1+ version : 5
2+ # #########
3+ # Common #
4+ # #########
5+ common :
6+ # Path to the event log in CSV format
7+ train_log_path : ../../event_logs/BPIC_2012_W_train.csv.gz
8+ # Event log to evaluate the discovered BPS model with
9+ test_log_path : ../../event_logs/BPIC_2012_W_test.csv.gz
10+ # Specify the name for each of the columns in the CSV file (XES standard by default)
11+ log_ids :
12+ case : " case_id"
13+ activity : " activity"
14+ resource : " resource"
15+ start_time : " start_time"
16+ end_time : " end_time"
17+ # Number of evaluations of the discovered BPS model
18+ num_final_evaluations : 10
19+ # Metrics to evaluate the discovered BPS model
20+ evaluation_metrics :
21+ - 3_gram_distance
22+ - 2_gram_distance
23+ - absolute_event_distribution
24+ - relative_event_distribution
25+ - circadian_event_distribution
26+ - arrival_event_distribution
27+ - cycle_time_distribution
28+ # Whether to discover case attributes or not
29+ discover_data_attributes : true
30+ # ################
31+ # Preprocessing #
32+ # ################
33+ preprocessing :
34+ multitasking : false
35+ enable_time_concurrency_threshold : 0.5
36+ # ###############
37+ # Control-flow #
38+ # ###############
39+ control_flow :
40+ # Metric to guide the optimization process (loss function to minimize)
41+ optimization_metric : two_gram_distance
42+ # Number of optimization iterations over the search space
43+ num_iterations : 30
44+ # Number of times to evaluate each iteration (using the mean of all of them)
45+ num_evaluations_per_iteration : 5
46+ # Methods for discovering gateway probabilities
47+ gateway_probabilities : discovery
48+ # Discover process model with SplitMiner v3
49+ mining_algorithm : sm1
50+ # Number of concurrent relations between events to be captured
51+ epsilon :
52+ - 0.05
53+ - 0.4
54+ # Threshold for filtering the incoming and outgoing edges
55+ eta :
56+ - 0.2
57+ - 0.7
58+ # Whether to replace non-trivial OR joins or not
59+ replace_or_joins :
60+ - true
61+ - false
62+ # Whether to prioritize parallelism over loops or not
63+ prioritize_parallelism : true
64+ # Discover data-aware branching rules, i.e., BPMN decision points based on value of data attributes
65+ discover_branch_rules : true
66+ # Minimum f-score value to consider the discovered data-aware branching rules
67+ f_score :
68+ - 0.3
69+ - 0.9
70+ # #################
71+ # Resource model #
72+ # #################
73+ resource_model :
74+ # Metric to guide the optimization process (loss function to minimize)
75+ optimization_metric : circadian_emd
76+ # Number of optimization iterations over the search space
77+ num_iterations : 40
78+ # Number of times to evaluate each iteration (using the mean of all of them)
79+ num_evaluations_per_iteration : 5
80+ # Whether to discover prioritization or batching behavior
81+ discover_prioritization_rules : false
82+ discover_batching_rules : false
83+ # Resource profiles configuration
84+ resource_profiles :
85+ # Resource profile discovery type
86+ discovery_type : differentiated
87+ # Time granularity (in minutes) for the resource calendar (the higher the density of events in the log, the smaller the granularity can be)
88+ granularity : 60
89+ # Minimum confidence of the intervals in the discovered calendar (of a resource or set of resources)
90+ confidence :
91+ - 0.5
92+ - 0.85
93+ # Minimum support of the intervals in the discovered calendar (of a resource or set of resources)
94+ support :
95+ - 0.05
96+ - 0.5
97+ # Participation of a resource in the process to discover a calendar for them (gathered together otherwise)
98+ participation : 0.4
0 commit comments