This dataset contains results of the experiment to analyze information preservation
and recovery by different event log abstractions in process mining described in:

Sander J.J. Leemans, Dirk Fahland "Information-Preserving Abstractions of Event Data in Process Mining"
Knowledge and Information Systems, ISSN: 0219-1377 (Print) 0219-3116 (Online), accepted May 2019

The experiment used data from the following datasets:

1) Unfiltered Public Event Logs from https://data.4tu.nl/repository/collection:event_logs_real
2) Filtered Public Event Logs of the TKDE Benchmark from http://doi.org/10.4121/uuid:adc42403-9a38-48dc-9f0a-a0a49bfb6371

<logroot>
  +- /BPIC11/hospital_log.xes.gz
  +- /BPIC12/financial_log.xes.gz
  +- /BPIC13/BPI_Challenge_2013_incidents.xes.gz
  +- /BPIC13/BPI_Challenge_2013_closed_problems.xes.gz
  +- /BPIC14/Detail Incident Activity.xes.gz
  +- /BPIC14/Detail Incident Activity_complete_cases.xes.gz
  +- /BPIC15/BPIC15_1.xes
  +- /BPIC15/BPIC15_2.xes
  +- /BPIC15/BPIC15_3.xes
  +- /BPIC15/BPIC15_4.xes
  +- /BPIC15/BPIC15_5.xes
  +- /BPIC17/BPI_Challenge_2017.xes.gz
  +- /Roadfines/Road_Traffic_Fine_Management_Process.xes.gz
  +- /Sepsis/Sepsis Cases - Event Log.xes.gz
  +- /TKDE_Benchmark/BPIC12.xes.gz
  +- /TKDE_Benchmark/BPIC13_cp.xes.gz
  +- /TKDE_Benchmark/BPIC13_i.xes.gz
  +- /TKDE_Benchmark/BPIC14_f.xes.gz
  +- /TKDE_Benchmark/BPIC15_1f.xes.gz
  +- /TKDE_Benchmark/BPIC15_2f.xes.gz
  +- /TKDE_Benchmark/BPIC15_3f.xes.gz
  +- /TKDE_Benchmark/BPIC15_4f.xes.gz
  +- /TKDE_Benchmark/BPIC15_5f.xes.gz
  +- /TKDE_Benchmark/BPIC17_f.xes.gz
  +- /TKDE_Benchmark/RTFMP.xes.gz
  +- /TKDE_Benchmark/SEPSIS.xes.gz


The results are structured as follows:

trees
  contains the process trees discovered in the experiment setup reported in the paper
  (IM-basic, IMf, IMa, IMfa, flower-model)

trees_all_miners
  contains the process trees discovered for all possible configurations of abstractions
  allowed by the Inductive Miner Framework (trees contains a subset of these)

petrinets
  contains the Petri Net models derived from the process trees in the directory "trees"

the root directory contains the following result files

result.csv - raw statistics about all operators and information retrieved from all miners
             based on the results in the trees_all_miners directory

results.xslx - processed file of result.csv including filtering and aggregation per event log

results_diff.xlsx - comparing differences in information recovered for the trees discovered by
                    (IM-basic, IMf, IMa, IMfa, flower-model) per event log to analyze
                    information gain for the different abstractions, and
                    comparison of precision and recall

results_model_quality_pcc2.xslx - precision and recall obtained with the technique of 
                    Sander J. J. Leemans, Dirk Fahland, Wil M. P. van der Aalst:
                    Scalable process discovery and conformance checking. 
                    Software and System Modeling 17(2): 599-631 (2018)
                    https://doi.org/10.1007/s10270-016-0545-x

                    with parameter k=2