Updates config_file dir structure

.github/workflows/test_gedi.yml

@@ -29,7 +29,7 @@ jobs:
 
     - name: Run test
       run:
-        python main.py -a config_files/algorithm/pipeline_steps/feature_extraction.json
+        python main.py -a config_files/pipeline_steps/feature_extraction.json
 
     - name: Compare output
       run: diff data/validation/test_feat.csv data/test_feat.csv
@@ -59,7 +59,7 @@ jobs:
 
     - name: Run test
       run:
-        python main.py -a config_files/algorithm/pipeline_steps/generation.json
+        python main.py -a config_files/pipeline_steps/generation.json
 
     - name: Compare output 1
       run: 
@@ -97,7 +97,7 @@ jobs:
 
     - name: Run test
       run:
-        python main.py -a config_files/algorithm/pipeline_steps/benchmark.json
+        python main.py -a config_files/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
@@ -126,7 +126,7 @@ jobs:
 
     - name: Run test
       run:
-        python main.py -a config_files/algorithm/pipeline_steps/augmentation.json
+        python main.py -a config_files/pipeline_steps/augmentation.json
 
   test_evaluation-plotter:
     runs-on: ubuntu-latest
@@ -153,7 +153,7 @@ jobs:
     - name: Run test
       run:
 
-        python main.py -a config_files/algorithm/pipeline_steps/evaluation_plotter.json
+        python main.py -a config_files/pipeline_steps/evaluation_plotter.json
 
   test_integration:
     runs-on: ubuntu-latest
@@ -179,7 +179,7 @@ jobs:
 
     - name: Run test
       run:
-        python main.py -a config_files/algorithm/experiment_test.json
+        python main.py -a config_files/test/experiment_test.json
 
   test_grid_experiments_script:
     runs-on: ubuntu-latest
@@ -205,7 +205,7 @@ jobs:
 
     - name: Run test
       run:
-        python execute_grid_experiments.py config_files/algorithm/test
+        python execute_grid_experiments.py config_files/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

README.md

@@ -27,7 +27,7 @@ conda install pyrfr swig
 ### Startup
 ```console
 conda activate gedi
-python main.py -a config_files/algorithm/experiment_test.json
+python main.py -a config_files/test/experiment_test.json
 ```
 The last step should take only a few minutes to run.
 
@@ -43,7 +43,7 @@ To run different steps of the GEDI pipeline, please adapt the `.json` accordingl
 conda activate gedi
 python main.py -a config_files/algorithm/pipeline_steps/<pipeline-step>.json
 ```
-For reference of possible keys and values for each step, please see `config_files/algorithm/experiment_test.json`.
+For reference of possible keys and values for each step, please see `config_files/test/experiment_test.json`.
 To run the whole pipeline please create a new `.json` file, specifying all steps you want to run and specify desired keys and values for each step.
 To reproduce results from out paper, please refer to [Experiments](#experiments).
 

config_files/grid_2obj/generator_grid_2objectives_enve_mvo.json

@@ -0,0 +1 @@
+[{"pipeline_step": "event_logs_generation", "output_path": "output/shaining/grid_2obj", "generator_params": {"experiment": {"input_path": "data/grid_2obj/grid_2objectives_enve_mvo.csv", "objectives": ["epa_normalized_variant_entropy", "mean_variant_occurrence"]}, "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/shaining/grid_2obj/grid_2objectives_enve_mvo/2_enve_mvo", "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/shaining/grid_2obj/grid_2objectives_enve_mvo/2_enve_mvo", "output_path": "output", "miners": ["heu", "imf", "ilp"]}]

config_files/grid_2obj/generator_grid_2objectives_enve_sam.json

@@ -0,0 +1 @@
+[{"pipeline_step": "event_logs_generation", "output_path": "output/shaining/grid_2obj", "generator_params": {"experiment": {"input_path": "data/grid_2obj/grid_2objectives_enve_sam.csv", "objectives": ["epa_normalized_variant_entropy", "start_activities_median"]}, "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/shaining/grid_2obj/grid_2objectives_enve_sam/2_enve_sam", "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/shaining/grid_2obj/grid_2objectives_enve_sam/2_enve_sam", "output_path": "output", "miners": ["heu", "imf", "ilp"]}]

config_files/grid_2obj/generator_grid_2objectives_mvo_sam.json

@@ -0,0 +1 @@
+[{"pipeline_step": "event_logs_generation", "output_path": "output/shaining/grid_2obj", "generator_params": {"experiment": {"input_path": "data/grid_2obj/grid_2objectives_mvo_sam.csv", "objectives": ["mean_variant_occurrence", "start_activities_median"]}, "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/shaining/grid_2obj/grid_2objectives_mvo_sam/2_mvo_sam", "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/shaining/grid_2obj/grid_2objectives_mvo_sam/2_mvo_sam", "output_path": "output", "miners": ["heu", "imf", "ilp"]}]

config_files/grid_experiments/genGrid1to3minMedian90Q.json

@@ -0,0 +1,293 @@
+[
+    {
+        "pipeline_step": "event_logs_generation",
+        "output_path": "data/genGrid1to3minMedian90Q",
+        "generator_params": {
+            "experiment": [
+                {
+                    "mean_variant_occurrence": 2.64
+                },
+                {
+                    "mean_variant_occurrence": 274.67
+                },
+                {
+                    "mean_variant_occurrence": 1.0
+                },
+                {
+                    "start_activities_median": 32.5
+                },
+                {
+                    "start_activities_median": 15583.2
+                },
+                {
+                    "start_activities_median": 1.0
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.7
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.8
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.0
+                },
+                {
+                    "mean_variant_occurrence": 2.64,
+                    "start_activities_median": 32.5
+                },
+                {
+                    "mean_variant_occurrence": 2.64,
+                    "start_activities_median": 15583.2
+                },
+                {
+                    "mean_variant_occurrence": 2.64,
+                    "start_activities_median": 1.0
+                },
+                {
+                    "mean_variant_occurrence": 274.67,
+                    "start_activities_median": 32.5
+                },
+                {
+                    "mean_variant_occurrence": 274.67,
+                    "start_activities_median": 15583.2
+                },
+                {
+                    "mean_variant_occurrence": 274.67,
+                    "start_activities_median": 1.0
+                },
+                {
+                    "mean_variant_occurrence": 1.0,
+                    "start_activities_median": 32.5
+                },
+                {
+                    "mean_variant_occurrence": 1.0,
+                    "start_activities_median": 15583.2
+                },
+                {
+                    "mean_variant_occurrence": 1.0,
+                    "start_activities_median": 1.0
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.7,
+                    "mean_variant_occurrence": 2.64
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.7,
+                    "mean_variant_occurrence": 274.67
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.7,
+                    "mean_variant_occurrence": 1.0
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.8,
+                    "mean_variant_occurrence": 2.64
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.8,
+                    "mean_variant_occurrence": 274.67
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.8,
+                    "mean_variant_occurrence": 1.0
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.0,
+                    "mean_variant_occurrence": 2.64
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.0,
+                    "mean_variant_occurrence": 274.67
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.0,
+                    "mean_variant_occurrence": 1.0
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.7,
+                    "start_activities_median": 32.5
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.7,
+                    "start_activities_median": 15583.2
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.7,
+                    "start_activities_median": 1.0
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.8,
+                    "start_activities_median": 32.5
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.8,
+                    "start_activities_median": 15583.2
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.8,
+                    "start_activities_median": 1.0
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.0,
+                    "start_activities_median": 32.5
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.0,
+                    "start_activities_median": 15583.2
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.0,
+                    "start_activities_median": 1.0
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.7,
+                    "mean_variant_occurrence": 2.64,
+                    "start_activities_median": 32.5
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.7,
+                    "mean_variant_occurrence": 2.64,
+                    "start_activities_median": 15583.2
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.7,
+                    "mean_variant_occurrence": 2.64,
+                    "start_activities_median": 1.0
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.7,
+                    "mean_variant_occurrence": 274.67,
+                    "start_activities_median": 32.5
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.7,
+                    "mean_variant_occurrence": 274.67,
+                    "start_activities_median": 15583.2
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.7,
+                    "mean_variant_occurrence": 274.67,
+                    "start_activities_median": 1.0
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.7,
+                    "mean_variant_occurrence": 1.0,
+                    "start_activities_median": 32.5
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.7,
+                    "mean_variant_occurrence": 1.0,
+                    "start_activities_median": 15583.2
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.7,
+                    "mean_variant_occurrence": 1.0,
+                    "start_activities_median": 1.0
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.8,
+                    "mean_variant_occurrence": 2.64,
+                    "start_activities_median": 32.5
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.8,
+                    "mean_variant_occurrence": 2.64,
+                    "start_activities_median": 15583.2
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.8,
+                    "mean_variant_occurrence": 2.64,
+                    "start_activities_median": 1.0
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.8,
+                    "mean_variant_occurrence": 274.67,
+                    "start_activities_median": 32.5
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.8,
+                    "mean_variant_occurrence": 274.67,
+                    "start_activities_median": 15583.2
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.8,
+                    "mean_variant_occurrence": 274.67,
+                    "start_activities_median": 1.0
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.8,
+                    "mean_variant_occurrence": 1.0,
+                    "start_activities_median": 32.5
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.8,
+                    "mean_variant_occurrence": 1.0,
+                    "start_activities_median": 15583.2
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.8,
+                    "mean_variant_occurrence": 1.0,
+                    "start_activities_median": 1.0
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.0,
+                    "mean_variant_occurrence": 2.64,
+                    "start_activities_median": 32.5
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.0,
+                    "mean_variant_occurrence": 2.64,
+                    "start_activities_median": 15583.2
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.0,
+                    "mean_variant_occurrence": 2.64,
+                    "start_activities_median": 1.0
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.0,
+                    "mean_variant_occurrence": 274.67,
+                    "start_activities_median": 32.5
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.0,
+                    "mean_variant_occurrence": 274.67,
+                    "start_activities_median": 15583.2
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.0,
+                    "mean_variant_occurrence": 274.67,
+                    "start_activities_median": 1.0
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.0,
+                    "mean_variant_occurrence": 1.0,
+                    "start_activities_median": 32.5
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.0,
+                    "mean_variant_occurrence": 1.0,
+                    "start_activities_median": 15583.2
+                },
+                {
+                    "epa_normalized_variant_entropy": 0.0,
+                    "mean_variant_occurrence": 1.0,
+                    "start_activities_median": 1.0
+                }
+            ],
+            "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, 1000]",
+                "duplicate": "[0]",
+                "or": "[0]"
+            },
+            "n_trials": 200
+        }
+    }
+]