Adds feature config in fabric

config_files/config_layout.json

@@ -14,11 +14,7 @@
       "experiment": "data/grid_objectives.csv",
       "experiment": {"input_path": "data/2_bpic_features.csv",
         "objectives": ["ratio_top_20_variants", "epa_normalized_sequence_entropy_linear_forgetting"]},
-      "experiment": [
-          {"epa_normalized_sequence_entropy_linear_forgetting": 0.2, "ratio_top_20_variants": 0.4},
-          {"epa_normalized_sequence_entropy_linear_forgetting": 0.4, "ratio_top_20_variants": 0.7}
-        ],
-      "experiment": {"epa_normalized_sequence_entropy_linear_forgetting": 0.2, "ratio_top_20_variants": 0.4},
+      "experiment": {"n_traces":832, "n_unique_traces":828, "ratio_variants_per_number_of_traces":0.99, "trace_len_min":1, "trace_len_max":132, "trace_len_mean":53.31, "trace_len_median":54, "trace_len_mode":61, "trace_len_std":19.89, "trace_len_variance":395.81, "trace_len_q1":44, "trace_len_q3":62, "trace_len_iqr":18, "trace_len_geometric_mean":48.15, "trace_len_geometric_std":1.69, "trace_len_harmonic_mean":37.58, "trace_len_skewness":0.0541, "trace_len_kurtosis":0.81, "trace_len_coefficient_variation":0.37, "trace_len_entropy":6.65, "trace_len_hist1":0.004, "trace_len_hist2":0.005, "trace_len_hist3":0.005, "trace_len_hist4":0.024, "trace_len_hist5":0.024, "trace_len_hist6":0.008, "trace_len_hist7":0.005, "trace_len_hist8":0.001, "trace_len_hist9":0.0, "trace_len_hist10":0.00, "trace_len_skewness_hist":0.05, "trace_len_kurtosis_hist":0.8, "ratio_most_common_variant":0.0, "ratio_top_1_variants":0.01, "ratio_top_5_variants":0.05, "ratio_top_10_variants":0.10, "ratio_top_20_variants":0.2, "ratio_top_50_variants":0.5, "ratio_top_75_variants":0.75, "mean_variant_occurrence":1.0, "std_variant_occurrence":0.07, "skewness_variant_occurrence":14.28, "kurtosis_variant_occurrence":202.00, "n_unique_activities":410, "activities_min":1, "activities_max":830, "activities_mean":108.18, "activities_median":12, "activities_std":187.59, "activities_variance":35189, "activities_q1":3, "activities_q3":125, "activities_iqr":122, "activities_skewness":2.13, "activities_kurtosis":3.81, "n_unique_start_activities":14, "start_activities_min":1, "start_activities_max":731, "start_activities_mean":59.43, "start_activities_median":1, "start_activities_std":186.72, "start_activities_variance":34863, "start_activities_q1":1, "start_activities_q3":8, "start_activities_iqr":7, "start_activities_skewness":3, "start_activities_kurtosis":9.0, "n_unique_end_activities":82, "end_activities_min":1, "end_activities_max":216, "end_activities_mean":10, "end_activities_median":1, "end_activities_std":35, "end_activities_variance":1247, "end_activities_q1":1, "end_activities_q3":3, "end_activities_iqr":2, "end_activities_skewness":5, "end_activities_kurtosis":26, "eventropy_trace":10, "eventropy_prefix":15, "eventropy_global_block":19, "eventropy_lempel_ziv":4, "eventropy_k_block_diff_1":7.1, "eventropy_k_block_diff_3":7.1, "eventropy_k_block_diff_5":7.1, "eventropy_k_block_ratio_1":7.1, "eventropy_k_block_ratio_3":7.1, "eventropy_k_block_ratio_5":7.1, "eventropy_knn_3":5.54, "eventropy_knn_5":5.04, "eventropy_knn_7":4.72, "epa_variant_entropy":240512, "epa_normalized_variant_entropy":0.68, "epa_sequence_entropy":285876, "epa_normalized_sequence_entropy":0.60, "epa_sequence_entropy_linear_forgetting":150546, "epa_normalized_sequence_entropy_linear_forgetting":0.32, "epa_sequence_entropy_exponential_forgetting":185312, "epa_normalized_sequence_entropy_exponential_forgetting":0.39},
       "config_space": {
         "mode": [5, 20],
         "sequence": [0.01, 1],
@@ -37,7 +33,7 @@
   {
     "pipeline_step": "feature_extraction",
     "input_path": "data/test",
-    "feature_params": {"feature_set":["trace_length"]},
+    "feature_params": {"feature_set": ["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_prefix_flattened", "eventropy_global_block", "eventropy_global_block_flattened", "eventropy_lempel_ziv", "eventropy_lempel_ziv_flattened", "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"]},
     "output_path": "output/plots",
     "real_eventlog_path": "data/BaselineED_feat.csv",
     "plot_type": "boxplot"

utils/config_fabric.py

@@ -210,6 +210,12 @@ if __name__ == '__main__':
                 if step_key == "generator_params":
                     st.subheader("Set-up experiments")
                     step_config[step_key] = set_generator_experiments(step_config[step_key])
+                elif step_key == "feature_params":
+                    layout_features = list(step_config[step_key]['feature_set'])
+                    step_config[step_key]["feature_set"] = st.multiselect(
+                            "features to extract",
+                            layout_features,
+                            layout_features)
                 elif step_key != "pipeline_step":
                     step_config[step_key] = st.text_input(step_key, step_config[step_key])
         with view_col: