.predict(test_df)
def test_next_activity_zero_padding_elapsed_time(self):
labelling = create_test_labelling(
label_type=LabelTypes.NEXT_ACTIVITY.value)
encoding = create_test_encoding(
value_encoding=ValueEncodings.BOOLEAN.value,
add_elapsed_time=True,
task_generation_type=TaskGenerationTypes.ONLY_THIS.value,
prefix_length=3)
_, 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, 10))
self.assertTrue('elapsed_time' in df.columns.values.tolist())
trace_5 = df[df.trace_id == '5'].iloc[0].values.tolist()
self.assertListEqual(trace_5, [
'5', True, True, True, False, False, False, False, 181200.0,
'decide'
])
trace_4 = df[df.trace_id == '4'].iloc[0].values.tolist()
self.assertListEqual(trace_4, [
'4', True, False, True, False, False, False, True, 171660.0,
'decide'
])
def test_label_remaining_time_with_elapsed_time_custom_threshold(self):
labelling = create_test_labelling(
label_type=LabelTypes.REMAINING_TIME.value,
threshold_type=ThresholdTypes.THRESHOLD_CUSTOM.value,
threshold=40000)
encoding = create_test_encoding(
value_encoding=ValueEncodings.BOOLEAN.value,
prefix_length=3,
add_elapsed_time=True,
add_remaining_time=True,
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, 10))
trace_5 = df[df.trace_id == '5'].iloc[0].values.tolist()
self.assertListEqual(trace_5, [
'5', True, True, True, False, False, False, False, 181200.0, False
])
trace_4 = df[df.trace_id == '4'].iloc[0].values.tolist()
self.assertListEqual(trace_4, [
'4', True, False, True, False, False, False, True, 171660.0, False
])
def test_next_activity_kmeans(self):
self.max_diff = None
job = create_test_job(
clustering=create_test_clustering(
clustering_type=ClusteringMethods.KMEANS.value),
split=repair_example(),
encoding=create_test_encoding(prefix_length=8, padding=True),
labelling=create_test_labelling(
label_type=LabelTypes.NEXT_ACTIVITY.value),
predictive_model=create_test_predictive_model(
predictive_model=PredictiveModels.CLASSIFICATION.value,
prediction_method=ClassificationMethods.RANDOM_FOREST.value))
result, _ = calculate(job)
del result['elapsed_time']
self.assertDictEqual(
result, {
'f1score': 0.54239884582595577,
'acc': 0.80995475113122173,
'true_positive': '--',
'true_negative': '--',
'false_negative': '--',
'false_positive': '--',
'precision': 0.62344720496894401,
'recall': 0.5224945442336747,
'auc': 0.4730604801339352
})
def test_class_no_cluster(self):
self.max_diff = None
job = create_test_job(
clustering=create_test_clustering(
clustering_type=ClusteringMethods.NO_CLUSTER.value),
split=repair_example(),
encoding=create_test_encoding(prefix_length=5,
padding=True,
add_elapsed_time=True),
predictive_model=create_test_predictive_model(
predictive_model=PredictiveModels.CLASSIFICATION.value,
prediction_method=ClassificationMethods.RANDOM_FOREST.value))
result, _ = calculate(job)
del result['elapsed_time']
self.assertDictEqual(
result, {
'f1score': 1.0,
'acc': 1.0,
'true_positive': '--',
'true_negative': '--',
'false_negative': '--',
'false_positive': '--',
'precision': 1.0,
'recall': 1.0,
'auc': 0.0
})
def test_no_exceptions(self):
filtered_labels = [enum.value for enum in LabelTypes]
filtered_classification_methods = [
enum.value for enum in ClassificationMethods
]
filtered_encoding_methods = [enum.value for enum in ValueEncodings]
filtered_padding = [True, False]
choices = [
filtered_encoding_methods, filtered_padding,
filtered_classification_methods, filtered_labels
]
job_combinations = list(itertools.product(*choices))
for (encoding, padding, method, label) in job_combinations:
print(encoding, padding, method, label)
if method == 'nn' and (padding == False or label
== LabelTypes.ATTRIBUTE_STRING.value):
pass
job = create_test_job(
predictive_model=create_test_predictive_model(
prediction_method=method),
encoding=create_test_encoding(value_encoding=encoding,
padding=padding),
labelling=create_test_labelling(label_type=label))
# with HidePrints():
calculate(job)
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.SHAP.value,
split=split,
predictive_model=predictive_model,
job=job,
results={}
)[0]
training_df_old, test_df_old = get_encoded_logs(job)
explanation_target = '2_101'
prefix_target = 'prefix_1'
explanation = explain(exp, training_df_old, test_df_old, explanation_target, prefix_target)
training_df_old, test_df_old = get_encoded_logs(job)
explanation_temp = shap_temporal_stability(exp, training_df_old, test_df_old, explanation_target)
self.assertTrue(type(explanation) is dict)
self.assertTrue(type(explanation_temp) is dict)
def test_prefix1_no_elapsed_time(self):
encoding = create_test_encoding(
value_encoding=ValueEncodings.FREQUENCY.value,
task_generation_type=TaskGenerationTypes.ONLY_THIS.value,
prefix_length=1)
df = frequency(self.log, self.event_names, self.labelling, encoding)
self.assertEqual(df.shape, (2, 9))
self.assertNotIn('elapsed_time', df.columns.values.tolist())
def setUp(self):
self.log = get_log(create_test_log(log_name=general_example_test_filename,
log_path=general_example_test_filepath))
self.labelling = create_test_labelling(label_type=LabelTypes.REMAINING_TIME.value)
self.encoding = create_test_encoding(
value_encoding=ValueEncodings.SIMPLE_INDEX.value,
task_generation_type=TaskGenerationTypes.ONLY_THIS.value,
add_elapsed_time=True,
prefix_length=1)
def test_prefix10(self):
encoding = create_test_encoding(
value_encoding=ValueEncodings.LAST_PAYLOAD.value,
task_generation_type=TaskGenerationTypes.ONLY_THIS.value,
add_elapsed_time=True,
prefix_length=10)
df = last_payload(self.log, self.labelling, encoding, self.add_col)
self.assertEqual(df.shape, (1, 17))
self.assertFalse(df.isnull().values.any())
def test_prefix10_zero_padding_all_in_one(self):
encoding = create_test_encoding(
value_encoding=ValueEncodings.LAST_PAYLOAD.value,
task_generation_type=TaskGenerationTypes.ALL_IN_ONE.value,
add_elapsed_time=True,
prefix_length=10, padding=True)
df = last_payload(self.log, self.labelling, encoding, self.add_col)
self.assertEqual(df.shape, (15, 17))
self.assertFalse(df.isnull().values.any())
def setUp(self):
self.train_log = get_log(create_test_log(log_name=general_example_train_filename,
log_path=general_example_train_filepath))
self.test_log = get_log(create_test_log(log_name=general_example_test_filename,
log_path=general_example_test_filepath_xes))
self.encoding = create_test_encoding(
value_encoding=ValueEncodings.SIMPLE_INDEX.value,
add_elapsed_time=True,
task_generation_type=TaskGenerationTypes.ONLY_THIS.value,
prefix_length=1)
def test_duration(self):
"""Trace atr, zero padding means prefix length has no effect"""
job = self.get_job()
job.labelling = create_test_labelling(label_type=LabelTypes.DURATION.value)
job.save()
result1, _ = calculate(job)
job.encoding = create_test_encoding(prefix_length=22, padding=True)
job.save()
result2, _ = calculate(job)
self.assertEqual(result1, result2)
def get_classification_job(predictive_model: str, prediction_method: str, metric: HyperOptLosses = HyperOptLosses.ACC.value):
encoding = create_test_encoding(prefix_length=8, padding=True)
pred_model = create_test_predictive_model(predictive_model=predictive_model,
prediction_method=prediction_method)
hyperparameter_optimizer = create_test_hyperparameter_optimizer(performance_metric=metric)
job = create_test_job(predictive_model=pred_model,
encoding=encoding,
hyperparameter_optimizer=hyperparameter_optimizer)
return job
def setUp(self):
self.train_log = get_log(
create_test_log(log_name=general_example_train_filename,
log_path=general_example_train_filepath))
self.test_log = get_log(
create_test_log(log_name=general_example_test_filename,
log_path=general_example_test_filepath))
self.add_col = get_additional_columns(self.train_log)
self.encoding = create_test_encoding(
value_encoding=ValueEncodings.COMPLEX.value,
add_elapsed_time=True,
task_generation_type=TaskGenerationTypes.ONLY_THIS.value,
prefix_length=2)
self.encodingPadding = create_test_encoding(
value_encoding=ValueEncodings.COMPLEX.value,
add_elapsed_time=True,
task_generation_type=TaskGenerationTypes.ONLY_THIS.value,
prefix_length=10,
padding=True)
def test_prefix10_all_in_one(self):
encoding = create_test_encoding(
value_encoding=ValueEncodings.COMPLEX.value,
add_elapsed_time=True,
task_generation_type=TaskGenerationTypes.ALL_IN_ONE.value,
prefix_length=10)
df = complex(self.log, self.labelling, encoding, self.add_col)
self.assertEqual(df.shape, (10, 55))
self.assertFalse(df.isnull().values.any())
def test_prefix5(self):
encoding = create_test_encoding(
value_encoding=ValueEncodings.COMPLEX.value,
add_elapsed_time=True,
task_generation_type=TaskGenerationTypes.ONLY_THIS.value,
prefix_length=5)
df = complex(self.log, self.labelling, encoding, self.add_col)
self.assertEqual(df.shape, (2, 30))
self.assertFalse(df.isnull().values.any())
def setUp(self):
self.log = get_log(create_test_log(log_name=general_example_test_filename,
log_path=general_example_test_filepath))
self.event_names = unique_events(self.log)
self.labelling = create_test_labelling(label_type=LabelTypes.REMAINING_TIME.value)
self.add_col = get_additional_columns(self.log)
self.encoding = create_test_encoding(
value_encoding=ValueEncodings.LAST_PAYLOAD.value,
add_elapsed_time=True,
task_generation_type=TaskGenerationTypes.ONLY_THIS.value,
prefix_length=1)
def test_prefix2(self):
df = simple_index(self.log, self.labelling, create_test_encoding(
value_encoding=ValueEncodings.FREQUENCY.value,
add_elapsed_time=True,
task_generation_type=TaskGenerationTypes.ONLY_THIS.value,
prefix_length=2))
self.assertEqual(df.shape, (2, 5))
row1 = df[df.trace_id == '5'].iloc[0]
self.assertListEqual(['5', 'register request', 'examine casually', 90840.0, 1485600.0], row1.values.tolist())
row2 = df[df.trace_id == '4'].iloc[0]
self.assertListEqual(['4', 'register request', 'check ticket', 75840.0, 445080.0], row2.values.tolist())
def test_prefix10_padding(self):
encoding = create_test_encoding(
value_encoding=ValueEncodings.BOOLEAN.value,
add_elapsed_time=True,
task_generation_type=TaskGenerationTypes.ONLY_THIS.value,
prefix_length=10,
padding=True)
df = boolean(self.log, self.event_names, self.labelling, encoding)
self.assertEqual(df.shape, (2, 10))
row1 = df[df.trace_id == '4'].iloc[0]
self.assertListEqual(['4', True, False, True, True, False, True, True, 520920.0, 0.0], row1.values.tolist())
def test_prefix10_padding_all_in_one(self):
encoding = create_test_encoding(value_encoding=ValueEncodings.BOOLEAN.value,
prefix_length=10,
add_elapsed_time=True,
padding=True,
task_generation_type=ALL_IN_ONE)
df = boolean(self.log, self.event_names, self.labelling, encoding)
self.assertEqual(df.shape, (15, 10))
row1 = df[df.trace_id == '4'].iloc[4]
self.assertListEqual(['4', True, False, True, True, False, True, True, 520920.0, 0.0], row1.values.tolist())
self.assertFalse(df.isnull().values.any())
def setUp(self):
self.df = DataFrame({
'literal_feature': [str(item) for item in ['a', 'b', None]],
'numeric_feature': [str(item) for item in [.1, 1, -.99]],
'misc_feature': [str(item) for item in ['a', None, -.99]]
})
self.how_it_should_be = DataFrame({
'literal_feature': [2, 3, 1],
'numeric_feature': [2, 3, 0],
'misc_feature': [3, 2, 0]
})
self.encoding = create_test_encoding()
def test_shape(self):
encoding = create_test_encoding(
value_encoding=ValueEncodings.LAST_PAYLOAD.value,
add_elapsed_time=True,
task_generation_type=TaskGenerationTypes.ONLY_THIS.value,
prefix_length=2)
df = last_payload(self.log, self.labelling, encoding, self.add_col)
self.assertEqual((2, 9), df.shape)
headers = ['trace_id', 'prefix_1', 'prefix_2', 'Activity_2', 'Costs_2',
'Resource_2', 'org:resource_2', 'elapsed_time', 'label']
self.assertListEqual(headers, df.columns.values.tolist())
