From 32600d551b213267763e101bfb7d017d84e429b1 Mon Sep 17 00:00:00 2001 From: Alessandro Berti Date: Wed, 20 Nov 2024 09:25:16 +0100 Subject: [PATCH] update --- docs/01_handling_event_data.md | 3 +++ docs/04_process_discovery.md | 13 ++++++++++++- docs/06_conformance_checking.md | 6 ++++++ docs/07_process_trees.md | 3 +++ docs/08_feature_selection.md | 3 +++ docs/09_statistics.md | 3 +++ docs/10_log-model_evaluation.md | 7 ++++++- docs/11_simulation.md | 18 ++++++++++++++++++ docs/15_streaming_process_mining.md | 3 +++ 9 files changed, 57 insertions(+), 2 deletions(-) diff --git a/docs/01_handling_event_data.md b/docs/01_handling_event_data.md index 29a678cf7..9b13056ac 100644 --- a/docs/01_handling_event_data.md +++ b/docs/01_handling_event_data.md @@ -114,6 +114,9 @@ as a |2|register request|20200422T0457|1479| |1|submit payment|20200422T0503|1337| ||||| + + + In this small example table, we observe four columns, i.e., `CaseID` , diff --git a/docs/04_process_discovery.md b/docs/04_process_discovery.md index 24b8952ca..09b861f4f 100644 --- a/docs/04_process_discovery.md +++ b/docs/04_process_discovery.md @@ -16,6 +16,9 @@ mining algorithms. |Weak against noise|Weak against noise||| + + + ## Alpha Miner @@ -167,6 +170,9 @@ if __name__ == "__main__": |dependency_threshold|dependency threshold of the Heuristics Miner (default: 0.5)| |and_threshold|AND measure threshold of the Heuristics Miner (default: 0.65)| |loop_two_threshold|thresholds for the loops of length 2 (default 0.5)| + + + To visualize the Heuristic Net, code is also provided on the right-hand side. @@ -407,6 +413,9 @@ generated model is less accurate (in comparison to the CLASSIC version) but the calculation is faster. The default chunk size is 100000 events.| + + + ## Temporal Profile @@ -438,4 +447,6 @@ See Parameters |---|---|---|---| |Parameters.ACTIVITY_KEY|string|concept:name|The attribute to use as activity.| |Parameters.START_TIMESTAMP_KEY|string|start_timestamp|The attribute to use as start timestamp.| -|Parameters.TIMESTAMP_KEY|string|time:timestamp|The attribute to use as timestamp.| \ No newline at end of file +|Parameters.TIMESTAMP_KEY|string|time:timestamp|The attribute to use as timestamp.| + + diff --git a/docs/06_conformance_checking.md b/docs/06_conformance_checking.md index d1167927e..aef278bfe 100644 --- a/docs/06_conformance_checking.md +++ b/docs/06_conformance_checking.md @@ -1043,6 +1043,9 @@ See Parameters |Parameters.ZETA|int|6|Multiplier for the standard deviation. Couples of events that are more distant than this are signaled by the temporal profile.| + + + ## LTL Checking @@ -1077,6 +1080,9 @@ log: event log A: the activity A of the rule (an activity of the log) Returns: Filtered log object (containing the cases which have A repeated by different people)| + + + The rules can be applied on both traditional event logs (XES) and Pandas dataframes, by looking at the packages pm4py.algo.filtering.log.ltl diff --git a/docs/07_process_trees.md b/docs/07_process_trees.md index b5151fc4e..895cedad4 100644 --- a/docs/07_process_trees.md +++ b/docs/07_process_trees.md @@ -81,6 +81,9 @@ if lt_dependency > 0: this can be 1 or 0 (True or False) (default True) (default 10)| + + + ## Generation of a log out of a process tree diff --git a/docs/08_feature_selection.md b/docs/08_feature_selection.md index e6ad390f7..ad0ff3dbc 100644 --- a/docs/08_feature_selection.md +++ b/docs/08_feature_selection.md @@ -126,6 +126,9 @@ the attribute among the events of the trace.| we have a trace [A,B,C], it might be important to include not only the presence of the single values A, B and C as features; but also the presence of the directly-follows couples (A,B) and (B,C).| + + + Let’s consider for example a feature selection where we are interested to:, - If a process execution contains, or not, an activity., diff --git a/docs/09_statistics.md b/docs/09_statistics.md index d30c3e04e..a2e8e01cf 100644 --- a/docs/09_statistics.md +++ b/docs/09_statistics.md @@ -131,6 +131,9 @@ the cycle time of the instance)| |@@approx_bh_overall_wasted_time|Difference between the partial lead time and the partial cycle time values| |@@approx_bh_this_wasted_time|Wasted time ONLY with regards to the activity described by the ‘interval’ event| |@@approx_bh_ratio_cycle_lead_time|Measures the incremental Flow Rate (between 0 and 1).| + + + The method that calculates the lead and the cycle time could be applied with the following line of code: diff --git a/docs/10_log-model_evaluation.md b/docs/10_log-model_evaluation.md index e65b06829..9db1da7b2 100644 --- a/docs/10_log-model_evaluation.md +++ b/docs/10_log-model_evaluation.md @@ -436,6 +436,9 @@ executed.| |RETURN_DIAGNOSTICS|Returns a dictionary containing the diagnostics.| |RETURN_ASAP_WHEN_NOT_SOUND|Stops the execution of WOFLAN when a condition determining that the Petri net is not a sound workflow net is found.| + + + On the provided Petri net, that is not sound, the output of the technique is False. To know why such Petri net is not sound, we repeat the execution of the script setting PRINT_DIAGNOSTICS to True and RETURN_ASAP_WHEN_NOT_SOUND to False (to get more @@ -516,4 +519,6 @@ Inspect outputs |R_G_S_C|| |R_G|| |LOCKING_SCENARIOS|| -|RESTRICTED_COVERABILITY_TREE|| \ No newline at end of file +|RESTRICTED_COVERABILITY_TREE|| + + diff --git a/docs/11_simulation.md b/docs/11_simulation.md index d1e7fd446..9f939ceac 100644 --- a/docs/11_simulation.md +++ b/docs/11_simulation.md @@ -20,6 +20,9 @@ specified number of process executions (repetitions may be possible).| |Variants.EXTENSIVE|A playout that accepts a Petri net along with an initial marking, and returns all the executions that are possible according to the model, up to a provided length of trace (may be computationally expensive).| + + + The list of parameters for such variants are: Inspect parameters @@ -34,6 +37,9 @@ Inspect parameters ||Parameters.TIMESTAMP_KEY|The name of the attribute to use as timestamp in the playout log.| ||Parameters.CASE_ID_KEY|The trace attribute that should be used as case identifier in the playout log.| ||Parameters.MAX_TRACE_LENGTH|The maximum trace length (after which, the extensive playout is stopped).| + + + An example application of the basic playout, given a Petri net, to get a log of 50 traces, is the following: @@ -142,6 +148,9 @@ the simulation process are: |simulated_log|The traces that have been simulated during the simulation.| |---|---| |res|The result of the simulation (Python dictionary).| + + + Among res , that is the result of the simulation, we have the following keys: @@ -160,6 +169,9 @@ fully enabled and the consumption of the tokens from the input places)| from the event log.| |total_cases_time|the difference between the last timestamp of the log, and the first timestamp of the simulated log.| + + + The last four items of the previous list are simple Python objects (floats and lists in the specific). The interval trees objects can be used in the following way to get time-specific information. For example, the following code snippet @@ -269,6 +281,9 @@ exponential)| should be printed every 10 seconds).| + + + ## Extensive Playout of a Process Tree @@ -309,6 +324,9 @@ Inspect parameters |---|---| |MAX_TRACE_LENGTH|Maximum length of a trace that is output of the algorithm.| |MAX_LOOP_OCC|Maximum number of times we enter in a loop.| + + + In the following, we see how the playout can be executed. First, a log can be imported: diff --git a/docs/15_streaming_process_mining.md b/docs/15_streaming_process_mining.md index 868f89233..58d40855e 100644 --- a/docs/15_streaming_process_mining.md +++ b/docs/15_streaming_process_mining.md @@ -479,6 +479,9 @@ if __name__ == "__main__": |Parameters.START_TIMESTAMP_KEY|string|start_timestamp|The attribute to use as start timestamp.| |Parameters.TIMESTAMP_KEY|string|time:timestamp|The attribute to use as timestamp.| |Parameters.ZETA|int|6|Multiplier for the standard deviation. Couples of events that are more distant than this are signaled by the temporal profile.| + + + We send the events of the log against the stream: