Merge branch 'bpm24' into 16-documentation-update-readme

* bpm24: (31 commits)
Adds grid_2 experiments
Adds grid_2 experiments
Passes arg to grid experiments script
Fixes paths
Hot fix for column name change
wip experiment with real targets
Converts encoding
Updates test data
Adds grid experiments script test
no need legacy config file
Adds convert to same encoding
Updates validation data
Sorts for replicability
CI augmentation pipeline step
Updates data
CI for benchmarking
Sorts file list
splits compare output
CI pipeline step generation
Adds validation data
...

.github/workflows/test_gedi.yml

@@ -29,10 +29,10 @@ jobs:
 
     - name: Run test
       run:
-        python main.py -o config_files/options/baseline.json -a config_files/algorithm/feature_extraction.json
+        python main.py -o config_files/options/baseline.json -a config_files/algorithm/pipeline_steps/feature_extraction.json
 
     - name: Compare output
-      run: diff data/test_feat.csv data/test_feat.csv
+      run: diff data/validation/test_feat.csv data/test_feat.csv
 
   test_generation:
     runs-on: ubuntu-latest
@@ -58,10 +58,15 @@ jobs:
 
     - name: Run test
       run:
-        python main.py -o config_files/options/baseline.json -a config_files/algorithm/generation.json
+        python main.py -o config_files/options/baseline.json -a config_files/algorithm/pipeline_steps/generation.json
 
-    - name: Compare output
-      run: diff output/features/grid_feat/2_enself_rt20v/genELexperiment2_07_04.json output/features/grid_feat/2_enself_rt20v/genELexperiment2_07_04.json
+    - name: Compare output 1
+      run: 
+        diff data/validation/genELexperiment2_07_04.json output/features/grid_feat/2_enself_rt20v/genELexperiment2_07_04.json
+
+    - name: Compare output 2
+      run: 
+        diff data/validation/genELexperiment1_04_02.json output/features/grid_feat/2_enself_rt20v/genELexperiment1_04_02.json
 
   test_benchmark:
     runs-on: ubuntu-latest
@@ -83,10 +88,13 @@ jobs:
 
     - name: Run test
       run:
-        python main.py -o config_files/options/baseline.json -a config_files/algorithm/benchmark.json
+        python main.py -o config_files/options/baseline.json -a config_files/algorithm/pipeline_steps/benchmark.json
+
+    - name: Convert output and validation to same encoding
+      run: iconv -f UTF-8 -t ASCII output/benchmark/test_benchmark.csv > data/validation/test_benchmark.csv
 
     - name: Compare output
-      run: diff output/benchmark/test_benchmark.csv output/benchmark/test_benchmark.csv
+      run: diff data/validation/test_benchmark.csv output/benchmark/test_benchmark.csv
 
   test_augmentation:
     runs-on: ubuntu-latest
@@ -108,7 +116,7 @@ jobs:
 
     - name: Run test
       run:
-        python main.py -o config_files/options/baseline.json -a config_files/algorithm/augmentation.json
+        python main.py -o config_files/options/baseline.json -a config_files/algorithm/pipeline_steps/augmentation.json
 
   test_evaluation-plotter:
     runs-on: ubuntu-latest
@@ -134,7 +142,7 @@ jobs:
 
     - name: Run test
       run:
-        python main.py -o config_files/options/baseline.json -a config_files/algorithm/evaluation_plotter.json
+        python main.py -o config_files/options/baseline.json -a config_files/algorithm/pipeline_steps/evaluation_plotter.json
 
   test_integration:
     runs-on: ubuntu-latest
@@ -161,3 +169,35 @@ jobs:
     - name: Run test
       run:
         python main.py -o config_files/options/baseline.json -a config_files/algorithm/experiment_test.json
+
+  test_grid_experiments_script:
+    runs-on: ubuntu-latest
+
+    # Setting up a python envronment  for the test script to run
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v4
+
+    - name: Set up Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: 3.9
+
+    - name: Install dependencies
+      run: |
+        sudo apt-get install build-essential python3 python3-dev
+
+    - name: Install feeed
+      run: |
+        python -m pip install --upgrade pip
+        pip install .
+
+    - name: Run test
+      run:
+        python execute_grid_experiments.py config_files/algorithm/test
+
+    - name: Convert output and validation to same encoding
+      run: iconv -f UTF-8 -t ASCII output/features/generated/2_bpic_features/2_ense_enseef_feat.csv > data/validation/2_ense_enseef_feat.csv
+
+    - name: Compare output
+      run: diff data/validation/2_ense_enseef_feat.csv output/features/generated/2_bpic_features/2_ense_enseef_feat.csv

config_files/algorithm/augmentation.json

@@ -1,12 +0,0 @@
-[
-  {
-    "pipeline_step": "instance_augmentation",
-    "augmentation_params":
-    {
-        "method":"SMOTE", "no_samples":20,
-        "feature_selection": ["n_traces", "n_unique_traces", "ratio_unique_traces_per_trace", "trace_len_min", "trace_len_max", "trace_len_mean", "trace_len_median", "trace_len_mode", "trace_len_std", "trace_len_variance", "trace_len_q1", "trace_len_q3", "trace_len_iqr", "trace_len_geometric_mean", "trace_len_geometric_std", "trace_len_harmonic_mean", "trace_len_skewness", "trace_len_kurtosis", "trace_len_coefficient_variation", "trace_len_entropy", "trace_len_hist1", "trace_len_hist2", "trace_len_hist3", "trace_len_hist4", "trace_len_hist5", "trace_len_hist6", "trace_len_hist7", "trace_len_hist8", "trace_len_hist9", "trace_len_hist10", "trace_len_skewness_hist", "trace_len_kurtosis_hist", "ratio_most_common_variant", "ratio_top_1_variants", "ratio_top_5_variants", "ratio_top_10_variants", "ratio_top_20_variants", "ratio_top_50_variants", "ratio_top_75_variants", "mean_variant_occurrence", "std_variant_occurrence", "skewness_variant_occurrence", "kurtosis_variant_occurrence", "n_unique_activities", "activities_min", "activities_max", "activities_mean", "activities_median", "activities_std", "activities_variance", "activities_q1", "activities_q3", "activities_iqr", "activities_skewness", "activities_kurtosis", "n_unique_start_activities", "start_activities_min", "start_activities_max", "start_activities_mean", "start_activities_median", "start_activities_std", "start_activities_variance", "start_activities_q1", "start_activities_q3", "start_activities_iqr", "start_activities_skewness", "start_activities_kurtosis", "n_unique_end_activities", "end_activities_min", "end_activities_max", "end_activities_mean", "end_activities_median", "end_activities_std", "end_activities_variance", "end_activities_q1", "end_activities_q3", "end_activities_iqr", "end_activities_skewness", "end_activities_kurtosis", "entropy_trace", "entropy_prefix", "entropy_global_block", "entropy_lempel_ziv", "entropy_k_block_diff_1", "entropy_k_block_diff_3", "entropy_k_block_diff_5", "entropy_k_block_ratio_1", "entropy_k_block_ratio_3", "entropy_k_block_ratio_5", "entropy_knn_3", "entropy_knn_5", "entropy_knn_7", "epa_variant_entropy", "epa_normalized_variant_entropy", "epa_sequence_entropy", "epa_normalized_sequence_entropy", "epa_sequence_entropy_linear_forgetting", "epa_normalized_sequence_entropy_linear_forgetting", "epa_sequence_entropy_exponential_forgetting", "epa_normalized_sequence_entropy_exponential_forgetting"]
-    },
-    "input_path": "data/bpic_features.csv",
-    "output_path": "output"
-  }
-]

config_files/algorithm/experiment_real_targets.json

@@ -0,0 +1,41 @@
+[
+   {
+    "pipeline_step": "event_logs_generation",
+    "output_path": "output",
+    "generator_params": {
+      "experiment": {
+        "input_path": "data/BaselineED_feat.csv",
+        "objectives":["ratio_variants_per_number_of_traces","ratio_most_common_variant","ratio_top_10_variants","epa_normalized_variant_entropy","epa_normalized_sequence_entropy","epa_normalized_sequence_entropy_linear_forgetting","epa_normalized_sequence_entropy_exponential_forgetting"]},
+        "config_space": {
+        "mode": [5, 20],
+        "sequence": [0.01, 1],
+        "choice": [0.01, 1],
+        "parallel": [0.01, 1],
+        "loop": [0.01, 1],
+        "silent": [0.01, 1],
+        "lt_dependency": [0.01, 1],
+        "num_traces": [10, 10001],
+        "duplicate": [0],
+        "or": [0]
+      },
+      "n_trials": 200,
+      "plot_reference_feature": ""
+    }
+  },
+  {
+    "pipeline_step": "feature_extraction",
+    "input_path": "output/BaselineED_feat/7_ense_enseef_enself_enve_rmcv_rt10v_rutpt/",
+    "input_path": "output/features/BaselineED_feat/7_ense_enseef_enself_enve_rmcv_rt10v_rutpt/",
+    "feature_params": {"feature_set":["ratio_variants_per_number_of_traces","ratio_most_common_variant","ratio_top_10_variants","epa_normalized_variant_entropy","epa_normalized_sequence_entropy","epa_normalized_sequence_entropy_linear_forgetting","epa_normalized_sequence_entropy_exponential_forgetting"]},
+    "output_path": "output/plots",
+    "real_eventlog_path": "data/BaselineED_feat.csv",
+    "plot_type": "boxplot"
+  },
+  {
+    "pipeline_step": "benchmark_test",
+    "benchmark_test": "discovery",
+    "input_path": "output/BaselineED_feat/7_ense_enseef_enself_enve_rmcv_rt10v_rutpt/",
+    "output_path":"output",
+    "miners" : ["heu", "imf", "ilp"]
+  }
+]

config_files/algorithm/experiment_test.json

@@ -47,6 +47,6 @@
     "benchmark_test": "discovery",
     "input_path":"data/test",
     "output_path":"output",
-    "miners" : ["inductive", "heuristics", "imf", "ilp"]
+    "miners" : ["inductive", "heu", "imf", "ilp"]
   }
 ]

config_files/algorithm/fix_24.json

@@ -1,34 +0,0 @@
-[
-  {
-    "pipeline_step": "event_logs_generation",
-    "output_path":"data/generated",
-    "generator_params": {
-      "objectives": {
-      "normalized_sequence_entropy_linear_forgetting": 0.05,
-      "ratio_top_20_variants": 0.4
-      },
-      "config_space": {
-        "mode": [5, 40],
-        "sequence": [0.01, 1],
-        "choice": [0.01, 1],
-        "parallel": [0.01, 1],
-        "loop": [0.01, 1],
-        "silent": [0.01, 1],
-        "lt_dependency": [0.01, 1],
-        "num_traces": [100, 1001],
-        "duplicate": [0],
-        "or": [0]
-      },
-      "n_trials": 20
-    }
-  },  
-  {
-    "pipeline_step": "feature_extraction",
-    "input_path": "data/generated",
-    "feature_params": {"feature_set":["simple_stats", "trace_length", "trace_variant", "activities", "start_activities", "end_activities", "entropies", "complexity"]},
-    "feature_params": {"feature_set":["trace_length"]},
-    "output_path": "output/plots",
-    "real_eventlog_path": "data/log_meta_features.csv",
-    "plot_type": "boxplot"
-  }
-]

config_files/algorithm/grid_2obj/generator_grid_2objectives_ense_enseef.json

@@ -0,0 +1 @@
+[{"pipeline_step": "event_logs_generation", "output_path": "output/generated/grid_2obj", "generator_params": {"experiment": {"input_path": "data/grid_2obj/grid_2objectives_ense_enseef.csv", "objectives": ["epa_normalized_sequence_entropy", "epa_normalized_sequence_entropy_exponential_forgetting"]}, "config_space": {"mode": [5, 20], "sequence": [0.01, 1], "choice": [0.01, 1], "parallel": [0.01, 1], "loop": [0.01, 1], "silent": [0.01, 1], "lt_dependency": [0.01, 1], "num_traces": [10, 10001], "duplicate": [0], "or": [0]}, "n_trials": 200}}, {"pipeline_step": "feature_extraction", "input_path": "output/features/generated/grid_2obj/grid_2objectives_ense_enseef/2_ense_enseef", "feature_params": {"feature_set": ["ratio_variants_per_number_of_traces", "ratio_most_common_variant", "ratio_top_10_variants", "epa_normalized_variant_entropy", "epa_normalized_sequence_entropy", "epa_normalized_sequence_entropy_linear_forgetting", "epa_normalized_sequence_entropy_exponential_forgetting"]}, "output_path": "output/plots", "real_eventlog_path": "data/BaselineED_feat.csv", "plot_type": "boxplot"}, {"pipeline_step": "benchmark_test", "benchmark_test": "discovery", "input_path": "output/generated/grid_2obj/grid_2objectives_ense_enseef/2_ense_enseef", "output_path": "output", "miners": ["heu", "imf", "ilp"]}]

config_files/algorithm/grid_2obj/generator_grid_2objectives_ense_enself.json

@@ -0,0 +1 @@
+[{"pipeline_step": "event_logs_generation", "output_path": "output/generated/grid_2obj", "generator_params": {"experiment": {"input_path": "data/grid_2obj/grid_2objectives_ense_enself.csv", "objectives": ["epa_normalized_sequence_entropy", "epa_normalized_sequence_entropy_linear_forgetting"]}, "config_space": {"mode": [5, 20], "sequence": [0.01, 1], "choice": [0.01, 1], "parallel": [0.01, 1], "loop": [0.01, 1], "silent": [0.01, 1], "lt_dependency": [0.01, 1], "num_traces": [10, 10001], "duplicate": [0], "or": [0]}, "n_trials": 200}}, {"pipeline_step": "feature_extraction", "input_path": "output/features/generated/grid_2obj/grid_2objectives_ense_enself/2_ense_enself", "feature_params": {"feature_set": ["ratio_variants_per_number_of_traces", "ratio_most_common_variant", "ratio_top_10_variants", "epa_normalized_variant_entropy", "epa_normalized_sequence_entropy", "epa_normalized_sequence_entropy_linear_forgetting", "epa_normalized_sequence_entropy_exponential_forgetting"]}, "output_path": "output/plots", "real_eventlog_path": "data/BaselineED_feat.csv", "plot_type": "boxplot"}, {"pipeline_step": "benchmark_test", "benchmark_test": "discovery", "input_path": "output/generated/grid_2obj/grid_2objectives_ense_enself/2_ense_enself", "output_path": "output", "miners": ["heu", "imf", "ilp"]}]

config_files/algorithm/grid_2obj/generator_grid_2objectives_ense_enve.json

@@ -0,0 +1 @@
+[{"pipeline_step": "event_logs_generation", "output_path": "output/generated/grid_2obj", "generator_params": {"experiment": {"input_path": "data/grid_2obj/grid_2objectives_ense_enve.csv", "objectives": ["epa_normalized_sequence_entropy", "epa_normalized_variant_entropy"]}, "config_space": {"mode": [5, 20], "sequence": [0.01, 1], "choice": [0.01, 1], "parallel": [0.01, 1], "loop": [0.01, 1], "silent": [0.01, 1], "lt_dependency": [0.01, 1], "num_traces": [10, 10001], "duplicate": [0], "or": [0]}, "n_trials": 200}}, {"pipeline_step": "feature_extraction", "input_path": "output/features/generated/grid_2obj/grid_2objectives_ense_enve/2_ense_enve", "feature_params": {"feature_set": ["ratio_variants_per_number_of_traces", "ratio_most_common_variant", "ratio_top_10_variants", "epa_normalized_variant_entropy", "epa_normalized_sequence_entropy", "epa_normalized_sequence_entropy_linear_forgetting", "epa_normalized_sequence_entropy_exponential_forgetting"]}, "output_path": "output/plots", "real_eventlog_path": "data/BaselineED_feat.csv", "plot_type": "boxplot"}, {"pipeline_step": "benchmark_test", "benchmark_test": "discovery", "input_path": "output/generated/grid_2obj/grid_2objectives_ense_enve/2_ense_enve", "output_path": "output", "miners": ["heu", "imf", "ilp"]}]

config_files/algorithm/grid_2obj/generator_grid_2objectives_ense_rmcv.json

@@ -0,0 +1 @@
+[{"pipeline_step": "event_logs_generation", "output_path": "output/generated/grid_2obj", "generator_params": {"experiment": {"input_path": "data/grid_2obj/grid_2objectives_ense_rmcv.csv", "objectives": ["epa_normalized_sequence_entropy", "ratio_most_common_variant"]}, "config_space": {"mode": [5, 20], "sequence": [0.01, 1], "choice": [0.01, 1], "parallel": [0.01, 1], "loop": [0.01, 1], "silent": [0.01, 1], "lt_dependency": [0.01, 1], "num_traces": [10, 10001], "duplicate": [0], "or": [0]}, "n_trials": 200}}, {"pipeline_step": "feature_extraction", "input_path": "output/features/generated/grid_2obj/grid_2objectives_ense_rmcv/2_ense_rmcv", "feature_params": {"feature_set": ["ratio_variants_per_number_of_traces", "ratio_most_common_variant", "ratio_top_10_variants", "epa_normalized_variant_entropy", "epa_normalized_sequence_entropy", "epa_normalized_sequence_entropy_linear_forgetting", "epa_normalized_sequence_entropy_exponential_forgetting"]}, "output_path": "output/plots", "real_eventlog_path": "data/BaselineED_feat.csv", "plot_type": "boxplot"}, {"pipeline_step": "benchmark_test", "benchmark_test": "discovery", "input_path": "output/generated/grid_2obj/grid_2objectives_ense_rmcv/2_ense_rmcv", "output_path": "output", "miners": ["heu", "imf", "ilp"]}]

config_files/algorithm/grid_2obj/generator_grid_2objectives_ense_rt10v.json

@@ -0,0 +1 @@
+[{"pipeline_step": "event_logs_generation", "output_path": "output/generated/grid_2obj", "generator_params": {"experiment": {"input_path": "data/grid_2obj/grid_2objectives_ense_rt10v.csv", "objectives": ["epa_normalized_sequence_entropy", "ratio_top_10_variants"]}, "config_space": {"mode": [5, 20], "sequence": [0.01, 1], "choice": [0.01, 1], "parallel": [0.01, 1], "loop": [0.01, 1], "silent": [0.01, 1], "lt_dependency": [0.01, 1], "num_traces": [10, 10001], "duplicate": [0], "or": [0]}, "n_trials": 200}}, {"pipeline_step": "feature_extraction", "input_path": "output/features/generated/grid_2obj/grid_2objectives_ense_rt10v/2_ense_rt10v", "feature_params": {"feature_set": ["ratio_variants_per_number_of_traces", "ratio_most_common_variant", "ratio_top_10_variants", "epa_normalized_variant_entropy", "epa_normalized_sequence_entropy", "epa_normalized_sequence_entropy_linear_forgetting", "epa_normalized_sequence_entropy_exponential_forgetting"]}, "output_path": "output/plots", "real_eventlog_path": "data/BaselineED_feat.csv", "plot_type": "boxplot"}, {"pipeline_step": "benchmark_test", "benchmark_test": "discovery", "input_path": "output/generated/grid_2obj/grid_2objectives_ense_rt10v/2_ense_rt10v", "output_path": "output", "miners": ["heu", "imf", "ilp"]}]

config_files/algorithm/grid_2obj/generator_grid_2objectives_ense_rvpnot.json

@@ -0,0 +1 @@
+[{"pipeline_step": "event_logs_generation", "output_path": "output/generated/grid_2obj", "generator_params": {"experiment": {"input_path": "data/grid_2obj/grid_2objectives_ense_rvpnot.csv", "objectives": ["epa_normalized_sequence_entropy", "ratio_variants_per_number_of_traces"]}, "config_space": {"mode": [5, 20], "sequence": [0.01, 1], "choice": [0.01, 1], "parallel": [0.01, 1], "loop": [0.01, 1], "silent": [0.01, 1], "lt_dependency": [0.01, 1], "num_traces": [10, 10001], "duplicate": [0], "or": [0]}, "n_trials": 200}}, {"pipeline_step": "feature_extraction", "input_path": "output/features/generated/grid_2obj/grid_2objectives_ense_rvpnot/2_ense_rvpnot", "feature_params": {"feature_set": ["ratio_variants_per_number_of_traces", "ratio_most_common_variant", "ratio_top_10_variants", "epa_normalized_variant_entropy", "epa_normalized_sequence_entropy", "epa_normalized_sequence_entropy_linear_forgetting", "epa_normalized_sequence_entropy_exponential_forgetting"]}, "output_path": "output/plots", "real_eventlog_path": "data/BaselineED_feat.csv", "plot_type": "boxplot"}, {"pipeline_step": "benchmark_test", "benchmark_test": "discovery", "input_path": "output/generated/grid_2obj/grid_2objectives_ense_rvpnot/2_ense_rvpnot", "output_path": "output", "miners": ["heu", "imf", "ilp"]}]

config_files/algorithm/grid_2obj/generator_grid_2objectives_enseef_enself.json

@@ -0,0 +1 @@
+[{"pipeline_step": "event_logs_generation", "output_path": "output/generated/grid_2obj", "generator_params": {"experiment": {"input_path": "data/grid_2obj/grid_2objectives_enseef_enself.csv", "objectives": ["epa_normalized_sequence_entropy_exponential_forgetting", "epa_normalized_sequence_entropy_linear_forgetting"]}, "config_space": {"mode": [5, 20], "sequence": [0.01, 1], "choice": [0.01, 1], "parallel": [0.01, 1], "loop": [0.01, 1], "silent": [0.01, 1], "lt_dependency": [0.01, 1], "num_traces": [10, 10001], "duplicate": [0], "or": [0]}, "n_trials": 200}}, {"pipeline_step": "feature_extraction", "input_path": "output/features/generated/grid_2obj/grid_2objectives_enseef_enself/2_enseef_enself", "feature_params": {"feature_set": ["ratio_variants_per_number_of_traces", "ratio_most_common_variant", "ratio_top_10_variants", "epa_normalized_variant_entropy", "epa_normalized_sequence_entropy", "epa_normalized_sequence_entropy_linear_forgetting", "epa_normalized_sequence_entropy_exponential_forgetting"]}, "output_path": "output/plots", "real_eventlog_path": "data/BaselineED_feat.csv", "plot_type": "boxplot"}, {"pipeline_step": "benchmark_test", "benchmark_test": "discovery", "input_path": "output/generated/grid_2obj/grid_2objectives_enseef_enself/2_enseef_enself", "output_path": "output", "miners": ["heu", "imf", "ilp"]}]

config_files/algorithm/grid_2obj/generator_grid_2objectives_enseef_enve.json

@@ -0,0 +1 @@
+[{"pipeline_step": "event_logs_generation", "output_path": "output/generated/grid_2obj", "generator_params": {"experiment": {"input_path": "data/grid_2obj/grid_2objectives_enseef_enve.csv", "objectives": ["epa_normalized_sequence_entropy_exponential_forgetting", "epa_normalized_variant_entropy"]}, "config_space": {"mode": [5, 20], "sequence": [0.01, 1], "choice": [0.01, 1], "parallel": [0.01, 1], "loop": [0.01, 1], "silent": [0.01, 1], "lt_dependency": [0.01, 1], "num_traces": [10, 10001], "duplicate": [0], "or": [0]}, "n_trials": 200}}, {"pipeline_step": "feature_extraction", "input_path": "output/features/generated/grid_2obj/grid_2objectives_enseef_enve/2_enseef_enve", "feature_params": {"feature_set": ["ratio_variants_per_number_of_traces", "ratio_most_common_variant", "ratio_top_10_variants", "epa_normalized_variant_entropy", "epa_normalized_sequence_entropy", "epa_normalized_sequence_entropy_linear_forgetting", "epa_normalized_sequence_entropy_exponential_forgetting"]}, "output_path": "output/plots", "real_eventlog_path": "data/BaselineED_feat.csv", "plot_type": "boxplot"}, {"pipeline_step": "benchmark_test", "benchmark_test": "discovery", "input_path": "output/generated/grid_2obj/grid_2objectives_enseef_enve/2_enseef_enve", "output_path": "output", "miners": ["heu", "imf", "ilp"]}]

config_files/algorithm/grid_2obj/generator_grid_2objectives_enseef_rmcv.json

@@ -0,0 +1 @@
+[{"pipeline_step": "event_logs_generation", "output_path": "output/generated/grid_2obj", "generator_params": {"experiment": {"input_path": "data/grid_2obj/grid_2objectives_enseef_rmcv.csv", "objectives": ["epa_normalized_sequence_entropy_exponential_forgetting", "ratio_most_common_variant"]}, "config_space": {"mode": [5, 20], "sequence": [0.01, 1], "choice": [0.01, 1], "parallel": [0.01, 1], "loop": [0.01, 1], "silent": [0.01, 1], "lt_dependency": [0.01, 1], "num_traces": [10, 10001], "duplicate": [0], "or": [0]}, "n_trials": 200}}, {"pipeline_step": "feature_extraction", "input_path": "output/features/generated/grid_2obj/grid_2objectives_enseef_rmcv/2_enseef_rmcv", "feature_params": {"feature_set": ["ratio_variants_per_number_of_traces", "ratio_most_common_variant", "ratio_top_10_variants", "epa_normalized_variant_entropy", "epa_normalized_sequence_entropy", "epa_normalized_sequence_entropy_linear_forgetting", "epa_normalized_sequence_entropy_exponential_forgetting"]}, "output_path": "output/plots", "real_eventlog_path": "data/BaselineED_feat.csv", "plot_type": "boxplot"}, {"pipeline_step": "benchmark_test", "benchmark_test": "discovery", "input_path": "output/generated/grid_2obj/grid_2objectives_enseef_rmcv/2_enseef_rmcv", "output_path": "output", "miners": ["heu", "imf", "ilp"]}]

config_files/algorithm/grid_2obj/generator_grid_2objectives_enseef_rt10v.json

@@ -0,0 +1 @@
+[{"pipeline_step": "event_logs_generation", "output_path": "output/generated/grid_2obj", "generator_params": {"experiment": {"input_path": "data/grid_2obj/grid_2objectives_enseef_rt10v.csv", "objectives": ["epa_normalized_sequence_entropy_exponential_forgetting", "ratio_top_10_variants"]}, "config_space": {"mode": [5, 20], "sequence": [0.01, 1], "choice": [0.01, 1], "parallel": [0.01, 1], "loop": [0.01, 1], "silent": [0.01, 1], "lt_dependency": [0.01, 1], "num_traces": [10, 10001], "duplicate": [0], "or": [0]}, "n_trials": 200}}, {"pipeline_step": "feature_extraction", "input_path": "output/features/generated/grid_2obj/grid_2objectives_enseef_rt10v/2_enseef_rt10v", "feature_params": {"feature_set": ["ratio_variants_per_number_of_traces", "ratio_most_common_variant", "ratio_top_10_variants", "epa_normalized_variant_entropy", "epa_normalized_sequence_entropy", "epa_normalized_sequence_entropy_linear_forgetting", "epa_normalized_sequence_entropy_exponential_forgetting"]}, "output_path": "output/plots", "real_eventlog_path": "data/BaselineED_feat.csv", "plot_type": "boxplot"}, {"pipeline_step": "benchmark_test", "benchmark_test": "discovery", "input_path": "output/generated/grid_2obj/grid_2objectives_enseef_rt10v/2_enseef_rt10v", "output_path": "output", "miners": ["heu", "imf", "ilp"]}]

config_files/algorithm/grid_2obj/generator_grid_2objectives_enseef_rvpnot.json

@@ -0,0 +1 @@
+[{"pipeline_step": "event_logs_generation", "output_path": "output/generated/grid_2obj", "generator_params": {"experiment": {"input_path": "data/grid_2obj/grid_2objectives_enseef_rvpnot.csv", "objectives": ["epa_normalized_sequence_entropy_exponential_forgetting", "ratio_variants_per_number_of_traces"]}, "config_space": {"mode": [5, 20], "sequence": [0.01, 1], "choice": [0.01, 1], "parallel": [0.01, 1], "loop": [0.01, 1], "silent": [0.01, 1], "lt_dependency": [0.01, 1], "num_traces": [10, 10001], "duplicate": [0], "or": [0]}, "n_trials": 200}}, {"pipeline_step": "feature_extraction", "input_path": "output/features/generated/grid_2obj/grid_2objectives_enseef_rvpnot/2_enseef_rvpnot", "feature_params": {"feature_set": ["ratio_variants_per_number_of_traces", "ratio_most_common_variant", "ratio_top_10_variants", "epa_normalized_variant_entropy", "epa_normalized_sequence_entropy", "epa_normalized_sequence_entropy_linear_forgetting", "epa_normalized_sequence_entropy_exponential_forgetting"]}, "output_path": "output/plots", "real_eventlog_path": "data/BaselineED_feat.csv", "plot_type": "boxplot"}, {"pipeline_step": "benchmark_test", "benchmark_test": "discovery", "input_path": "output/generated/grid_2obj/grid_2objectives_enseef_rvpnot/2_enseef_rvpnot", "output_path": "output", "miners": ["heu", "imf", "ilp"]}]

config_files/algorithm/grid_2obj/generator_grid_2objectives_enself_enve.json

@@ -0,0 +1 @@
+[{"pipeline_step": "event_logs_generation", "output_path": "output/generated/grid_2obj", "generator_params": {"experiment": {"input_path": "data/grid_2obj/grid_2objectives_enself_enve.csv", "objectives": ["epa_normalized_sequence_entropy_linear_forgetting", "epa_normalized_variant_entropy"]}, "config_space": {"mode": [5, 20], "sequence": [0.01, 1], "choice": [0.01, 1], "parallel": [0.01, 1], "loop": [0.01, 1], "silent": [0.01, 1], "lt_dependency": [0.01, 1], "num_traces": [10, 10001], "duplicate": [0], "or": [0]}, "n_trials": 200}}, {"pipeline_step": "feature_extraction", "input_path": "output/features/generated/grid_2obj/grid_2objectives_enself_enve/2_enself_enve", "feature_params": {"feature_set": ["ratio_variants_per_number_of_traces", "ratio_most_common_variant", "ratio_top_10_variants", "epa_normalized_variant_entropy", "epa_normalized_sequence_entropy", "epa_normalized_sequence_entropy_linear_forgetting", "epa_normalized_sequence_entropy_exponential_forgetting"]}, "output_path": "output/plots", "real_eventlog_path": "data/BaselineED_feat.csv", "plot_type": "boxplot"}, {"pipeline_step": "benchmark_test", "benchmark_test": "discovery", "input_path": "output/generated/grid_2obj/grid_2objectives_enself_enve/2_enself_enve", "output_path": "output", "miners": ["heu", "imf", "ilp"]}]

config_files/algorithm/grid_2obj/generator_grid_2objectives_enself_rmcv.json

@@ -0,0 +1 @@
+[{"pipeline_step": "event_logs_generation", "output_path": "output/generated/grid_2obj", "generator_params": {"experiment": {"input_path": "data/grid_2obj/grid_2objectives_enself_rmcv.csv", "objectives": ["epa_normalized_sequence_entropy_linear_forgetting", "ratio_most_common_variant"]}, "config_space": {"mode": [5, 20], "sequence": [0.01, 1], "choice": [0.01, 1], "parallel": [0.01, 1], "loop": [0.01, 1], "silent": [0.01, 1], "lt_dependency": [0.01, 1], "num_traces": [10, 10001], "duplicate": [0], "or": [0]}, "n_trials": 200}}, {"pipeline_step": "feature_extraction", "input_path": "output/features/generated/grid_2obj/grid_2objectives_enself_rmcv/2_enself_rmcv", "feature_params": {"feature_set": ["ratio_variants_per_number_of_traces", "ratio_most_common_variant", "ratio_top_10_variants", "epa_normalized_variant_entropy", "epa_normalized_sequence_entropy", "epa_normalized_sequence_entropy_linear_forgetting", "epa_normalized_sequence_entropy_exponential_forgetting"]}, "output_path": "output/plots", "real_eventlog_path": "data/BaselineED_feat.csv", "plot_type": "boxplot"}, {"pipeline_step": "benchmark_test", "benchmark_test": "discovery", "input_path": "output/generated/grid_2obj/grid_2objectives_enself_rmcv/2_enself_rmcv", "output_path": "output", "miners": ["heu", "imf", "ilp"]}]

config_files/algorithm/grid_2obj/generator_grid_2objectives_enself_rt10v.json

@@ -0,0 +1 @@
+[{"pipeline_step": "event_logs_generation", "output_path": "output/generated/grid_2obj", "generator_params": {"experiment": {"input_path": "data/grid_2obj/grid_2objectives_enself_rt10v.csv", "objectives": ["epa_normalized_sequence_entropy_linear_forgetting", "ratio_top_10_variants"]}, "config_space": {"mode": [5, 20], "sequence": [0.01, 1], "choice": [0.01, 1], "parallel": [0.01, 1], "loop": [0.01, 1], "silent": [0.01, 1], "lt_dependency": [0.01, 1], "num_traces": [10, 10001], "duplicate": [0], "or": [0]}, "n_trials": 200}}, {"pipeline_step": "feature_extraction", "input_path": "output/features/generated/grid_2obj/grid_2objectives_enself_rt10v/2_enself_rt10v", "feature_params": {"feature_set": ["ratio_variants_per_number_of_traces", "ratio_most_common_variant", "ratio_top_10_variants", "epa_normalized_variant_entropy", "epa_normalized_sequence_entropy", "epa_normalized_sequence_entropy_linear_forgetting", "epa_normalized_sequence_entropy_exponential_forgetting"]}, "output_path": "output/plots", "real_eventlog_path": "data/BaselineED_feat.csv", "plot_type": "boxplot"}, {"pipeline_step": "benchmark_test", "benchmark_test": "discovery", "input_path": "output/generated/grid_2obj/grid_2objectives_enself_rt10v/2_enself_rt10v", "output_path": "output", "miners": ["heu", "imf", "ilp"]}]

config_files/algorithm/grid_2obj/generator_grid_2objectives_enself_rvpnot.json

@@ -0,0 +1 @@
+[{"pipeline_step": "event_logs_generation", "output_path": "output/generated/grid_2obj", "generator_params": {"experiment": {"input_path": "data/grid_2obj/grid_2objectives_enself_rvpnot.csv", "objectives": ["epa_normalized_sequence_entropy_linear_forgetting", "ratio_variants_per_number_of_traces"]}, "config_space": {"mode": [5, 20], "sequence": [0.01, 1], "choice": [0.01, 1], "parallel": [0.01, 1], "loop": [0.01, 1], "silent": [0.01, 1], "lt_dependency": [0.01, 1], "num_traces": [10, 10001], "duplicate": [0], "or": [0]}, "n_trials": 200}}, {"pipeline_step": "feature_extraction", "input_path": "output/features/generated/grid_2obj/grid_2objectives_enself_rvpnot/2_enself_rvpnot", "feature_params": {"feature_set": ["ratio_variants_per_number_of_traces", "ratio_most_common_variant", "ratio_top_10_variants", "epa_normalized_variant_entropy", "epa_normalized_sequence_entropy", "epa_normalized_sequence_entropy_linear_forgetting", "epa_normalized_sequence_entropy_exponential_forgetting"]}, "output_path": "output/plots", "real_eventlog_path": "data/BaselineED_feat.csv", "plot_type": "boxplot"}, {"pipeline_step": "benchmark_test", "benchmark_test": "discovery", "input_path": "output/generated/grid_2obj/grid_2objectives_enself_rvpnot/2_enself_rvpnot", "output_path": "output", "miners": ["heu", "imf", "ilp"]}]

config_files/algorithm/grid_2obj/generator_grid_2objectives_enve_rmcv.json

@@ -0,0 +1 @@
+[{"pipeline_step": "event_logs_generation", "output_path": "output/generated/grid_2obj", "generator_params": {"experiment": {"input_path": "data/grid_2obj/grid_2objectives_enve_rmcv.csv", "objectives": ["epa_normalized_variant_entropy", "ratio_most_common_variant"]}, "config_space": {"mode": [5, 20], "sequence": [0.01, 1], "choice": [0.01, 1], "parallel": [0.01, 1], "loop": [0.01, 1], "silent": [0.01, 1], "lt_dependency": [0.01, 1], "num_traces": [10, 10001], "duplicate": [0], "or": [0]}, "n_trials": 200}}, {"pipeline_step": "feature_extraction", "input_path": "output/features/generated/grid_2obj/grid_2objectives_enve_rmcv/2_enve_rmcv", "feature_params": {"feature_set": ["ratio_variants_per_number_of_traces", "ratio_most_common_variant", "ratio_top_10_variants", "epa_normalized_variant_entropy", "epa_normalized_sequence_entropy", "epa_normalized_sequence_entropy_linear_forgetting", "epa_normalized_sequence_entropy_exponential_forgetting"]}, "output_path": "output/plots", "real_eventlog_path": "data/BaselineED_feat.csv", "plot_type": "boxplot"}, {"pipeline_step": "benchmark_test", "benchmark_test": "discovery", "input_path": "output/generated/grid_2obj/grid_2objectives_enve_rmcv/2_enve_rmcv", "output_path": "output", "miners": ["heu", "imf", "ilp"]}]

config_files/algorithm/grid_2obj/generator_grid_2objectives_enve_rt10v.json

@@ -0,0 +1 @@
+[{"pipeline_step": "event_logs_generation", "output_path": "output/generated/grid_2obj", "generator_params": {"experiment": {"input_path": "data/grid_2obj/grid_2objectives_enve_rt10v.csv", "objectives": ["epa_normalized_variant_entropy", "ratio_top_10_variants"]}, "config_space": {"mode": [5, 20], "sequence": [0.01, 1], "choice": [0.01, 1], "parallel": [0.01, 1], "loop": [0.01, 1], "silent": [0.01, 1], "lt_dependency": [0.01, 1], "num_traces": [10, 10001], "duplicate": [0], "or": [0]}, "n_trials": 200}}, {"pipeline_step": "feature_extraction", "input_path": "output/features/generated/grid_2obj/grid_2objectives_enve_rt10v/2_enve_rt10v", "feature_params": {"feature_set": ["ratio_variants_per_number_of_traces", "ratio_most_common_variant", "ratio_top_10_variants", "epa_normalized_variant_entropy", "epa_normalized_sequence_entropy", "epa_normalized_sequence_entropy_linear_forgetting", "epa_normalized_sequence_entropy_exponential_forgetting"]}, "output_path": "output/plots", "real_eventlog_path": "data/BaselineED_feat.csv", "plot_type": "boxplot"}, {"pipeline_step": "benchmark_test", "benchmark_test": "discovery", "input_path": "output/generated/grid_2obj/grid_2objectives_enve_rt10v/2_enve_rt10v", "output_path": "output", "miners": ["heu", "imf", "ilp"]}]

config_files/algorithm/grid_2obj/generator_grid_2objectives_enve_rvpnot.json

@@ -0,0 +1 @@
+[{"pipeline_step": "event_logs_generation", "output_path": "output/generated/grid_2obj", "generator_params": {"experiment": {"input_path": "data/grid_2obj/grid_2objectives_enve_rvpnot.csv", "objectives": ["epa_normalized_variant_entropy", "ratio_variants_per_number_of_traces"]}, "config_space": {"mode": [5, 20], "sequence": [0.01, 1], "choice": [0.01, 1], "parallel": [0.01, 1], "loop": [0.01, 1], "silent": [0.01, 1], "lt_dependency": [0.01, 1], "num_traces": [10, 10001], "duplicate": [0], "or": [0]}, "n_trials": 200}}, {"pipeline_step": "feature_extraction", "input_path": "output/features/generated/grid_2obj/grid_2objectives_enve_rvpnot/2_enve_rvpnot", "feature_params": {"feature_set": ["ratio_variants_per_number_of_traces", "ratio_most_common_variant", "ratio_top_10_variants", "epa_normalized_variant_entropy", "epa_normalized_sequence_entropy", "epa_normalized_sequence_entropy_linear_forgetting", "epa_normalized_sequence_entropy_exponential_forgetting"]}, "output_path": "output/plots", "real_eventlog_path": "data/BaselineED_feat.csv", "plot_type": "boxplot"}, {"pipeline_step": "benchmark_test", "benchmark_test": "discovery", "input_path": "output/generated/grid_2obj/grid_2objectives_enve_rvpnot/2_enve_rvpnot", "output_path": "output", "miners": ["heu", "imf", "ilp"]}]

config_files/algorithm/grid_2obj/generator_grid_2objectives_rmcv_rt10v.json

@@ -0,0 +1 @@
+[{"pipeline_step": "event_logs_generation", "output_path": "output/generated/grid_2obj", "generator_params": {"experiment": {"input_path": "data/grid_2obj/grid_2objectives_rmcv_rt10v.csv", "objectives": ["ratio_most_common_variant", "ratio_top_10_variants"]}, "config_space": {"mode": [5, 20], "sequence": [0.01, 1], "choice": [0.01, 1], "parallel": [0.01, 1], "loop": [0.01, 1], "silent": [0.01, 1], "lt_dependency": [0.01, 1], "num_traces": [10, 10001], "duplicate": [0], "or": [0]}, "n_trials": 200}}, {"pipeline_step": "feature_extraction", "input_path": "output/features/generated/grid_2obj/grid_2objectives_rmcv_rt10v/2_rmcv_rt10v", "feature_params": {"feature_set": ["ratio_variants_per_number_of_traces", "ratio_most_common_variant", "ratio_top_10_variants", "epa_normalized_variant_entropy", "epa_normalized_sequence_entropy", "epa_normalized_sequence_entropy_linear_forgetting", "epa_normalized_sequence_entropy_exponential_forgetting"]}, "output_path": "output/plots", "real_eventlog_path": "data/BaselineED_feat.csv", "plot_type": "boxplot"}, {"pipeline_step": "benchmark_test", "benchmark_test": "discovery", "input_path": "output/generated/grid_2obj/grid_2objectives_rmcv_rt10v/2_rmcv_rt10v", "output_path": "output", "miners": ["heu", "imf", "ilp"]}]

config_files/algorithm/grid_2obj/generator_grid_2objectives_rmcv_rvpnot.json

@@ -0,0 +1 @@
+[{"pipeline_step": "event_logs_generation", "output_path": "output/generated/grid_2obj", "generator_params": {"experiment": {"input_path": "data/grid_2obj/grid_2objectives_rmcv_rvpnot.csv", "objectives": ["ratio_most_common_variant", "ratio_variants_per_number_of_traces"]}, "config_space": {"mode": [5, 20], "sequence": [0.01, 1], "choice": [0.01, 1], "parallel": [0.01, 1], "loop": [0.01, 1], "silent": [0.01, 1], "lt_dependency": [0.01, 1], "num_traces": [10, 10001], "duplicate": [0], "or": [0]}, "n_trials": 200}}, {"pipeline_step": "feature_extraction", "input_path": "output/features/generated/grid_2obj/grid_2objectives_rmcv_rvpnot/2_rmcv_rvpnot", "feature_params": {"feature_set": ["ratio_variants_per_number_of_traces", "ratio_most_common_variant", "ratio_top_10_variants", "epa_normalized_variant_entropy", "epa_normalized_sequence_entropy", "epa_normalized_sequence_entropy_linear_forgetting", "epa_normalized_sequence_entropy_exponential_forgetting"]}, "output_path": "output/plots", "real_eventlog_path": "data/BaselineED_feat.csv", "plot_type": "boxplot"}, {"pipeline_step": "benchmark_test", "benchmark_test": "discovery", "input_path": "output/generated/grid_2obj/grid_2objectives_rmcv_rvpnot/2_rmcv_rvpnot", "output_path": "output", "miners": ["heu", "imf", "ilp"]}]

config_files/algorithm/grid_2obj/generator_grid_2objectives_rt10v_rvpnot.json

@@ -0,0 +1 @@
+[{"pipeline_step": "event_logs_generation", "output_path": "output/generated/grid_2obj", "generator_params": {"experiment": {"input_path": "data/grid_2obj/grid_2objectives_rt10v_rvpnot.csv", "objectives": ["ratio_top_10_variants", "ratio_variants_per_number_of_traces"]}, "config_space": {"mode": [5, 20], "sequence": [0.01, 1], "choice": [0.01, 1], "parallel": [0.01, 1], "loop": [0.01, 1], "silent": [0.01, 1], "lt_dependency": [0.01, 1], "num_traces": [10, 10001], "duplicate": [0], "or": [0]}, "n_trials": 200}}, {"pipeline_step": "feature_extraction", "input_path": "output/features/generated/grid_2obj/grid_2objectives_rt10v_rvpnot/2_rt10v_rvpnot", "feature_params": {"feature_set": ["ratio_variants_per_number_of_traces", "ratio_most_common_variant", "ratio_top_10_variants", "epa_normalized_variant_entropy", "epa_normalized_sequence_entropy", "epa_normalized_sequence_entropy_linear_forgetting", "epa_normalized_sequence_entropy_exponential_forgetting"]}, "output_path": "output/plots", "real_eventlog_path": "data/BaselineED_feat.csv", "plot_type": "boxplot"}, {"pipeline_step": "benchmark_test", "benchmark_test": "discovery", "input_path": "output/generated/grid_2obj/grid_2objectives_rt10v_rvpnot/2_rt10v_rvpnot", "output_path": "output", "miners": ["heu", "imf", "ilp"]}]

config_files/algorithm/pipeline_steps/augmentation.json

@@ -0,0 +1,12 @@
+[
+  {
+    "pipeline_step": "instance_augmentation",
+    "augmentation_params":
+    {
+        "method":"SMOTE", "no_samples":20,
+        "feature_selection": ["n_traces", "n_unique_traces", "ratio_variants_per_number_of_traces", "trace_len_min", "trace_len_max", "trace_len_mean", "trace_len_median", "trace_len_mode", "trace_len_std", "trace_len_variance", "trace_len_q1", "trace_len_q3", "trace_len_iqr", "trace_len_geometric_mean", "trace_len_geometric_std", "trace_len_harmonic_mean", "trace_len_skewness", "trace_len_kurtosis", "trace_len_coefficient_variation", "trace_len_entropy", "trace_len_hist1", "trace_len_hist2", "trace_len_hist3", "trace_len_hist4", "trace_len_hist5", "trace_len_hist6", "trace_len_hist7", "trace_len_hist8", "trace_len_hist9", "trace_len_hist10", "trace_len_skewness_hist", "trace_len_kurtosis_hist", "ratio_most_common_variant", "ratio_top_1_variants", "ratio_top_5_variants", "ratio_top_10_variants", "ratio_top_20_variants", "ratio_top_50_variants", "ratio_top_75_variants", "mean_variant_occurrence", "std_variant_occurrence", "skewness_variant_occurrence", "kurtosis_variant_occurrence", "n_unique_activities", "activities_min", "activities_max", "activities_mean", "activities_median", "activities_std", "activities_variance", "activities_q1", "activities_q3", "activities_iqr", "activities_skewness", "activities_kurtosis", "n_unique_start_activities", "start_activities_min", "start_activities_max", "start_activities_mean", "start_activities_median", "start_activities_std", "start_activities_variance", "start_activities_q1", "start_activities_q3", "start_activities_iqr", "start_activities_skewness", "start_activities_kurtosis", "n_unique_end_activities", "end_activities_min", "end_activities_max", "end_activities_mean", "end_activities_median", "end_activities_std", "end_activities_variance", "end_activities_q1", "end_activities_q3", "end_activities_iqr", "end_activities_skewness", "end_activities_kurtosis", "entropy_trace", "entropy_prefix", "entropy_global_block", "entropy_lempel_ziv", "entropy_k_block_diff_1", "entropy_k_block_diff_3", "entropy_k_block_diff_5", "entropy_k_block_ratio_1", "entropy_k_block_ratio_3", "entropy_k_block_ratio_5", "entropy_knn_3", "entropy_knn_5", "entropy_knn_7", "epa_variant_entropy", "epa_normalized_variant_entropy", "epa_sequence_entropy", "epa_normalized_sequence_entropy", "epa_sequence_entropy_linear_forgetting", "epa_normalized_sequence_entropy_linear_forgetting", "epa_sequence_entropy_exponential_forgetting", "epa_normalized_sequence_entropy_exponential_forgetting"]
+    },
+    "input_path": "data/bpic_features.csv",
+    "output_path": "output"
+  }
+]

config_files/algorithm/{benchmark.json → pipeline_steps/benchmark.json}

@@ -4,6 +4,6 @@
     "benchmark_test": "discovery",
     "input_path":"data/test",
     "output_path":"output",
-    "miners" : ["inductive", "heuristics", "imf", "ilp"]
+    "miners" : ["inductive", "heu", "imf", "ilp"]
   }
 ]

config_files/algorithm/{evaluation_plotter.json → pipeline_steps/evaluation_plotter.json}

@@ -1,7 +1,7 @@
 [
     {
         "pipeline_step": "evaluation_plotter",
-        "input_path": "output/features/generated/34_bpic_features/",
+        "input_path": "output/features/generated/BaselineED_feat/",
         "input_path": "output/features/generated/grid_2obj/",
         "input_path": ["output/features/generated/grid_1obj/", "output/features/generated/grid_2obj/"],
         "input_path": "output/features/generated/grid_1obj/1_enve_feat.csv",
@@ -9,7 +9,7 @@
         "reference_feature": "epa_normalized_sequence_entropy",
         "reference_feature": "epa_normalized_sequence_entropy_exponential_forgetting",
         "reference_feature": "epa_normalized_variant_entropy",
-        "targets": "data/34_bpic_features.csv",
+        "targets": "data/BaselineED_feat.csv",
         "targets": "data/grid_experiments/grid_2obj/",
         "targets": ["data/grid_experiments/grid_1obj/", "data/grid_experiments/grid_2obj/"],
         "targets": "data/grid_experiments/grid_1obj/grid_1objectives_enve.csv",

config_files/algorithm/{feature_extraction.json → pipeline_steps/feature_extraction.json}

@@ -2,7 +2,7 @@
   {
     "pipeline_step": "feature_extraction",
     "input_path": "data/test",
-    "feature_params": {"feature_set":["simple_stats", "trace_length", "trace_variant", "activities", "start_activities", "end_activities", "eventropies", "epa_based"]},
+    "feature_params": {"feature_set":["ratio_variants_per_number_of_traces", "ratio_most_common_variant", "ratio_top_10_variants", "epa_normalized_variant_entropy", "epa_normalized_sequence_entropy", "epa_normalized_sequence_entropy_linear_forgetting", "epa_normalized_sequence_entropy_exponential_forgetting"]},
     "output_path": "output/plots",
     "real_eventlog_path": "data/BaselineED_feat.csv",
     "plot_type": "boxplot",

dashboard.py

@@ -1,295 +0,0 @@
-from copy import deepcopy
-from meta_feature_extraction.simple_stats import simple_stats
-from meta_feature_extraction.trace_length import trace_length
-from meta_feature_extraction.trace_variant import trace_variant
-from meta_feature_extraction.activities import activities
-from meta_feature_extraction.start_activities import start_activities
-from meta_feature_extraction.end_activities import end_activities
-from meta_feature_extraction.entropies import entropies
-from pm4py import discover_petri_net_inductive as inductive_miner
-from pm4py import generate_process_tree
-from pm4py import save_vis_petri_net, save_vis_process_tree
-from pm4py.algo.filtering.log.variants import variants_filter
-from pm4py.algo.simulation.tree_generator import algorithm as tree_generator
-from pm4py.algo.simulation.playout.process_tree import algorithm as playout
-from pm4py.objects.conversion.log import converter as log_converter
-from pm4py.objects.log.exporter.xes import exporter as xes_exporter
-from pm4py.objects.log.importer.xes import importer as xes_importer
-from pm4py.objects.log.util import dataframe_utils
-from pm4py.sim import play_out
-
-import matplotlib.image as mpimg
-import os
-import pandas as pd
-import streamlit as st
-
-OUTPUT_PATH = "output"
-SAMPLE_EVENTS = 500
-
-@st.cache(allow_output_mutation=True)
-def load_from_xes(uploaded_file):
-    bytes_data = uploaded_file.getvalue()
-    log1 = xes_importer.deserialize(bytes_data)
-    get_stats(log1)
-    return log1
-
-@st.cache
-def load_from_csv(uploaded_file, sep):
-    if uploaded_file is not None:
-        df = pd.read_csv(uploaded_file, sep=sep, index_col=False)
-        return df
-
-def get_stats(log, save=True):
-    """Returns the statistics of an event log."""
-    num_traces = len(log)
-    num_events = sum([len(c) for c in log])
-    num_utraces = len(variants_filter.get_variants(log))
-    if save:
-        st.session_state["num_traces"] = num_traces
-        st.session_state["num_events"] = num_events
-        st.session_state["num_utraces"] = num_utraces
-    return num_utraces, num_traces, num_events
-
-#@st.cache
-def df_to_log(df, case_id, activity, timestamp):
-    df.rename(columns={case_id: 'case:concept:name',
-                       activity: 'concept:name',
-                       timestamp: "time:timestamp"}, inplace=True)
-    temp = dataframe_utils.convert_timestamp_columns_in_df(df)
-    #temp = temp.sort_values(timestamp)
-    log = log_converter.apply(temp)
-    return log, 'concept:name', "time:timestamp"
-
-def read_uploaded_file(uploaded_file):
-    extension = uploaded_file.name.split('.')[-1]
-    log_name = uploaded_file.name.split('.')[-2]
-
-    st.sidebar.write("Loaded ", extension.upper(), '-File: ', uploaded_file.name)
-    if extension == "xes":
-        event_log = load_from_xes(uploaded_file)
-        log_columns = [*list(event_log[0][0].keys())]
-        convert_button = False
-        case_id = "case:concept:name"
-        activity = "concept:name"
-        timestamp = "time:timestamp"
-        default_act_id = log_columns.index("concept:name")
-        default_tst_id = log_columns.index("time:timestamp")
-
-        event_df = log_converter.apply(event_log, variant=log_converter.Variants.TO_DATA_FRAME)
-        df_path = OUTPUT_PATH+"/"+log_name+".csv"
-        event_df.to_csv(df_path, sep =";", index=False)
-        return event_log, event_df, case_id, activity
-
-    elif extension == "csv":
-        sep = st.sidebar.text_input("Columns separator", ";")
-        event_df = load_from_csv(uploaded_file, sep)
-        old_df = deepcopy(event_df)
-        log_columns = event_df.columns
-
-        case_id = st.sidebar.selectbox("Choose 'case' column:", log_columns)
-        activity = st.sidebar.selectbox("Choose 'activity' column:", log_columns, index=0)
-        timestamp = st.sidebar.selectbox("Choose 'timestamp' column:", log_columns, index=0)
-
-        convert_button = st.sidebar.button('Confirm selection')
-        if convert_button:
-            temp = deepcopy(event_df)
-            event_log, activity, timestamp = df_to_log(temp, case_id, activity, timestamp)
-            #xes_exporter.apply(event_log, INPUT_XES)
-            log_columns = [*list(event_log[0][0].keys())]
-            st.session_state['log'] = event_log
-            return event_log, event_df, case_id, activity
-
-def sample_log_traces(complete_log, sample_size):
-    '''
-    Samples random traces out of logs.
-    So that number of events is slightly over SAMPLE_SIZE.
-    :param complete_log: Log extracted from xes
-    '''
-
-    log_traces = variants_filter.get_variants(complete_log)
-    keys = list(log_traces.keys())
-    sample_traces = {}
-    num_evs = 0
-    while num_evs < sample_size:
-        if len(keys) == 0:
-            break
-        random_trace = keys.pop()
-        sample_traces[random_trace] = log_traces[random_trace]
-        evs = sum([len(case_id) for case_id in sample_traces[random_trace]])
-        num_evs += evs
-    log1 = variants_filter.apply(complete_log, sample_traces)
-    return log1
-
-def show_process_petrinet(event_log, filter_info, OUTPUT_PATH):
-            OUTPUT_PLOT = f"{OUTPUT_PATH}_{filter_info}".replace(":","").replace(".","")+".png" # OUTPUT_PATH is OUTPUT_PATH+INPUT_FILE
-
-            try:
-                fig_pt = mpimg.imread(OUTPUT_PLOT)
-                st.write("Loaded from memory")
-            except FileNotFoundError:
-                net, im, fm = inductive_miner(event_log)
-                           # parameters={heuristics_miner.Variants.CLASSIC.value.Parameters.DEPENDENCY_THRESH: 0.99,
-                           #     pn_visualizer.Variants.FREQUENCY.value.Parameters.FORMAT: "png"})
-                #parameters = {pn_visualizer.Variants.FREQUENCY.value.Parameters.FORMAT: "png"}
-                save_vis_petri_net(net, im, fm, OUTPUT_PLOT)
-                st.write("Saved in: ", OUTPUT_PLOT)
-            fig_pt = mpimg.imread(OUTPUT_PLOT)
-            st.image(fig_pt)
-
-def show_loaded_event_log(event_log, event_df):
-        get_stats(event_log)
-        st.write("### Loaded event-log")
-        col1, col2 = st.columns(2)
-        with col2:
-            st.dataframe(event_df)
-        with col1:
-            show_process_petrinet(event_log, None, OUTPUT_PATH+"running-example")
-
-def extract_meta_features(log, log_name):
-    mtf_cols = ["log", "n_traces", "n_unique_traces", "ratio_unique_traces_per_trace", "n_events", "trace_len_min", "trace_len_max",
-                "trace_len_mean", "trace_len_median", "trace_len_mode", "trace_len_std", "trace_len_variance", "trace_len_q1",
-                "trace_len_q3", "trace_len_iqr", "trace_len_geometric_mean", "trace_len_geometric_std", "trace_len_harmonic_mean",
-                "trace_len_skewness", "trace_len_kurtosis", "trace_len_coefficient_variation", "trace_len_entropy", "trace_len_hist1",
-                "trace_len_hist2", "trace_len_hist3", "trace_len_hist4", "trace_len_hist5", "trace_len_hist6", "trace_len_hist7",
-                "trace_len_hist8", "trace_len_hist9", "trace_len_hist10", "trace_len_skewness_hist", "trace_len_kurtosis_hist",
-                "ratio_most_common_variant", "ratio_top_1_variants", "ratio_top_5_variants", "ratio_top_10_variants", "ratio_top_20_variants",
-                "ratio_top_50_variants", "ratio_top_75_variants", "mean_variant_occurrence", "std_variant_occurrence", "skewness_variant_occurrence",
-                "kurtosis_variant_occurrence", "n_unique_activities", "activities_min", "activities_max", "activities_mean", "activities_median",
-                "activities_std", "activities_variance", "activities_q1", "activities_q3", "activities_iqr", "activities_skewness",
-                "activities_kurtosis", "n_unique_start_activities", "start_activities_min", "start_activities_max", "start_activities_mean",
-                "start_activities_median", "start_activities_std", "start_activities_variance", "start_activities_q1", "start_activities_q3",
-                "start_activities_iqr", "start_activities_skewness", "start_activities_kurtosis", "n_unique_end_activities", "end_activities_min",
-                "end_activities_max", "end_activities_mean", "end_activities_median", "end_activities_std", "end_activities_variance",
-                "end_activities_q1", "end_activities_q3", "end_activities_iqr", "end_activities_skewness", "end_activities_kurtosis", "entropy_trace",
-                "entropy_prefix", "entropy_global_block", "entropy_lempel_ziv", "entropy_k_block_diff_1", "entropy_k_block_diff_3",
-                "entropy_k_block_diff_5", "entropy_k_block_ratio_1", "entropy_k_block_ratio_3", "entropy_k_block_ratio_5", "entropy_knn_3",
-                "entropy_knn_5", "entropy_knn_7"]
-    features = [log_name]
-    features.extend(simple_stats(log))
-    features.extend(trace_length(log))
-    features.extend(trace_variant(log))
-    features.extend(activities(log))
-    features.extend(start_activities(log))
-    features.extend(end_activities(log))
-    features.extend(entropies(log_name, OUTPUT_PATH))
-
-    mtf = pd.DataFrame([features], columns=mtf_cols)
-
-    st.dataframe(mtf)
-    return mtf
-
-def generate_pt(mtf):
-    OUTPUT_PLOT = f"{OUTPUT_PATH}/generated_pt".replace(":","").replace(".","")#+".png" # OUTPUT_PATH is OUTPUT_PATH+INPUT_FILE
-
-    st.write("### PT Gen configurations")
-    col1, col2, col3, col4, col5, col6 = st.columns(6)
-    with col1:
-            param_mode = st.text_input('Mode', str(round(mtf['activities_median'].iat[0]))) #?
-            st.write("Sum of probabilities must be one")
-    with col2:
-            param_min = st.text_input('Min', str(mtf['activities_min'].iat[0]))
-            param_seq = st.text_input('Probability Sequence', 0.25)
-    with col3:
-            param_max = st.text_input('Max', str(mtf['activities_max'].iat[0]))
-            param_cho = st.text_input('Probability Choice (XOR)', 0.25)
-    with col4:
-            param_nmo = st.text_input('Number of models', 1)
-            param_par = st.text_input('Probability Parallel', 0.25)
-    with col5:
-            param_dup = st.text_input('Duplicates', 0)
-            param_lop = st.text_input('Probability Loop', 0.25)
-    with col6:
-            param_sil = st.text_input('Silent', 0.2)
-            param_or = st.text_input('Probability Or', 0.0)
-
-    PT_PARAMS = {tree_generator.Variants.PTANDLOGGENERATOR.value.Parameters.MODE: round(float(param_mode)), #most frequent number of visible activities
-            tree_generator.Variants.PTANDLOGGENERATOR.value.Parameters.MIN: int(param_min), #minimum number of visible activities
-            tree_generator.Variants.PTANDLOGGENERATOR.value.Parameters.MAX: int(param_max), #maximum number of visible activities
-            tree_generator.Variants.PTANDLOGGENERATOR.value.Parameters.SEQUENCE: float(param_seq), #probability to add a sequence operator to tree
-            tree_generator.Variants.PTANDLOGGENERATOR.value.Parameters.CHOICE: float(param_cho), #probability to add a choice (XOR) operator to tree
-            tree_generator.Variants.PTANDLOGGENERATOR.value.Parameters.PARALLEL: float(param_par), #probability to add a parallel operator to tree
-            tree_generator.Variants.PTANDLOGGENERATOR.value.Parameters.LOOP: float(param_lop), #probability to add a loop operator to tree
-            tree_generator.Variants.PTANDLOGGENERATOR.value.Parameters.OR: float(param_or), #probability to add an or operator to tree
-            tree_generator.Variants.PTANDLOGGENERATOR.value.Parameters.SILENT: float(param_sil), #probability to add silent activity to a choice or loop operator
-            tree_generator.Variants.PTANDLOGGENERATOR.value.Parameters.DUPLICATE: int(param_dup), #probability to duplicate an activity label
-            tree_generator.Variants.PTANDLOGGENERATOR.value.Parameters.NO_MODELS: int(param_nmo)} #number of trees to generate from model population
-
-    process_tree = generate_process_tree(parameters=PT_PARAMS)
-    save_vis_process_tree(process_tree, OUTPUT_PLOT+"_tree.png")
-
-    st.write("### Playout configurations")
-
-    param_ntraces = st.text_input('Number of traces', str(mtf['n_traces'].iat[0]))
-    PO_PARAMS = {playout.Variants.BASIC_PLAYOUT.value.Parameters.NO_TRACES : int(param_ntraces)}
-
-    ptgen_log = play_out(process_tree, parameters=PO_PARAMS)
-
-    net, im, fm = inductive_miner(ptgen_log)
-    save_vis_petri_net(net, im, fm, OUTPUT_PLOT+".png")
-    st.write("Saved in: ", OUTPUT_PLOT)
-    fig_pt_net = mpimg.imread(OUTPUT_PLOT+".png")
-    fig_pt_tree = mpimg.imread(OUTPUT_PLOT+"_tree.png")
-
-    fcol1, fcol2 = st.columns(2)
-    with fcol1:
-        st.image(fig_pt_tree)
-    with fcol2:
-        st.image(fig_pt_net)
-    extract_meta_features(ptgen_log, "gen_pt")
-
-
-if __name__ == '__main__':
-    st.set_page_config(layout='wide')
-    """
-    # Event Log Generator
-    """
-    start_options =  ['Event-Log', 'Meta-features']
-    start_preference = st.sidebar.selectbox("Do you want to start with a log or with metafeatures?", start_options,0)
-    #lets_start = st.sidebar.button("Let's start with "+start_preference+'!')
-
-    if start_preference==start_options[0]:
-        st.sidebar.write("Upload a dataset in csv or xes-format:")
-        uploaded_file = st.sidebar.file_uploader("Pick a logfile")
-
-        bar = st.progress(0)
-
-        os.makedirs(OUTPUT_PATH, exist_ok=True)
-        event_log = st.session_state['log'] if "log" in st.session_state else None
-        if uploaded_file:
-            event_log, event_df, case_id, activity_id = read_uploaded_file(uploaded_file)
-            #event_log = deepcopy(event_log)
-
-            use_sample = st.sidebar.checkbox('Use random sample', True)
-            if use_sample:
-                sample_size = st.sidebar.text_input('Sample size of approx number of events', str(SAMPLE_EVENTS))
-                sample_size = int(sample_size)
-
-                event_log = sample_log_traces(event_log, sample_size)
-                sample_cases = [event_log[i].attributes['concept:name'] for i in range(0, len(event_log))]
-                event_df = event_df[event_df[case_id].isin(sample_cases)]
-
-            show_loaded_event_log(event_log, event_df)
-            ext_mtf = extract_meta_features(event_log, "running-example")
-            generate_pt(ext_mtf)
-
-    elif start_preference==start_options[1]:
-        LOG_COL = 'log'
-        st.sidebar.write("Upload a dataset in csv-format")
-        uploaded_file = st.sidebar.file_uploader("Pick a file containing meta-features")
-
-        bar = st.progress(0)
-
-        os.makedirs(OUTPUT_PATH, exist_ok=True)
-        event_log = st.session_state[LOG_COL] if "log" in st.session_state else None
-        if uploaded_file:
-            sep = st.sidebar.text_input("Columns separator", ";")
-            mtf = load_from_csv(uploaded_file, sep)
-            st.dataframe(mtf)
-
-            log_options = mtf['log'].unique()
-            log_preference = st.selectbox("What log should we use for generating a new event-log?", log_options,1)
-            mtf_selection = mtf[mtf[LOG_COL]==log_preference]
-            generate_pt(mtf_selection)
-            st.write("##### Original")
-            st.write(mtf_selection)
-

data/2_bpic_features.csv

@@ -0,0 +1,3 @@
+log,n_traces,n_unique_traces,ratio_unique_traces_per_trace,trace_len_min,trace_len_max,trace_len_mean,trace_len_median,trace_len_mode,trace_len_std,trace_len_variance,trace_len_q1,trace_len_q3,trace_len_iqr,trace_len_geometric_mean,trace_len_geometric_std,trace_len_harmonic_mean,trace_len_skewness,trace_len_kurtosis,trace_len_coefficient_variation,trace_len_entropy,trace_len_hist1,trace_len_hist2,trace_len_hist3,trace_len_hist4,trace_len_hist5,trace_len_hist6,trace_len_hist7,trace_len_hist8,trace_len_hist9,trace_len_hist10,trace_len_skewness_hist,trace_len_kurtosis_hist,ratio_most_common_variant,ratio_top_1_variants,ratio_top_5_variants,ratio_top_10_variants,ratio_top_20_variants,ratio_top_50_variants,ratio_top_75_variants,mean_variant_occurrence,std_variant_occurrence,skewness_variant_occurrence,kurtosis_variant_occurrence,n_unique_activities,activities_min,activities_max,activities_mean,activities_median,activities_std,activities_variance,activities_q1,activities_q3,activities_iqr,activities_skewness,activities_kurtosis,n_unique_start_activities,start_activities_min,start_activities_max,start_activities_mean,start_activities_median,start_activities_std,start_activities_variance,start_activities_q1,start_activities_q3,start_activities_iqr,start_activities_skewness,start_activities_kurtosis,n_unique_end_activities,end_activities_min,end_activities_max,end_activities_mean,end_activities_median,end_activities_std,end_activities_variance,end_activities_q1,end_activities_q3,end_activities_iqr,end_activities_skewness,end_activities_kurtosis,eventropy_trace,eventropy_prefix,eventropy_global_block,eventropy_lempel_ziv,eventropy_k_block_diff_1,eventropy_k_block_diff_3,eventropy_k_block_diff_5,eventropy_k_block_ratio_1,eventropy_k_block_ratio_3,eventropy_k_block_ratio_5,eventropy_knn_3,eventropy_knn_5,eventropy_knn_7,epa_variant_entropy,epa_normalized_variant_entropy,epa_sequence_entropy,epa_normalized_sequence_entropy,epa_sequence_entropy_linear_forgetting,epa_normalized_sequence_entropy_linear_forgetting,epa_sequence_entropy_exponential_forgetting,epa_normalized_sequence_entropy_exponential_forgetting,eventropy_global_block_flattened,eventropy_lempel_ziv_flattened,eventropy_prefix_flattened
+Sepsis_Cases_Event_Log,1050,846,0.805714285714285,3,185,14.48952380952381,13,8,11.470474925273926,131.57179501133788,9,16,7,12.281860759040903,1.7464004837799152,10.47731701485374,7.250526815880918,87.0376906898399,0.791639192292468,6.769403523350811,0.04861329147043401,0.005285190999476001,0.000575614861329,0.000209314495028,0.000104657247514,0.0,5.2328623757195225e-05,0.0,0.0,0.000104657247514,2.612850778156251,4.931206347805768,0.033333333333333,0.12,0.215238095238095,0.274285714285714,0.355238095238095,0.5971428571428571,0.7980952380952381,1.241134751773049,1.759408518249193,13.637101374069475,217.44268017168216,16,6,3383,950.875,788.0,1008.5815457239935,1017236.734375,101.75,1085.25,983.5,1.391238560701821,1.05777753209275,6,6,995,175.0,12.0,366.73787187399483,134496.66666666666,7.75,17.0,9.25,1.7883562472303312,1.199106773708694,14,2,393,75.0,32.5,112.91400014423114,12749.57142857143,14.0,53.5,39.5,2.004413358907822,2.500757934341361,9.334,10.227,14.501,1.7269999999999999,3.238,1.712,1.104,3.238,2.262,1.871,4.956,4.49,4.191,40624.49329803771,0.6957588422064961,76528.6794749776,0.5223430410751391,32139.284589305265,0.219365233602993,43880.53919110408,0.299504635939686,,,
+CoSeLoG_WABO_1,937,916,0.9775880469583771,2,95,41.56243329775881,43,40,16.678023092416094,278.1564542711645,36,51,15,36.71275216938179,1.784073253119976,28.84499612652788,-0.16821637154603802,0.17918482321640303,0.40127638757174006,6.750635463329985,0.006311609919555001,0.009524793151329002,0.006311609919555001,0.014229811454998001,0.039820520765196,0.016869211966812,0.008147714623426,0.0037869659517330003,0.002065617791854,0.00045902617596700005,1.7771796608234571,2.353958246469541,0.009605122732123,0.032017075773746004,0.07043756670224101,0.11953041622198501,0.21771611526147203,0.511205976520811,0.7556029882604051,1.022925764192139,0.33126487599778903,19.52280427642022,422.82376078444236,381,1,937,102.21522309711285,15.0,193.12603388747905,37297.6649651077,3.0,81.0,78.0,2.463005335171609,5.5066536611772605,11,1,899,85.18181818181819,2.0,257.3832721066592,66246.14876033057,1.0,7.5,6.5,2.844783898567343,6.0957042298129664,101,1,292,9.277227722772277,2.0,31.163929012921322,971.1904715223994,1.0,5.0,4.0,7.672745189703872,64.72182800579148,9.806000000000001,13.867,18.357,3.2640000000000002,6.888,1.299,0.582,6.888,3.542,2.403,5.413,4.929,4.629,195166.2442745276,0.6466967918841,247624.8365497508,0.601566424410453,120536.03113478613,0.292823733970692,154887.76808660102,0.37627599125765404,18.361,3.276,13.885

data/bpic_features.csv

@@ -1,4 +1,4 @@
-log,n_traces,n_unique_traces,ratio_unique_traces_per_trace,trace_len_min,trace_len_max,trace_len_mean,trace_len_median,trace_len_mode,trace_len_std,trace_len_variance,trace_len_q1,trace_len_q3,trace_len_iqr,trace_len_geometric_mean,trace_len_geometric_std,trace_len_harmonic_mean,trace_len_skewness,trace_len_kurtosis,trace_len_coefficient_variation,trace_len_entropy,trace_len_hist1,trace_len_hist2,trace_len_hist3,trace_len_hist4,trace_len_hist5,trace_len_hist6,trace_len_hist7,trace_len_hist8,trace_len_hist9,trace_len_hist10,trace_len_skewness_hist,trace_len_kurtosis_hist,ratio_most_common_variant,ratio_top_1_variants,ratio_top_5_variants,ratio_top_10_variants,ratio_top_20_variants,ratio_top_50_variants,ratio_top_75_variants,mean_variant_occurrence,std_variant_occurrence,skewness_variant_occurrence,kurtosis_variant_occurrence,n_unique_activities,activities_min,activities_max,activities_mean,activities_median,activities_std,activities_variance,activities_q1,activities_q3,activities_iqr,activities_skewness,activities_kurtosis,n_unique_start_activities,start_activities_min,start_activities_max,start_activities_mean,start_activities_median,start_activities_std,start_activities_variance,start_activities_q1,start_activities_q3,start_activities_iqr,start_activities_skewness,start_activities_kurtosis,n_unique_end_activities,end_activities_min,end_activities_max,end_activities_mean,end_activities_median,end_activities_std,end_activities_variance,end_activities_q1,end_activities_q3,end_activities_iqr,end_activities_skewness,end_activities_kurtosis,entropy_trace,entropy_prefix,entropy_global_block,entropy_lempel_ziv,entropy_k_block_diff_1,entropy_k_block_diff_3,entropy_k_block_diff_5,entropy_k_block_ratio_1,entropy_k_block_ratio_3,entropy_k_block_ratio_5,entropy_knn_3,entropy_knn_5,entropy_knn_7,Log Nature,epa_variant_entropy,epa_normalized_variant_entropy,epa_sequence_entropy,epa_normalized_sequence_entropy,epa_sequence_entropy_linear_forgetting,epa_normalized_sequence_entropy_linear_forgetting,epa_sequence_entropy_exponential_forgetting,epa_normalized_sequence_entropy_exponential_forgetting,accumulated_time_time_min,accumulated_time_time_max,accumulated_time_time_mean,accumulated_time_time_median,accumulated_time_time_mode,accumulated_time_time_std,accumulated_time_time_variance,accumulated_time_time_q1,accumulated_time_time_q3,accumulated_time_time_iqr,accumulated_time_time_geometric_mean,accumulated_time_time_geometric_std,accumulated_time_time_harmonic_mean,accumulated_time_time_skewness,accumulated_time_time_kurtosis,accumulated_time_time_coefficient_variation,accumulated_time_time_entropy,accumulated_time_time_skewness_hist,accumulated_time_time_kurtosis_hist,execution_time_time_min,execution_time_time_max,execution_time_time_mean,execution_time_time_median,execution_time_time_mode,execution_time_time_std,execution_time_time_variance,execution_time_time_q1,execution_time_time_q3,execution_time_time_iqr,execution_time_time_geometric_mean,execution_time_time_geometric_std,execution_time_time_harmonic_mean,execution_time_time_skewness,execution_time_time_kurtosis,execution_time_time_coefficient_variation,execution_time_time_entropy,execution_time_time_skewness_hist,execution_time_time_kurtosis_hist,remaining_time_time_min,remaining_time_time_max,remaining_time_time_mean,remaining_time_time_median,remaining_time_time_mode,remaining_time_time_std,remaining_time_time_variance,remaining_time_time_q1,remaining_time_time_q3,remaining_time_time_iqr,remaining_time_time_geometric_mean,remaining_time_time_geometric_std,remaining_time_time_harmonic_mean,remaining_time_time_skewness,remaining_time_time_kurtosis,remaining_time_time_coefficient_variation,remaining_time_time_entropy,remaining_time_time_skewness_hist,remaining_time_time_kurtosis_hist,within_day_time_min,within_day_time_max,within_day_time_mean,within_day_time_median,within_day_time_mode,within_day_time_std,within_day_time_variance,within_day_time_q1,within_day_time_q3,within_day_time_iqr,within_day_time_geometric_mean,within_day_time_geometric_std,within_day_time_harmonic_mean,within_day_time_skewness,within_day_time_kurtosis,within_day_time_coefficient_variation,within_day_time_entropy,within_day_time_skewness_hist,within_day_time_kurtosis_hist
+log,n_traces,n_unique_traces,ratio_variants_per_number_of_traces,trace_len_min,trace_len_max,trace_len_mean,trace_len_median,trace_len_mode,trace_len_std,trace_len_variance,trace_len_q1,trace_len_q3,trace_len_iqr,trace_len_geometric_mean,trace_len_geometric_std,trace_len_harmonic_mean,trace_len_skewness,trace_len_kurtosis,trace_len_coefficient_variation,trace_len_entropy,trace_len_hist1,trace_len_hist2,trace_len_hist3,trace_len_hist4,trace_len_hist5,trace_len_hist6,trace_len_hist7,trace_len_hist8,trace_len_hist9,trace_len_hist10,trace_len_skewness_hist,trace_len_kurtosis_hist,ratio_most_common_variant,ratio_top_1_variants,ratio_top_5_variants,ratio_top_10_variants,ratio_top_20_variants,ratio_top_50_variants,ratio_top_75_variants,mean_variant_occurrence,std_variant_occurrence,skewness_variant_occurrence,kurtosis_variant_occurrence,n_unique_activities,activities_min,activities_max,activities_mean,activities_median,activities_std,activities_variance,activities_q1,activities_q3,activities_iqr,activities_skewness,activities_kurtosis,n_unique_start_activities,start_activities_min,start_activities_max,start_activities_mean,start_activities_median,start_activities_std,start_activities_variance,start_activities_q1,start_activities_q3,start_activities_iqr,start_activities_skewness,start_activities_kurtosis,n_unique_end_activities,end_activities_min,end_activities_max,end_activities_mean,end_activities_median,end_activities_std,end_activities_variance,end_activities_q1,end_activities_q3,end_activities_iqr,end_activities_skewness,end_activities_kurtosis,entropy_trace,entropy_prefix,entropy_global_block,entropy_lempel_ziv,entropy_k_block_diff_1,entropy_k_block_diff_3,entropy_k_block_diff_5,entropy_k_block_ratio_1,entropy_k_block_ratio_3,entropy_k_block_ratio_5,entropy_knn_3,entropy_knn_5,entropy_knn_7,Log Nature,epa_variant_entropy,epa_normalized_variant_entropy,epa_sequence_entropy,epa_normalized_sequence_entropy,epa_sequence_entropy_linear_forgetting,epa_normalized_sequence_entropy_linear_forgetting,epa_sequence_entropy_exponential_forgetting,epa_normalized_sequence_entropy_exponential_forgetting,accumulated_time_time_min,accumulated_time_time_max,accumulated_time_time_mean,accumulated_time_time_median,accumulated_time_time_mode,accumulated_time_time_std,accumulated_time_time_variance,accumulated_time_time_q1,accumulated_time_time_q3,accumulated_time_time_iqr,accumulated_time_time_geometric_mean,accumulated_time_time_geometric_std,accumulated_time_time_harmonic_mean,accumulated_time_time_skewness,accumulated_time_time_kurtosis,accumulated_time_time_coefficient_variation,accumulated_time_time_entropy,accumulated_time_time_skewness_hist,accumulated_time_time_kurtosis_hist,execution_time_time_min,execution_time_time_max,execution_time_time_mean,execution_time_time_median,execution_time_time_mode,execution_time_time_std,execution_time_time_variance,execution_time_time_q1,execution_time_time_q3,execution_time_time_iqr,execution_time_time_geometric_mean,execution_time_time_geometric_std,execution_time_time_harmonic_mean,execution_time_time_skewness,execution_time_time_kurtosis,execution_time_time_coefficient_variation,execution_time_time_entropy,execution_time_time_skewness_hist,execution_time_time_kurtosis_hist,remaining_time_time_min,remaining_time_time_max,remaining_time_time_mean,remaining_time_time_median,remaining_time_time_mode,remaining_time_time_std,remaining_time_time_variance,remaining_time_time_q1,remaining_time_time_q3,remaining_time_time_iqr,remaining_time_time_geometric_mean,remaining_time_time_geometric_std,remaining_time_time_harmonic_mean,remaining_time_time_skewness,remaining_time_time_kurtosis,remaining_time_time_coefficient_variation,remaining_time_time_entropy,remaining_time_time_skewness_hist,remaining_time_time_kurtosis_hist,within_day_time_min,within_day_time_max,within_day_time_mean,within_day_time_median,within_day_time_mode,within_day_time_std,within_day_time_variance,within_day_time_q1,within_day_time_q3,within_day_time_iqr,within_day_time_geometric_mean,within_day_time_geometric_std,within_day_time_harmonic_mean,within_day_time_skewness,within_day_time_kurtosis,within_day_time_coefficient_variation,within_day_time_entropy,within_day_time_skewness_hist,within_day_time_kurtosis_hist
 BPIC15_2,832,828,0.9951923076923076,1,132,53.31009615384615,54.0,61,19.89497651105348,395.8100903753698,44.0,62.0,18.0,48.15011097917017,1.6953108255055442,37.583741492631816,0.0541383907866727,0.8049916722455452,0.3731934088739797,6.6467154289258925,0.0038534938344098,0.0048627422196124,0.0046792425132119,0.0239467116852613,0.0237632119788608,0.0082574867880211,0.0047709923664122,0.0013762477980035,0.0006422489724016,0.0001834997064004,0.0541383907866727,0.8049916722455452,0.0024038461538461,0.0144230769230769,0.0540865384615384,0.1033653846153846,0.203125,0.5024038461538461,0.7512019230769231,1.0048309178743962,0.0693367154319194,14.283026792978164,202.00485436893203,410,1,830,108.18048780487806,12.0,187.5881623228515,35189.31864366448,3.0,125.5,122.5,2.1294119001489484,3.808278466770415,14,1,731,59.42857142857143,1.0,186.71740078284623,34863.387755102034,1.0,8.25,7.25,3.300411469802443,8.960767075527839,82,1,216,10.146341463414634,1.0,35.31879964786925,1247.4176085663291,1.0,3.0,2.0,5.098791193232185,25.861991394282988,9.691,14.524,19.448,3.859,7.105,7.105,7.105,7.105,7.105,7.105,5.545,5.039,4.721,Real,240512.2242485009,0.6279728735030676,285876.9226982823,0.6023712370019746,150546.57168151825,0.3172166670686898,185312.93742252485,0.3904728730604407,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
 BPI_Challenge_2018,43809,28457,0.6495697231162546,24,2973,57.39154055102833,49.0,49,34.87213051501663,1216.065486656354,44.0,59.0,15.0,53.775007740790905,1.3673968195217023,51.6515023255421,26.12645867504185,1720.3996647748236,0.6076179551934296,10.59875768208314,0.0033846328873849,5.263453617722996e-06,9.28844756068764e-07,0.0,0.0,0.0,0.0,0.0,7.740372967239698e-08,7.740372967239698e-08,26.12645867504185,1720.3996647748236,0.0269807573786208,0.2903741240384396,0.3730055468054509,0.4153712707434545,0.4803350909630441,0.6752037252619325,0.837590449451026,1.53948061988263,12.487438103768865,64.62568045475237,5083.4558063165005,41,17,466141,61323.56097560976,7530.0,120522.24741658216,14525612122.343842,902.0,45907.0,45005.0,2.444006846537922,4.7732537682944125,4,2,38623,10952.25,2592.0,16111.407548302535,259577453.1875,36.5,13507.75,13471.25,1.098736017040351,-0.714799753613248,21,1,34830,2086.1428571428573,13.0,7431.744980540056,55230833.45578231,2.0,193.0,191.0,4.062386890920656,14.95282428002514,13.191,16.272,20.972,1.023,-0.01,1.855,0.511,1.403,3.572,2.001,7.849,7.371,7.067,Real,11563842.153239768,0.7120788464629594,21146257.119093828,0.5706879719331716,14140225.903138256,0.3816115919659581,15576076.832943872,0.4203618469408319,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
 Receipt_WABO_CoSeLoG,1434,116,0.0808926080892608,1,25,5.981171548117155,6.0,6,2.166128830112964,4.692114108646557,6.0,6.0,0.0,5.414708441482159,1.7049649652198722,4.356444755372117,1.276525010246869,12.296005610487518,0.3621579506100023,7.197192878385,0.0360297536029753,0.008135750813575,0.341120409112041,0.0235355648535564,0.0037773128777312,0.0017433751743375,0.0002905625290562,0.0014528126452812,0.0,0.0005811250581125,1.276525010246869,12.296005610487518,0.4972105997210599,0.4972105997210599,0.796373779637378,0.8870292887029289,0.9302649930264992,0.9595536959553695,0.9797768479776848,12.362068965517242,68.36027740401485,9.380686726353323,92.2819193173858,27,1,1434,317.6666666666667,27.0,553.3898230870318,306240.2962962963,8.0,50.0,42.0,1.342950616318748,-0.1780942423969453,1,1434,1434,1434.0,1434.0,0.0,0.0,1434.0,1434.0,0.0,,,14,1,828,102.42857142857144,6.0,225.87155461384123,51017.95918367348,1.25,33.25,32.0,2.471765166310402,4.8465409223704325,3.209,4.746,7.019,0.385,2.672,2.966,0.804,1.484,2.966,2.966,3.26,2.845,2.584,Real,2382.325855313024,0.6893625408247437,18296.27229411094,0.235532333261429,7814.867608807029,0.1006026786464005,10728.696951225804,0.1381131076951861,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,

data/grid_1obj/{grid_1objectives_rutpt.csv → grid_1objectives_rvpnot.csv}

@@ -1,4 +1,4 @@
-task,ratio_unique_traces_per_trace
+task,ratio_variants_per_number_of_traces
 task_1,0.0
 task_2,0.1
 task_3,0.2

data/grid_2obj/{grid_2objectives_enve_rutpt.csv → grid_2objectives_ense_rvpnot.csv}

@@ -1,4 +1,4 @@
-task,epa_normalized_variant_entropy,ratio_unique_traces_per_trace
+task,epa_normalized_sequence_entropy,ratio_variants_per_number_of_traces
 task_1,0.0,0.0
 task_2,0.0,0.1
 task_3,0.0,0.2

data/grid_2obj/{grid_2objectives_enseef_rutpt.csv → grid_2objectives_enseef_rvpnot.csv}

@@ -1,4 +1,4 @@
-task,epa_normalized_sequence_entropy_exponential_forgetting,ratio_unique_traces_per_trace
+task,epa_normalized_sequence_entropy_exponential_forgetting,ratio_variants_per_number_of_traces
 task_1,0.0,0.0
 task_2,0.0,0.1
 task_3,0.0,0.2

data/grid_2obj/{grid_2objectives_enself_rutpt.csv → grid_2objectives_enself_rvpnot.csv}

@@ -1,4 +1,4 @@
-task,epa_normalized_sequence_entropy_linear_forgetting,ratio_unique_traces_per_trace
+task,epa_normalized_sequence_entropy_linear_forgetting,ratio_variants_per_number_of_traces
 task_1,0.0,0.0
 task_2,0.0,0.1
 task_3,0.0,0.2

data/grid_2obj/{grid_2objectives_rt10v_rutpt.csv → grid_2objectives_enve_rvpnot.csv}

@@ -1,4 +1,4 @@
-task,ratio_top_10_variants,ratio_unique_traces_per_trace
+task,epa_normalized_variant_entropy,ratio_variants_per_number_of_traces
 task_1,0.0,0.0
 task_2,0.0,0.1
 task_3,0.0,0.2

data/grid_2obj/{grid_2objectives_ense_rutpt.csv → grid_2objectives_rmcv_rvpnot.csv}

@@ -1,4 +1,4 @@
-task,epa_normalized_sequence_entropy,ratio_unique_traces_per_trace
+task,ratio_most_common_variant,ratio_variants_per_number_of_traces
 task_1,0.0,0.0
 task_2,0.0,0.1
 task_3,0.0,0.2

data/grid_2obj/{grid_2objectives_rmcv_rutpt.csv → grid_2objectives_rt10v_rvpnot.csv}

@@ -1,4 +1,4 @@
-task,ratio_most_common_variant,ratio_unique_traces_per_trace
+task,ratio_top_10_variants,ratio_variants_per_number_of_traces
 task_1,0.0,0.0
 task_2,0.0,0.1
 task_3,0.0,0.2

data/validation/2_ense_enseef_feat.csv

@@ -0,0 +1,3 @@
+epa_normalized_sequence_entropy,epa_normalized_sequence_entropy_exponential_forgetting,log
+0.617035580430171,0.25759383686118104,CoSeLoG_WABO_1
+0.547597168193871,0.22387845232743803,Sepsis_Cases_Event_Log

data/validation/genELexperiment1_04_02.json

@@ -0,0 +1 @@
+{"ratio_top_20_variants": 0.20017714791851196, "epa_normalized_sequence_entropy_linear_forgetting": 0.052097205658647734, "log": "experiment1"}

data/validation/genELexperiment2_07_04.json

@@ -0,0 +1 @@
+{"ratio_top_20_variants": 0.38863337713534823, "epa_normalized_sequence_entropy_linear_forgetting": 0.052097205658647734, "log": "experiment2"}

data/validation/test_benchmark.csv

@@ -0,0 +1,3 @@
+log,fitness_inductive,precision_inductive,fscore_inductive,size_inductive,pnsize_inductive,cfc_inductive,fitness_heu,precision_heu,fscore_heu,size_heu,pnsize_heu,cfc_heu,fitness_imf,precision_imf,fscore_imf,size_imf,pnsize_imf,cfc_imf,fitness_ilp,precision_ilp,fscore_ilp,size_ilp,pnsize_ilp,cfc_ilp
+gen_el_169,0.9998052420892378,0.6662312989788649,0.7996241723917423,34,24,22,0.9383563249832565,0.5979149389882715,0.7304143193451293,22,14,13,0.9358843752091403,0.6513022517490741,0.7680805654451066,28,18,16,0.9999637006454563,0.432690150325331,0.6040181215566763,27,7,9
+gen_el_168,0.9997678338833808,0.6033523537803138,0.7525477883058467,61,34,20,0.48155419290534085,0.9449078138718174,0.6379760800037585,60,35,32,0.9479094601490539,0.5169524053224155,0.669037930473001,67,38,24,0.9999513902099882,0.4283471743974073,0.5997714527549697,93,30,28

data/validation/test_feat.csv

@@ -0,0 +1,3 @@
+log,ratio_most_common_variant,ratio_top_10_variants,epa_normalized_variant_entropy,epa_normalized_sequence_entropy,epa_normalized_sequence_entropy_linear_forgetting,epa_normalized_sequence_entropy_exponential_forgetting,ratio_variants_per_number_of_traces
+gen_el_168,0.13580246913580246,0.5709876543209876,0.6920749183939835,0.6241163465815115,0.06011912975523125,0.2577500062839078,0.44135802469135804
+gen_el_169,0.25813692480359146,0.6846240179573513,0.6517697077716751,0.4929433574247866,0.06332152226023505,0.21109493857555106,0.3153759820426487

execute_grid_experiments.py

@@ -1,5 +1,6 @@
 import multiprocessing
 import os
+import sys
 
 from datetime import datetime as dt
 from gedi.utils.io_helpers import sort_files
@@ -13,15 +14,18 @@ def multi_experiment_wrapper(config_file, i=0):
     print(f"=========================FINISHED EXPERIMENT #{i+1}=======================")
 
 if __name__ == '__main__':
-    EXPERIMENTS_FOLDER = os.path.join('config_files','algorithm','34_bpic_features')
-    EXPERIMENTS_FOLDER = os.path.join('config_files','algorithm','grid_1obj')
-    EXPERIMENTS_FOLDER = os.path.join('config_files','algorithm','grid_experiments')
-    EXPERIMENTS_FOLDER = os.path.join('config_files','algorithm','test')
+    EXPERIMENTS_FOLDER = sys.argv[1]
+    """
+    Following args run the following experiments:
+    - config_files/algorithm/grid_1obj
+    - config_files/algorithm/grid_experiments
+    - config_files/algorithm/test
+    """
     start = dt.now()
 
     experiment_list = list(tqdm(sort_files(os.listdir(EXPERIMENTS_FOLDER))))
     experiment_list = [os.path.join(EXPERIMENTS_FOLDER, config_file) for config_file in experiment_list]
-    experiment_list = experiment_list[:10]
+    #experiment_list = experiment_list[:10]
 
     print(f"========================STARTING MULTIPLE EXPERIMENTS=========================")
     print(f"INFO: {EXPERIMENTS_FOLDER} contains config files for {len(experiment_list)}.")

gedi/benchmark.py

@@ -34,7 +34,7 @@ class BenchmarkTest:
                 event_logs = [""]
             else:
                 try:
-                    event_logs =[filename for filename in os.listdir(log_path) if filename.endswith(".xes")]
+                    event_logs =sorted([filename for filename in os.listdir(log_path) if filename.endswith(".xes")])
                 except FileNotFoundError:
                     print(f"        FAILED: Cannot find {params[INPUT_PATH]}" )
                     return
@@ -94,7 +94,7 @@ class BenchmarkTest:
         else:
             log_name = "gen_el_"+str(log_counter)
             results = {"log": event_log}
-            
+
         for miner in miners:
             miner_cols = [f"fitness_{miner}", f"precision_{miner}", f"fscore_{miner}", f"size_{miner}", f"cfc_{miner}", f"pnsize_{miner}"]# f"generalization_{miner}",f"simplicity_{miner}"]
             start_miner = dt.now()
@@ -186,6 +186,8 @@ class BenchmarkTest:
             if miner == 'imf':
                 miner = 'inductive'
                 miner_params = f', noise_threshold={NOISE_THRESHOLD}'
+            elif miner == 'heu':
+                miner = 'heuristics'
             net, im, fm = eval(f"discover_petri_net_{miner}(log {miner_params})")
             bpmn_graph = convert_to_bpmn(net, im, fm)
         fitness = fitness_alignments(log, net, im, fm)['log_fitness']